Karary University

College of Engineering
Department of Electrical and Computer Engineering
Cnt 521
Fuzzy Logic Control
Lecture 8

Fuzzy Control Systems

[email protected]

[Karary University‐ Abusabah I. A. Ahmed] 1

Lecture Outline
 Introduction
 Typical fuzzy control systems
 Architecture of Madmani fuzzy control system
 Takagi Sugeno Fuzzy System
 Types of Fuzzy Controllers

[Karary University‐ Abusabah I. A. Ahmed]

 Introduction
 Fuzzy control system is nonlinear mapping that derives its output based on
fuzzy reasoning and a set of fuzzy if-then rules. The domain and range of the
mapping could be fuzzy sets or points in a multidimensional spaces.
 Fuzzy logic is a tech to embody human-like thinking into a control system

 Traditional control approach require formal modelling of the plant

 Fuzzy control incorporate ambiguous human logic into computer
programs. It is suitable for control problems that can not be easily
represented by mathematical models:
 Weak model
 Parameter variation
 Unavailable or incomplete data
 Very complex plants
 Because of the unconventional approach they leads to easier development
and implementation cycle

[Karary University‐ Abusabah I. A. Ahmed]

 Typical Fuzzy Control Systems

 The most popular Fuzzy Control Systems are:

Mamdani type
Larsen
Takagi Sugeno Kang (TSK)
Tsukamoto
Other methods

[Karary University‐ Abusabah I. A. Ahmed]

Fuzzy Control System

Crisp Input

Fuzzification Input Membership Functions

Fuzzy Input

Rule Evaluation Rules / Inferences

Fuzzy Output

Defuzzification Output Membership Functions

Crisp Output

[Karary University‐ Abusabah I. A. Ahmed]

 Mamdani Fuzzy Inference System

 The most commonly used fuzzy inference technique is

Mamdani inference method.

 In 1975, Professor Ibrahim Mamdani of London University

built one of the first fuzzy systems to control a steam engine
and boiler combination.

 Original Goal: Control a steam engine & boiler combination by

a set of linguistic control rules obtained from experienced
human operators.

[Karary University‐ Abusabah I. A. Ahmed]

Mamdani Fuzzy Inference System
 The Mamdani-style fuzzy inference process is
performed in four steps:
 Fuzzification of the input variables,
 Rule evaluation,
 Aggregation of the rule outputs, and finally

 Defuzzification.

[Karary University‐ Abusabah I. A. Ahmed]

Mamdani Fuzzy Inference System
Using If-Then type fuzzy rules converts the fuzzy input to the fuzzy
output.

[Karary University‐ Abusabah I. A. Ahmed]

 Example 8-1
Let’s examine a simple two-input one-output problem that
includes three rules:

 Rule: 1 Rule: 1
IF IF project_funding is adequate
OR OR project_staffing is small
THEN THEN risk is low

 Rule: 2 Rule: 2
IF IF project_funding is marginal
AND AND project_staffing is large
THEN THEN risk is normal

 Rule: 3 Rule: 3
IF IF project_funding is inadequate
THEN THEN risk is high

[Karary University‐ Abusabah I. A. Ahmed]

Example 8-1
Step 1: Fuzzification
Take the crisp inputs, and (project funding and project
staffing).
Determine the degree to which these inputs belong to each of
the appropriate fuzzy sets.

[Karary University‐ Abusabah I. A. Ahmed]

 Example 8-1
Step 2: Rule Evaluation

 take the fuzzified inputs, (x=A1) = 0.5, (x=A2) = 0.2, (y=B1)

= 0.1 and (y=B2) = 0.7

 apply them to the antecedents of the fuzzy rules.

 If a given fuzzy rule has multiple antecedents, the fuzzy

operator (AND or OR) is used to obtain a single number that
represents the result of the antecedent evaluation. This
number (the truth value) is then applied to the consequent
membership function.

