PC based PI-type control of DC motor aided genetic algorithms

ABSTRACT Today, Fuzzy Control are now considered as one of the most important applications of the fiizzy-rule-based systems which is widely being used in industry. The experience of skilled operators and the knowledge of control engineers are expressed qualitatively by a set of fiizzy control rules. The construction of fuzzy rules has been mainly based on the operator's control experience or actions. Genetic algorithms (GAs) are search algorithms based on the mechanics of natural selection and natural genetics. GAs have the properties that make them a powerful technique for selecting high-performance parameters for FLCs. In a few years many different approaches have been presented using the genetic algorithms (Gas) as a base of the learning process. Gas have demonstrated to be a powerful tool for automating the definition of the fuzzy control rule knowledge base. These approaches called the general name of genetic fuzzy systems (GFSs).We propose a GFS methodology based on three stages. In this thesis, genetic algorithms are used to learn PI-typefuzzy control rules for direct current motor speed control. Comparisons are made between systems utilizing learning rules and human expert based rules to verify the performance of the work. Recently GFS algorithm has been searched in developing well-performing fiizzy rule-base without help of human expertise. Learning the rale-base requires experience human with long time. Genetic Fuzzy System provides a method to design automatically the knowledge base a direct fuzzy controller. In this work, we are interested in automatically learning rule-base for a fuzzy logic based dc motor controller. At the same time, we provide an analysis of Genetic Fuzzy System for dc motor control system. It seems that we designed GFS is powerful method for control of dc motor and gives well performance. In this study, I have been used Pentium 120 mHz computer and Turbo C program. Hence, it provides an approach to computer aided design about automation for dc motor control system. As a result, this approach can provide a low-cost and robust means of design of the fuzzy rule-based controller. We achieved a result, the proposed genetic algorithm model has demonstrated its capabilities in term so high robustness, flexibility and reliability by consistently improving the performance of the fuzzy logic controller. Keywords: Fuzzy control, Genetic Algorithms, Rule Base, DC motor, Learning Control xui