Intelligent Fault Diagnosis of Machinery Using BPSO-Optimized Ensemble Filters and an Improved Sparse Representation Classifier

Tang, Yuyao; Yang, Yapeng; Zhao, Xiaoyu; Lv, Qi; He, Jiapeng; Zhang, Zhiqiang

doi:10.3390/s25165175

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Intelligent Fault Diagnosis of Machinery Using BPSO-Optimized Ensemble Filters and an Improved Sparse Representation Classifier

by

Yuyao Tang

^1,*,

Yapeng Yang

¹,

Xiaoyu Zhao

¹,

Qi Lv

¹,

Jiapeng He

¹ and

Zhiqiang Zhang

²

¹

China Institute for Radiation Protection, Taiyuan 030006, China

²

School of Electrical Engineering and Automation, Hefei University of Technology, Hefei 230009, China

^*

Author to whom correspondence should be addressed.

Sensors 2025, 25(16), 5175; https://doi.org/10.3390/s25165175

Submission received: 12 July 2025 / Revised: 10 August 2025 / Accepted: 12 August 2025 / Published: 20 August 2025

(This article belongs to the Section Fault Diagnosis & Sensors)

Download Versions Notes

Abstract

In this paper, we propose an ensemble approach for the intelligent fault diagnosis of machinery, which consists of six feature selection methods and classifiers. In the proposed approach, six filters, based on distinct metrics, are utilized. Each filter is combined with an improved sparse representation classifier (ISRC) to form a base model, in which the ISRC is an improved version of a sparse representation classifier and has the advantages of high classification accuracy and being less time consuming than the unimproved version. For each base model, the filter selects a feature subset that is used to train and test the ISRC, where the two hyper-parameters involved in the filter and ISRC are optimized by the binary particle swarm optimization algorithm. The outputs of six base models are aggregated through the cumulative reconstruction residual (CRR), where the CRR is devised to replace the commonly used voting strategy. The effectiveness of the proposed method is verified on six mechanical datasets involving information about bearings and gears. In particular, we conduct a detailed comparison between CRR and voting and carry out an intensive exploration into the question of why CRR is superior to voting in the ensemble model.

Keywords: intelligent fault diagnosis; feature selection; sparse representation classifier; binary particle swarm optimization; cumulative reconstruction residual

Share and Cite

MDPI and ACS Style

Tang, Y.; Yang, Y.; Zhao, X.; Lv, Q.; He, J.; Zhang, Z. Intelligent Fault Diagnosis of Machinery Using BPSO-Optimized Ensemble Filters and an Improved Sparse Representation Classifier. Sensors 2025, 25, 5175. https://doi.org/10.3390/s25165175

AMA Style

Tang Y, Yang Y, Zhao X, Lv Q, He J, Zhang Z. Intelligent Fault Diagnosis of Machinery Using BPSO-Optimized Ensemble Filters and an Improved Sparse Representation Classifier. Sensors. 2025; 25(16):5175. https://doi.org/10.3390/s25165175

Chicago/Turabian Style

Tang, Yuyao, Yapeng Yang, Xiaoyu Zhao, Qi Lv, Jiapeng He, and Zhiqiang Zhang. 2025. "Intelligent Fault Diagnosis of Machinery Using BPSO-Optimized Ensemble Filters and an Improved Sparse Representation Classifier" Sensors 25, no. 16: 5175. https://doi.org/10.3390/s25165175

APA Style

Tang, Y., Yang, Y., Zhao, X., Lv, Q., He, J., & Zhang, Z. (2025). Intelligent Fault Diagnosis of Machinery Using BPSO-Optimized Ensemble Filters and an Improved Sparse Representation Classifier. Sensors, 25(16), 5175. https://doi.org/10.3390/s25165175

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Intelligent Fault Diagnosis of Machinery Using BPSO-Optimized Ensemble Filters and an Improved Sparse Representation Classifier

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI