Of Induction Motor Using Artificial Neural Network and Implementation in MATLAB

Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only.
. 1 Abstract: Motors play an important role in daily lifelike in industrial manufact uring and in many other applications. Induction motors are robust, simple, small in size, low in cost, almost maintenancefree and possess a wide range of speeds compared to DC motors. However, complexity of signal processing and poor precis ion limits its usage. Speed estimation in an induction motor is very difficult b ecause of its non-linear dynamic nature. Filed Oriented Control or Vector Contro l developed by Blaschke(1972) and Vas (1900) respectively is used in motor contr ol. But it gives incorrect measurement of flux at low speed and lacks robustness . It has high drive cost, low reliability and noise immunity. Also these methods employ speed sensors. However, the algorithm of vector control theory requires manipulation of the electric parameters of the motor so that the governing equat ions in rectangular coordinates can be developed, prior knowledge of the state e quations is necessary when the estimation theory is used to estimate the speed p recisely. However, the values of the electric parameters may deviate from the de signated values due to changes in the working environment, temperature, speed, e xternal load and noise. The speed estimation technique employed here is dependen t on expressions obtained from the induction motor dynamic equations. The equati ons have singularity therefore direct speed estimation cannot be employed. Two A NNs are used here to recover the speed from these two equations. The two equatio ns are then combined and singularities are removed. This method is robust and is easily implementable using commercially available ANN tools. 1
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 2
LIST OF FIGURES FIGURE PAGE NO. FIG 1.1 Induction Motor cuit on Stationary Frame 14 FIG 1.4 Dynamic Equivalent Circuit on Arbitrary Fram Axis Equation of Induction Motor..17 FIG 2.1 Numerator Curve 2
Table of Contents CERTIFICATE02 ACKNOWLEDGEMENT..03 AB nciple 1.1.3 Construction 1.2 Speed of Induction Motor 1.3 Speed Control of Indu ction Motor 1.4 Dynamic Nature of Induction Motor 1.4.1 Per phase equivalent Cir cuit 1.4.2 Stationary Frame Circuit 1.4.3 Arbitrary Frame Circuit 1.5 d-q Axis E quation 1.6 Characteristic Equation 2. SPEED FUNCTION 2.1 Speed expression 2.2 M ethod of Singular Point 2.2.1 Non-Singularity 2.2.2 Continuity 2.2.3 Square inte grable 22 3 08 08 08 08 09 09 11 12 14 15 17 17 19 19 21 21 21
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 4 3. ARTIFICIAL NEURAL NETWORK 3.1 Neural Network 3.2 Definitions 3.3 Function App roximation 3.4 Data 3.5 Training 4. CONCLUSION 5. REFERENCES 6. APPENDIX 24 24 25 27 27 30 49 50 51 A. MATLAB Command B. Plots 51 52 4
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 5 CHAPTER 1 INDUCTION MOTOR 1.1 Introduction 1.1.1 Induction Motor Induction motor is the most popular type of a.c. motor. It is very commonly used for industrial drives since it is cheap, robust, efficient and reliable. It has good speed regulation and high starting torque. It has a reasonable overload capacity. Along with variable frequency AC inverters, induction motors are used in many adjustable speed applications which do not require fast dynamic response. 1.1.2 Principle: It works on the principl e of electromagnetic induction. A rotating magnetic field is produced when a 3phase supply is connected to the 3- phase winding of the stator. 1.1.3 Construct ion: A three phase induction motor consists of mainly two parts: 1. Stator 2. Ro tor The stator is the stationary part and the rotor is the rotating part. The st ator is built up of highgrade alloy steel laminations to reduce eddy current los ses. The rotor is also built up of thin laminations of the same material as stat or. The laminated cylindrical core is mounted directly on the shaft or a spider carried by the shaft. There are two types of induction motor rotors: 1. Squirrel cage rotor 2. Wound rotor 5
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 6 FIG 1.1 1.2 Speed of induction motor: Induction motor speed is given by following formul a: Where, v = speed of rotor f = frequency of rotor And, n = number of poles 1.3 Speed control of induction motor: The main method employed for speed control of induction motor are as follows: 1. 2. 3. 4. 5. Pole changing methods Stator voltage control Supply frequency control Rotor resi stance control Slip energy recovery 6
