Deterministic Global Nonlinear Model Predictive Control with Neural Networks Embedded. Issue 2 (2020)

• Record Type: Journal Article
• Authors: Doncevic, Danimir T.; Schweidtmann, Artur M.; Vaupel, Yannic; Schäfer, Pascal; Caspari, Adrian; Mitsos, Alexander
• Is Part Of: IFAC-PapersOnLine. Volume 53:Issue 2(2020)
• Page Start: 5273
• Page End: 5278
• Publication Date: 2020
• Subjects: Nonlinear process control -- Model predictive -- optimization-based control -- Global optimization -- Recurrent neural networks -- Neural networks in process control; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2020.12.1207
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: 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.