1.

1 INTRODUCTION
1.1.1 Speed control of induction motor
In the past, DC motors were used extensively in areas where variable-speed
operations were required. DC motors have certain disadvantages, however, which are due
to the existence of the commutator and the brushes which makes the motor more bulky,
costly and heavy. These problems could be overcome by application of AC motors. AC
motors have simpler and more rugged structure, higher maintainability and economy than
DC motors. They are also robust and immune to heavy loading. The speed of the
induction motor has to be controlled and so different types of controllers are used to
obtain the desired speed.
Various speed control techniques implemented by modern-age Variable Frequency
Drive are mainly classified in the following three categories:
Scalar Control (V/f Control)
Vector Control (Indirect Torque Control)
Direct Torque Control (DTC)
The aim of our project is to control the induction motor using vector control. We
employ indirect rotor flux vector control to control the induction motor.
The dynamic modeling of induction motor is done in the SIMULINK using the
necessary equations. The vector control of the induction motor is also modeled in the
SIMULINK using the necessary equations. The type of speed controller used in this
indirect rotor vector control induction motor is PI speed controller.
Neural Networks is implemented in the system for better control of the induction
motor. This is done by collecting samples from the PI controller and training the network
with the collected samples and writing the necessary program to create a neural network
for the system.

1.2 OVERVIEW OF THE PROJECT

A motor is nothing but a machine which converts electrical energy into mechanical
energy. It means that it takes electrical input as flow of current and gives the mechanical
output in the form of torque, which makes the machine to rotate in its own direction.
The induction motor is controlled using indirect rotor flux vector control method in
our project. The speed control mechanism in implemented using the PI controller and
Neural Networks.
In chapter 2,Theoretical analysis, which covers the induction motor principle,
motoring action, different types of induction motors, and different kinds of speed control
mechanisms used. Also includes the characteristics of the induction motor.
In chapter 3, Theoretical analysis of the vector control concept is covered.
Different types of vector control methods are discussed and the necessary block diagrams
and the transformations required are discussed.
In chapter 4, Theoretical analysis of neural network is covered which includes,
basics of neural network, human neuron analogy to artificial neuron, back propagation
algorithm, perceptron learning rules.
In chapter 5, the dynamic modeling of induction motor and vector control
modeling is done using the necessary equations in the SIMULINK. The PI speed control
and the neural network implementation is discussed in this chapter.
Chapter 6 Consists of implementation of the system PI speed control and Neural
Network.
Chapter 7 Consists of simulation results using both PI controller and Neural
Network.

THEORETICAL ANALYSIS OF INDUCTION MOTOR

2.1 INTRODUCTION
AC induction motors are the most common motors used in industrial motion
control systems, as well as in main powered home appliances. Simple and rugged design,
low-cost, low maintenance and direct connection to an AC power source are the main
advantages of AC induction motors. Various types of AC induction motors are available
in the market. Different motors are suitable for different applications. Although AC
induction motors are easier to design than DC motors, the speed and the torque control in
various types of AC induction motors require a greater understanding of the design and
the characteristics of these motors. This application note discusses the basics of an AC
induction motor; the different types, their characteristics, the selection criteria for
different applications and basic control techniques.

2.2 BASIC CONSTRUCTION AND OPERATING PRINCIPLE

Like most of motors, an AC induction motor has a fixed outer portion, called the
stator and a rotor that spins inside with a carefully engineered air gap between the two.
Virtually all electrical motors use magnetic field rotation to spin their rotors. A threephase AC induction motor is the only type where the rotating magnetic field is created
naturally in the stator because of the nature of the supply. DC motors depend either on
mechanical or electronic commutation to create rotating magnetic fields.
A single-phase AC induction motor depends on extra electrical components to
produce this rotating magnetic field. Two sets of electromagnets are formed inside any
motor. In an AC induction motor, one set of electromagnets is formed in the stator
because of the AC supply connected to the stator windings.

The alternating nature of the supply voltage induces an Electromagnetic Force (EMF) in
the rotor (just like the voltage is induced in the transformer secondary) as per Lenzs law,
thus generating another set of electromagnets; hence the name induction motor.
Interaction between the magnetic field of these electromagnets generates twisting force,
or torque. As a result, the motor rotates in the direction of the resultant torque.
2.2.1 STATOR:
The stator is made up of several thin laminations of aluminum or cast iron. They
are punched and clamped together to form a hollow cylinder (stator core) with slots as
shown in Fig 2.1. Coils of insulated wires are inserted into these slots. Each grouping of
coils, together with the core it surrounds, forms an electro- magnet (a pair of poles) on the
application of AC supply. The number of poles of an AC induction motor depends on the
internal connection of the stator windings. The stator windings are connected directly to
the power source. Internally they are connected in such a way, that on applying AC
supply, a rotating magnetic field is created.

Stator

Fig 2.1

2.2.2 ROTOR:
The rotor is made up of several thin steel laminations with evenly spaced bars,
which are made up of aluminum or copper, along the periphery. In the most popular type
of rotor (squirrel cage rotor), these bars are connected at ends mechanically and
electrically by the use of rings. Almost 90% of induction motors have squirrel cage
rotors. This is because the squirrel cage rotor has a simple and rugged construction. The
rotor consists of a cylindrical laminated core with axially placed parallel slots for
carrying the conductors. Each slot carries a copper, aluminum, or alloy bar. These rotor
bars are permanently short-circuited at both ends by means of the end rings, as shown in
Fig 2.2. This total assembly resembles the look of a squirrel cage, which gives the rotor
its name.
The rotor slots are not exactly parallel to the shaft. Instead, they are given a skew
for two main reasons. The first reason is to make the motor run quietly by reducing
magnetic hum and to decrease slot harmonics. The second reason is to help reduce the
locking tendency of the rotor. The rotor teeth tend to remain locked under the stator teeth
due to direct magnetic attraction between the two. This happens when the numbers of
stator teeth are equal to the number of rotor teeth.
The rotor is mounted on the shaft using bearings on each end; one end of the
shaft is normally kept longer than the other for driving the load. Some motors may have
an accessory shaft on the non-driving end for mounting speed or position sensing devices.
Between the stator and the rotor, there exists an air gap, through which due to induction,
the energy is transferred from the stator to the rotor. The generated torque forces the rotor
and then the load to rotate. Regardless of the type of rotor used, the principle employed
for rotation remains the same.

2.3 SPEED OF INDUCTION MOTOR:

The magnetic field created in the stator rotates at a synchronous speed (NS) is given by
Ns=(120 * f ) / P
Where ,

--------(2.1)

Ns= Synchronous speed of the stator

P= the no of poles in the stator
f= the supply frequency in Hz

The magnetic field produced in the rotor because of the induced voltage is alternating in
nature. To reduce the relative speed, with respect to the stator, the rotor starts running in
the same direction as that of the stator flux and tries to catch up with the rotating flux.
However, in practice, the rotor never succeeds in catching up to the stator field. The
rotor runs slower than the speed of the stator field. This speed is called the Base Speed
(Nb). The difference between NS and Nb is called the slip. The slip varies with the load.
An increase in load will cause the rotor to slow down or increase slip. A decrease in load
will cause the rotor to speed up or decrease slip. The slip is expressed as a percentage and
can be determined as follows.
% Slip = [(Ns Nb) / Ns] * 100

-------- (2.2)

2.4 TYPES OF AC INDUCTION MOTORS

Generally, induction motors are categorized based on the number of stator windings.
They are:
Single-phase induction motor
Three-phase induction motor

2.4.1 Single-Phase Induction Motor:

There are probably more single-phase AC induction motors in use today than
the total of all the other types put together. It is logical that the least expensive, lowest
maintenance type motor should be used most often. The single-phase AC induction motor
best fits this description. As the name suggests, this type of motor has only one stator
winding (main winding) and operates with a single-phase power supply. In all singlephase induction motors, the rotor is the squirrel cage type. The single-phase induction
motor is not self-starting.
When the motor is connected to a single-phase power supply, the main winding
carries an alternating current. This current produces a pulsating magnetic field. Due to
induction, the rotor is energized. As the main magnetic field is pulsating, the torque
necessary for the motor rotation is not generated. This will cause the rotor to vibrate, but
not to rotate. Hence, the single phase induction motor is required to have a starting
mechanism that can provide the starting kick for the motor to rotate. The starting
mechanism of the single-phase induction motor is mainly an additional stator winding
(start/ auxiliary winding) as shown in Fig 2.3. The start winding can have a series
capacitor and/or a centrifugal switch.
When the supply voltage is applied, current in the main winding lags the
supply voltage due to the main winding impedance. At the same time, current in the start
winding leads/lags the supply voltage depending on the starting mechanism impedance.
Interaction between magnetic fields generated by the main winding and the starting
mechanism generates a resultant magnetic field rotating in one direction. The motor starts
rotating in the direction of the resultant magnetic field.

Once the motor reaches about 75% of its rated speed, a centrifugal switch
disconnects the start winding. From this point on, the single-phase motor can maintain
sufficient torque to operate on its own. Except for special capacitor start/capacitor run
types, all single-phase motors are generally used for applications up to 3/4 hp only.
Depending on the various start techniques, single phase AC induction motors are further
classified as described in the following sections.

2.4.2 THREE-PHASE AC INDUCTION MOTOR:

The AC induction motor is a rotating electric machine designed to operate from a
3-phase source of alternating voltage. For variable speed drives, the source is normally an
inverter that uses power switches to produce approximately sinusoidal voltages and
currents of controllable magnitude and frequency. Slots in the inner periphery of the
stator accommodate 3-phase winding a,b,c. The turns in each winding are distributed so
that a current in a stator winding produces an approximately sinusoidally-distributed flux
density around the periphery of the air gap.
When three currents that are sinusoidally varying in time, but displaced in phase
by 120 from each other, flow through the three symmetrically-placed windings, a
radially-directed air gap flux density is produced that is also sinusoidally distributed
around the gap and rotates at an angular velocity equal to the angular frequency, Ws, of
the stator currents.

