文章基本信息

标题：Optimal PID and Antiwindup Control Design as a Reinforcement Learning Problem
本地全文：下载
作者：Nathan P. Lawrence ; Gregory E. Stewart ; Philip D. Loewen 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2020
卷号：53
期号：2
页码：236-241
DOI：10.1016/j.ifacol.2020.12.129
语种：English
出版社：Elsevier
摘要：AbstractDeep reinforcement learning (DRL) has seen several successful applications to process control. Common methods rely on a deep neural network structure to model the controller or process. With increasingly complicated control structures, the closed-loop stability of such methods becomes less clear. In this work, we focus on the interpretability of DRL control methods. In particular, we view linear fixed-structure controllers as shallow neural networks embedded in the actor-critic framework. PID controllers guide our development due to their simplicity and acceptance in industrial practice. We then consider input saturation, leading to a simple nonlinear control structure. In order to effectively operate within the actuator limits we then incorporate a tuning parameter for anti-windup compensation. Finally, the simplicity of the controller allows for straightforward initialization. This makes our method inherently stabilizing, both during and after training, and amenable to known operational PID gains.
关键词：Keywordsneural networksreinforcement learningactor-critic networksprocess controlPID controlanti-windup compensation