An Introduction to Fuzzy ControlFuzzy controllers are a class of knowledge based controllers using artificial intelligence techniques with origins in fuzzy logic to compute an appropriate control action. These fuzzy knowledge based controllers can be found either as stand-alone control elements or as integral parts of distributed control systems including conventional controllers in a wide range of industrial process control systems and consumer products. Applications of fuzzy controllers have become a well established practice for Japanese manufacturers of control equipment and systems, and are becoming more and more common for their European and American counterparts. The main aim of this book is to show that fuzzy control is not totally ad hoc, that there exist formal techniques for the analysis of a fuzzy controller, and that fuzzy control can be implemented even when no expert knowledge is available. Thus the book is mainly oriented toward control engineers and theorists rather than fuzzy and non-fuzzy AI people. However, parts can be read without any knowledge of control theory and may be of interest to AI people. The book has six chapters. Chapter 1 introduces two major classes of knowledge based systems for closedloop control. Chapter 2 introduces relevant parts of fuzzy set theory and fuzzy logic. Chapter 3 introduces the principal design parameters of a fuzzy knowledge based controller (FKBC) and discusses their relevance with respect to its performance. Chapter 4 considers an FKBC as a particular type of nonlinear controller. Chapter 5 considers tuning and adaptation of FKBCs, which are nonlinear and so can be designed to cope with a certain amount of nonlinearity. Chapter 6 considers several approaches for stability analysis of FKBCs in the context of classical nonlinear dynamic systems theory. |
From inside the book
Results 1-5 of 65
Page 10
... error as was done with “ classi- cal " artificial intelligence systems , where after some initial success in relatively narrow application areas it was believed that artificial intelligence could be used as a universal stand - alone ...
... error as was done with “ classi- cal " artificial intelligence systems , where after some initial success in relatively narrow application areas it was believed that artificial intelligence could be used as a universal stand - alone ...
Page 13
... error situations which have occurred before , and giving suggestions on how to improve the current situation . In order to be able to assist the process operator in these tasks the KBS for monitoring has to provide means for ...
... error situations which have occurred before , and giving suggestions on how to improve the current situation . In order to be able to assist the process operator in these tasks the KBS for monitoring has to provide means for ...
Page 14
... errors in power generators , developed by Westinghouse Corp. [ 154 ] ; AFS , for alarm filtering , developed by Idaho National Engineering Lab . [ 40 ] ; COOKER , for on - line monitoring of batch manufacturing processes , developed by ...
... errors in power generators , developed by Westinghouse Corp. [ 154 ] ; AFS , for alarm filtering , developed by Idaho National Engineering Lab . [ 40 ] ; COOKER , for on - line monitoring of batch manufacturing processes , developed by ...
Page 18
... - ual control strategy by employing a rule base which determines the control output signal , given information about process output variables , e.g. , error , ΑΣ Plant DECS Fig . 1.2 . The structure of 18 1. Introduction.
... - ual control strategy by employing a rule base which determines the control output signal , given information about process output variables , e.g. , error , ΑΣ Plant DECS Fig . 1.2 . The structure of 18 1. Introduction.
Page 19
... error , etc. The need for such a KBS is motivated if the nature of the process under control is such that appropriate analytic models do not exist or are inadequate , but the process operator can manually control the process to a ...
... error , etc. The need for such a KBS is motivated if the nature of the process under control is such that appropriate analytic models do not exist or are inadequate , but the process operator can manually control the process to a ...
Contents
1 | |
4 | |
The Mathematics of Fuzzy Control | 37 |
FKBC Design Parameters | 103 |
CenterofLargestArea | 132 |
Adaptive Fuzzy Control | 197 |
Membership Function Tuning Using Performance Criteria | 214 |
Stability of Fuzzy Control Systems | 245 |
References | 291 |
Other editions - View all
An Introduction to Fuzzy Control Dimiter Driankov,Hans Hellendoorn,Michael Reinfrank Limited preview - 2013 |
An Introduction to Fuzzy Control Dimiter Driankov,Hans Hellendoorn,Michael Reinfrank Snippet view - 1993 |
An Introduction to Fuzzy Control Dimiter Driankov,Hans Hellendoorn,Michael Reinfrank Snippet view - 1993 |
Common terms and phrases
Ae(k algorithm applications Au(k binary relation change-of-error closed loop transient compute consider control output variables control system control theory control variable conventional control crisp input cross-point defined Definition defuzzification defuzzification method degree of membership denormalization denoted described domain elements equation error example FKBC fuzzy control fuzzy logic fuzzy model fuzzy propositions fuzzy relation fuzzy set theory given Gödel heuristic if-then rules implication inference engine intersection knowledge representation linear linguistic values linguistic variable loop transient step LX(k Mamdani membership degree membership functions NB NB nonlinear normalized obtain on-line overshoot PB PB performance phase plane PID-controller process control process state variables property symbol representing the meaning robot rule base rule-antecedent scaling factors Section set of rules set-point sliding mode sliding mode control T-norm term set transient step response tuple universe of discourse vector Zadeh zero Уз