The most common type of induction motor has a squirrel cage rotor in which
aluminum conductors or bars arecast into slots in the outer periphery of the rotor. These
conductors or bars are shorted together at both ends ofthe rotor by cast aluminum end
rings, which also can be shaped to act as fans. In larger induction motors,copper or
copper-alloy bars are used to fabricate the rotor cage winding. As the sinusoidallydistributed flux density wave produced by the stator magnetizing currents sweeps past the
rotor conductors, it generates a voltage in them.
The result is a sinusoidally-distributed set of currents in the short-circuited rotor
bars. Because of the low resistance of these shorted bars, only a small relative angular
velocity, between the angular velocity, of the flux wave and the mechanical angular
velocity of the two-pole rotor is required to produce the necessary rotor current. The
relative angular velocity, is called the slip velocity. The interaction of the sinusoidallydistributed air gap flux density and induced rotor currents produces a torque on the rotor.
The typical induction motor speed-torque characteristic is shown in Fig 2.4.

Fig 2.4

Squirrel-cage induction motors are popular for their simple construction, low cost
per horsepower, and low maintenance (they contain no brushes, as do DC motors). They
are available in a wide range of power ratings. With field-oriented vector control
methods,induction motors can fully replace standard DC motors, even in highperformance applications.
2.4.2.1 Squirrel Cage Motor:
Almost 90% of the three-phase AC Induction motors are of this type. Here, the rotor
is of the squirrel cage type and it works as explained earlier. The power ratings range
from one-third to several hundred horsepower in the three-phase motors. Motors of this
type, rated one horsepower or larger, cost less and can start heavier loads than their
single-phase counterparts.
2.4.2.2 Wound-Rotor Motor:
The slip-ring motor or wound-rotor motor is a variation of the squirrel cage
induction motor. While the stator is the same as that of the squirrel cage motor, it has a set
of windings on the rotor which are not short-circuited, but are terminated to a set of slip
rings. These are helpful in adding external resistors and contactors. The slip necessary to
generate the maximum torque (pull-out torque) is directly proportional to the rotor
resistance. In the slip-ring motor, the effective rotor resistance is increased by adding
external resistance through the slip rings. Thus, it is possible to get higher slip and hence,
the pull-out torque at a lower speed.
A particularly high resistance can result in the pull-out torque occurring at almost
zero speed, providing a very high pull-out torque at a low starting current. As the motor
accelerates, the value of the resistance can be reduced, altering the motor characteristic to
suit the load requirement. Once the motor reaches the base speed, external resistors are
removed from the rotor. This means that now the motor is working as the standard
induction motor. This motor type is ideal for very high inertia loads, where it is required
to generate the pull-out torque at almost zero speed and accelerate to full speed in the

10

minimum time with minimum current draw.

The downside of the slip ring motor is that slip rings and brush assemblies need regular
maintenance, which is a cost not applicable to the standard cage motor.
If the rotor windings are shorted and a start is attempted (i.e., the motor is converted to a
standard induction motor), it will exhibit an extremely high locked rotor current
typically as high as 1400% and a very low locked rotor torque, perhaps as low as 60%.
In most of the applications, this is not an option. Modifying the speed torque curve by
altering the rotor resistors, the speed at which the motor will drive a particular load can
be altered. At full load, you can reduce the speed effectively to about 50% of the motor
synchronous speed, particularly when driving variable torque/variable speed loads, such
as printing presses or compressors. Reducing the speed below 50% results in very low
efficiency due to higher power dissipation in the rotor resistances. This type of motor is
used in applications for driving variable torque/ variable speed loads, such as in printing
presses, compressors, conveyer belts, hoists and elevators.
2.5 TORQUE EQUATION GOVERNING MOTOR OPERATION:
The motor load system can be described by a fundamental torque equation.
T TL

J (dWm/ dt) + Wm (dJ/dt)

------(2.3)

Where,
T= the Instantaneous value of the developed motor torque (N-m)
TL= the Instantaneous value of the load torque (N-m)
11

Wm = the Instantaneous Angular velocity of the motor shaft (rad/sec)

J= the moment of inertia of the motor-load system(Kg-m2)
For drives with constant inertia, (dJ/dt) = 0. Therefore, the equation would be:
T= TL + J (dWm/ dt)

---------(2.4)

This shows that the torque developed by the motor is counter balanced by a load torque,
TL and a dynamic torque, J(dwm/dt). The torque component, J(dwm/dt), is called the
dynamic torque because it is present only during the transient operations. The drive
accelerates or decelerates depending on whether T is greater or less than T L. During
acceleration, the motor should supply not only the load torque, but an additional torque
component, J(dwm/dt), in order to overcome the drive inertia.
In drives with large inertia, such as electric trains, the motor torque must
exceed the load torque by a large amount in order to get adequate acceleration. In drives
requiring fast transient response, the motor torque should be maintained at the highest
value and the motor load system should be designed with the lowest possible inertia. The
energy associated with the dynamic torque, J(dWm/dt), is stored in the form of Kinetic
Energy (KE) given by, J(dWm/2). During deceleration, the dynamic torque, J(dWm/dt),
has a negative sign. Therefore, it assists the motor developed torque T and maintains the
drive motion by extracting energy from the stored kinetic energy. To summarize, in order
to get steady state rotation of the motor, the torque developed by the motor (T) should
always be equal to the torque requirement of the load (T L). The torque-speed curve of the
typical three-phase induction motor is shown in Fig 2.6.

12

2.6 Characterstics of the Induction motor:

2.6.1 STARTING CHARACTERISTICS:
Induction motors, at rest, appear just like a short circuited transformer and if
connected to the full supply voltage, draw a very high current known as the Locked
Rotor Current. They also produce torque which is known as the Locked Rotor Torque.
The Locked Rotor Torque (LRT) and the Locked Rotor Current (LRC) are a function of
the terminal voltage of the motor and the motor design. As the motor accelerates, both the
torque and the current will tend to alter with rotor speed if the voltage is maintained
constant. The starting current of a motor with a fixed voltage will drop very slowly as the
motor accelerates and will only begin to fall significantly when the motor has reachedat
least 80% of the full speed.
The actual curves for the induction motors can vary considerably between designs
but the general trend is for a high current until the motor has almost reached full speed.
The LRC of a motor can range from 500% of Full-Load Current (FLC) to as high as
1400% of FLC. Typically, good motors fall in the range of 550% to 750% of FLC. The
starting torque of an induction motor starting with a fixed voltage will drop a little to the
minimum torque, known as the pull-up torque, as the motor accelerates and then rises to a
13

maximum torque, known as the breakdown or pull-out torque, at almost full speed and
then drop to zero at the synchronous speed. The curve of the start torque against the rotor
speed is dependant on the terminal voltage and the rotor design. The LRT of an induction
motor can vary from as low as 60% of FLT to as high as 350% of FLT. The pull-up torque
can be as low as 40% of FLT and the breakdown torque can be as high as 350% of FLT.
Typically, LRTs for medium to large motors are in the order of 120% of FLT to 280% of
FLT. The PF of the motor at start is typically 0.1-0.25, rising to a maximum as the motor
accelerates and then falling again as the motor approaches full speed.

2.6.2 RUNNING CHARACTERISTICS:

Once the motor is up to speed, it operates at a low slip, at a speed determined by
the number of the stator poles. Typically, the full-load slip for the squirrel cage induction
motor is less than 5%. The actual full-load slip of a particular motor is dependant on the
motor design.
The typical base speed of the four pole induction motor varies between 1420 and
1480 RPM at 50 Hz, while the synchronous speed is 1500 RPM at 50 Hz. The current
drawn by the induction motor has two components: reactive component (magnetizing
current) and active component (working current). The magnetizing current is independent
of the load but is dependant on the design of the stator and the stator voltage. The actual
magnetizing current of the induction motor can vary, from as low as 20% of FLC for the
large two pole machine, to as high as 60% for the small eight pole machine.
The working current of the motor is directly proportional to the load. The tendency
for the large machines and high-speed machines is to exhibit a low magnetizing current,
while for the low-speed machines and small machines the tendency is to exhibit a high
magnetizing current. A typical medium sized four pole machine has a magnetizing
current of about 33% of FLC. A low magnetizing current indicates a low iron loss, while
a high magnetizing current indicates an increase in iron loss and a resultant reduction in
the operating efficiency. Typically, the operating efficiency of the induction motor is
highest at 3/4 load and varies from less than 60% for small low-speed motors to greater
than 92% for large high-speed motors. The operating PF and efficiencies are generally
quoted on the motor data sheets.

14

2.6.3 LOAD CHARACTERISTICS:

In real applications, various kinds of loads exist with different torque-speed
curves. For example, Constant Torque, Variable Speed Load (screw compressors,
conveyors, feeders), Variable Torque, Variable Speed Load (fan, pump), Constant Power
Load (traction drives), Constant Power, Constant Torque Load (coiler drive) and High
Starting/Breakaway Torque followed by Constant Torque Load (extruders, screw pumps).
The motor load system is said to be stable when the developed motor torque is equal to
the load torque requirement. The motor will operate in a steady state at a fixed speed. The
response of the motor to any disturbance gives us an idea about the stability of the motor
load system. This concept helps us in quickly evaluating the selection of a motor for
driving a particular load. In most drives, the electrical time constant of the motor is
negligible as compared to its mechanical time constant.
Therefore, during transient operation, the motor can be assumed to be in an
electrical equilibrium, implying that the steady state torque-speed curve is also applicable
to the transient operation. As an example, Fig 2.7 shows torque-speed curves of the motor
with two different loads. The system can be termed as stable, when the operation will be
restored after a small departure from it, due to a disturbance in the motor or load. For
example, disturbance causes a reduction of Wm in speed.
In the first case, at a new speed, the motor torque (T) is greater than the load
torque (TL). Consequently, the motor will accelerate and the operation will be restored to
X. Similarly, an increase of wm in the speed, caused by a disturbance, will make the
load torque (TL) greater than the motor torque (T), resulting in a deceleration and
restoration of the point of operation to X. Hence, at point X, the system is stable. In the
second case, a decrease in the speed causes the load torque (T L) to become greater than
the motor torque (T), the drive decelerates and the operating point moves away from Y.
Similarly, an increase in the speed will make the motor torque (T) greater than the load
torque (TL), which will move the operating point further away from Y. Thus, at point Y,
the system is unstable. This shows that, while in the first case, the motor selection for
driving the given load is the right one; in the second case, the selected motor is not the
right choice and requires changing for driving the given load. The typical existing loads

15

with their torque-speed curves are described in the following sections.

