文章基本信息

标题：Deterministic Global Nonlinear Model Predictive Control with Neural Networks Embedded
本地全文：下载
作者：Danimir T. Doncevic ; Artur M. Schweidtmann ; Yannic Vaupel 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：5273-5278
DOI：10.1016/j.ifacol.2020.12.1207
语种：English
出版社：Elsevier
摘要：AbstractNonlinear model predictive control requires the solution of nonlinear programs with potentially multiple local solutions. Here, deterministic global optimization can guarantee to find a global optimum. However, its application is currently severely limited by computational cost and requires further developments in problem formulation, optimization solvers, and computing architectures. In this work, we propose a reduced-space formulation for the global optimization of problems with recurrent neural networks (RNN) embedded, based on our recent work on feed-forward artificial neural networks embedded. The method reduces the dimensionality of the optimization problem significantly, lowering the computational cost. We implement the NMPC problem in our open-source solver MAiNGO and solve it using parallel computing on 40 cores. We demonstrate real-time capability for the illustrative van de Vusse CSTR case study. We further propose two alternatives to reduce computational time: i) reformulate the RNN model by exposing a selected state variable to the optimizer; ii) replace the RNN with a neural multi-model. In our numerical case studies each proposal results in a reduction of computational time by an order of magnitude.
关键词：KeywordsNonlinear process controlModel predictiveoptimization-based controlGlobal optimizationRecurrent neural networksNeural networks in process control