Learning-based data-enabled moving horizon estimation with application to membrane-based biological wastewater treatment process
For control engineers dealing with complex nonlinear systems where first-principles models are unavailable, this work offers a data-driven estimation approach that avoids explicit system identification.
This paper proposes a data-enabled moving horizon estimation (MHE) method for nonlinear systems without explicit models, using Koopman operator theory and Willems fundamental lemma. The method is validated on a simulated membrane-based biological wastewater treatment process, demonstrating effective state estimation.
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.