基于遗传算法和模糊神经网络的PID控制器参数优化方法  

Parameters Optimization Method of PID Controller Based on Genetic Algorithm and Fuzzy Neural Network

作　　者：周頔[1] 

机构地区：[1]四川文理学院,四川达州635000

出　　处：《计算机与现代化》2013年第9期8-12,共5页Computer and Modernization

基　　金：国家自然科学基金资助项目(60971016;61108086);四川省教育厅自然科学重点项目(11ZA168);达州市重大科技攻关项目(2010zdzx006)

摘　　要：针对传统的PID控制器参数优化需要被控对象精确数学模型问题,利用不需要被控对象数学模型的模糊控制理论和神经网络的自适应和自学习的能力以及遗传算法的全局优化能力,提出一种基于遗传算法、模糊控制理论和神经网络相结合的PID控制器参数优化方法。该方法首先利用十进制编码对遗传算法进行编码,然后集中优化模糊神经网络参数和结构,接着再用优化的模糊神经网络确定PID控制器参数,获得模糊神经网络PID控制器。最后通过达州钢铁集团扎钢厂中央空调控制系统实际应用,结果表明该优化方法具有较强的抗干扰能力和鲁棒性。In allusion to the disadvantages of the traditional parameters optimization method of PID controller for needing the precise mathematic model,the adaptive ability and learning ability of fuzzy control theory and neural network and the global optimization ability of genetic algorithm are used.A parameters optimization method of PID controller based on genetic algorithm,fuzzy control theory and neural network is proposed.The parameters and structure of fuzzy neural network are comprehensively optimized by using genetic algorithm based on the decimal coding.Then the optimized fuzzy neural network is used to compute the three parameters of PID controller in order to obtain the optimization PID controller.Finally,the optimization method is applied in the central air conditioning control system of Dazhou Iron ＆ Steel Group,the simulation results show that the optimization method takes on the strong anti-interference ability and robustness.

关 键 词：遗传算法 模糊控制理论 神经网络 优化 PID控制器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]