0% found this document useful (0 votes)
101 views3 pages

IC368 Computational Intelligence in Control Engineering

This document describes a course on computational intelligence in control engineering. The course aims to provide fundamentals of artificial neural networks and fuzzy logic, and make students capable of applying these techniques to design systems. The syllabus covers topics like fuzzy logic, fuzzy reasoning, neural networks, neural network training, and neural-fuzzy controllers. Upon completing the course, students should have knowledge of neural networks and fuzzy logic principles, and be able to design different systems using these methods. The course is divided into modules covering these topics, and will be evaluated through internal exams, assignments, and an end-semester exam.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
101 views3 pages

IC368 Computational Intelligence in Control Engineering

This document describes a course on computational intelligence in control engineering. The course aims to provide fundamentals of artificial neural networks and fuzzy logic, and make students capable of applying these techniques to design systems. The syllabus covers topics like fuzzy logic, fuzzy reasoning, neural networks, neural network training, and neural-fuzzy controllers. Upon completing the course, students should have knowledge of neural networks and fuzzy logic principles, and be able to design different systems using these methods. The course is divided into modules covering these topics, and will be evaluated through internal exams, assignments, and an end-semester exam.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Course code Course Name L-T-P- Year of

Credits Introduction
IC368 COMPUTATIONAL INTELLIGENCE IN 3-0-0-3 2016
CONTROL ENGINEERING
Prerequisite: Nil

Course Objectives
 To provide the fundamentals of Artificial neural networks and fuzzy logics
 To make the students capable of applying these techniques for the design of related
systems.
Syllabus
Need of expert systems, techniques of intelligent control, elements of fuzzy logic, fuzzy
reasoning, the fuzzy control algorithm, fuzzy industrial controllers, model-based fuzzy
controllers, neural control, neural network training, rule-based neural control, application of
neural networks, neural-fuzzy controllers.
Expected Outcome
Upon completing this course, students should have:
 Knowledge in principles of neural networks and fuzzy logic fundamentals.
 Design of different systems using ANN and fuzzy logic.
Text Book

1. Robert E. King, Computational Intelligence in Control Engineering, Marcel Dekker.

References:
1. Limin Fu, Neural Networks in Computer Intelligence, McGraw Hill.
2. Fakhreddine o. Karray and Clarence De Silva, Soft Computing and Intelligence Systems
Design, Theory, Tools and Applications, Pearson Education.
3. S.N. Sivanandam, S.Sumathi and S.N.Deepa, Introduction to Neural Networks using
Matlab 6, McGraw Hill Education.
4. J-S.R.Jang, C-T.Sun & E.Mizutani, Neuro-Fuzzy & Soft Computing, Pearson.
5. Timothy.J.Ross, Fuzzy Logic with Engineering Applications, McGraw Hill.
6. Simon Haykin, Neural Networks, PHI.
7. S.Rajasekaran and G.A.Vijayalakshmi Pai, Neural Networks, Fuzzy Logic, and Genetic
Algorithms Synthesis and Applications, PHI.
8. Satish Kumar, Neural Networks, McGraw Hill Education.
9. D.Driankov, H. Hellendoorn and M.Reinfrank, Fuzzy Control, Narosa.
Course Plan
Module Contents Hours Sem.
Exam
Marks
I Need of expert system, Intelligent control: conditions for the use 1 15%
of intelligent control, objectives of intelligent control.
Techniques of intelligent control: unconventional control,
autonomy and intelligent control, knowledge based systems.
Elements of fuzzy logic: basic concepts, fuzzy algorithms, fuzzy 2
operators, operations on fuzzy sets, algebraic properties of fuzzy
sets, linguistic variables.
Fuzzy Reasoning: the fuzzy algorithm, fuzzy reasoning, 3
generalized modus ponens, generalized modus tollens, Boolean
implication, lukasiewicz implication, zadeh implication, mamdani
implication, Larsen implication, GMP implication, the
compositional rules of inerence.
II The Fuzzy Control Algorithm: controller decomposition, 7 15%
fuzzification, defuzzification of the composite controller output
membership function (COA and COG), design considerations.
FIRST INTERNAL EXAM
III Fuzzy Industrial Controllers: controller tuning, fuzzy three term 3 15%
controllers, coarse and fine fuzzy controllers.
Model-Based Fuzzy Control: the takagi-sugeno model based 4
approach to fuzzy control, fuzzy variables and fuzzy spaces, the
fuzzy process model, the fuzzy control law, the locally linearized
process model, the second takagi-sugeno approach, the fuzzy gain
scheduling.
IV Neural Control: the elemental artificial neuron, topologies of 3 15%
multi-layer neural network, neural control, properties of neural
controllers, neural controller architecture.
Perceptron. 4
Neural network training: the widrow-Hoff training algorithm, the
delta training algorithm.
SECOND INTERNAL EXAM
V Multi-layer ANN training algorithm, Back propagation learning 4 20%
algorithm, limitations of Multi-layer perceptron.
Rule-based Neural Control: encoding linguistic rules, training rule 4
based neural controllers.
VI Case study: SVM and SVR. 7 20%
Application of Neural networks: Semiconductor manufacturing
processes, Communication, Process monitoring and optimal
control, Robotics, Decision fusion and pattern recognition.
Neuro-Fuzzy Controller: Neuro-Fuzzy controller architecture,
neuro-fuzzy isomorphism.

END SEMESTER EXAM


QUESTION PAPER PATTERN:

Maximum Marks: 100 Exam Duration: 3 Hours

Part A

Answer any two out of three questions uniformly covering Modules 1 and 2. Each question
carries 15 marks and can have not more than four sub divisions. (15 x 2 = 30 marks)

Part B

Answer any two out of three questions uniformly covering Modules 3 and 4. Each question
carries 15 marks and can have not more than four sub divisions. (15 x 2 = 30 marks)

Part C

Answer any two out of three questions uniformly covering Modules 5 and 6. Each question
carries 20 marks and can have not more than four sub divisions. (20 x 2 = 40 marks)

You might also like