JAWAHARLAL NEHRU TECHNOLOGICAL UNIVERSITY HYDERABAD

Course Objectives:

• 1. Gaining an understanding of the functional operation of a variety of intelligent control techniques and their bio-foundations
• 2. the study of control-theoretic foundations
• 3. learning analytical approaches to study properties

Course Outcomes

Upon the completion of this course, the student will be able to

• 1. Develop Neural Networks, Fuzzy Logic, and Genetic algorithms.
• 2. Implement soft computing to solve real-world problems mainly pertaining to control system applications

UNIT - I

Introduction and motivation. Approaches to intelligent control. Architecture for intelligent control. Symbolic reasoning system, rule-based systems, the AI approach. Knowledge representation. Expert systems.

UNIT - II

Concept of Artificial Neural Networks and its basic mathematical model, McCulloch-Pitts neuron model, simple perceptron, Adaline and Madaline, Feedforward Multilayer Perceptron. Learning and Training the neural network. Data Processing: Scaling, Fourier transformation, principal-component analysis.

UNIT - III

Networks: Hopfield network, Self-organizing network and Recurrent network. Neural Network based controller Case studies: Identification and control of linear and nonlinear dynamic systems using Matlab-Neural Network toolbox. Stability analysis of Neural-Network interconnection systems.

UNIT - IV

Genetic Algorithm: Basic concept of Genetic algorithm and detail algorithmic steps, adjustment of free parameters. Solution of typical control problems using genetic algorithm. Concept on some other search techniques like tabu search and ant-colony search techniques for solving optimization problems.

UNIT - V

Introduction to crisp sets and fuzzy sets, basic fuzzy set operation and approximate reasoning. Introduction to fuzzy logic modeling and control. Fuzzification, inferencing and defuzzification. Fuzzy knowledge and rule bases. Fuzzy modeling and control schemes for nonlinear systems. Fuzzy logic control for nonlinear time-delay system. Implementation of fuzzy logic controller using Matlab fuzzy- logic toolbox. Stability analysis of fuzzy control systems.

TEXT BOOKS:

• 1. Simon Haykins, Neural Networks: A comprehensive Foundation, Pearson Edition, 2003.
• 2. T.J. Ross, Fuzzy logic with Fuzzy Applications, Mc Graw Hill Inc, 1997.
• 3. David E Goldberg, Genetic Algorithms.
• 4. John Yen and Reza Langari, Fuzzy logic Intelligence, Control, and Information, Pearson Education, Indian Edition, 2003. R19 M.TECH CONTROL ENGINEERING. / CONTROL SYSTEM

REFERENCES:

• 1. M.T. Hagan, H. B. Demuth and M. Beale, Neural Network Design, Indian reprint, 2008.
• 2. Fredric M. Ham and Ivica Kostanic, Principles of Neuro computing for science and Engineering, McGraw Hill, 2001.
• 3. N. K. Bose and P. Liang, Neural Network Fundamentals with Graphs, Algorithms, and Applications, Mc - Graw Hill, Inc. 1996.
• 4. Yung C. Shin and Chengying Xu, Intelligent System - Modeling, Optimization and Control, CRC Press, 2009.
• 5. N. K. Sinha and Madan M Gupta, Soft computing & Intelligent Systems - Theory & Applications, Indian Edition, Elsevier, 2007.
• 6. Witold Pedrycz, Fuzzy Control and Fuzzy Systems, Overseas Press, Indian Edition, 2008. R19 M.TECH CONTROL ENGINEERING. / CONTROL SYSTEM M. Tech – I Year – I Sem. (Control Engineering. / Control System.)