Studies On Fuzzy Controller Based On A Hybrid Genetic Algorithm

The Genetic Algorithm (GA) is a kind of parallel, efficient and overall optimal search algorithm based on nature evolution theory. The basic concept of GA is designed to simulate processes in natural system necessary for evolution (via natural selection, mutation, crossover), specifically those that follow the principles first laid down by Charles Darwin of survival of the fittest, then the satisfying solution is obtained. However, there are some shortages in the conventional Genetic Algorithm, for example, the probability of premature convergence caused by its lower search efficiency. Especially when hi the calculation of Genetic Algorithm of binary code, the task is very huge because of the complex decoding procedures. And it's necessary for Genetic Algorithm of binary code to encode itself with a string long enough, which may subsequently cause the increase of calculation complexity and the decrease of the convergence speed, if a highly precise result expected by a function optimizer. Considering the disadvantages of standard Genetic Algorithm, it is of great importance to improve on GA or to research on a better GA integrated with other algorithms, subsequently many unproved methods are proposed.In the paper, the importance of the crossover and mutation operators in the convergence of Genetic Algorithm is fully considered, In traditional Genetic Algorithm, the probability of crossover and mutation keep stable during the whole period of Evolution, which may cause the premature convergence directly. To avoid the limitation of Simple Genetic Algorithm, an unproved Genetic Algorithm, Hybrid Genetic Algorithm (HGA), is presented, In different phase of the evolution, each chromosome's possibilities of crossover and mutation can be changed according to different fitness of environment and similarity of the parents. The ability of adjust of mutation possibility not only insure the diversity of sample, but also unproved the search capacity of algorithm, which make it jump out of the local optima efficiently.Fuzzy Control is an important branch of Intelligent Control, and it mainly depends on the human experience but not the mathematical model of controlled-object. Thus, Fuzzy controller can fulfill some human's intelligence and is widely used in complex process and object-model control. The efficiency of Fuzzy Control depends on several key parameters: membership functions and fuzzy control-rule table. Conventional methods that select the parameters mainly reckon on experts' experience and practical modulation, so there exist subjectivity and randomness. In the thesis a new method based on decimal-code and binary-code is provided, which unites the membership functions and fuzzy control rule-table into a integrated one for whole-scope searching, and the operators of GA is adjusted for the change of the code. Finally, the result of simulation shows that the method is effective and applicatory.