Advances and Challenges on Intelligent Learning in Control Systems英文文献资料.pdfVIP

PART II LEARNING AND CONTROL CHAPTER 6 ADVANCES AND CHALLENGES ON INTELLIGENT LEARNING IN CONTROL SYSTEMS 1 2 3 CHING-CHIH TSAI , KAO-SHING HWANG , ALAN LIU , and CHIA-FENG JUANG1 1 Department of Electrical Engineering, National Chung Hsing University, Taichung, Taiwan 2 Department of Electrical Engineering, National Sun-Yat-Sen University, Kaohsiung, Taiwan 3 Department of Electrical Engineering, National Chung Cheng University, Taichung, Taiwan 6.1 INTRODUCTION In recent years, a trend has emerged in which techniques of machine learning, evolu- tionary computations, and intelligent control have been integrated into autonomous systems on a variety of scales to meet the needs of implementation at the angle of products. Many learning methods, such as expert systems, reinforcement learning, mimetic algorithms, evolutionary computations, and support vector machines and so on, have been investigated by a inite number of researchers. On the other hand, several intelligent control approaches, including fuzzy control, neural networks, real-coded genetic algorithm, ant colony optimization (ACO), artiicial immune networks, and swarm intelligence, have gained successful applications in many engineering ields. In light of this emerging trend, the technical committee on intelligent learning in control systems has been timely established to promote the advanced theory, prac- tice, and interdisciplinary aspects of integration of intelligent learning and control in control systems. Contemporary Issues in Systems Science and Engineering, First Edition. Edited by MengChu Zhou, Han-Xiong Li and Margot Weijnen. © 2015 The Institute of Electrical and Electronics Engineers, Inc. Published 2015 by John Wiley Sons, Inc. 243 244 ADVANCES AND CHALLENGES ON INTELLIGENT LEARNING IN CONTROL S