基于改进BP网络的网络控制系统建模与仿真  

Modeling and Simulation of Networked Control Systems Based on Improved BP Network

作　　者：李世峰[1] 邱占芝[1,2] 樊丽萍 赵丽娜[1,2,4] Li Shifeng;Qiu Zhanzhi;Fan Liping;Zhao Lina(Mechanical Engineering Inst, Dalian Jiaotong University, Dalian 116028, China;Software Technology Inst, Dalian Jiaotong University, Dalian 116028, China;Electrical Information Inst, Dalian Jiaotong University, Dalian 116028, China;Electrical Engineering Inst, Dalian Institute of Science and Technology, Dalian 116052, China)

机构地区：[1]大连交通大学机械工程学院,大连116028 [2]大连交通大学软件学院,大连116028 [3]大连交通大学电气信息学院,大连116028 [4]大连科技学院电气工程学院,大连116052

出　　处：《系统仿真学报》2018年第6期2279-2287,共9页Journal of System Simulation

基　　金：国家自然科学基金(61074029);大连市计划(2014A11GX006)

摘　　要：针对网络化控制系统中时延模型和被控对象模型均未知的情况,研究了一类基于改进BP网络的网络化预测控制系统。针对BP网络隐含层节点数求取问题,提出了一种快速求取方法。针对BP网络局部最优问题,提出了一种混合学习方法。在上述算法的基础上,提出了一种离线BP网络模型用于应对时延预测问题。针对网络化控制系统中的线性和非线性控制问题,设计了基于在线BP网络的单步预测控制器。仿真结果表明:系统在运行速度、时延预测、线性和非线性控制方面均具有良好的性能。In the circumstance where both the delay model and the controlled object model were unknown in networked control systems, a class of networked predictive control systems based on improved BP network were studied. For the problem of obtaining the hidden layer nodes number of BP network, a rapid calculation method was proposed. For the problem of avoiding local optimum of BP network, a hybrid learning method was proposed. A off-line BP network model was proposed for coping with the problem of the delay prediction based on the above algorithms. For the problem of the linear and nonlinear control of the networked control systems, a single step prediction controller based on on-line BP network was designed. The simulation results show that the performance of the networked predictive control systems is improved in the running speed, the delay prediction, the linear and nonlinear controls.

关 键 词：网络化控制系统 BP网络 时延预测 遗传算法 线性被控对象 非线性被控对象 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]