Structured Hammerstein-Wiener Model Learning for Model Predictive Control

TL;DR

This paper introduces a novel structured Hammerstein-Wiener model integrated with input convex neural networks to enhance the reliability and solvability of optimal control problems in machine learning-based systems.

Contribution

It presents a new model combining Hammerstein-Wiener structures with input convex neural networks, enabling convex optimization in control applications.

Findings

Effective modeling of engine airpath system

Convexity allows efficient online control optimization

Retains flexible modeling capabilities

Abstract

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.