Economic data-enabled predictive control using machine learning

TL;DR

This paper introduces a neural network-based convex data-driven predictive control method that models nonlinear economic costs in a transformed state space, enabling explicit output constraint handling and improved control performance.

Contribution

It develops a novel neural network approach within DeePC to approximate nonlinear economic costs as quadratic functions, facilitating convex optimization and explicit constraint management.

Findings

Effective modeling of nonlinear economic costs using neural networks.

Successful application to a simulated chemical process demonstrating improved control.

Explicit handling of output constraints in the predictive control framework.

Abstract

In this paper, we propose a convex data-based economic predictive control method within the framework of data-enabled predictive control (DeePC). Specifically, we use a neural network to transform the system output into a new state space, where the nonlinear economic cost function of the underlying nonlinear system is approximated using a quadratic function expressed by the transformed output in the new state space. Both the neural network parameters and the coefficients of the quadratic function are learned from open-loop data of the system. Additionally, we reconstruct constrained output variables from the transformed output through learning an output reconstruction matrix; this way, the proposed economic DeePC can handle output constraints explicitly. The performance of the proposed method is evaluated via a case study in a simulated chemical process.