1. Pole changing methods: The number of stator poles can be changed by a multiple s tator windings, b methods of consequent poles c pole-amplitude modulation PAM . The meth ds of speed control by pole changing is suitable for cage motors only because th e cage rotor automatically develops number of poles equal to the poles of the ro tor winding. 2. Stator voltage control: The speed of a 3-phase induction motor can be varied by varying the supply voltage .Torque developed in induction motor is proportion al to square of the supply voltage. Speed control is obtained by varying the sup plying voltage until the torque required by the load is developed at the desired speed. 3. Variable-frequency control: The synchronous speed of an induction motor is gi ven by: Ns=120f/P The synchronous speed and, therefore, the speed of the inducti on motor can be controlled by varying the supply frequency. 4. Rotor resistance control: The speed of wound induction motor can be controlle d by connecting external resistance in the rotor circuit through slip rings. Thi s method is not applicable to cage motors. 7
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 8 5. Supply energy frequency: In the rotor resistance control,the slip power in ro tor circuit is wasted as I2 R Loss during the low speed operation. The efficienc y of the drive system by this Method of speed control is, therefore, reduced. Th e slip power from the rotor Circuit can be recovered and fed back to the a.c. so urce so as to utilize it outside the motor. Thus, the overall efficiency of the drive system can be increased. This method of speed control is used in large pow er applications where variation of speed over a wide range involves a large amou nt of slip power. 1.4 Dynamic model of induction motor: The concept of vector control has opened u p a new possibility that induction motors can be controlled to achieve dynamic p erformance as good as that of DC or brushless DC motors. In order to understand an analyze vector control , the dynamic model of induction motor is necessary . it has been found that the dynamic model equations developed on a rotating refer ence frame is easier to describe the characteristic of induction motors. It is t he objective of the project to derive and explain induction motor model in relat ively simple terms by using the concept of space vectors and d-q variables .when we choose a synchronous reference frame in which rotor flux lies on the d-axis ,dynamic equations of induction motor is simplified and analogous to a DC motor. 1.4.1 CONVENTIONAL PER PHASE EQUIVALENT CIRCUIT : 8
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 9 FIG 1.2 The inductance of rotor and stator is given by: Inductance of rotor circ uit Lr = Llr + Lm Where, Inductance of stator circuit Ls = Lls + Lm, Where, Lr = rotor inductance, Llr = rotor leakage inductance, Ls = stator inductance, Lls = stator leakage inductance, Lm = magnetizing inductance of motor. If the excitat ion frequency injected into the stator is e and the actual speed converted into e lectrical frequency unit is o, slip s is defined by, s = 9 e o e
Generated by Foxit PDF Creator Foxit Soft are http:// valuation only. 10
.foxitsoft are.com For e
= r/ e Where r is called the slip frequency, hich is the frequency of actual rot or current. The po er consumption in stator circuit is given by, Is2Rs The po er consumption in rotor circuit and load (output) is given by , Ir2Rs/s Torque pro duced is given by: T =Ir2Rr (P/2)(1-s)/s e =Ir2Rr(P/2 e) Where P is the no. of p oles, although the per-phase equivalent circuit is useful in analyzing and predi cting steady-state performance, it is not applicable to explain dynamic performa nce of the induction motor. In the next section, e ill develop dynamic model o f induction motors in general frame ork and introduce several equivalent circui ts as special cases. With space vector notation, voltage equations on the stator and rotor circuits of induction motors are, Vs s = Rs Is s + p s s Vr = Rr Ir + p r 0 (1) (2) It is very convenient to transform actual rotor variables (Vr, Ir, r) from eqs.2 . on a rotor reference frame into a ne variables ( Vr s, Ir s, r s) on a stator refe rence frame as in the derivation of conventional steady-state equivalent circuit . Vs s = Rs Is s + p s s 0 = Rr Ir s + (p - jo) r s (3) (4) Where o = p o, is the speed of the motor in electrical fre uency unit and Is s + Lm Ir s r s = Lm Is s + Lr Ir s (5) (6) 1.4.2 DYNAMIC EQUIVALENT CIRCUIT ON STATIONARY REFERENCE FRAME: 10
s s = Ls
FIG 1.3 EQUATIONS: It is very convenient to transform actual rotor variables (Vr, Ir, r) from . on a rotor reference frame into a new variab es ( Vr s, Ir s, r s) on a stator reference frame as in the derivation of conventiona steady-state equi va ent circuit. Let the stator to rotor winding turn ratio be n and the angu ar position of the rotor be , and define Ir s = (1/n) exp (j ) Ir, r s = n exp (j ) r ) A so, by defining referred rotor impedances as Rr = n2 Rr, etc., we have Vs s = R s Is s + p s s 0 = Rr Ir s + (p - jo) r s (8) (9) Where o = p o, is the speed of the motor in electrical fre uency unit and s s = Ls Is s + Lm Ir s r s = Lm Is s + Lr Ir s (10) (11) The above 4 equations (8-11) constitute a dynamic mode of the induction motor o n a stationary (stator) reference frame in space vector form. These mode equati ons may be simp ified by e iminating f ux inkages as Vs s = (Rs + Ls p) Is s + Lm p Ir s 0 = (Rr + Lr (p - jo)) Irs + Lm (p - jo) Is s. (12) (13) From (12-13) , The dynamic equivalent circuit model on a stationary reference fr ame can be dra n as in Fig.1.2 For steady-state operation ith excitation freque ncy e, p in may be replaced by je and after some algebraic manipulation, e get 11
Vs s = (Rs + je Ls ) Is s + Lm p Ir s 0 = (Rr/ s + je Lr) Ir s + je Lm Is s. (14) (15)
hich exactly describes the conventional steady-state equivalent circuit of Fig. 1.1.
1.4.3 DYNAMIC EQUIVALENT CIRCUIT ON ARBITRARY REFERENCE FRAME: FIG 1.4 Equations: No , the previous procedure can be generalized so that the dynamic mo del is described on an arbitrary reference frame rotating at a speed a, here is a special case ith a,= 0 To do that, define the ne space vector on the arbitrar y frame as Y a = exp(- j a ) Y s (16) and reconstruct all the model equations in terms of the ne space vectors. In th e arbitrary reference frame, Eqs are modified to Vs a = (Rs + Ls p) Is a + Lm p Ir a + ja s a (17) 12
0 = (Rr + Lr p) Ir a + Lm p Is a + j (a - o) r a, ith ne flux linkage equations d efined by, s a = Ls Is a + Lm Ir a r a = Lm Is a + Lr Ir a As before, by substitut ing Eqs. into Eqs, e have Vsa = (Rs + Ls (p + ja)) Is a + Lm (p + ja ) Ir a 0 = ( Rr + Lr (p + ja - jo)) Ir a + Lm (p + ja - jo) Is a here eliminated flux linkage va riables are eliminated. (21) (19) (20) (18) (22) The generalized equivalent circuit on a arbitrarily rotating frame based on Eq. is sho n in .. No , depending on a specific choice of a, many forms of dynamic eq uivalent circuit can be established. Among them, the synchronous frame form can be obtained by choosing a = e. This form is very useful in describing the concept of vector control of induction motors as ell as of PM synchronous motors becaus e at this rotating frame, space vector is not rotating, but fixed and have a con stant magnitude in steady-state. Since space vectors in the synchronous frame i ll frequently be used, they are denoted ithout any superscript indicating the t ype of frame. Another possible reference frame used in vector control is the rot or reference frame by choosing c = o hich is , in fact, the reverse step of . it h n =1. 1.5 d-q axis equations of induction motor: 13
FIG 1.5 In many cases, analysis of induction motors ith space vector model is c omplicated due to the the fact that e have to deal ith variables of complex nu mbers. For any space vector Y, define t o real quantities Sq and Sd as, S = Sq j S d . In other ords, Sq = Re (S) and Sd = - Im (S) illustrates the relations hip bet een d-q axis and complex plane on a rotating frame ith respect to stati onary a-b-c frame. Note that d- and q-axes are defined on a rotating reference f rame at the speed of a = p a ith respect to fixed a-b-c frame. Fig. 3.1 Definitio n of d-axis and q-axis on an arbitrary reference frame ith the above definition can be translated into the follo ing 4 equations of real variables expressed in a matrix form. 1.6 Characteristic equation: The d-q axis dynamic equations for the squirrel cage induction motor are given b y [l] 14
Generated by Foxit PDF Creator Foxit Soft are http:// valuation only. 15 V = AI (1)
here, In the above equations, subscript s denotes stator quantities, r denotes rotor quantities, q and d refer to the quadrature and direct axis quantities res pectively and L, is the magnetizing inductance. CHAPTER-2 15
Generated by Foxit PDF Creator Foxit Soft are http:// valuation only. 16 SPEED FUNCTION
2.1 Speed Expression: If the stator voltages and stator currents are kno n along ith the machine parameters. We have only three unkno ns r , ird and irq . We ca n thus solve for r (speed of induction motor) in terms of stator quantities only. First , e obtain the rotor currents as function of stator quantities and r ,fro m the first t o ro s of characteristic equation . since the rotor currents are n ot accessible in a squirrel cage induction motor . the expressions for ird and i rq are obtained as: ird= 1/Lm [ (Vsd-Rsisd)dt- Lsisd] irq=1/Lm[ (Vsq-Rsisq)dt-Lsisq] We can substitute ird and irq in the last t o ro s of characteristic equation an d obtain the equations of rotor speed r as: r = -[ 2disd/dt RrLsisd + Rr Vxddt + LrVxd ] /[ 2isq+Lr Vxqdt] Where, 2=Lm2-LrLs, Vxd=Vsd-Rsisd, Vxq=Vsq-Rsisq The speed can be recover from this equation directly but due to singularities in this function it is difficult to calculate speed for regular induction motor operation. 16
Generated by Foxit PDF Creator Foxit Soft are http:// valuation only. 17 FIG 2.1 FIG 2.2
It can be seen from the above figures of numerator and denominator functions tha t both aveforms are in phase, resulting in simultaneous zero-crossings, and hen ce singular points. Hence e cannot obtain the speed of induction motor directly . So for calculating the speed of induction motor e use artificial neural net o rk. 17
2.1 METHOD OF SINGULAR POINTS : One of the necessary conditions for an ANN to ap proximate a function is that the function should be square integrable, non-linea r, singular and continuous. 2.1.1 Non singularity: A square matrix is nonsingular if Ax = 0n implies x = 0n. Other ise it is a singular matrix Properties of singular matrix: 1.A nn is nonsi ngular if and only if r(A) = n. 2.A is nonsingular if and only if A has a linear inverse A1. 2.1.2 Continuity: FIG 2.3 A continuous function is a function for which, intuitively, small changes in the input result in small changes in the output continuity of a function in the fol lowing intuitive terms: an infinitesimal change in the independent variable corr esponds to an infinitesimal change of the 18
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 19 dependent variable .We call a function continuous, if, and only if, it is contin uous at every point of its domain. More generally, we say that a function is con tinuous on some subset of its domain if it is continuous at every point of that subset. 2.1.3 S uare integrable: A real or complex valued function of a real or complex variable is s uare integrable on an interval if the integral of the s ua re of its a absolute value, over that interval, is finite. The basic idea in this method is to partition the main speed function having sin gularities into smaller function which do not have any singularities , and to tr ain small ANNs to identify these smaller functions. The desired output can be obt ained from the outputs of these ANNs by avoiding the singular points of the main functions. In this case one of the simplest ways to partition the functions is t o consider their numerators and denominators separately.
D1=
2is +Lr Vx dt
ANNs can be trained to approximate N1 and D1. The output of these ANNs can then be passed through a filter which performs the re uired division at points where bo th the numerators and denominators are non zero. Inputs given to the numerator A NN are: Isd,disd/dt,vsd, vsddt and isddt Input given to thedenominator ANN are: vs , vs dt and is dt 19
N1=
[ 2disd/dt RrLsisd+Rr Vxddt+LrVxd]
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 20 Block diagram of ANN FIG 2.4 CHAPTER 3 20
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 21 NEURAL NETWORK 3.1 Neural Network An Artificial Neural Network (ANN) is an information processi ng paradigm that is inspired by the way biological nervous systems, such as the brain, process information. The key element of this paradigm is the novel struct ure of the information processing system. It is composed of a large number of hi ghly interconnected processing elements (neurons) working in unison to solve spe cific problems. ANNs, like people, learn by example. An ANN is configured for a specific application, such as pattern recognition or data classification, throug h a learning process. Learning in biological systems involves adjustments to the synaptic connections that exist between the neurons. This is true of ANNs as we ll. Use Neural networks, with their remarkable ability to derive meaning from compli cated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techni ues. A t rained neural network can be thought of as an "expert" in the category of inform ation it has been given to analyse. This expert can then be used to provide proj ections given new situations of interest and answer "what if" uestions. Other a dvantages include: 1. Adaptive learning: An ability to learn how to do tasks bas ed on the data given for training or initial experience. 2. Self Organisation: A n ANN can create its own organisation or representation of the information it re ceives during learning time. 3. Real Time Operation: ANN computations may be car ried out in parallel, and special hardware devices are being designed and manufa ctured which take advantage of this capability. 4. Fault Tolerance via Redundant Information Coding: Partial destruction of a network leads to the corresponding degradation of performance. However, some network capabilities may be retained even with major network damage. 21
