%0 Conference Paper
%A Doncevic, Danimir
%A Schweidtmann, Artur M.
%A Vaupel, Yannic
%A Schäfer, Pascal
%A Caspari, Adrian
%A Mitsos, Alexander
%T Deterministic Global Nonlinear Model Predictive Control with Neural Networks Embedded
%J IFAC-PapersOnLine
%V 53
%N 2
%@ 2405-8963
%C Laxenburg
%I IFAC
%M FZJ-2021-03179
%P 5273 - 5278
%D 2020
%X Nonlinear 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.
%B 1st Virtual IFAC World Congress
%C 11 Jul 2020 - 17 Jul 2020, online (Germany)
Y2 11 Jul 2020 - 17 Jul 2020
M2 online, Germany
%F PUB:(DE-HGF)16 ; PUB:(DE-HGF)8
%9 Journal ArticleContribution to a conference proceedings
%U <Go to ISI:>//WOS:000652593000151
%R 10.1016/j.ifacol.2020.12.1207
%U https://juser.fz-juelich.de/record/894319