Fuzzy Set: - Introduction

FUZZY SET
INTRODUCTION
A SET is defined as collection of objects
FUZZY SET is a range of values which form the basis of fuzzy
logic. Each value has a grade of membership between 0 and 1.
Logic expression defines values as either TRUE or FALSE. To
express degree of intensity of control, variable fuzzy logic uses labels
like slow,medium,fast or moderate. The set can be of any shape
like trapezoidal or bell curve or triangular
FUZZY SET
FUZZY VARIABLES:
Fuzzy variables or linguistic are adjectives that modify the variable .
If we want minimum of variables ,we can simply have +ve ,0 and ve
variables for each of the control parameters.
MEMBERSHIP FUNCTION
The membership function is a graphical representation of the
magnitude of participation of each input .It associates with each of
the input that are processed ,defines functional overlap between inputs
and determines an output response.
DUALITY BETWEEN FUZZY AND PROBABILITY
Probably deals with uncertainty an likelihood
Fuzzy logic deals with ambiguity an vagueness
FUZZY LOGIC
IF ( a set of conditions are satisfied )THEN ( a set o consequences can
inferred)
DIFFERENCE BETWEEN CLASSICAL SET AND FUZZY SET
S.n CLASSICAL SET FUZZY SET
o
1 Definite value to any query Indefinite value to any query
2 Values are either 0 or 1 Values lies between 0 and 1
3 Satisfy precise properties of Satisfy in precise properties of

membership membership
4 Unique membership function Indefinite membership function

5 Boolean algebra is fundamental Fuzzy are fundamental theory
theory
6 Deals with discrete membership Deals with discrete continuous
functions membership functions
OPERATIONS ON FUZZY SETS
OPERATIONS ON FUZZY SETS:
The operations that are possible on fuzzy set theory are
1.Inclusion
2.Comparability
3.Equality
4.Complement
5.Union
6.Difference
7.Intersection
1.INCLUSION:
Let A and B are two fuzzy sets defined in same universal space X .
The fuzzy set A is included in fuzzy set B
if and only if
A(x) <= B(x)
COMPARABILITY:
Let A and B are two fuzzy sets defined in some universal space x.
The two fuzzy sets A and B are comparable if the condition A B or
B A holds i.e. if one set is subset of other, then they are comparable
The two fuzzy sets A and B are not comparable if the condition A not
equal to b holds
EQUALITY:
Let A and B are fuzzy sets defined in some space X then A =B if and
only if A(x)=B(x)
UNION:
Let A and B be the two fuzzy sets defined in some space X .The union
is defined as the smallest fuzzy set that contains both A and B .it is
denoted by A B
(AUB)(x)=max(A(x).B(x));for all x X
COMPLEMENT:
INTERSECTION:
Let A AND B be the two fuzzy sets defined in some space X
intersection is defined as the greatest fuzzy set that include both A and
B
(A U B) (x)=min[A(x),B(x)]
DIFFERENCE :
Let A and B are the two fuzzy sets defined in some space X it is
denoted by A^B
(A-B)(x)=min[A(X),1-B(x)]
FUZZY ARITHEMATIC:
Fast and easy to explain
Requires little data
Applicable to all kind of uncertainty
Fully comprehensive
Fast and easy to compute
LIMITATIONS OF FUZZY ARITHMETIC:
Controversial
Not optimal when there is lot of data
Not conservative against all possible dependencies
FUZZY PROPEERTIES:
1.Related to union: 2. related to intersection
Identity AUB=A absorption to empty set - A =
Idempotence AUA=A identity A x =A
Commutative AUB =BUA Idempotence A A=A
Associative AU(BUC)=(AUB)UC associativity A(BC)=(A B) C
ADDITIONAL PROPERTIES:
Distributivity ----- A(BC)=(AB)(AC)
Law of exclude middle------ AUA=X
Law of contradiction ------- AA=
MEMBERSHIP FUNCTION:
Membership function is one that characterizes the fuzziness in a fuzzy set in graphical form.
It is used to express the fuzziness in the data.
It takes values between o and 1.
The membership value of o represents zero membership and 1 represents complete membership.
Any value between 0 and 1 represents partial membership.
The most popular choices for shapes of the membership functions are bell shaped etc. The reason for choosing these
steps for membership function are
1. Easy of description as a function
2. Minimum usage of memory for storage and
3. Manipulation efficiency is high
TRAPEZOIDAL MEMBERSHIP FUNCTIONS :
These membership functions are better than the triangular functions
Oscillators encountered due to use of triangular function can be overcome by use of trapezoidal function
This is due to the flattop in the function
Bell shaped membership function greatly reduces the oscillations and also rise time
The characteristic of membership function are:
Core is the region of universe that is characterized by complete and full membership ( a=1)
Support is the region of universe that is characterized by a non zero membership( a(x)>0)
Boundary is the region of universe that is characterized by non zero membership but not complete
membership(0<A(x)<1)
A Normal fuzzy set is one whose membership function has at least one element x in the universe whose
membership value is one
A convex fuzzy set is one whose membership values are strictly monotonically increasing or decreasing
or first increasing and then decreasing with increasing values for the elements in the universe
The height of a fuzzy set is the max value of membership
Cross point between two adjacent fuzzy sets is defined as that point where the two fuzzy sets have equal
members value the meeting point of two adjacent fuzzy sets is cross point
It influences the firing of rules and in turn the control actions
The shape symmetry cross points and width if membership function influence the final control action
FEATURES:
core : a=1
support : a(x)>0
Boundary : 0<A(x)<1
DEFUZZIFICATION: It is the process of conversion of fuzzy quantity into a precise quantity

methods:
max membership principle
Centroid method
Weighted average method
Mean f maxima
Centre of sums

Max membership principle:
Fuzzy set with largest membership value is selected
Centroid method:
Also known as centre of mass .here the overlapping area is controlled area
Defuzzicationvalue: for continous membership is
x^*=
(x) dx
For discrete x^*= xi (xi)
(xi)
where n is number of elements in a sample
xi= elements.
Weighted average method: is valid for only symmetrical output membership functions
Defuzzification value= x^*= ifn

i
Mean of maxima: Itthe arithmetic average of mean values of all intervals contained including 0 length intervals
Also known as height method it is used only for practical output functions
x^*= xi
|M|
Centre of sums: here overlapping area is counted twice calculations are very fast the average sum of output form
each of the contributing fuzzy sets
I n fuzzy control the steps taken are1.fuzzification
2.rule evaluation
Defuzzification FUZZY CONTROL
FUZZY INFERENCE SYSTEM:

It is also known as fuzzy rule based systems
It is key unit of fuzzy logic algorithm
The primary work of this system is decision making
FIS uses IF THEN rules along with connected OR AND for making necessary decision rules
The input FIS maybe fuzzy but the output form from FIS is always fuzzy set
Hence there should be a defuzzification unit for converting fuzzy variables into crisp variables
There are 2 types of fuzzy inference
1. mamdani FIS
2. sugeno FIS
ADVANTAGES OF FLC:
No need for mathematical model
Less sensitive to system fluctuations
Implementation is simple and straight forward
Flexible
Easy to understand
DISADVANTAGES:
More complex then PID
Need to tune more parameters
PROCEDURE TO SOLVE A FUZZY PROBLEM
1.Define the fuzzy problem in detail
Identify all important variables and their ranges
Determine membership profiles for each variable range
Determine rules including action needed
Select the defuzzification methodology
Test the system for correct answers if needed go back to step 1

Fuzzy Set: - Introduction

Uploaded by

Copyright:

Available Formats

Fuzzy Set: - Introduction

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Fuzzy Set: - Introduction

Uploaded by

Copyright:

Available Formats

FUZZY SET

3 Satisfy precise properties of Satisfy in precise properties of

4 Unique membership function Indefinite membership function

DEFUZZIFICATION: It is the process of conversion of fuzzy quantity into a precise quantity

Defuzzification value= x^*= ifn

FUZZY INFERENCE SYSTEM:

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.