Neural Moving Horizon Estimation: A Systematic Literature Review

TL;DR

This paper provides a comprehensive review of neural moving horizon estimation (NMHE), discussing its principles, architectures, neural network designs, real-time implementation, limitations, and future research directions to advance state estimation in complex systems.

Contribution

It systematically consolidates existing knowledge on NMHE, offering design guidelines, analyzing architectures, and outlining future research avenues.

Findings

Explains fundamental principles of NMHE

Analyzes different NMHE architectures and their advantages

Provides insights into neural network designs for NMHE

Abstract

The neural moving horizon estimator (NMHE) is a relatively new and powerful state estimator that combines the strengths of neural networks (NNs) and model-based state estimation techniques. Various approaches exist for constructing NMHEs, each with its unique advantages and limitations. However, a comprehensive literature review that consolidates existing knowledge, outlines design guidelines and highlights future research directions is currently lacking. This systematic literature review synthesizes the existing knowledge on NMHE, addressing the above knowledge gap. The paper (1) explains the fundamental principles of NMHE, (2) explores different NMHE architectures, discussing the pros and cons of each, (3) investigates the NN architectures used in NMHE, providing insights for future designs, (4) examines the real-time implementability of current approaches, offering recommendations for practical applications, and (5) discusses the current limitations of NMHE approaches and outlines directions for future research. These insights can significantly improve the design and application of NMHE, which is critical for enhancing state estimation in complex systems.