Structured Hammerstein-Wiener Model Learning for Model Predictive Control
This work addresses reliability issues in optimal control for engineering systems like engines, though it appears incremental by integrating existing methods.
The paper tackled the challenge of non-convex optimal control problems in machine learning-based models by proposing a Hammerstein-Wiener model combined with input convex neural networks, resulting in effectively solvable control problems while maintaining modeling flexibility, as demonstrated in an engine airpath system application.
This paper aims to improve the reliability of optimal control using models constructed by machine learning methods. Optimal control problems based on such models are generally non-convex and difficult to solve online. In this paper, we propose a model that combines the Hammerstein-Wiener model with input convex neural networks, which have recently been proposed in the field of machine learning. An important feature of the proposed model is that resulting optimal control problems are effectively solvable exploiting their convexity and partial linearity while retaining flexible modeling ability. The practical usefulness of the method is examined through its application to the modeling and control of an engine airpath system.