Constant Torque, Variable Speed Loads:

The torque required by this type of load is constant regardless of the speed. In
contrast, the power is linearly proportional to the speed. Equipment, such as screw
compressors, conveyors and feeders, have this type of characteristic.

Variable Torque, Variable Speed Loads:

This is most commonly found in the industry and sometimes is known as a
quadratic torque load. The torque is the square of the speed, while the power is the cube
of the speed. This is the typical torque-speed characteristic of a fan or a pump.

16

Constant Power Loads:

This type of load is rare but is sometimes found in the industry. The power
remains constant while the torque varies. The torque is inversely proportional to the
speed, which theoretically means infinite torque at zero speed and zero torque at infinite
speed. In practice, there is always a finite value to the breakaway torque required. This
type of load is characteristic of the traction drives, which require high torque at low
speeds for the initial acceleration and then a much reduced torque when at running speed.

Constant Power, Constant Torque Loads:

This is common in the paper industry. In this type of load, as speed increases, the
torque is constant with the power linearly increasing. When the torque starts to decrease,
the power then remains constant.

17

High Starting/Breakaway Torque Followed by Constant Torque:

This type of load is characterized by very high torque at relatively low
frequencies. Typical applications include extruders and screw pumps.

18

THEORETICAL ANAYLSIS OF VECTOR CONTROL

3.1 INTRODUCTION:
Various speed control techniques implemented by modern-age Variable Frequency Drives
are mainly classified as follows.
Scalar Control (V/f Control)
Vector Control (Indirect Torque Control)
Direct Torque Control (DTC)
3.1.1 Scalar Control:
In this type of control, the motor is fed with variable frequency signals generated
by the PWM control from an inverter. Here, the V/f ratio is maintained constant in order
to get constant torque over the entire operating range. Since only magnitudes of the input
variables frequency and voltage are controlled, this is known as Scalar control.
Generally, the drives with such a control are without any feedback devices (Openloop
control). Hence, a control of this type offers low cost and is an easy to implement
solution.
In such controls, very little knowledge of the motor is required for frequency
control. Thus, this control is widely used. A disadvantage of such a control is that the
torque developed is load dependent as it is not controlled directly. Also, the transient
response of such a control is not fast due to the predefined switching pattern of the
inverter. However, if there is a continuous block to the rotor rotation, it will lead to
heating of the motor regardless of implementation of the overcurrent control loop. By
adding a speed/position sensor, the problem relating to the blocked rotor and the load
dependent speed can be overcome. However, this will add to the system cost, size and
complexity. There are a number of ways to implement scalar control. The popular
schemes are described in the following sections.

19

3.1.2 Vector Control:

This control is also known as the field oriented control, or flux oriented
control

or

Indirect

torque

control.

Using

field

orientation

(Clarke-Park

transformation), three-phase current vectors are converted to a two-dimensional rotating

reference frame (d-q) from a three-dimensional stationary reference frame. The d
component represents the flux producing component of the stator current and the q
component represents the torque producing component. These two decoupled
components can be independently controlled by passing though separate PI controllers.
The outputs of the PI controllers are transformed back to the three-dimensional stationary
reference plane using the inverse of the Clarke-Park transformation. The corresponding
switching pattern is pulse width modulated and implemented using the Space Vector
Modulation.
This control simulates a separately exited DC motor model, which provides an excellent
torque-speed curve.
The transformation from the stationary reference frame to the rotating reference frame is
done and controlled (stator flux linkage, rotor flux linkage or magnetizing flux linkage).
In general, there exists three possibilities for such selection and hence, three different
vector controls. They are:
Stator flux oriented control
Rotor flux oriented control
Magnetizing flux oriented control
As the torque producing component in this type of control is controlled only after
transformation is done and is not the main input reference, such control is known as
Indirect torque control. The most challenging and ultimately, the limiting feature of the
field orientation, is the method whereby the flux angle is measured or estimated.
Depending on the method of measurement, the vector control is divided into two
subcategories: direct and indirect vector control. In direct vector control, the flux
measurement is done by using the flux sensing coils or the Hall devices. This adds to

20

additional hardware cost and in addition, measurement is not highly accurate.

Therefore, this method is not a very good control technique. The more common
method is indirect vector control. In this method, the flux angle is not measured directly,
but is estimated from the equivalent circuit model and from measurements of the rotor
speed, the stator current and the voltage. One common technique for estimating the rotor
flux is based on the slip relation. This requires the measurement of the rotor position and
the stator current. With current and position sensors, this method performs reasonably
well over the entire speed range. The most high-performance VFDs in operation today
employ indirect field orientation based on the slip relation.
The main disadvantage of this method is the need of the rotor position information
using the shaft mounted encoder. This means additional wiring and component cost. This
increases the size of the motor. When the drive and the motor are far apart, the additional
wiring poses a challenge. To overcome the sensor/encoder problem, todays main
research focus is in the area of a sensorless approach. The advantages of the vector
control are to better the torque response compared to the scalar control, full-load torque
close to zero speed, accurate speed control and performance approaching DC drive,
among others. But this requires a complex algorithm for speed calculation in real-time.
Due to feedback devices, this control becomes costly compared to the scalar control.
3.1.3 Direct Torque Control (DTC):
The difference between the traditional vector control and the DTC is that the DTC
has no fixed switching pattern. The DTC switches the inverter according to the load
needs. Due to elimination of the fixed switching pattern (characteristic of the vector and
the scalar control), the DTC response is extremely fast during the instant load changes.
Although the speed accuracy up to 0.5% is ensured with this complex technology, it
eliminates the requirement of any feedback device. The heart of this technology is its
adaptive motor model. This model is based on the mathematical expressions of basic
motor theory. This model requires information about the various motor parameters, like
stator resistance, mutual inductance, saturation coefficiency, etc.

21

The algorithm captures all these details at the start from the motor without rotating
the motor. But rotating the motor for a few seconds helps in the tuning of the model. The
better the tuning, the higher the accuracy of speed and torque control. With the DC bus
voltage, the line currents and the present switch position as inputs, the model calculates
actual flux and torque of the motor. These values are fed to two-level comparators of the
torque and flux, respectively. The output of these comparators is the torque and flux
reference signals for the optimal switch selection table. Selected switch position is given
to the inverter without any modulation, which means faster response time. The external
speed set reference signal is decoded to generate the torque and flux reference. Thus, in
the DTC, the motor torque and flux become direct controlled variables and hence, the
name Direct Torque Control. The advantage of this technology is the fastest response
time, elimination of feedback devices, reduced mechanical failure, performance nearly
the same as the DC machine without feedback, etc. The disadvantage is due to the
inherent hysteresis of the comparator, higher torque and flux ripple exist. Since switching
is not done at a very high frequency, the low order harmonics increases. It is believed that
the DTC can be implemented using an Artificial Intelligence model instead of the model
based on mathematical equations. This will help in better tuning of the model and less
dependence on the motor parameters.
3.2 VECTOR CONTROL THEORY:
3.2.1 Background:
The induction motor is the workhorse of industrial and residential motor
applications due to its simple construction and durability. These motors have no brushes
to wear out or magnets to add to the cost. The rotor assembly is a simple steel cage. IMs
are designed to operate at a constant input voltage and frequency, but you can effectively
control an IM in an open loop variable speed application if the frequency of the motor
input voltage is varied. If the motor is not mechanically overloaded, the motor will
operate at a speed that is roughly proportional to the input frequency. As you decrease the
frequency of the drive voltage, you also need to decrease the amplitude by a proportional
amount. Otherwise, the motor will consume excessive current at low input frequencies.

22

This control method is called Volts-Hertz control.

In practice, a custom Volts-Hertz profile is developed that ensures the motor
operates correctly at any speed setting. This profile can take the form of a look-up table
or can be calculated during run time. Often, a slope variable is used in the application that
defines a linear relationship between drive frequency and voltage at any operating point.
The Volts-Hertz control method can be used in conjunction with speed and current
sensors to operate the motor in a closed-loop fashion. The Volts-Hertz method works very
well for slowly changing loads such as fans or pumps. But, it is less effective when fast
dynamic response is required. In particular, high current transients can occur during rapid
speed or torque changes. The high currents are a result of the high slip factor that occurs
during the change. Fast dynamic response can be realized without these high currents if
both the torque and flux of the motor are controlled in a closed loop manner. This is
accomplished using Vector Control techniques. Vector control is also commonly referred
to as Field Oriented Control (FOC). The benefits of vector control can be directly realized
as lower energy consumption. This provides higher efficiency, lower operating costs and
reduces the cost of drive components.

3.2.2 Vector control or field-oriented control:

Scalar control is somewhat simple to implement, but the inherent coupling effect
( i.e., both torque and flux are functions of voltage or current and frequency) gives
sluggish response and the system is easily prone to instability because of high-order
(fifth-order) system effect.
These problems can be solved by vector or field - oriented control. The invention
of vector control in the beginning of 1970s , and the demonstration that an induction
motor can be controlled of ac drives. Because of dc machine-like performance, vector
control is also known as decoupling, orthogonal, or Transvector control, Vector control is
applicable to both induction and synchronous motor drives.
Ideally, a vector controlled induction motor drive operates like a separately excited
dc motor drive. Fig 3.1 explains this analogy, in a dc machine, neglecting the
armature reaction effect and field saturation, the developed torque is given by

23

Te = Kt Ia If

---------------(3.1)

Where Ia = armature current and If = field current

The construction of a dc machine is such that the field current I f is perpendicular to the
armature current Ia Because of decoupling, when the field current I f is controlled,
it affects the field flux f only but not the flux a . Because of the inherent coupling
problem, an induction motor cannot generally give such fast response.
DC machine - like performance can also be extended to an induction motor if the
machine control is considered in a synchronously rotating reference frame (d e-qe), where
the sinusoidal variables appear as dc quantities in steady state. In fig 4.2 the
induction motor with the inverter and vector control in the front end is shown with
two control current inputs, Ids and Iqs .

24

With vector, control. Ids is analogous field current If and Iqs is analogous to armature
current Ia of a dc machine.
Therefore, the torque can be expressed as
Te=Kf ids iqs

---------(3.2)

Te=Kf r iqs

----------(3.3)

r = is the peak value of the sinusoidal space vector. This dc

Where

machine like performance in only possible if I ds is oriented ( or aligned ) in the direction

r and Iqs established perpendicular to it, as shown by the space-vector diagram
of flux

on the right of figure 3.2 . This means that when I qs is controlled, it affects the actual
r . Note that when compared to dc
Iqs current only and but does not affect the flux

machine space vectors, induction machine space vectors rotate synchronously

frequency e as indicated in the figure. In summary, vector control should assure the
correct orientation and equality of command and actual currents.
3.3 Principles of Vector Control:
The fundamentals of vector control implementation can be explained with the help of
figure. Where the machine model is represented in a synchronously rotating reference
frame. The inverter is omitted from the figure, assuming that it has unity by 3/2
transformation. The machine terminal phase currents I a , Ib and Ic are converted to Iqss and
Idss components converted to synchronously rotating frame by the unit vector components
cose and sine before applying them to the de-qe machine model as shown.

Figure3.3 : Vector control implementation principle with machine de-qe model

25

The controller makes two stages of inverse transformation, as shown, so that the control
currents Ids* and Iqs* correspond to the machine curent with the flux vector r and Iqs
perpendicular to it, as shown. Note that the

transformation and inverse

transformation including the inverter ideally do not incorporate any dynamics, and
therefore the response to Ids and Iqs is instantaneous ( neglecting computational and
sampling delays ). There are essentially two general methods of vector control. One
called the direct or feed back method was invented by Blaschke, and the other, known
as the indirect or feed forward method, was invented by Hasse. The methods are
different essentially by how the unit vector (cose and sine) is generated for the control.
3.4 Direct or feedback Vector Control:
In the direct vector control method, the principal vector control parameters,
Ids* and Iqs* which are dc values (VR) with the help of a unit vector (Cose and Sine)
generated from flux vector signals drs and qrs. The resulting stationary frame signals
are then converted to phase current commands for the inverter. The flux signals drs and
qrs are generated from the machine terminal voltages and currents with the help of the
voltage model estimator. The generation of a unit vector signal from feedback flux vector
gives the name direct vector control.
In the direct vector control, the measurement of voltages and currents are required. In
this the r is estimated by observer and flux vectors are estimated from the
voltage model method and current model method. the three voltages and three current
sensors are required. From r we get the speed e and then get the angle e.
3.5 Indirect or Feed forward Vector Control :
In this modeling the indirect vector control method is used. In the indirect vector
control the unit vector signals (Cose and Sine) are generated in feedforwawrd manner,
indirect vector control is very popular in industrial application. Figure (3.1) explains the
fundamental principle of indirect vector control with the help of phasor diagram. The
ds-qs axes are fixed on the stator, but of d r-qr axes. Which are fixed on the rotor, are
moving at speed r as shown.

26

Synchronously rotating axes de-qe is rotating ahead of the dr-qr axes by the
positive slip angle sl corresponding to slip frequency sl. Since the rotor pole is
directed on the d e axes and e = r = sl we can write
e e dt

sl dt r sl -------- (3.4)

Note that the rotor pole position is not absolute, but is slipping with respect to the
rotor at frequency sl. The phasor suggest that for decoupling control, the stator flux
component of current

Iqs should be aligned on the d e axis, and the torque component

of current Iqs should be on the qe axis as shown.[6]

Figure 3.4: Phasor diagram explaining Indirect vector control:

For decoupling control, we can now make a derivation of control equations of
indirect vector control with the help of d e qe equivalent circuits. The circuit equations
can be written as.
ddr /dt+Rr Idr (e-r) qr = 0
dqr /dt+Rr Iqr + (e-r) qr = 0

------------ (3.5)
------------

(3.6)

From the rotor flux equations the currents Idr, Iqr equations as:
27

Idr = l/Lr dr - Lm/Lr ids

Iqr = l/Lr qr Lm/Lr iqs

--------------(3.7)
---------------------

(3.8)

From the above equations we get,

ddr /dt + Rr/Lr dr Lm/Lr Rr Ids - sl qr = 0

-------- (3.9)

dqr /dt + Rr/Lr qr Lm/Lr Rr Iqs + sl dr = 0 ---------(3.10)

Where sl = e r has been substituted.
For decoupling control, it is desirable that
qr =0

------------ (3.11)

dqr/dt = 0

------------ (3.12)

That is,
So that the total rotor flux r is directed on the de axis.
Substituting the above conditions in equations 3.9 & 3.10, and simplified we get

L r d r
r L m i ds
R r dt
L
sl m
r
Where r

i qs

-------- (3.13)
-------------- (3.14)

Lr
r = dr has been substituted.
= rotor time constant,
Rr

r = constant, which is usually the case, i.e. d

r /dt =0 and the from
If rotor flux
equation 3.12

r /Lm
Ids =

------------- (3.15)

In other words, the rotor flux is directly proportional to current Ids in steady state.
The Iqs is estimated as follows.
The Torque is given by
Te = (3/2) (p/2)(dr Iqr - qr Idr)

------------- (3.16)

From the Equation 3.13 and substitute in above equation we get

28

Te = (3/2)(p/2)( dr I qr )

---------------- (3.17)

after substitution the value of I qr then equation I qs as

r
Iqs = (2/3) (2/p) (Lr/Lm) (Te/

-------------- (3.18)

From these equation we can write

The field component of the stator current
Ids*=

r /Lm

-------------- 3.19)

Similarly
The torque component of the stator current Iqs*
I
qs

rest )
= (2/3)(2/p) (Lr/Lm) (Te*/

----------(3.20)

rest = (Lm Ids) /(1+rs)

Where
Therefore the slip speed

rest )
sl* = Lm/ r. (Iqs*/

---------------(3.21)

To implement the indirect vector control strategy, it is necessary to take

equations 3.4, 3.10, 3.15, 3.16, to 3.21 into consideration and these equations are
implemented in simulink.

3.6 A MATTER OF PERSPECTIVE:

.
The key to understanding how vector control works is to form a mental picture of the

29

coordinate reference transformation process. If you picture how an AC motor works, you
might imagine the operation from the perspective of the stator. From this perspective, a
sinusoidal input current is applied to the stator. This time variant signal causes a rotating
magnetic flux to be generated. The speed of the rotor is going to be a function of the
rotating flux vector. From a stationary perspective, the stator currents and the rotating
flux vector look like AC quantities. Now, instead of the previous perspective, imagine
that you could climb inside the motor. Once you are inside the motor, picture yourself
running alongside the spinning rotor at the same speed as the rotating flux vector that is
generated by the stator currents. Looking at the motor from this perspective during steady
state conditions, the stator currents look like constant values, and the rotating flux vector
is stationary! Ultimately, you want to control the stator currents to get the desired rotor
currents (which cannot be measured directly). With the coordinate transformation, the
stator currents can be controlled like DC values using standard control loops.
3.7 Block Diagram of the Vector Control:
Figure (A) shows the basic structure of the vector control of the AC induction motor. To
perform vector control, follow these steps:
Measure the motor quantities (phase voltages and currents)
Transform them to the 2-phase system ( ,) using a Clarke transformation
Calculate the rotor flux space vector magnitude and position angle
Transform stator currents to the d-q coordinate system using a Park transformation
The stator current torque- (isq) and flux- (isd) producing components are separately
controlled.
The output stator voltage space vector is calculated using the decoupling block.
An inverse Park transformation transforms the stator voltage space vector back from the
d-q coordinate system to the 2-phase system fixed with the stator.

30

Fig 3.5Vector controller block diagram

3.8.TRANSFORMATIONS:
31

3.8.1 Forward and Inverse Clarke Transformation (a,b,c to , and backwards)

The forward Clarke transformation converts a 3-phase system (a, b, c) to a 2-phase
coordinate system (, ).
Figure (B) shows graphical construction of the space vector and projection of the space
vector to the quadrature-phase components ,.

Fig 3.6

Clarke Transformation

is=k[isa(1/2) isb (1/2) isc] ---------(3.22)

is=k(

/2) (isb isc)

---------(3.23)

32

Assuming that the a axis and the axis are in the same direction, the
quadrature-phase stator currents is(and is(are related to the actual 3-phase stator
currents as follows:

where:
isa = Actual current of the motor Phase A [A]
isb = Actual current of the motor Phase B [A]
isC= Actual current of the motor Phase C [A]
The constant k equals k = 2/3 for the non-power-invariant transformation. In this case, the
quantities isa and isare equal. If its assumed that isa+ isb+ isc= 0 , the quadraturephase components can be expressed utilizing
only two phases of the 3-phase system:

is=isa
is=(1/

--------(3.24)
3 ) isa + (2/ 3 )isb
-------(3.25)

The inverse Clarke transformation goes from a 2-phase ((to a 3-phase isa, isb, isc
system. For constant k = 2/3, it is calculated by the following equations:

isa = is
isb= -(1/2) is+(
isc= -(1/2) is-(

-------------(3.26)
/2) is

------------ (3.27)

/2) is

-----------(3.28)

33

3.8.2 Forward and Inverse Park Transformation (, to d-q and backwards):

The components is and is, calculated with a Clarke transformation, are
attached to the stator reference frame ,. In vector control, all quantities must be
expressed in the same reference frame. The stator reference frame is not suitable for the
control process.
The space vector is is rotating at a rate equal to the angular frequency of the
phase currents. The components is and is depend on time and speed. These components
can be transformed from the stator reference frame to the d-q reference frame rotating at
the same speed as the angular frequency of the phase currents. The i sd and isq components
do not then depend on time and speed. If the d-axis is aligned with the rotor flux, the
transformation is illustrated in Figure below where field is the rotor flux position.

