Learning-based data-enabled moving horizon estimation with application to membrane-based biological wastewater treatment process

TL;DR

This paper introduces a data-driven moving horizon estimation method for nonlinear systems using Koopman operator theory, neural networks, and Willems fundamental lemma, demonstrated on wastewater treatment process.

Contribution

It develops a convex, data-enabled MHE approach that estimates nonlinear system states without explicit model identification, leveraging learned Koopman surrogates.

Findings

The method accurately estimates system states in simulation.

It ensures stability of the estimation error under certain conditions.

Effective application demonstrated on wastewater treatment process.

Abstract

In this paper, we propose a data-enabled moving horizon estimation (MHE) approach for a class of nonlinear systems without explicit modeling, by leveraging Koopman operator theory and Willems fundamental lemma. Specifically, the nonlinear system is lifted to a linear parameter-varying Koopman surrogate, in which the lifting functions and scheduling mappings are learned directly from data using neural networks. Willems fundamental lemma is then employed to construct a trajectory-based representation of the Koopman surrogate, which bypasses the explicit identification of the matrices of the Koopman surrogate. Based on this representation, we formulate a convex data-enabled MHE design, which provides real-time estimates of the Koopman surrogate states, from which the states of the original nonlinear system are reconstructed. Sufficient conditions are derived to ensure the stability of the estimation error. The effectiveness of the proposed method is illustrated using a simulated membrane-based biological wastewater treatment process.