Advanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selection

Abstract In this exploration, we introduce a novel intelligent hybrid methodology for multiclass bearing fault detection under varying rotational speeds. Unlike previous studies, our approach combines empirical mode decomposition (EMD), wavelet packet decomposition (WPD), and a comprehensive attribu...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongxu Chai, Xiaoshi Ma, Feng Zhu, Yandong Hu
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:Journal of Engineering and Applied Science
Subjects:
Online Access:https://doi.org/10.1186/s44147-025-00683-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849332784439492608
author Hongxu Chai
Xiaoshi Ma
Feng Zhu
Yandong Hu
author_facet Hongxu Chai
Xiaoshi Ma
Feng Zhu
Yandong Hu
author_sort Hongxu Chai
collection DOAJ
description Abstract In this exploration, we introduce a novel intelligent hybrid methodology for multiclass bearing fault detection under varying rotational speeds. Unlike previous studies, our approach combines empirical mode decomposition (EMD), wavelet packet decomposition (WPD), and a comprehensive attribute retrieval strategy from both time and frequency domains. Critically, we present an enhanced distance compensation evaluation technique (CDET) for feature selection, in which the threshold parameter is automatically optimized using particle swarm optimization (PSO) rather than being set arbitrarily. Furthermore, the parameters of both CDET and support vector machine (SVM) classifiers are jointly optimized by PSO, resulting in enhanced classification accuracy and computational efficiency. Extensive experiments on benchmark databases demonstrate that the recommended tactic surpasses conventional tactics regarding fault detection accuracy, stability, and feature compactness. From the original signals, 20 statistical features in the time domain and 6 in the frequency domain were extracted, along with 4 decomposition levels from WPD and the first 6 components from EMD. The outcomes demonstrate that specific features can effectively differentiate various bearing conditions at different speeds, highlighting the efficacy of the recommended approach compared to other fault detection methods.
format Article
id doaj-art-7ca86e1755be407cab111aa29bbfe754
institution Kabale University
issn 1110-1903
2536-9512
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series Journal of Engineering and Applied Science
spelling doaj-art-7ca86e1755be407cab111aa29bbfe7542025-08-20T03:46:07ZengSpringerOpenJournal of Engineering and Applied Science1110-19032536-95122025-07-0172112110.1186/s44147-025-00683-zAdvanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selectionHongxu Chai0Xiaoshi Ma1Feng Zhu2Yandong Hu3Gansu Province Special Equipment Inspection and Testing InstituteGansu Province Special Equipment Inspection and Testing InstituteGansu Province Special Equipment Inspection and Testing InstituteTechnology and Engineering Center for Space Utilization, Chinese Academy of SciencesAbstract In this exploration, we introduce a novel intelligent hybrid methodology for multiclass bearing fault detection under varying rotational speeds. Unlike previous studies, our approach combines empirical mode decomposition (EMD), wavelet packet decomposition (WPD), and a comprehensive attribute retrieval strategy from both time and frequency domains. Critically, we present an enhanced distance compensation evaluation technique (CDET) for feature selection, in which the threshold parameter is automatically optimized using particle swarm optimization (PSO) rather than being set arbitrarily. Furthermore, the parameters of both CDET and support vector machine (SVM) classifiers are jointly optimized by PSO, resulting in enhanced classification accuracy and computational efficiency. Extensive experiments on benchmark databases demonstrate that the recommended tactic surpasses conventional tactics regarding fault detection accuracy, stability, and feature compactness. From the original signals, 20 statistical features in the time domain and 6 in the frequency domain were extracted, along with 4 decomposition levels from WPD and the first 6 components from EMD. The outcomes demonstrate that specific features can effectively differentiate various bearing conditions at different speeds, highlighting the efficacy of the recommended approach compared to other fault detection methods.https://doi.org/10.1186/s44147-025-00683-zVibration analysisFeature selectionSVMPSODPDEMD
spellingShingle Hongxu Chai
Xiaoshi Ma
Feng Zhu
Yandong Hu
Advanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selection
Journal of Engineering and Applied Science
Vibration analysis
Feature selection
SVM
PSO
DPD
EMD
title Advanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selection
title_full Advanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selection
title_fullStr Advanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selection
title_full_unstemmed Advanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selection
title_short Advanced bearing fault detection at varying rotational speeds using PSO-optimized SVM and CDET feature selection
title_sort advanced bearing fault detection at varying rotational speeds using pso optimized svm and cdet feature selection
topic Vibration analysis
Feature selection
SVM
PSO
DPD
EMD
url https://doi.org/10.1186/s44147-025-00683-z
work_keys_str_mv AT hongxuchai advancedbearingfaultdetectionatvaryingrotationalspeedsusingpsooptimizedsvmandcdetfeatureselection
AT xiaoshima advancedbearingfaultdetectionatvaryingrotationalspeedsusingpsooptimizedsvmandcdetfeatureselection
AT fengzhu advancedbearingfaultdetectionatvaryingrotationalspeedsusingpsooptimizedsvmandcdetfeatureselection
AT yandonghu advancedbearingfaultdetectionatvaryingrotationalspeedsusingpsooptimizedsvmandcdetfeatureselection