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 22 FIG 3.1 3.2 Definitions: Feed forward network: Feed forward networks have the following characteristics: 1. Perceptrons are arranged in layers, with the first layer taking in inputs and the last layer producing outputs. The middle layers have no connection with the external world, and hence are called hidden layers. 2. Each perceptron in one l ayer is connected to every perceptron on the next layer. Hence information is co nstantly "fed forward" from one layer to the next., and this explains why these networks are called feed forward networks. 3. There is no connection among perce ptrons in the same layer. Feedback Network: By using loops in the network, Feedback networks transfer sign als in both directions. Feedback networks are powerful and complex. Feedback net works state is changing dynamically until they reach an e uilibrium point. Until the input changes, they remain at the e uilibrium point. Feedback architectures are called as interactive or recurrent Back propagation: It is a supervised learning method, and is an implementation o f the Delta rule. It re uires a teacher that knows, or can calculate, the desire d output for any given input. It is most useful for feed forward networks (netwo rks that have no feedback, or simply, that have no connections that 22
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 23 loop). The term is an abbreviation for "backwards propagation of errors". Back p ropagation re uires that the activation function used by the artificial neurons (or "nodes") is differentiable. FIG 3.2 Supervised learning: Supervised learning incorporates an external teacher, so th at each output unit is told what its desired response to input signals ought to be. During the learning process global information may be re uired. Paradigms of supervised learning include error correction learning, reinforcement learning a nd stochastic learning. An important issue concerning supervised learning is the problem of error convergence, i.e. the minimisation of error between the desire d and computed unit values. The aim is to determine a set of weights which minim izes the error. Neuralwares Predict: NeuralWorks Predict is an integrated, state of the art tool for rapidly creating and deploying prediction and classificatio n applications. Predict combines neural network technology with 23
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 24 genetic algorithms, statistics, and fuzzy logic to automatically find optimal or near optimal solutions for a wide range of problems. Predict incorporates years of modeling and analysis experience gained from working with customers faced wi th a wide variety of analysis and interpretationproblems. Predict re uires no pr ior knowledge of neural networks. With only minimal user involvement it addresse s all the issues associated with building robust models from available empirical data. Predict analyzes input data to identify appropriate transforms, partition s the input data into training and test sets, selects relevant input variables, and then constructs, trains, and optimizes a neural network tailored to the prob lem. For advanced users, Predict also offers direct access to all key training a nd network parameters. 3.3 FUNCTION APPROXIMATION When input data originates fro m a function with real valued outputs over a continuous range, the neural networ k is said to perform a traditional function approximation. An example of an appr oximation problem could be one where the temperature of an object is to be deter mined from secondary measurements, such as emission of radiation. Another more t rivial example could be to estimate shoe size based on a persons height. These tw o examples involve models with one input and one output. A more advanced model o f the second example might use gender as a second input in order to derive a mor e accurate estimate of the shoe size. 3.4 DATA FOR NEURAL NETWORK TRAINING: Induction motor parameters used in simulat ion work: Parameters Stator resistance Rotor resistance Stator inductance Rotor inductance Magnetizing inductance Symbol Rs Rr Ls Lr Lm Value 0.49 0.45 0.0388mH 0 .0354mH 0.0354mH 24
