Research and Application on Internal Model Control Algorithm Based on Echo State Network
作者单位:School of control and computer engineeringNorth China Electric Power University
会议名称:《第32届中国控制与决策会议》
主办单位:IEEE Control Systems Society (CSS);Northeastern University;State Key Laboratory of Synthetical Automation for Process Industries;Technical Committee on Control Theory, Chinese Association of Automation
会议日期:2020年
学科分类:08[工学] 0802[工学-机械工程] 0835[工学-软件工程] 0811[工学-控制科学与工程] 080201[工学-机械制造及其自动化]
基 金:National Natural Science Foundation of China, NSFC, (61833011) China Postdoctoral Science Foundation, (2018M641292)
关 键 词:internal model controlEcho State Networkcoordinated control systemmutual information
摘 要:Internal model controller(IMC) is widely used due to its simple structure and flexible parameter ***,the inverse model of the object is difficult to obtain accurately,especially for some non-minimum phase *** solve this problem,this paper proposed an neural network IMC combining Echo State Network(ESN) and IMC *** initial ESN inverse controller and reference model are trained offline based on input and output *** order to detect the model mismatch,the mutual information between input and model deviation are *** online update of controller and reference model are achieved based on Recursive Least Square method to enhance better *** and experiments shows the effectiveness of this method and it has some ability of self diagnosis and self recovery.