Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.06580 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910564689641472 |
|---|---|
| author | Wang, Wenlong Zhang, Haohao Wang, Yujia Tian, Yuhe Wu, Zhe |
| author_facet | Wang, Wenlong Zhang, Haohao Wang, Yujia Tian, Yuhe Wu, Zhe |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06580 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fast Explicit Machine Learning-Based Model Predictive Control of Nonlinear Processes Using Input Convex Neural Networks Wang, Wenlong Zhang, Haohao Wang, Yujia Tian, Yuhe Wu, Zhe Optimization and Control 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. |
| title | Fast Explicit Machine Learning-Based Model Predictive Control of Nonlinear Processes Using Input Convex Neural Networks |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2408.06580 |