Enhanced Distributed Outlier-Resilient Fusion Estimation With Novel Dimensionality Reduction Under IT-2 T-S Fuzzy System

• Published in: IEEE transactions on fuzzy systems Vol. 32; no. 11; pp. 6044 - 6055
• Main Authors: Yang, Yunyi, Wen, Guoguang, Wang, Yidi, Peng, Zhaoxia, Xiong, Kai
• Format: Journal Article
• Language: English
• Published: IEEE 01.11.2024
• Subjects: Anomaly detection; Dimensionality reduction; Dimensionality reduction (DR); distributed fusion estimation; Estimation; Fuzzy systems; interval type-2 (IT-2) Takagi–Sugeno (T–S) fuzzy system; Noise measurement; outlier detection; Protocols; Robot sensing systems; Round–Robin protocol (RRP); Takagi-Sugeno model; zonotopic set-membership filter
• ISSN: 1063-6706; 1941-0034
• DOI: 10.1109/TFUZZ.2024.3436941

This article addresses an enhanced distributed outlier-resilient fusion estimation problem using an interval type-2 (IT-2) Takagi-Sugeno (T-S) fuzzy model, integrating outlier detection schemes and dimensionality reduction (DR) strategies. First, the IT-2 T-S fuzzy model is employed to handle system uncertainty and nonlinearity effectively. Then, the outlier-resilient local estimator is proposed using the zonotope-based set-membership filters (ZSMFs), where the outlier detection scheme only relies on the intersection between the predicted set and the measurement set. Furthermore, the compressed local estimate (LE) are designed when there are bandwidth constraints in sensor networks, and a novel DR strategy is proposed to design this compressed LE, where the compression matrix is determined by the Round-Robin protocol (RRP). After this, based on the compressed LEs, a distributed resilient zonotopic fusion estimator (DRZFE) is derived by the matrix-weighted fusion method. Note that the computational load of the DRZFE is reduced effectively due to the zonotope order reduction and the RRP-based DR independent of the online optimization. Moreover, the compensation of outliers and the compensating state estimate of RRP-based DR may improve the resilience of the algorithm and reduce information loss. Finally, two numerical examples are provided to validate the advantages and effectiveness of the proposed methods, and we use root-mean-square-error as the indicator to assess the estimation accuracy.