Moving horizon estimation based on distributionally robust optimisation

This paper presents a novel moving horizon estimation approach based on distributionally robust optimisation to tackle the state estimation problem of non-linear systems with missing noise distribution information. The proposed method adopts a fuzzy set to mitigate the impact of uncertainties on sta...

Full description

Saved in:
Bibliographic Details
Published in:International journal of systems science 2024-05, Vol.55 (7), p.1363-1376
Main Authors: Yang, Aolei, Wang, Hao, Sun, Qing, Fei, Minrui
Format: Article
Language:English
Subjects:
Distributionally robust optimisation
Fuzzy sets
moving horizon estimation
Moving horizon state estimation
Nonlinear systems
Optimization
Robustness
State estimation
Wasserstein metric
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents a novel moving horizon estimation approach based on distributionally robust optimisation to tackle the state estimation problem of non-linear systems with missing noise distribution information. The proposed method adopts a fuzzy set to mitigate the impact of uncertainties on state estimation. Specifically, the method derives an empirical distribution within the prediction window using a priori data and constructs a fuzzy sphere set using the Wasserstein metric with the empirical distribution as the sphere centre. This enables the estimation of the state sequence under the worst probability distribution of the fuzzy set. To demonstrate the effectiveness of the proposed method, a simple simulation example is conducted to compare its performance with that of traditional moving horizon estimation. The results provide evidence of the feasibility and superiority of the proposed approach.
ISSN:0020-7721
1464-5319
DOI:10.1080/00207721.2024.2305691