Fig:3.7
Park Transformation
34

The components isd and isq of the current space vector in the d-q reference frame are
determined by the following equations:

isd = is Cos Field + is Sin Field

-------(3 .29)

isq = -is Sin Field+ is Cos Field

-------(3.30)

The component isd is called the direct axis component (the flux-producing
component) and isq is called the quadrature axis component (the torque-producing
component).
They are time invariant; flux and torque control with them is easy. To avoid using
trigonometric functions on the hybrid controller, directly calculate sin Field and cosField
using division, defined by the following equations:

------(3.31)

Sin Field =(r / rd)

Cos Field=(r / rd)

--------(3.32)
---------(3.33)

The inverse Park transformation from the d-q to the , coordinate system is found by
the following equations:

is= isdcos Field-isqsin Field ---------(3.34)

is= isd sinField +isqcos Field -------(3.35)

35

NEURAL NETWORKS

4.1 INTRODUCTION
Neural networks are composed of simple elements operating in parallel. These elements
are inspired by biological nervous systems. As in nature, the network function is
determined largely by the connections between elements. We can train a neural network
to perform a particular function by adjusting the values of the connections (weights)
between elements. Commonly neural networks are adjusted, or trained, so that a
particular input leads to a specific target output. Such a situation is shown below. There,
the network is adjusted, based on a comparison of the output and the target, until the
network output matches the target. Typically many such input/target pairs are used, in this
supervised learning, to train a network

Fig 4.1 Neural Network

Batch training of a network proceeds by making weight and bias changes based on an
entire set (batch) of input vectors. Incremental training changes the weights and biases of
a network as needed after presentation of each individual input vector. Incremental
training is sometimes referred to as "on line" or "adaptive" training.

36

Neural networks have been trained to perform complex functions in various fields of
application including pattern recognition, identification, classification, speech, vision and
control systems. Today neural networks can be trained to solve problems that are difficult
for conventional computers or human beings. The supervised training methods are
commonly used, but other networks can be obtained from unsupervised training
techniques or from direct design methods. Unsupervised networks can be used, for
instance, to identify groups of data. Certain kinds of linear networks and Hopfield
networks are designed directly. In summary, there are a variety of kinds of design and
learning techniques that enrich the choices that a user can make. The field of neural
networks has a history of some five decades but has found solid application only in the
past fifteen years, and the field is still developing rapidly. Thus, it is distinctly different
from the fields of control systems or optimization where the terminology, basic
mathematics, and design procedures have been firmly established and applied for many
years.
4.2 Simple Neuron
A neuron with a single scalar input and no bias appears on the left below.

Fig 4.2 Simple Neuron

The scalar input p is transmitted through a connection that multiplies its strength
by the scalar weight w, to form the product wp, again a scalar. Here the weighted input
wp is the only argument of the transfer function f, which produces the scalar output a.

37

The neuron on the right has a scalar bias, b. You may view the bias as simply being
added to the product wp as shown by the summing junction or as shifting the function f to
the left by an amount b. The bias is much like a weight, except that it has a constant input
of 1. The transfer function net input n, again a scalar, is the sum of the weighted input wp
and the bias b. This sum is the argument of the transfer function f. (Radial Basis
Networks discusses a different way to form the net input n.) Here f is a transfer function,
typically a step function or a sigmoid function, which takes the argument n and produces
the output a. Examples of various transfer functions are given in the next section. Note
that w and b are both adjustable scalar parameters of the neuron.
The central idea of neural networks is that such parameters can be adjusted so that
the network exhibits some desired or interesting behavior. Thus, we can train the network
to do a particular job by adjusting the weight or bias parameters, or perhaps the network
itself will adjust these parameters to achieve some desired end. All of the neurons in this
toolbox have provision for a bias, and a bias is used in many of our examples and will be
assumed in most of this toolbox. However, you may omit a bias in a neuron if you want.
As previously noted, the bias b is an adjustable (scalar) parameter of the neuron. It is not
an input. However, the constant 1 that drives the bias is an input and must be treated as
such when considering the linear dependence of input vectors in Linear Filters.
4.3 Transfer Functions:
The behaviour of an ANN (Artificial Neural Network) depends on both the weights and
the input-output function (transfer function) that is specified for the units. This function
typically falls into one of three categories:
linear (or ramp)
threshold
sigmoid
For linear units, the output activity is proportional to the total weighted output.

38

For threshold units, the output is set at one of two levels, depending on whether the total
input is greater than or less than some threshold value.
For sigmoid units, the output varies continuously but not linearly as the input changes.
Sigmoid units bear a greater resemblance to real neurones than do linear or threshold
units, but all three must be considered rough approximations.
4.4 Architecture of neural networks:
4.4.1Feed-forward networks:
Feed-forward ANNs (figure 4.3) allow signals to travel one way only; from input to
output. There is no feedback (loops) i.e. the output of any layer does not affect that same
layer. Feed-forward ANNs tend to be straight forward networks that associate inputs with
outputs. They are extensively used in pattern recognition. This type of organisation is also
referred to as bottom-up or top-down.
4.4.2Feedback networks:
Feedback networks (figure 4.4) can have signals travelling in both directions by
introducing loops in the network. Feedback networks are very powerful and can get
extremely complicated. Feedback networks are dynamic; their 'state' is changing
continuously until they reach an equilibrium point. They remain at the equilibrium point
until the input changes and a new equilibrium needs to be found. Feedback architectures
are also referred to as interactive or recurrent, although the latter term is often used to
denote feedback connections in single-layer organisations.

39

40

4.5 Network layers:

The commonest type of artificial neural network consists of three groups, or layers, of
units: a layer of "input" units is connected to a layer of "hidden" units, which is
connected to a layer of "output" units. (see Figure 5.1)

The activity of the input units represents the raw information that is fed into the
network.

The activity of each hidden unit is determined by the activities of the input units
and the weights on the connections between the input and the hidden units.

The behaviour of the output units depends on the activity of the hidden units and
the weights between the hidden and output units.

This simple type of network is interesting because the hidden units are free to construct
their own representations of the input. The weights between the input and hidden units
determine when each hidden unit is active, and so by modifying these weights, a hidden
unit can choose what it represents.
We also distinguish single-layer and multi-layer architectures. The single-layer
organisation, in which all units are connected to one another, constitutes the most general
case and is of more potential computational power than hierarchically structured multilayer organisations. In multi-layer networks, units are often numbered by layer, instead of
following a global numbering.
4.6 Perceptrons:
The most influential work on neural nets in the 60's went under the heading of
'perceptrons' a term coined by Frank Rosenblatt. The perceptron (figure 4.5) turns out to
be an MCP model ( neuron with weighted inputs ) with some additional, fixed, pre-processing. Units labelled A1, A2, Aj , Ap are called association units and their task is to
extract specific, localised featured from the input images. Perceptrons mimic the basic

41

idea behind the mammalian visual system. They were mainly used in pattern recognition
even though their capabilities extended a lot more.

Figure 4.5 Perceptron

In 1969 Minsky and Papert wrote a book in which they described the limitations of single
layer Perceptrons. The impact that the book had was tremendous and caused a lot of
neural network researchers to loose their interest. The book was very well written and
showed mathematically that single layer perceptrons could not do some basic pattern
recognition operations like determining the parity of a shape or determining whether a
shape is connected or not. What they did not realised, until the 80's, is that given the
appropriate training, multilevel perceptrons can do these operations.

4.7 Backpropagation
4.7.1 Introduction:
Backpropagation was created by generalizing the Widrow-Hoff learning rule to
multiple-layer networks and nonlinear differentiable transfer functions. Input vectors and
the corresponding target vectors are used to train a network until it can approximate a
function, associate input vectors with specific output vectors, or classify input vectors in
an appropriate way as defined by you. Networks with biases, a sigmoid layer, and a linear
42

output layer are capable of approximating any function with a finite number of
discontinuities.
Standard backpropagation is a gradient descent algorithm, as is the Widrow-Hoff learning
rule, in which the network weights are moved along the negative of the gradient of the
performance function. The term backpropagation refers to the manner in which the
gradient is computed for nonlinear multilayer networks. There are a number of variations
on the basic algorithm that are based on other standard optimization techniques, such as
conjugate gradient and Newton methods. The Neural Network Toolbox implements a
number of these variations. This chapter explains how to use each of these routines and
discusses the advantages and disadvantages of each. Properly trained backpropagation
networks tend to give reasonable answers when presented with inputs that they have
never seen. Typically, a new input leads to an output similar to the correct output for
input vectors used in training that are similar to the new input being presented. This
generalization property makes it possible to train a network on a representative set of
input/target pairs and get good results without training the network on all possible
input/output pairs. There are two features of the Neural Network Toolbox that are
designed to improve network generalization - regularization and early stopping. These
features and their use are discussed later in this chapter. This chapter also discusses
preprocessing and postprocessing techniques, which can improve the efficiency of
network training. Before beginning this chapter you may want to read a basic reference
on backpropagation, such as D.E Rumelhart, G.E. Hinton, R.J. Williams, "Learning
internal representations by error propagation," D. Rumelhart and J. McClelland, editors.
Parallel Data Processing, Vol.1, Chapter 8, the M.I.T. Press, Cambridge, MA 1986 pp.
318-362. This subject is also covered in detail in Chapters 11 and 12 of M.T. Hagan, H.B.
Demuth, M.H. Beale, Neural Network Design, PWS Publishing Company, Boston, MA
1996. The primary objective of this chapter is to explain how to use the backpropagation
training functions in the toolbox to train feedforward neural networks to solve specific
problems. There are generally four steps in the training process: Assemble the training
data Create the network object Train the network Simulate the network response to new
inputs This chapter discusses a number of different training functions, but in using each
function we generally follow these four steps. The next section, Fundamentals, describes

43

the basic feedforward network structure and demonstrates how to create a feedforward
network object. Then the simulation and training of the network objects are presented.
4.7.2 Creating a Network (newff):
The first step in training a feedforward network is to create the network object. The
function newff creates a feedforward network. It requires four inputs and returns the
network object. The first input is an R by 2 matrix of minimum and maximum values for
each of the R elements of the input vector. The second input is an array containing the
sizes of each layer. The third input is a cell array containing the names of the transfer
functions to be used in each layer. The final input contains the name of the training
function to be used. For example, the following command creates a two-layer network.
There is one input vector with two elements. The values for the first element of the input
vector range between -1 and 2, the values of the second element of the input vector range
between 0 and 5. There are three neurons in the first layer and one neuron in the second
(output) layer. The transfer function in the first layer is tan-sigmoid, and the output layer
transfer function is linear. The training function is traingd (which is described in a later
section).
net=newff([-1 2; 0 5],[3,1],{'tansig','purelin'},'traingd');
This command creates the network object and also initializes the weights and biases of
the network; therefore the network is ready for training. There are times when you may
want to reinitialize the weights, or to perform a custom initialization. The next section
explains the details of the initialization process.
4.7.3 Initializing Weights (init).