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 25 Numerator X1 9.54 8.9 9.3 9.1 10.1 10.5 9.5 8.4 9.4 8.3 8.7 8.5 9.6 10.4 10.9 11 .1 11.5 11.8 11.3 11.4 11.7 12.3 12.5 12.8 12.6 12.4 12.9 13.2 13.4 13.6 X2 7.8 8.7 8.4 8.2 9.3 9.4 8.9 8.6 10.1 10.5 10.8 10.7 8.5 9.2 9.8 10.3 10.2 10.7 10.4 10.6 9.6 11.2 11.3 11.6 11.4 11.7 11.5 12.1 12.5 13.8 X3 4.9 4.79 2.51 1.52 2.34 1.21 2.4 1.59 4.5 4.4 4.35 3.4 2.9 2.5 2.4 2.1 2.12 1.9 1.8 1.6 2.1 2.5 2.4 2.2 4.35 4.45 4.5 4.9 5.2 5.35 X4 6.8 6.34 3.23 2.45 1.9 0.78 1.75 2.34 6.7 6.54 6. 48 6.3 2.41 1.8 0.6 0.45 0.4 0.35 0.32 0.3 0.4 0.5 2.1 2.8 6.4 6.6 6.8 7.1 7.5 7 .9 X5 5.1 5.31 7.13 7.81 8.12 9.89 8.3 7.9 4.98 4.95 5.1 5.15 7.9 8.5 10.15 13.5 15.1 15.9 16.8 17.5 14.5 13.2 10.5 9.9 5.2 5.1 4.9 3.9 3.5 3.2 N1 2.111 1.87 0.02 0.562 0.84 1.7761 0.961 0.6287 2.0787 2 1.94 1.82 0.54 0.97 1.87 2.695 3.0669 3.2732 3.4882 3.6583 2.93 2.5905 1.28 0.8401 1.889 2.005 2.1413 2.51 2.789 3.0403 X1=disd/dt ,X2=isd, X3=Vsd, X4= Vsddt, X5= isddt 25
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 26 Y1 80.9 70.8 90.4 99.3 120 130.1 140.3 120.25 135.55 112.9 115.7 132.7 122.5 134 .45 145.85 129.89 124.6 127.7 154.85 149.65 148.43 152.35 145.76 155.91 143.87 1 56.24 165.34 130.5 135.9 141.95 Y2 46.27 69.13 70 113 130 204 127 93 95 100 98 97.5 88 102 131.1 153 160 161 154 168 149 156 101 84 137 136 134 130 125 120 Y3 700 610 138 120 108 98 100 91 490 460 425 390 130 125 116 110 108 116 112 133 140 175 137 128 390 394 402 410 416 420
Y1=dis /dt, Y2= Vs dt, Y3= is dt 26
D1 0.0105 0.00813 0.000072 0.00193 0.00275 0.00553 0.00278 0.001722 0.00513 0.00444 0.00391 0.0033 0.000892 0.00144 0.00263 0.00354 0.0038 0.003719 0.0035 4 0.00365 0.00285 0.00251 0.001219 0.000785 0.00189 0.00201 0.00214 0.00251 0.00279 3.04403
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 27 3.5 TRAINING STEPS FOR NEURAL NETWORK: 27
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 28 28
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 46 CONCLUSION: This project outlines techni ue for speed estimation of induction motor using ar tificial neural networks. The dynamic model of induction motor is considered and expression for rotor speed is obtained . The expression obtained have singulari ties thus ANNs cannot be used to obtain the speed directly from speed function. A method is used in this project in which two ANNs are trained to approximate the numerator and the denominator functions in the speed expression. By training suc h ANNs and using a filter to avoid singular points , the speed can be recovered . REFERENCES: 1. Electrical Machinary by A.E. Fitzgerald. 2. Electric Machines by Ashfa Hussain. 3. Control System Engineering by I. J. Nagrath and M. Gopal 46
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 47 4. Dynamic model of induction motors for vector control Dal Y. Ohm, Drivetech Inc. , Blacksburg,Virginia. 5. Speed Estimation Of Induction Motor Using Artificial Ne ural Networks by Prashant Mehrotra, John E. Quaicoe and R. Venkatesan. 6. Motor Sp eed Identification Via Neural Network by L.Ben Brahim. 7. Neural Network Documenta tion by Wolframesearch. 8. www.google.com 9. www.wikipedia.com 10. Neuralware pre dict APPENDIX: A. MATLAB COMMANDS: >> y1= [80.9 70.8 90.4 99.3 120 130.1 140.3 120.25 135.55 112.9 115.7 132.7 122. 5 134.45 145.85 129.89 124.6 127.7 154.85 149.65 148.43 152.35 145.76 155.91 143 .87 156.24 165.34 130.5 135.9 141.95]; 47
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 48 >> y2= [46.27 69.13 70 113 88 102 131.1 153 137 136 134 130 >> y3= [700 130 390 610 125 394 138 116 402 120 110 410 130 160 125 108 108 416 204 127 161 154 120]; 98 100 116 112 420]; 93 168 95 149 100 156 98 101 97.5 84 91 133 490 140 460 175 425 137 390 128 >> d1= 0.12*(10^ 9)*y1+0.0354*(10^ 3)*y2 0.01734*(10^ 3)*y3; >> plot(d1); >> x1 =[9.54 8.9 9.6 10.4 12.6 12.4 >> x2=[7.8 8.5 11.4 >> x3=[4.9 2.9 4.35 >> x4=[6.8 2.41 6.4 >> x5=[5.1 7.9 5.2 8.7 9.2 11.7 4.79 2.5 4.45 6.34 1.8 6.6 5.31 8.5 5. 1 9.3 10.9 12.9 8.4 9.8 11.5 2.51 2.4 4.5 3.23 0.6 6.8 9.1 11.1 13.2 8.2 10.3 12 .1 1.52 2.1 4.9 2.45 0.45 7.1 10.1 11.5 13.4 9.3 10.2 12.5 2.34 2.12 5.2 1.9 0.4 7.5 8.12 15.1 3.5 10.5 9.5 11.8 11.3 13.6]; 9.4 8.9 10.7 10.4 13.8]; 1.21 2.4 1 .9 1.8 5.35]; 0.78 0.35 7.9]; 9.89 15.9 3.2 1.75 0.32 8.4 11.4 9.4 11.7 8.3 12.3 8.7 12.5 8.5 12.8 8.6 10.6 10.1 9.6 10.5 11.2 10.8 11.3 10.7 11.6 1.59 1.6 4.5 2.1 4.4 2.5 4.35 2.4 3.4 2.2
2.34 0.3 6.7 0.4 6.54 0.5 6.48 2.1 6.3 2.8 7.13 7.81 10.15 13.5 4.9 3.9 8.3 16.8 7.9 17.5 4.98 14.5 4.95 13.2 5.1 10.5 5.15 9.9 >> n1= ( 0.12*10^( 9)*x1 0.03474*10^( 3)*x2+0.0354*x3+0.45*x4 0.22*x5); >> wr=n1 ./d1; >> plot(wr) B. PLOTS: 48
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 49 Numerator plot 49
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 50 Denominator plot 50
Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only. 51 Speed plot 51

