基于改进遗传算法的模糊控制器设计

针对模糊控制器的隶属度函数和模糊控制规则的选取及优化缺乏自学习能力与知识采集的手段,以及遗传算法具有自适应、启发式、概率性、迭代式全局收敛的特点,该文章将遗传算法与模糊控制相结合,给出了一种基于改进遗传算法的模糊控制器设计策略.改进算法引入了分裂算子来避免遗传算法在寻优过程中陷入局部最优解,同时对编码方式、选择算子、交叉算子以及变异算子做了相应的调整与改进.并将此改进算法用于优化模糊控制器的隶属度函数与模糊控制规则.仿真结果表明用该改进算法优化后的模糊控制器较用普通遗传算法优化后的模糊控制器具有更好的控制性能.

Design of Fuzzy Controllers Based on Improved Genetic Algorithms

For the selection and optimization of the fuzzy controller＇s membership functions and fuzzy control rules are lack of self-learning ability and knowledge acquisition means,and the genetic algorithm has the characteristics of adaptive,heuristic,probabilistic and iterative global convergence,so this article combines the genetic algorithms and fuzzy control,and gives a fuzzy controller design strategy based on improved genetic algorithm.The improved algorithm introduces a split operator to avoid the genetic algorithm optimization process to fall into the local optimal solution,simultaneously,the encoding,selection operator,crossover operator and mutation operator to be the appropriate adjustments and improvements.And this article makes use of this improved algorithm for optimizing membership function and fuzzy control rules of the fuzzy controller.The simulation results show that the improved algorithm optimized fuzzy controller compares with ordinary genetic algorithm optimized fuzzy controller has better control performance.