In this paper, implementation of deep neural networks applied in process control is presented. In our approach, training of the neural network is based on model predictive control, which is popular for its ability to be tuned by the weighting matrices and for it respecting the system constraints. A neural network that can approximate the MPC behavior by mimicking the control input trajectory while the constraints on states and control input remain unimpaired by the weighting matrices is introduced. This approach is demonstrated in a simulation case study involving a continuous stirred tank reactor where a multi-component chemical reaction takes place.
If the inline PDF is not rendering correctly, you can download the PDF file here.
Bakará č P Kvasnica M (2018) Fast nonlinear model predictive control of a chemical reactor: a random shooting approach. Acta Chimica Slovaca 11(2): 175—181.
Bakošová M Mészáros A Klemeš J Oravec J (2012) Robust and optimal control approach for exothermic reactor stabilization. Theoretical Foundations of Chemical Engineering (46): 740—746.
Bakošová M Oravec J Mészáros A Vasičkaninová A (2017) Neural-Network-Based and Robust Model-Based Predictive Control of a Tubular Heat Exchanger. Chemical Engineering Transactions (61): 301—306.
Bakošová M Oravec J (2014) Robust mpc of an unstable chemical reactor using the nominal system optimization. Acta Chimica Slovaca 7(2): 87—93.
Bemporad A Morari M Dua V Pistikopoulos EN (2002) The explicit linear quadratic regulator for constrained systems. Automatica 38(1): 3—20.
Borrelli F Bemporad A Morari M (2017) Predictive Control for Linear and Hybrid Systems. Cambridge University Press.
Fissore D (2008) Robust control in presence of parametric uncertainties: observer-based feedback controller design. Chemical Engineering Science 63(7): 1890—1900.
Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Networks 4(2): 251—257.
Karg B Lucia S (2018) Efficient representation and approximation of model predictive control laws via deep learning.
Klaučo M Kvasnica M (2019) MPC-Based Reference Governors. Springer 1st edition.
Lofberg J (2004) YALMIP: A Toolbox for Modeling and Optimization in MATLAB. In Proc. of the CACSD Conference Taipei Taiwan. Available from http://users.isy.liu.se/johanl/yalmip/.
Lohr Y Klaučo M Kalúz M Monnigmann M (2019) Mimicking predictive control with neural networks in domestic heating systems. In Fikar M and Kvasnica M editors Proceedings of the 22nd International Conference on Process Control pages 19—24 Šrbské Pleso Slovakia. Slovak University of Technology in Bratislava Slovak Chemical Library.
Maciejowski JM (2002) Predictive Control with Constraints. PEARSON Prentice-Hall.
Mayne DQ Rawlings JB Rao CV Scokaert POM (2000) Constrained model predictive control: Stability and optimality. Automatica 36(6): 789—814.
Pourdehi S Karimaghaee P (2018) Stability analysis and design of model predictive reset control for nonlinear time-delay systems with application to a two-stage chemical reactor system. Journal of Process Control 71: 103—115.
Prasath G Recke B Chidambaram M Jørgensen J (2010) Application of Soft Constrained MPC to a Cement Mill Circuit. In Proceedings of the 9th International Symposium on Dynamics and Control of Process Systems Belgium Leuven.
Singh A de Villiers P Rambalee P Gous G de Klerk J Humphries G (2010) A holistic approach to the application of model predictive control to batch reactors. IFAC Proceedings Volumes 43(9): 127—132. 13th IFAC Symposium on Automation in Mining Mineral and Metal Processing.
Smets IY Claes JE November EJ Bastin GP Impe JFV (2004) Optimal adaptive control of (bio)chemical reactors: past present and future. Journal of Process Control 14(7): 795—805. Dynamics Monitoring Control and Optimization of Biological Systems.