Beruflich Dokumente
Kultur Dokumente
Submitted By:
Submitted To:
FUZZY LOGIC
Introduction:
Fuzzification
Fuzzy inference
Defuzzyfication.
• The fuzzyfication means that the real variables are transferred on linguistic
variables. The definition of linguistic variable goes out from basic linguistic variables,
for example, at the variable risk it is set up the following attributes: none, very low,
low, medium, high, very high risk. Usually there are used from three to seven
attributes of variable. The attributes are defined by the so called membership
function, such as L, F, Z, S and some others. The membership function is set up for
input and output variables.
• The fuzzy inference defines the behaviour of system by means of rules of type
<When>, <Then> on linguistic level. The conditional clauses evaluate the state of
input variables by the rules. The conditional clauses are in the form <When> Inputa
<And> Inputb ….. Inputx <Or> Inputy …….. <Then> Output1, it means, when the state
occurs Inputa and Inputb.... Inputx or Inputy …… then the situation is Output1.
The fuzzy logic represents the expert systems. Each combination of attributes of
variables, incoming into the system and occurring in condition <When>, <Then>,
presents one rule. Every condition behind <When> has a corresponding result
behind <Then>. It is necessary to determine every rule and its degree of supports
(the weight of rule in the system). The rules are created by the expert himself.
• The defuzzification transfers the results of fuzzy inference on the output variables,
that describes the results verbally for example, whether the risk exists or not. The
system with fuzzy logics can work as an automatic system with entering input data.
The input data can be represented by many variables.
Fuzzy logic models employ fuzzy sets to handle and describe imprecise and
complex phenomena and uses logic operations to arrive to conclusion. Fuzzy sets in
particular fuzzy numbers and fuzzy logic applied to control problems form a field of
knowledge called fuzzy logic control. It deals with control problems in an
environment of uncertainty and imprecision; it is very effective when high precision is
not required and the control objects has variables available for measurement or
estimation. Imitating human judgment in common sense reasoning fuzzy logic
control uses linguistic values framed in if then rules. For instance: if client's annual
income is low and total net worth is high, then client's risk tolerance is moderate.
Here the linguistic variables annual income and total net worth are inputs; the
linguistic variable risk tolerance is output; low, high, and moderate are values (terms
or labels) of linguistic variables. The implementation of fuzzy logic requires the
development of a knowledge base which would make possible the stipulation of if
then rules by using fuzzy sets. Important role here plays the experience and
knowledge of human experts. They should be able to state the objective of the
system to be controlled. The goal of control in engineering is action. In business,
finance, and management the meaning of control and give broader interpretation of
action; it might be also advise, suggestion, instruction, conclusion, evaluation,
forecasting.
(ii) Selection of shapes, peaks, and flats of the membership functions of Ai, Bj
and Ck. Most often triangular, trapezoidal, or bell-shaped types of
membership functions are used hence then sets are fuzzy numbers.
(iii) Specifying the number of terms AB and C i.e. the numbers n, m and l
Usually these numbers are between 2 and 7.
(iv) Specifying the supporting intervals (domains) for the terms Ai, Bj and Ck.