Before training a feedforward network, the weights and biases must be initialized. The
newff command will automatically initialize the weights, but you may want to reinitialize
them. This can be done with the command init. This function takes a network object as
input and returns a network object with all weights and biases initialized. Here is how a
network is initialized (or reinitialized):

44

net = init(net);
4.7.4 Simulation (sim):
The function sim simulates a network. sim takes the network input p, and the network
object net, and returns the network outputs a. Here is how you can use sim to simulate the
network we created above for a single input vector:
p = [1;2];
a = sim(net,p)
a = -0.1011
(If you try these commands, your output may be different, depending on the state of your
random number generator when the network was initialized.) Below, sim is called to
calculate the outputs for a concurrent set of three input vectors. This is the batch mode
form of simulation, in which all of the input vectors are place in one matrix. This is much
more efficient than presenting the vectors one at a time.
p = [1 3 2;2 4 1];
a=sim(net,p)
a = -0.1011 -0.2308

0.4955

4.7.5 Training:
Once the network weights and biases have been initialized, the network is ready for
training. The network can be trained for function approximation (nonlinear regression),
pattern association, or pattern classification. The training process requires a set of
examples of proper network behavior - network inputs p and target outputs t. During
training the weights and biases of the network are iteratively adjusted to minimize the
network performance function net.performFcn. The default performance function for
feedforward networks is mean square error mse - the average squared error between the
network outputs a and the target outputs t. The remainder of this chapter describes several
different training algorithms for feedforward networks. All of these algorithms use the
gradient of the performance function to determine how to adjust the weights to minimize
performance. The gradient is determined using a technique called backpropagation,
which involves performing computations backwards through the network. The

45

backpropagation computation is derived using the chain rule of calculus and is described
in Chapter 11 of [HDB96]. The basic backpropagation training algorithm, in which the
weights are moved in the direction of the negative gradient, is described in the next
section. Later sections describe more complex algorithms that increase the speed of
convergence.
4.7.6 Levenberg-Marquardt (trainlm):

Like the quasi-Newton methods, the Levenberg-Marquardt algorithm was designed to

approach second-order training speed without having to compute the Hessian matrix.
When the performance function has the form of a sum of squares (as is typical in training
feedforward networks), then the Hessian matrix can be approximated as and the gradient
can be computed as where is the Jacobian matrix that contains first derivatives of the
network errors with respect to the weights and biases, and e is a vector of network errors.
The Jacobian matrix can be computed through a standard backpropagation technique (see
[HaMe94]) that is much less complex than computing the Hessian matrix.
The Levenberg-Marquardt algorithm uses this approximation to the Hessian
matrix in the following Newton-like update: When the scalar is zero, this is just
Newton's method, using the approximate Hessian matrix. When is large, this becomes
gradient descent with a small step size. Newton's method is faster and more accurate near
an error minimum, so the aim is to shift towards Newton's method as quickly as possible.
Thus, is decreased after each successful step (reduction in performance function) and is
increased only when a tentative step would increase the performance function. In this
way, the performance function will always be reduced at each iteration of the algorithm.
In the following code, we reinitialize our previous network and retrain it using the
Levenberg-Marquardt algorithm. The training parameters for trainlm are epochs, show,
goal, time, min_grad, max_fail, mu, mu_dec, mu_inc, mu_max, mem_reduc. We have
discussed the first six parameters earlier. The parameter mu is the initial value for . This
value is multiplied by mu_dec whenever the performance function is reduced by a step. It
is multiplied by mu_inc whenever a step would increase the performance function. If mu
becomes larger than mu_max, the algorithm is stopped.

46

The parameter mem_reduc is used to control the amount of memory used by the
algorithm. It is discussed in the next section.
The parameters show and epoch are set to 5 and 300, respectively.
p = [-1 -1 2 2;0 5 0 5];
t = [-1 -1 1 1];
net=newff(minmax(p),[3,1],{'tansig','purelin'},'trainlm');
net.trainParam.show = 5;
net.trainParam.epochs = 300;
net.trainParam.goal = 1e-5;
[net,tr]=train(net,p,t);
TRAINLM, Epoch 0/300, MSE 2.7808/1e-05, Gradient 7.77931/1e-10
TRAINLM, Epoch 4/300, MSE 3.67935e-08/1e-05, Gradient
0.000808272/1e-10
TRAINLM, Performance goal met.
a = sim(net,p)
a = -1.0000 -1.0000

1.0000

0.9996

The original description of the Levenberg-Marquardt algorithm is given in [Marq63]. The

application of Levenberg-Marquardt to neural network training is described in [HaMe94]
and starting on page 12-19 of [HDB96]. This algorithm appears to be the fastest method
for training moderate-sized feedforward neural networks (up to several hundred weights).
It also has a very efficient MATLAB implementation, since the solution of the matrix
equation is a built-in function, so its attributes become even more pronounced in a
MATLAB setting.

47

4.8 Applications of neural networks:

Neural Networks in Practice :
Given this description of neural networks and how they work, what real world
applications are they suited for? Neural networks have broad applicability to real world
business problems. In fact, they have already been successfully applied in many
industries.
Since neural networks are best at identifying patterns or trends in data, they are well
suited for prediction or forecasting needs including:
sales forecasting
industrial process control
customer research
data validation
risk management
target marketing
But to give you some more specific examples; ANN are also used in the following
specific paradigms: recognition of speakers in communications; diagnosis of hepatitis;
recovery of telecommunications from faulty software; interpretation of multimeaning
Chinese words; undersea mine detection; texture analysis; three-dimensional object
recognition; hand-written word recognition; and facial recognition.
Neural networks in medicine:

48

Artificial Neural Networks (ANN) are currently a 'hot' research area in medicine and it is
believed that they will receive extensive application to biomedical systems in the next
few years. At the moment, the research is mostly on modelling parts of the human body
and recognising diseases from various scans (e.g. cardiograms, CAT scans, ultrasonic
scans, etc.).
Neural networks are ideal in recognising diseases using scans since there is no need to
provide a specific algorithm on how to identify the disease. Neural networks learn by
example so the details of how to recognise the disease are not needed. What is needed is a
set of examples that are representative of all the variations of the disease.
The quantity of examples is not as important as the 'quantity'. The examples need to be
selected very carefully if the system is to perform reliably and efficiently.
Modelling and Diagnosing the Cardiovascular System:
Neural Networks are used experimentally to model the human cardiovascular system.
Diagnosis can be achieved by building a model of the cardiovascular system of an
individual and comparing it with the real time physiological measurements taken from
the patient. If this routine is carried out regularly, potential harmful medical conditions
can be detected at an early stage and thus make the process of combating the disease
much easier.
A model of an individual's cardiovascular system must mimic the relationship among
physiological variables (i.e., heart rate, systolic and diastolic blood pressures, and
breathing rate) at different physical activity levels. If a model is adapted to an individual,
then it becomes a model of the physical condition of that individual. The simulator will
have to be able to adapt to the features of any individual without the supervision of an
expert. This calls for a neural network.
Another reason that justifies the use of ANN technology, is the ability of ANNs to
provide sensor fusion which is the combining of values from several different sensors.
Sensor fusion enables the ANNs to learn complex relationships among the individual

49

sensor values, which would otherwise be lost if the values were individually analysed. In
medical modelling and diagnosis, this implies that even though each sensor in a set may
be sensitive only to a specific physiological variable, ANNs are capable of detecting
complex medical conditions by fusing the data from the individual biomedical sensors.
Electronic noses:
ANNs are used experimentally to implement electronic noses. Electronic noses have
several potential applications in telemedicine. Telemedicine is the practice of medicine
over long distances via a communication link. The electronic nose would identify odours
in the remote surgical environment. These identified odours would then be electronically
transmitted to another site where an door generation system would recreate them.
Because the sense of smell can be an important sense to the surgeon, telesmell would
enhancetelepresentsurgery.
Instant Physician:
An application developed in the mid-1980s called the "instant physician" trained
an autoassociative memory neural network to store a large number of medical records,
each of which includes information on symptoms, diagnosis, and treatment for a
particular case. After training, the net can be presented with input consisting of a set of
symptoms. it will then find the full stored pattern that represents the "best" diagnosis and
treatment.
Neural Networks in business
Business is a diverted field with several general areas of specialisation such as accounting
or financial analysis. Almost any neural network application would fit into one business
area or financial analys. There is some potential for using neural networks for business
purposes, including resource allocation and scheduling. There is also a strong potential
for using neural networks for database mining, that is, searching for patterns implicit
within the explicitly stored information in database. Most of the funded work in this area
is classified as proprietary. Thus, it is not possible to report on the full extent of the work

50

going on. Most work is applying neural networks, such as the Hopfield-Tank network for
optimization and scheduling.
Marketing:
There is a marketing application which has been integrated with a neural network
system. The Airline Marketing Tactician (a trademark abbreviated as AMT) is a computer
system made of various intelligent technologies including expert systems. A feedforward
neural network is integrated with the AMT and was trained using back-propagation to
assist the marketing control of airline seat allocations.
The adaptive neural approach was amenable to rule expression. Additionaly, the
application's environment changed rapidly and constantly, which required a continuously
adaptive solution. The system is used to monitor and recommend booking advice for each
departure. Such information has a direct impact on the profitability of an airline and can
provide a technological advantage for users of the system. [Hutchison & Stephens, 1987]
While it is significant that neural networks have been applied to this problem, it is also
important to see that this intelligent technology can be integrated with expert systems and
other approaches to make a functional system. Neural networks were used to discover the
influence of undefined interactions by the various variables. While these interactions
were not defined, they were used by the neural system to develop useful conclusions. It is
also noteworthy to see that neural networks can influence the bottom line.
Credit Evaluation:
The HNC company, founded by Robert Hecht-Nielsen, has developed several neural
network applications. One of them is the Credit Scoring system which increase the
profitability of the existing model up to 27%. The HNC neural systems were also applied
to mortgage screening. A neural network automated mortgage insurance underwritting
system was developed by the Nestor Company. This system was trained with 5048
applications of which 2597 were certified. The data related to property and borrower
qualifications. In a conservative mode the system agreed on the underwritters on 97% of

51

the cases. In the liberal model the system agreed 84% of the cases. This is system run on
an Apollo DN3000 and used 250K memory while processing a case file in approximately
1 sec.

