基于免疫遗传算法的模糊神经网络在交流伺服系统中的应用  

Application of immune genetic algorithm based fuzzy neural network in AC servo system

作　　者：王瑞明[1] 曾玉金[1] 蒋静坪[1] 

机构地区：[1]浙江大学电气工程学院,浙江杭州310027

出　　处：《浙江大学学报（工学版）》2005年第8期1156-1159,1222,共5页Journal of Zhejiang University：Engineering Science

摘　　要：为了满足交流伺服系统高精度、快响应的要求,结合免疫遗传算法寻优速度快和模糊神经网络控制不依赖于控制对象的优点,设计了一种基于免疫遗传算法优化的模糊神经网络控制的交流伺服系统.采用免疫遗传算法优化模糊神经网络控制器中隶属函数的平均值、标准偏差以及隶属函数层与规划层的连接权值.实验和仿真结果验证了该控制策略的可行性.该方法对于系统调节和设定值跟踪均具有很好的控制效果,而且具有很好的抗干扰性能和较强的鲁棒性,使交流伺服系统具有良好的动、静态性能.To satisfy the requirements of higher accuracy and faster response in AC servo system, a system with a fuzzy neural network controller based on immune genetic algorithm （IGA） optimization was designed. The controller combined the advantage of fast searching optimization of IGA and the advantage of not depending on controlled plant of fuzzy neural network controller. This method uses immune genetic algorithm to search the optimal mean, the optimal standard deviation and the optimal weights that connect membership layer and rule layer. Simulation and experimental results verified the effectiveness of the method. The results show that this method has good control effect on both system regulating and set-point following. For AC system in practice, this method has quite good disturbance resistance and strong robustness, and both dynamic and steady performance were improved evidently.

关 键 词：模糊神经网络控制器 交流伺服系统 免疫遗传算法 优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]