Of Induction Motor Using Artificial Neural Network and Implementation in MATLAB

Hochgeladen von

Dokumentinformationen

Originalbeschreibung:

Originaltitel

Copyright

Verfügbare Formate

Dieses Dokument teilen

Dokument teilen oder einbetten

Freigabeoptionen

Stufen Sie dieses Dokument als nützlich ein?

Sind diese Inhalte unangemessen?

Copyright:

Verfügbare Formate

Of Induction Motor Using Artificial Neural Network and Implementation in MATLAB

Hochgeladen von

Copyright:

Verfügbare Formate

Generated by Foxit PDF Creator Foxit Software http://www.foxitsoftware.com For e valuation only.

.foxitsoft are.com For e

.foxitsoft are.com For e

Vs s = (Rs + je Ls ) Is s + Lm p Ir s 0 = (Rr/ s + je Lr) Ir s + je Lm Is s. (14) (15)

.foxitsoft are.com For e

.foxitsoft are.com For e

.foxitsoft are.com For e

.foxitsoft are.com For e

.foxitsoft are.com For e

.foxitsoft are.com For e

[ 2disd/dt RrLsisd+Rr Vxddt+LrVxd]

Y1=dis /dt, Y2= Vs dt, Y3= is dt 26

Das könnte Ihnen auch gefallen