Fast Explicit Machine Learning-Based Model Predictive Control of Nonlinear Processes Using Input Convex Neural Networks
Industrial & Engineering Chemistry Research · 09.10.2024 · 63 (40) · 17279-17293
DOI: 10.1021/acs.iecr.4c02257 ↗Kurz gefasst
Fachartikel in der Zeitschrift Industrial & Engineering Chemistry Research, online erschienen am 26.09.2024. Verfasst von Wenlong Wang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: Ministry of Education - Singapore, National Research Foundation Singapore.
Abstract (Originalsprache)
Explicit machine learning-based model predictive control (explicit ML-MPC) has been developed to reduce the real-time computational demands of traditional ML-MPC. However, the evaluation of candidate control actions in explicit ML-MPC can be time-consuming due to the non-convex nature of machine learning models. To address this issue, we leverage Input Convex Neural Networks (ICNN) to develop explicit ICNN-MPC, which is formulated as a convex optimization problem. Specifically, ICNN is employed to capture nonlinear system dynamics and incorporated into MPC, with sufficient conditions provided to ensure the convexity of ICNN-based MPC. We then formulate mixed-integer quadratic programming (MIQP) problems based on the candidate control actions derived from the solutions of multi-parametric quadratic programming (mpQP) problems within the explicit ML-MPC framework. Optimal control actions are obtained by solving real-time convex MIQP problems. The effectiveness of the proposed method is demonstrated through two case studies, including a chemical reactor example, and a chemical process network simulated by Aspen Plus Dynamics, where explicit ML-MPC written in Python is integrated with Aspen dynamic simulation through a programmable interface.
Förderung
- Ministry of Education - Singapore
- National Research Foundation Singapore
Zitieren
APA
Wang, W., Zhang, H., Wang, Y., Tian, Y., & Wu, Z. (2024). Fast Explicit Machine Learning-Based Model Predictive Control of Nonlinear Processes Using Input Convex Neural Networks. Industrial & Engineering Chemistry Research, 63(40), 17279-17293. https://doi.org/10.1021/acs.iecr.4c02257
Vancouver
Wang W, Zhang H, Wang Y, Tian Y, Wu Z. Fast Explicit Machine Learning-Based Model Predictive Control of Nonlinear Processes Using Input Convex Neural Networks. Industrial & Engineering Chemistry Research. 2024;63(40):17279-17293. doi:10.1021/acs.iecr.4c02257
BibTeX
@article{Wang2024,
author = {Wang, Wenlong and Zhang, Haohao and Wang, Yujia and Tian, Yuhe and Wu, Zhe},
title = {Fast Explicit Machine Learning-Based Model Predictive Control of Nonlinear Processes Using Input Convex Neural Networks},
journal = {Industrial & Engineering Chemistry Research},
year = {2024},
volume = {63},
number = {40},
pages = {17279--17293},
doi = {10.1021/acs.iecr.4c02257}
}
EUVIMED