文章基本信息

标题：Deep Neural Network Approximation of Nonlinear Model Predictive Control
本地全文：下载
作者：Yankai Cao ; R. Bhushan Gopaluni
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：11319-11324
DOI：10.1016/j.ifacol.2020.12.538
语种：English
出版社：Elsevier
摘要：AbstractThis paper focuses on developing effective computational methods to enable the real-time application of model predictive control (MPC) for nonlinear systems. To achieve this goal, we follow the idea of approximating the MPC control law with a Deep Neural Network (DNN). To train the deep neural network offline, we propose a new “optimize and train” method that combines the steps of data generation and neural network training into a single high-dimensional stochastic optimization problem. This approach directly optimizes the closed loop performance of the DNN controller over a finite horizon for a number of initial states. The large-scale optimization problem can be solved efficiently using parallel computing techniques. The benefits of this approach over the conventional “optimize then train” protocol is illustrated through numerical results.
关键词：KeywordsModel Predictive ControlStochastic OptimizationDeep Neural NetworksNonlinear Systems