Machine‐learning‐based predictive control of nonlinear processes. Part II: Computational implementation

• Published in: AIChE journal Vol. 65; no. 11
• Main Authors: Wu, Zhe, Tran, Anh, Rincon, David, Christofides, Panagiotis D.
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.11.2019; American Institute of Chemical Engineers; Wiley Blackwell (John Wiley & Sons)
• Subjects: Chemical reactors; Computer applications; Dynamical systems; ensemble learning; Learning algorithms; Machine learning; model predictive control; Neural networks; Nonlinear control; Nonlinear dynamics; Nonlinear systems; Organic chemistry; parallel computing; Parallel processing; Predictive control; Recurrent neural networks; Regression analysis
• ISSN: 0001-1541; 1547-5905; 1547-5905
• DOI: 10.1002/aic.16734

Machine learning is receiving more attention in classical engineering fields, and in particular, recurrent neural networks (RNNs) coupled with ensemble regression tools have demonstrated the capability of modeling nonlinear dynamic processes. In Part I of this two‐article series, the Lyapunov‐based model predictive control (LMPC) method using a single RNN model and an ensemble of RNN models, respectively, was rigorously developed for a general class of nonlinear systems. In the present article, computational implementation issues of this new control method ranging from training of the RNN models, ensemble regression of the RNN models, and parallel computation for accelerating the real‐time model calculations are addressed. Furthermore, a chemical reactor example is used to demonstrate the implementation and effectiveness of these machine‐learning tools in LMPC as well as compare them with standard state‐space model identification tools.