Intelligence control using fuzzy logic

21
INTELLIGENT CONTROL ON FUZZY LOGIC Presented by N. Elakiya M.Phil Mathematics

Transcript of Intelligence control using fuzzy logic

Page 1: Intelligence control using fuzzy logic

INTELLIGENT CONTROL ON FUZZY LOGIC

Presented by N. Elakiya M.Phil Mathematics

Page 2: Intelligence control using fuzzy logic

OVERVIEWIntroduction

Problem Statement

Methodology

Applications

Concluding

Page 3: Intelligence control using fuzzy logic

INTRODUCTIONFuzzy sets were introduced by Zadeh in 1965 to represent

data and information possessing non-statistical uncertainties. It

was specifically designed to mathematically represent

uncertainty and vagueness and to provide formalized tools for

dealing with the imprecision intrinsic to many problems.

Fuzzy Logic is based on the theory of fuzzy sets , which is a

generalization of the classical set theory . Fuzzy Logic can be

considered as an extension of infinite-valued logic in the sense

of cooperate fuzzy sets and fuzzy relations into the system.

Page 4: Intelligence control using fuzzy logic

HISTORY OF FUZZYIn 1930s Fuzzy or multivalued logic was introduced by Jan

Lukasiewicz, a polish philosopher.

In 1937- Max Black published a paper called “Vagueness: a

exercise in logical analysis”.

In 1965 - Lotfi Zadeh published his famous paper “Fuzzy

Sets”. Zadeh extended the work on possibility theory into a

formal system of mathematical logic, and introduced a new

concept for applying natural language terms.

Page 5: Intelligence control using fuzzy logic

In 1965- 1975: Zadeh continued to broaden the foundation of fuzzy set

theory

- Fuzzy multistage decision-making

- Fuzzy similarity relations

- Fuzzy Restrictions

- Linguistic Hedges

In 1975: Mamdani, united kingdom developed the first fuzzy logic

controller.

In 1977: Dubois applied fuzzy sets in a comphrensive study of traffic

conditions.

In 1976-1987: Industrial application of fuzzy logic in Japan and Europe.

Page 6: Intelligence control using fuzzy logic

WHAT IS FUZZY LOGIC?Fuzzy Logic is a superset of conventional (Boolean)

logic that has been extended to handle the concept of partial

truth-values between “completely true” and “Completely false”.

It is based on the idea that human reasoning is

approximate, non-quantitative, and non-binary.

The simplest example is temperature. Usually when you

as someone the temperature they respond with “cool” ,

“warm” , “hot” , “very hot” as opposed to telling the exact

temperature such as “ 28.5 degrees” or “33.1 degrees”.

Page 7: Intelligence control using fuzzy logic

GENERAL APPROACH TO FUZZY LOGIC CONTOLThe general approaches to designing a fuzzy logic controller is

made up 5 steps:

Define the Input and Output Variables.

Define the subsets(Fuzzy sets) intervals.

Choose the Membership functions

Set the IF-THEN rules

Perform calculations(using Fuzzy Inference) and adjust rules

Page 8: Intelligence control using fuzzy logic

WHY USE FUZZY LOGIC? Control system requires less information

Can be quicker to implemented

Rules can be tested individually.

Speed and position control in mechatronic systems

Robot trajectory control and obstacle avoidance

control appliances such as washing machine

Page 9: Intelligence control using fuzzy logic

WHAT ABOUT INTELLIGENT CONTROL?

The premise behind intelligent control is that the system to be

controlled does not have to e rigidly modelled.

This is unlike classical control and biggest distinction between the

two approaches.

Humans can perform complex tasks without knowing exactly how

they do them .Therefore, one may say that an intelligent model solves

* A difficult (non-trivial, complex, complicated) problem.

* In a non-trivial human-like way

Page 10: Intelligence control using fuzzy logic

TYPES OF INTELLIGENT CONTROLTypes of intelligent control include:

o Fuzzy logic

oArtificial neural networks

oGenetic programming

o Support vector machines

oReinforcement learning

Page 11: Intelligence control using fuzzy logic

METHODOLOGYFuzzification, Fuzzy Inference, Defuzzification Measured variable Command

Variables (Linguistic Variable) (Linguistic

Variable)

LinguisticLevel

-----------------------------------------------------------------------NumericalLevel

Measured Variable Command Variables

(Numerical Values) (Numerical values)

ITS Manageme

nt

Page 12: Intelligence control using fuzzy logic

COMPONENTS OF INTELLIGENT SYSTEM

user

user interface

Knowledge engineer Developers interface

Knowledge base

(passive)

Inference engine(active)

Knowledge base manager

(active)

Page 13: Intelligence control using fuzzy logic

APPLICATIONTRAFFIC MANAGEMNT USING FUZZY LOGIC

CONTROLLER

The inputs regarding the number of vehicles at each participating signal

are obtained through vision sensors.

The number of detected vehicles is sent to the controller which acts as the

brain of the system and produce a unique output for each scenario form

the basis of operation.

Their relations have been defined in the form of “if else” statements in

the fuzzy inference.

Page 14: Intelligence control using fuzzy logic

Input Fuzzy Membership Functions

Output Fuzzy Membership Functions

Page 15: Intelligence control using fuzzy logic

Fuzzy Inference System Rules

1. If ( Route-A is light) then (signal-A is +A)

2. If ( Route-A is lighter) then (signal-A is +A)

3. If ( Route-A is high) then (signal-A is +++A)

4. If ( Route-A is medium ) then (signal-A is ++A)

5. If ( Route-A is higher) then (signal-A is ++++A)

6. If ( Route-A is nothing) then (signal-A is null)

7. If (Route-A is light) and (Route-B is few) then (signal-A is +A)

8. If (Route-A is lighter) and (Route-B is fewer) then (signal-A is +A)

9. If (Route-A is high) and (Route-B is more) then (signal-A is ++A)

10. If (Route-A is medium) and (Route-B is much) then (signal-A is +++A)

11. If (Route-A is higher) and (Route-B is numerous) then (signal-A is ++++A)

12. If (Route-A is higher) and (Route-B is few) then (signal-A is +A)

13. If (Route-A is higher) and (Route-B is fewer) then (signal-A is ++A)

14. If (Route-A is higher) and (Route-B is more) then (signal-A is +++A)

15. If (Route-A is medium) and (Route-B is few) then (signal-A is ++A)

Page 16: Intelligence control using fuzzy logic

The Concept of extension of signal operation time provides longer green light intervals for routes with a greater amount of traffic.

S.No Number of Vehicles Output Time(S)

1 1-3 5

2 4-5 10

3 6 15

4 7 20

PIC16F877A MICROCONTROLLER

The Fuzzy logic Controller is then Followed by the PIC

16F877A Microcontroller which manages the traffic lights according to

the data it receives from the controller.

The main role of the microcontroller is to serially receive and

manipulate the data from the controller and carry out particular action.

Page 17: Intelligence control using fuzzy logic

Flow chart of overall system working

Page 18: Intelligence control using fuzzy logic

Traffic Signal Operation

Page 19: Intelligence control using fuzzy logic

SOME OF APPLICATIONS Aerospace

Chemical Industry

Electronics

Financial

Industrial

Manufacturing

Marine

Medical

Mining and Metal Processing

Robotics

Securities

Page 20: Intelligence control using fuzzy logic

CONCLUSIONThis presentation has demonstrated Intelligent Control and an improved traffic Controller using fuzzy logic and microcontroller.

Page 21: Intelligence control using fuzzy logic

THANK YOU