MODELLING

5.1

DYNAMIC MODELLING OF INDUCTION MOTOR:

Consider a space vector Yss of stator voltage, current and flux linkage.

Ys

= (2/3) (Ya + Yb + 2 Yc)

----------(5.1)
Where = exp (j2/3)
The above transform being reversible

Ya = Re (Ys s), Yb = Re (2 Ys s), Yc = Re (Ys s).

----------(5.2)

Voltage equations on the stator with respect to stationary reference

frame

Vs

= Rs Is

+ p s

-----------(5.3)

52

Voltage equations for rotor on rotor reference frame is :

Vr = Rr Ir + p r = 0
---------(5.4)

Fig 5.1 Dynamic Equivalent Circuit on a Stationary

Reference Frame

NEED FOR TRANSFORMATION OF FRAMES:

The voltage equations describes the performance of induction and synchronous

machine

We found that some of the machine inductances are functions of the rotor speed,
where upon the coefficients of the differential equations which describe the
behavior of these machines are time varying except when the rotor is stalled.

A change of variables is often used to reduce the complexity of these differential

53

equations

There are several changes of variables which refers machine variables to a frame
of reference which rotates at a n arbitrary angular velocity.

It is very convenient to transform actual rotor variables (Vr,Ir,r) on a rotor reference

frame into new variables (Vrs,Irs,rs) on a stator reference frame.

Rotor reference frame to stator reference frame is:

Ir s = (1/n) exp (j) Ir

-----------(5.5)

r s = n exp (j) r

-----------(5.6)

Rr =n2Rr

------------(5.7)

Therefore the stator equation with respect to stationary reference frame is:

Vs s = Rs Is s + p s s

---------------(5.8)

The rotor equation with respect to stationary reference frame is:

0 = Rr Ir s + (p j0) r s

-------------(5.9)

Where 0 = p0 ; speed of motor in electrical frequency unit

54

The flux linkage equations are given as:

s s = Ls Is s + Lm Ir s
r s = Lm Is s + Lr Ir s

where

-----------------(5.10)
----------------(5.11)

Ls = Lls + Lm

---------------------(5.12)

Lr = Llr + Lm

-----------------(5.13)

Dynamic model of induction motor on a stationary (stator) reference frame

Vs s = (Rs + Ls p) Is s + Lm p Ir s
0 = (Rr + Lr (p - jo)) Irs + Lm (p j0) Is s

------------(5.14)
---------(5.15)

For a arbitrary reference frame rotating at a speed a

55

Fig 5.2

Dynamic Equivalent Circuit on an Arbitray Reference Frame Rotating at .

Y a = exp (- j a) Y s

-------------------(5.16)

Reconstructing the equations:

Vs a = (Rs + Ls p) Is a + Lm p Ir a + ja s a

----------(5.17)

0 = (Rr + Lr p) Ir a + Lm p Is a + j (a - o) r a,

--------(5.18)

Again reconstructing the equation:

Vsa = Rs Is a + p ( Ls Is a + Lm Ir a)+ jasa

----------------(5.19)

0 = Rr Ir a + p (Lm Is a + Lr Ir a )+ (ja jo)ra

--------(5.20)

Since

s a = Ls Isa + Lm Ira

--------------------(5.21)

56

r a = Lm Isa + Lr Ir a

------------------(5.22)

we can write the above equations as:

Vsa = Rs Is a + ps a + ja s a

--------(5.23)

0 = Rr Ir a + pr a + j (a - o) r a

-------(5.24)

The dynamic model of induction motor is shown in figure below with the help of the
above equations:

Vsa = Rs Is a + ps a + ja s a ------(5.25)

57

Fig 5.3

0 = Rr Ir a + pr a + j (a - o) r a --------(5.26)
Flux current relations:
From the figure 5.2 the flux linkage equations can be written as:

s = Lls Is + Lm( Is + Ir)

-------(5.27)

r = Llr Ir + Lm(Is + Ir)

--------(5.28)

the above equations can be written as :

s = Is (Lls + Lm) + LmIr

-----------(5.29)

r = IsLm + (Llr + Lm)Ir

-----------(5.30)

by matrix manipulation we get :

58

Is = Gss -

Gm r

----------------(5.31)

Ir = -Gm1s + Ggr

---------------(5.32)

Where:

Gs = (Llr + Lm)/K

Gg

-------------(5.33)

Gm = Lm/K

----------(5.34)

Gm1 = Lm/K

--------------(5.35)

= (Lls + Lm)/K

------------(5.36)

And K = LlsLlr + LlsLm + LmLlr ----------(5.37)

Using the above equations between Current and Flux:

Fig 5.4 Current and Flux Diagram

5.2 Modeling of Vector Controller:

59

Indirect or feed forward vector control:

The control is done using the unit vector signals ( cose and sine)

Very popular in industrial applications

ds-qs

fixed on stator

dr-qr

fixed on rotor are moving at a speed r

de-qe

rotating ahead of dr-qr

by positive slip angle sl corresponding to slip

frequency sl
therefore rotor pole is directed on the de axis and e = r + sl. We can write as:
e = wedt = (r + sl)dt = r + sl

---------------------(5.38)

for decoupling control, the stator flux component I ds should be aligned on the de
axis and torque component of current Iqs should be on qe axis

for decouling control we can now make a derivation of control equations of

indirect vector control with the help of de-qe equivalent circuits. The rotor circuits
equations can be written as :

The equivalent circuits are :

Fig 5.5 Dynamic de-qe equivalent circuit of machine -- qe axis circuit

60

Fig 5.6 Dynamic de-qe equivalent circuit of machine -- de axis circuit

The rotor circuit equations can be written as :

ddr/dt + RrIdr (e-r)dr =0

-------(5.39)

dqr /dt + RrIqr + (e-r)qr = 0

------(5.40)

the rotor flux linkage expressions can be given as:

qr = LrIqr + LmIqs
dr = LrIdr + LmIds

-------------------

(5.41)

---------------(5.42)

we write the above equations as :

Idr = (1/Lr)dr - (Lm/Lr)Ids

------------------(5.43)

Iqr = (1/Lr)qr - (Lm/Lr)Iqs---------------------(5.44)

Substituting the above equations in (5.39) and (5.40) :

ddr/dt + (Rr/Lr)dr - (Lm/Lr)RrIds - slqr = 0------(5.45)

61

dqr/dt + (Rr/Lr) qr - (Lm/Lr) RrIqs + sldr = 0-------(5.46)

where sl = e r

for decoupling control it is desirable that:

qr = 0

-----------(5.47)

that is
dqr/dt = 0

--------(5.48)

so that total rotor flux r is directed on the de axis

r = dr

-------------------(5.49)

therefore the above equations can be written as:

dr/dt + (Rr/Lr)r - (Lm/Lr)RrIds

= 0-----------(5.50)

dr/dt + (Rr/Lr)r = (Lm/Lr)RrIds

(Lr/Rr)( dr/dt) + r = LmIds

---------(5.51)
-----------(5.52)

And
- (Lm/Lr) RrIqs + slr = 0-----------------(5.53)
slr = (Lm/Lr) RrIqs
sl = (LmRr/rLr)Iqs

----------------(5.54)
--------------(5.55)

If r is constant then the equation is

r = LmIds

-----------------------(5.56)

62

 To implement the indirect vector control strategy it sis necessary to take equations
e = r + sl

-------------------(5.57)

(Lr/Rr)( dr/dt) + r = LmIds

sl = (LmRr/rLr)Iqs

--------------(5.58)
------------------(5.59)

the speed control loop generates the torque component of current iqs* as usual
the flux component of current Ids* for the desired rotor flux r is determined
from equation r = LmIds and is maintained constant in open loop manner.

The variation of magnetizing inductance Lm will cause some drift in the flux.
The slip frequency sl* is generated from Iqs* in feedforward manner from
sl = (LmRr/rLr)Iqs

----------------------(5.60)

The corresponding slip gain Ks is:

Ks = sl*/ Iqs*= LmRr/Lrr

------------------(5.61)

Signal sl* is added with speeed signal r to generate frequency signal e

The unit vector signals cose and sine are then generated from e by integration.

Torque equation:
i q* Cal cul ator

Te = (3/2)(p/2)(LmTe*
/Lr) rIqs
Phir

Iq*

------------------(5.62)

Iq* Calculator
63

1
Te*

u[1]*0.341/(u[2]+1e-3)

1
Iq*

Phir

Lm = 34.7 mH

Iq= ( 2/3) * (2/p) * ( Lr/Lm) * (Te / Phir)

Lr = Ll'r +Lm = 0.8 +34.7= 35.5 mH

Iq= 0.341 * (Te / Phir)

p= # of poles = 4

Fig 5.7 Iq* Calculator

Id* calculator

id* Calculator
Phir*

Id*

-K-

Phir*

1
Id*

KF
Id* = Phir*/ Lm
Lm= 34.7 mH

Fig 5.8Id* calculator

Theta calculator
Theta Calculator
Iq

1
Iq

Phir

Mux

theta

34.7e-3*u[1]/(u[2]*0.1557+1e-3)
wm

2
Phir

wsl

1
s

1
theta

wm
Theta= Electrical angle= integ ( wsl + wm)
wsl=slip speed (rad/s) = Lm *Iq / ( Tr * Phir)
wm= Rotor speed (rad/s)

Lm = 34.7 mH
Lr = Ll'r +Lm = 0.8 +34.7= 35.5 mH
Rr= 0.228 ohms
Tr = Lr / Rr = 0.1557 s

64

Fig 5.9 Theta calculator

abc2dq

abc to dq

iabc
theta

idq

f(u)

2
theta

Fcn

2/3

1
idq

1
f(u)

iabc

Fcn1

Fig 5.10 abc to dq

Fcn = u(1)*cos(u(4))+u(2)*cos(u(4)-2*pi/3)+u(3)*cos(u(4)+2*pi/3)

----------(5.63)

Fcn1 = -u(1)*sin(u(4))-u(2)*sin(u(4)-2*pi/3)-u(3)*sin(u(4)+2*pi/3)
dq2abc

----------(5.64)

idq

dq to abc

theta

iabc^

65

f(u)
Fcn
1
f(u)

idq

1
iabc^

Fcn1

f(u)

