Coding is an important and a difficult subject of research on genetic algorithm (GA). float code (FC) is super to other codes in use. But, noise and its influence on GA performance were ignored by researches in geneti...
详细信息
Coding is an important and a difficult subject of research on genetic algorithm (GA). float code (FC) is super to other codes in use. But, noise and its influence on GA performance were ignored by researches in genetic operation. Mutation played an important role of improving GA performance. This paper presents a float-coded genetic algorithm (FCGA) with wavelet denoising mutation. They are called the bound crossover and wavelet denoising mutation. By introducing the proposed genetic operation, both the solution quality and stability are better than GA with conventional genetic operations. Decomposing of FC noise was proved with wavelet in theory. FC denoising mutation was implemented in it. Experiments were made in it. The results of the research and experiments indicate that the theory is credible and the method is feasible in it. FCGA is of active significance to extend application space of GA.
An approach of reduced-order H ∞ controller for a class of linear continuous dynamic systems is presented based on Genetic Algorithm. Necessary and sufficient conditions are given, in terms of linear matrix inequalit...
详细信息
An approach of reduced-order H ∞ controller for a class of linear continuous dynamic systems is presented based on Genetic Algorithm. Necessary and sufficient conditions are given, in terms of linear matrix inequality for the existence of controller. A rank condition is changed to object function of genetic algorithm(GA). The minimum order n k of the controller and a corresponding parameter pair ( X,Y ) of positive definite matrix are obtained by means of searching the object function. And then the reduced-order H ∞ controllers are constructed. In this paper, the code is float, the selection operator is rank-based fitness assignment and elitist model, the crossover operator is improved real cross, the mutation operator is real mutation. The simulation results show that the controller has the same control effect as all-order H ∞ controllers based on MATLAB.
暂无评论