A tutorial review of machine learning-based model predictive control methods

Wu, Zhe [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore] (ORCID:000000022923149X); Christofides, Panagiotis D. [Department of Chemical and Biomolecular Engineering, Department of Electrical and Computer Engineering , University of California , Los Angeles , CA , USA]; Wu, Wanlu [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore]; Wang, Yujia [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore]; Abdullah, Fahim [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA]; Alnajdi, Aisha [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA]; Kadakia, Yash [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA]

doi:10.1515/revce-2024-0055

DOE OSTI · 2480589

A tutorial review of machine learning-based model predictive control methods

Wu, Zhe [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore] (ORCID:000000022923149X)·Christofides, Panagiotis D. [Department of Chemical and Biomolecular Engineering, Department of Electrical and Computer Engineering , University of California , Los Angeles , CA , USA]·Wu, Wanlu [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore]·Wang, Yujia [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore]·Abdullah, Fahim [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA]·Alnajdi, Aisha [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA]·Kadakia, Yash [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA]

View original source ↗Export metadata ↓

Abstract

Abstract This tutorial review provides a comprehensive overview of machine learning (ML)-based model predictive control (MPC) methods, covering both theoretical and practical aspects. It provides a theoretical analysis of closed-loop stability based on the generalization error of ML models and addresses practical challenges such as data scarcity, data quality, the curse of dimensionality, model uncertainty, computational efficiency, and safety from both modeling and control perspectives. The application of these methods is demonstrated using a nonlinear chemical process example, with open-source code available on GitHub. The paper concludes with a discussion on future research directions in ML-based MPC.

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Wu, Zhe [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore] (ORCID:000000022923149X), Christofides, Panagiotis D. [Department of Chemical and Biomolecular Engineering, Department of Electrical and Computer Engineering , University of California , Los Angeles , CA , USA], Wu, Wanlu [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore], Wang, Yujia [Department of Chemical and Biomolecular Engineering , 37580 National University of Singapore , Singapore , Singapore], Abdullah, Fahim [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA], Alnajdi, Aisha [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA], Kadakia, Yash [Department of Chemical and Biomolecular Engineering , University of California , Los Angeles , CA , USA]. 2024-12-10. A tutorial review of machine learning-based model predictive control methods. https://doi.org/10.1515/revce-2024-0055

Cite the original work for its findings. Save a collection to share your selection of sources.