永磁同步直线电机DDPG自适应控制  

DDPG Adaptive Control of Permanent Magnet Synchronous Linear Motor

作　　者：张振宇 张昱 陈丽[1] 张东波 ZHANG Zhenyu;ZHANG Yu;CHEN Li;ZHANG Dongbo(School of Information Science and Engineering, Shenyang University of Technology, Shenyang 110870,China;Guangdong Institute of Intelligent Manufacturing, Guangdong Key Laboratory of Modern Control Technology,Guangdong 510070,China)

机构地区：[1]沈阳工业大学信息科学与工程学院,沈阳110870 [2]广东省智能制造研究所,广东省现代控制技术重点实验室,广州510070

出　　处：《微电机》2020年第4期89-92,102,共5页Micromotors

基　　金：广东省科学院实施创新驱动发展能力建设专项(2017GDASCX-0115);广东省科学院实施创新驱动发展能力建设专项(2018GDASCX-0115);广东省科学院建设国内一流研究机构行动专项资金项目(2019GDASYL-0103077)。

摘　　要：为了在高速高精度应用场合实现对非线性、强耦合、负载扰动大的永磁同步直线电机的快速精准控制,提出一种基于深度确定性策略梯度(DDPG)算法的自适应控制策略,应用在PMSLM的速度环中,以速度作为控制变量,以交轴电流iq做被控变量,在Simulink仿真平台上进行仿真,并与传统PID控制策略进行比较,结果显示,采用DDPG自适应控制策略以后,直线电机伺服系统的快速性、稳定性及抗干扰能力有了明显的提升。基于DDPG自适应控制的直线电机控制系统具有较强的自学习自整定性能,使直线电机伺服系统具有更好的动态响应性和更稳定的跟踪性能。In order to achieve in high speed and high precision applications of nonlinear,strong coupling,large load disturbance of rapid precise control of permanent magnet synchronous linear motor(PMSLM),in this paper,a deep deterministic policy gradient(DDPG)algorithm for adaptive control strategies,application in PMSLM velocity loop,speed as control variables,controlled variables and quadrature axis current iq do,simulation in Simulink platform,and comparing with the traditional PID control strategy,the results show that the DDPG adaptive control strategy was used.The speed,stability and anti-interference ability of linear motor servo system was improved obviously.DDPG-based PMSLM control system has strong self-learning and self-integration qualitative energy,which makes the PMSLM servo system have better dynamic response and more stable tracking performance.

关 键 词：永磁同步直线电机 DDPG自适应控制策略 速度环 SIMULINK仿真 

分 类 号：TM359.4[电气工程—电机] TP273.2[自动化与计算机技术—检测技术与自动化装置]