[Karary University‐ Abusabah I. A. Ahmed]

 Example 8-1
Step 2: Rule Evaluation
 To evaluate the disjunction of the rule antecedents, we use the
OR fuzzy operation. Typically, fuzzy expert systems make
use of the classical fuzzy operation union:
A B(x) = max [ A(x), B(x)]

 Similarly, in order to evaluate the conjunction of the rule

antecedents, we apply the AND fuzzy operation
intersection:
A B(x) = min [ A(x), B(x)]

[Karary University‐ Abusabah I. A. Ahmed]

Example 8-1
Step 2: Rule Evaluation

IF 0 OR (0.1) THEN (0.1)

IF 0.2 AND 0.7 THEN (0.2)

IF (0.5) THEN (0.5)

[Karary University‐ Abusabah I. A. Ahmed]

 Example 8-1
Step 2: Rule Evaluation
 Now the result of the antecedent evaluation can be applied to
the membership function of the consequent.
 The most common method is to cut the consequent
membership function at the level of the antecedent truth.
 This method is called clipping (Max-Min Composition) .
 The clipped fuzzy set loses some information.
 Clipping is still often preferred because:
 it involves less complex and faster mathematics
 it generates an aggregated output surface that is easier to
defuzzify.

[Karary University‐ Abusabah I. A. Ahmed]

 Example 8-1
Step 2: Rule Evaluation

 While clipping is a frequently used method, scaling (Max-Product

Composition) offers a better approach for preserving the original
shape of the fuzzy set.

 The original membership function of the rule consequent is

adjusted by multiplying all its membership degrees by the truth
value of the rule antecedent.

 This method, which generally loses less information, can be very

useful in fuzzy expert systems.

[Karary University‐ Abusabah I. A. Ahmed]

Example 8-1
Step 2: Rule Evaluation
Clipped and scaled membership functions

Max-Min Composition Max-Product Composition

[Karary University‐ Abusabah I. A. Ahmed]

 Example 8-1
Step 3: Aggregation of The Rule Outputs
 Aggregation is the process of unification of the outputs of all rules.
 We take the membership functions of all rule consequents previously
clipped or scaled and combine them into a single fuzzy set.

(0.1) (0.2) (0.5)

[Karary University‐ Abusabah I. A. Ahmed]

 Example 8-1
Step 4: Defuzzification
 Fuzziness helps us to evaluate the rules, but the final output of a fuzzy
system has to be a crisp number.
 The input for the defuzzification process is the aggregated output fuzzy
set and the output is a single number.
 There are several defuzzification methods, but probably the most
popular one is the centroid technique.
 It finds the point where a vertical line would slice the aggregate set into
two equal masses. Mathematically this Centre Of Gravity (COG) can
be expressed as: b

  x  x dx
A

COG  a
b

  x  dx
a
A

[Karary University‐ Abusabah I. A. Ahmed]

Example 8-1
Step 4: Defuzzification
 Centroid defuzzification method finds a point representing the
centre of gravity of the fuzzy set, A, on the interval, ab.
 A reasonable estimate can be obtained by calculating it over a
sample of points.
( x)
1.0
0.8
0.6 A

0.4
0.2
a b
0.0 X
150 160 170 180 190 200 210

[Karary University‐ Abusabah I. A. Ahmed]

Example 8-1

Step 4: Defuzzification
Degree of
Membership
1.0
0.8
0.6

0.4
0.2
0.0
0 10 20 30 40 50 60 70 80 90 100
67.4 Z

(0  10  20)  0.1  (30  40  50  60)  0.2  (70  80  90  100)  0.5

COG   67.4
0.1  0.1  0.1  0.2  0.2  0.2  0.2  0.5  0.5  0.5  0.5

[Karary University‐ Abusabah I. A. Ahmed]

 Takagi-Sugeno Fuzzy Models
 Also known as TSK fuzzy model, Takagi, Sugeno & Kang, 1985.
 Goal: Generation of fuzzy rules from a given input-output data
set.

 Mamdani-style inference, requires to find the centroid of a

two-dimensional shape
 by integrating across a continuously varying function.
 In general, this process is not computationally efficient.
 Michio Sugeno suggested to use a single spike, a singleton, as
the membership function of the rule consequent.
 A fuzzy singleton, is a fuzzy set with a membership function
that is unity at a single particular point on the universe of
discourse and zero everywhere else.