2
theta

Fcn2

Fig 5.11 dq to abc

Fcn = u(1)*cos(u(3))-u(2)*sin(u(3))

--------------(5.65)

Fcn1 = u(1)*cos(u(3)-2*pi/3)-u(2)*sin(u(3)-2*pi/3)

--------------(5.66)

Fcn2 = u(1)*cos(u(3)+2*pi/3)-u(2)*sin(u(3)+2*pi/3-----------------(5.67)
Flux calculator

Flux Calculator
Phir

1
Phir

Id

.157s+1
Transfer Fcn

34.7e-3
Lm

1
Id

Phir = Lm *Id / (1 +Tr .s)

Lm = 34.7 mH
Tr = Lr / Rr = 0.1557 s
Lr = Ll'r +Lm = 0.8 +34.7= 35.5 mH

Rr = 0.228 ohms

66

Fig 5.12 Flux calculator

Flux Cal culator

Phir

Id

T heta Calculator

abc2dq

Iq
Phir

iabc
theta

theta

wm

idq

Demux

INVERT ER
iq* Cal culator
2
T e*

Te*
Phir

dq2abc

Ie*

idq

Iq*

theta

iabc^

i d* Calculator
3

Phir*

Id*

Phir*
2

Is

p/2

Wmec

67

Fig-5.13
Vector Control Subsystem

INDIRECT VECTOR CONTROL OF INDUCTION MOTOR WITH PI

SPEED CONTROLLER AND NEURAL NETWORKS
6.1 PI CONTROLLER BACKGROUND:
A complete discussion of Proportional Integral (PI) controllers is beyond the scope
of this application note, but this section will provide you with the basics of PI operation.
A PI controller responds to an error signal in a closed control loop and attempts to adjust
the controlled quantity to achieve the desired system response. The controlled parameter
can be any measurable system quantity such as speed, torque, or flux. The benefit of the
PI controller is that it can be adjusted empirically by adjusting one or more gain values
and observing the change in system response.
A digital PI controller is executed at a periodic sampling interval. It is assumed that
the controller is executed frequently enough so that the system can be properly

68

controlled. The error signal is formed by subtracting the desired setting of the parameter
to be controlled from the actual measured value of that parameter. The sign of the error
indicates the directionof change required by the control input. The Proportional (P) term
of the controller is formed by multiplying the error signal by a P gain, causing the PI
controller to produce a control response that is a function of the error magnitude. As the
error signal becomes larger, the P term of the controller becomes larger to provide more
correction.
The effect of the P term tends to reduce the overall error as time elapses. However,
the effect of the P term reduces as the error approaches zero. In most systems, the error of
the controlled parameter gets very close to zero but does not converge. The result is a
small remaining steady state error. The Integral (I) term of the controller is used to
eliminate small steady state errors.
The I term calculates a continuous running total of the error signal. Therefore, a small
steady state error accumulates into a large error value over time. This accumulated error
signal is multiplied by an I gain factor and becomes the I output term of the PI controller.

Fig-6.1

PI BASED CONTROLLER

6.1.1 TUNING OF PI CONTROLLERS:

69

Proportional-integral (PI) controllers have been introduced in process control

industries. Hence various techniques using PI controllers to achieve certain performance
index for system response are presented. The technique to be adapted for determining the
proportional integral constants of the controller, called Tuning, depends upon the dynamic
response of the plant.
In presenting the various tuning techniques we shall assume the basic control
configuration wherein the controller input is the error between the desired output
(command set point input) and the actual output. This error is manipulated by the
controller (PI) to produce a command signal for the plant according to the relationship.
U(s) = Kp (1+1/ is)

Or in time domain
U(t) = Kp [e(t) + (1/ i ) edt]
where

Kp = proportional gain
i = integral time constant

If this response is S-shaped as in, Ziegler-Nichols tuning method is applicable.

Fig -6.2 S- shaped response of the plant

Zeigler- Nichols Rules for tuning PI controllers:
First Rule: The S-shaped response is characterized by two constants, the dead time L
and the time constant T as shown. These constants can be determined by drawing a
tangent to the S-shaped curve at the inflection point and state value of the output. From
the response of this nature the plant can be mathematically modeled as first order system
with a time constant T and delay time L as shown in block diagram. The gain K

70

corresponds to the steady state value of the output Css. The value of Kp,Ti and Td of the
controllers can then be calculated as below:
Kp=1.2(T/L)
i = 2L

Fig 6.3 PI Controller 1st order system block diagram

6.2 NEURAL NETWORKS BASED CONTROLLER:

Neural networks can perform massively parallel operations. The exhibit fault tolerance
since the information is distributed in the connections throughout the network. By using
neural PI controller the peak overshoot is reduced and the system reaches the steady state
quickly when compared to a conventional PI controller
.

71

Fig-6.4

NN BASED CONTROLLER

6.2.1 Program for creating the neural network:

load n
k1=max(i');
k2=max(o1');
P=i'/k1;
T=o1'/k2;
n=157128;
net = newff(minmax(P),[5 1],{'tansig' 'purelin'});
net.trainParam.epochs = 200;
net = train(net,P,T);
Y = sim(net,P);
plot(P,T,P,Y,'o')

72

gensim(net,-1)

Fig 6.5

NN Controller 1st order system block diagram

Simulation Results
#Case 1: No-Load
PI Controller:

Speed(rad/s) Vs Time(s):

73

Speed(rad/s)

Time(s)
Fig 7.1
Torque(N-m) Vs Time(s)
Torque(N-m)

74

Time(s)
Fig 7.2
Current (A) Vs Time(s)
Current (A)

75

Time(s)
Fig 7.3
At No-Load:
NN Controller:

Speed(rad/s) Vs Time(s):

76

Speed(rad/s)

Time(s)
Fig 7.4
Torque(N-m) Vs Time(s)
Torque(N-m)

77

Time(s)
Fig 7.5
Current (A) Vs Time(s)
Current (A)

78

Time(s)
Fig 7.6
#Case 2: Step Change in -Load
PI Controller:

Speed(rad/s)Vs Time(s):
79

Speed(rad/s)

Time(s)
Fig 7.7
Torque(N-m)Vs Time(s)
Torque(N-m)

80

Time(s)
Fig 7.8
Current (A) Vs Time(s)
Current (A)

81

Time(s)
Fig 7.9
At Step Change in Load
NN Controller:

Speed(rad/s)Vs Time(s):

82

Speed(rad/s)

Time(s)
Fig 7.10
Torque(N-m)Vs Time(s)
Torque(N-m)

83

Time(s)
Fig 7.11
Current (A) Vs Time(s)
Current (A)

84

Time(s)
Fig 7.12

#Case 3 : Speed Reversal:

PI Controller:
Speed(rad/s)Vs Time(s):

85

Speed(rad/s)

Time(s)
Fig 7.13
Torque(N-m)Vs Time(s)
Torque(N-m)

86

Time(s)
Fig 7.14
Current (A) Vs Time(s)
Current (A)

87

Time(s)
Fig 7.15
NN Controller:

Speed(rad/s)Vs Time(s):
Speed(rad/s)

88

Time(s)
Fig 7.16
Torque(N-m)Vs Time(s)
Torque(N-m)

89

Time(s)
Fig 7.17
Current (A) Vs Time(s)
Current (A)

90

Time(s)
Fig 7.18

DISCUSSION OF RESULTS
91

In this chapter the obtained Results are discussed. The dynamic model
induction motor is developed in the SIMULINK, and the Vector controller is interfaced
with it in the SIMULINK.

The PI controller is designed with appropriate gain values and interfaced to

the Vector controlled induction motor. The system is simulated in the MATLAB and the
results are observed. The results of the PI controlled system is not accurate as it shows
peak overshoot. To overcome this we implement Neural Networks based controller which
reduces the overshoot and gives more accurate results than PI based controller.

92

Conclusion & Future Scope

Challenging and excelling the human brain is one of our long cherished dreams.
Intelligent controllers reflect human thinking, human perception and human way of
reasoning. Simulation studies show that the Neural Networks based controller provides
better results for an induction motor when compared to a conventional PI controller.
So, Neural Networks controller is an attractive technique when the plant model is
complex. The only drawback of using more neurons in the hidden layer is the increased
in number of weights and therefore the calculations involved in the training algorithm.

# In real time system it is more uncertain and time varying in its operation either
Neural Networks controller or FUZZY controller can provide prompt control over the
speed or torque output of an induction motor provided that training is rigorous .But
unfortunately the training time is very high for an NN controller or FUZZY controller to
give accurate output.
# Further the of Neuro- Fuzzy design and implementation to avoid the prolong
training time of NN controller.

# The extension of this project is to implementation of Neuro-Fuzzy Controller

(NEFCON) for further better performance. NEFCON combines the merits of fuzzy
systems and neural networks.

93

BIBILOGRAPHY
1.C.M.Liaw.Y.S.Kung
inductionmachines

and

M.S.Ouyang

Identification

and

control

of

using artificial neural networks.IEEE Trans Ind.Applicat.

vol.31.pp.612-619,1995.
2. C.M.Liaw.Y.S.Kung and C.M.Wu Design and implementation of a high performance
field oriented inductionmotor drive.IEEE Trans Ind.Applicat. vol.38.pp.275-282,1991.
3.M.A.Wishart and R.G.Harley Identification and control of

inductionmachines using

artificial neural networks.IEEE Trans Ind.Applicat. vol.34.pp.412-419,1994.

4.Levin and K.S.Narendra Control dynamics systems using neural networks
controllability and stabilization. IEEE Trans on Neural networks.NN-1. 1,4-27,1990.
5..ARTIFICIAL NEURAL NETWORKS B.YAGNA NARAYANA
6.AN INTRODUCTION TO NEURAL NETWORKS J.A.ANDERSON
7.ELECTRICAL MACHINES P.S.BIMBRA
8.ELECTRICAL MACHINES S.K.BHATTA CHARYA
9.MACHINE MODELLING KRAUSE
10.ELECTRICAL DRIVES---- VEDAM SUBRAMANYAM
11.MODERN POWER ELECTRONICS AND AC DRIVES-----BIMAL.K.BOSE

94