基于BP神经网络PID参数自整定的研究  

Research on self-tuning of PID parameters based on BP Neural Networks

作　　者：廖芳芳[1] 肖建[1] 

机构地区：[1]西南交通大学电气工程学院,四川成都610031

出　　处：《系统仿真学报》2005年第7期1711-1713,共3页Journal of System Simulation

摘　　要：PID控制是迄今为止在过程控制中应用最为广泛的控制方法。但在实际应用中,其参数整定仍未得到较好的解决。本文把神经网络技术应用在PID控制中,充分利用神经网络具有非线性函数逼近能力,构造神经网络PID自整定控制器,并通过仿真试验,取得较好的结果。PID controllers are used in a large number of industries, particularly in process industries. However, up to now, there are no satisfactory solutions about the tuning of PID parameters. NN (Neural Network) technique was used in PID control because it could change parameters itself on line. In this way, a NN PID controller of self-tuning could be constructed. The simulation experiments prove it satisfactory.

关 键 词：PID(比例积分微分器) 自整定 BP神经网络 仿真 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]