基于蚁群优化的神经网络智能PID控制策略研究  

Application of BP Neural Network Intelligent PID Controller Based on the Ant Colony Optimization

作　　者：姜万录[1] 刘伟[1] 张瑞娟[1] 陈海军[1] 

机构地区：[1]燕山大学机械工程学院,河北秦皇岛066004

出　　处：《机床与液压》2010年第13期22-25,共4页Machine Tool & Hydraulics

基　　金：国家自然科学基金(50775198);河北省自然科学基金(E2008000812)

摘　　要：提出了一种基于蚁群优化、BP网络学习和RBF网络辨识的智能PID控制策略,有效地克服了BP算法训练过程中收敛慢和易陷入局部极小值的缺陷。利用该控制策略,对PID参数进行在线调整,并应用于材料试验机电液位置伺服系统。仿真结果表明,与各种传统PID控制策略相比,采用该智能PID控制器控制的系统具有更好的动态响应特性和抗扰动能力。A new intelligent PID control method based on Ant Colony Optimization （ACO）, BP neural network and RBF neural network was proposed, which solved the systemic error immersed in a local minimum and accelerated the network＇s convergence during the training of BP neural network effectively. This method can automatically adjust PID parameters to obtain satisfied performance, and was applied in the position server electro-hydraulic material testing system. The simulation result shows that the intelligent PID controller possesses better dynamic characteristics and robust performance than traditional one.

关 键 词：神经网络 蚁群优化 PID 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] TH137[自动化与计算机技术—计算机科学与技术]