文章基本信息

标题：An Adaptive Correction Scheme for Offset-Free Asymptotic Performance in Deep Learning-based Economic MPC ⁎
本地全文：下载
作者：Dinesh Krishnamoorthy ; Ali Mesbah ; Joel A. Paulson 等
期刊名称：IFAC PapersOnLine
印刷版ISSN：2405-8963
出版年度：2021
卷号：54
期号：3
页码：584-589
DOI：10.1016/j.ifacol.2021.08.305
语种：English
出版社：Elsevier
摘要：AbstractThere has been an increasing interest in explicit and cheap-to-evaluate control policies that approximate (computationally expensive) control laws such as model predictive control (MPC). However, approximate control policies are subject to approximation errors, leading to asymptotic performance losses. The contribution of this paper is three-fold: (i) a closed-loop training scheme is presented for deep neural network approximation of economic MPC; (ii) an online adaptive correction scheme is presented to account for the performance losses induced by approximation errors; and (iii) an offline performance verification scheme is presented to ensure that the approximate control policy converges to an equilibrium point of the system. The proposed approach is illustrated using a Williams-Otto reactor problem.
关键词：KeywordsApproximate MPCdeep neural networksprobabilistic guaranteesadaptive correctionoffset-free performance