[Karary University‐ Abusabah I. A. Ahmed]

Takagi-Sugeno Fuzzy Models
 Sugeno-style fuzzy inference is very similar to the Mamdani
method.
 Sugeno changed only a rule consequent. Instead of a fuzzy set,
he used a mathematical function of the input variable.
 The format of the Sugeno-style fuzzy rule is
IF x is A AND y is B
THEN z is f (x, y)
where x, y and z are linguistic variables
A and B are fuzzy sets on universe of discourses X and Y
f (x, y) is a mathematical function

[Karary University‐ Abusabah I. A. Ahmed]

 Takagi-Sugeno Fuzzy Models

 The most commonly used zero-order Sugeno fuzzy model applies

fuzzy rules in the following form:
IF x is A AND y is B
THEN z is k
where k is a constant.

 In this case, the output of each fuzzy rule is constant.

 All consequent membership functions are represented by singleton
spikes.

[Karary University‐ Abusabah I. A. Ahmed]

Takagi-Sugeno Fuzzy Models

Fuzzy Rules of TSK Model

If x is A and y is B then z = f(x, y)

Fuzzy Sets Crisp Function

f(x, y) is very often a polynomial function w.r.t. x and y.

[Karary University‐ Abusabah I. A. Ahmed]

Takagi-Sugeno Fuzzy Models
Example 8-2

R1: if X is small and Y is small then z = x +y +1

R2: if X is small and Y is large then z = y +3

R3: if X is large and Y is small then z = x +3

R4: if X is large and Y is large then z = x + y + 2

[Karary University‐ Abusabah I. A. Ahmed]

Takagi-Sugeno Fuzzy Models
Example 8-2

[Karary University‐ Abusabah I. A. Ahmed]

 Takagi-Sugeno Fuzzy Models
Sugeno-style rule evaluation

IF 0 OR (0.1) THEN (0.1)

IF 0.2 OR (0.7) THEN (0.2)

IF 0.5 THEN (0.5)

[Karary University‐ Abusabah I. A. Ahmed]

 Takagi-Sugeno Fuzzy Models
Sugeno-style aggregation of the rule outputs
(0.1) (0.2) (0.5)

Weighted Average (WA)

(k1)  k1  (k 2)  k 2  (k 3)  k 3 0.1 20  0.2  50  0.5  80
WA    65
(k1)  (k 2)  (k 3) 0.1  0.2  0.5

Sugeno-style defuzzification 0 z1 Z

Crisp Output
z1

[Karary University‐ Abusabah I. A. Ahmed]

 Types of Fuzzy Controllers
Direct Controller
The Outputs of the Fuzzy Logic System are the command
variables of the plant:
The Outputs of the Fuzzy Logic System Are the Command Variables of the Plant:
Set Point Variable

Command
IF temp=low
AND P=high
Variables

Plant
THEN A=med

IF ...

Fuzzification Inference Defuzzification

Measured Variables

[Karary University‐ Abusabah I. A. Ahmed]

 Types of Fuzzy Controllers
Supervisory Control
Fuzzy Logic Controller Outputs Set Values for Underlying PID Controllers:

IF temp=low
Set Values PID
AND P=high
THEN A=med

PID Plant
IF ...

Fuzzification Inference Defuzzification PID

Measured Variables

[Karary University‐ Abusabah I. A. Ahmed]

 Types of Fuzzy Controllers
PID Adaptation
Fuzzy Logic Controller Adapts the P, I, and D Parameter of a
Conventional PID Controller:
Set Point Variable

IF temp=low
AND P=high P
THEN A=med
I Command Variable
D
IF ...
PID Plant
Fuzzification Inference Defuzzification

Measured Variable

The Fuzzy Logic System analyzes the performance of the PID

controller and optimizes It.
[Karary University‐ Abusabah I. A. Ahmed]
 Types of Fuzzy Controllers
Feed forward Control
Fuzzy Logic Controller compensates for measurable
Disturbance
Disturbance

IF temp=low
AND P=high
THEN A=med

IF ...

Fuzzification Inference Defuzzification

Ref +
Deviation + Action Output
Controller Plant
+
‐

[Karary University‐ Abusabah I. A. Ahmed]

[Karary University‐ Abusabah I. A. Ahmed] 33