Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine

ObjectiveIn response to challenges such as large sampling data, extended diagnosis time, and subjective fault feature selection in traditional bearing fault diagnosis, a CS-DMKELM intelligent diagnosis model for rolling bearings is proposed based on compressed sensing(CS) and deep multi-kernel extre...

Full description

Saved in:
Bibliographic Details
Main Authors: FU Qiang, HU Dong, YANG Tongliang, LUO Guoqing, TAN Weimin
Format: Article
Language:zho
Published: Editorial Office of Journal of Mechanical Strength 2024-01-01
Series:Jixie qiangdu
Subjects:
Online Access:http://www.jxqd.net.cn/thesisDetails?columnId=78737352&Fpath=home&index=0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850092753219747840
author FU Qiang
HU Dong
YANG Tongliang
LUO Guoqing
TAN Weimin
author_facet FU Qiang
HU Dong
YANG Tongliang
LUO Guoqing
TAN Weimin
author_sort FU Qiang
collection DOAJ
description ObjectiveIn response to challenges such as large sampling data, extended diagnosis time, and subjective fault feature selection in traditional bearing fault diagnosis, a CS-DMKELM intelligent diagnosis model for rolling bearings is proposed based on compressed sensing(CS) and deep multi-kernel extreme learning machine(D-MKELM) theory.MethodsFirstly, sparse signals were obtained through threshold processing of transformed domain signals. A Gaussian random matrix was employed as the measurement matrix to compress the processed data. Subsequently, the compressed data was used as the input signal for the D-MKELM. Particle swarm optimization(PSO) algorithm was applied to optimize critical parameters, enabling intelligent fault diagnosis.ResultsResults demonstrate that the proposed method, using only a small amount of bearing diagnostic data, automatically extracts feature information of bearings from a limited number of measurement signals through the D-MKELM. The proposed method enables rapid fault diagnosis of bearings. With a diagnostic time of 0.55 s, a final recognition accuracy of 99.29% was achieved. The proposed method reduces diagnostic time and exhibits high diagnostic accuracy, providing a new approach for handling massive bearing data in fault diagnosis.
format Article
id doaj-art-2d1448cfa50c4a95b6b3064bbaaeb8ac
institution DOAJ
issn 1001-9669
language zho
publishDate 2024-01-01
publisher Editorial Office of Journal of Mechanical Strength
record_format Article
series Jixie qiangdu
spelling doaj-art-2d1448cfa50c4a95b6b3064bbaaeb8ac2025-08-20T02:42:04ZzhoEditorial Office of Journal of Mechanical StrengthJixie qiangdu1001-96692024-01-011978737352Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machineFU QiangHU DongYANG TongliangLUO GuoqingTAN WeiminObjectiveIn response to challenges such as large sampling data, extended diagnosis time, and subjective fault feature selection in traditional bearing fault diagnosis, a CS-DMKELM intelligent diagnosis model for rolling bearings is proposed based on compressed sensing(CS) and deep multi-kernel extreme learning machine(D-MKELM) theory.MethodsFirstly, sparse signals were obtained through threshold processing of transformed domain signals. A Gaussian random matrix was employed as the measurement matrix to compress the processed data. Subsequently, the compressed data was used as the input signal for the D-MKELM. Particle swarm optimization(PSO) algorithm was applied to optimize critical parameters, enabling intelligent fault diagnosis.ResultsResults demonstrate that the proposed method, using only a small amount of bearing diagnostic data, automatically extracts feature information of bearings from a limited number of measurement signals through the D-MKELM. The proposed method enables rapid fault diagnosis of bearings. With a diagnostic time of 0.55 s, a final recognition accuracy of 99.29% was achieved. The proposed method reduces diagnostic time and exhibits high diagnostic accuracy, providing a new approach for handling massive bearing data in fault diagnosis.http://www.jxqd.net.cn/thesisDetails?columnId=78737352&Fpath=home&index=0Compressed sensingBearingKernel functionExtreme learning machineFault diagnosis
spellingShingle FU Qiang
HU Dong
YANG Tongliang
LUO Guoqing
TAN Weimin
Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine
Jixie qiangdu
Compressed sensing
Bearing
Kernel function
Extreme learning machine
Fault diagnosis
title Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine
title_full Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine
title_fullStr Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine
title_full_unstemmed Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine
title_short Bearing fault diagnosis method based on improved compressed sensing and deep multi-kernel extreme learning machine
title_sort bearing fault diagnosis method based on improved compressed sensing and deep multi kernel extreme learning machine
topic Compressed sensing
Bearing
Kernel function
Extreme learning machine
Fault diagnosis
url http://www.jxqd.net.cn/thesisDetails?columnId=78737352&Fpath=home&index=0
work_keys_str_mv AT fuqiang bearingfaultdiagnosismethodbasedonimprovedcompressedsensinganddeepmultikernelextremelearningmachine
AT hudong bearingfaultdiagnosismethodbasedonimprovedcompressedsensinganddeepmultikernelextremelearningmachine
AT yangtongliang bearingfaultdiagnosismethodbasedonimprovedcompressedsensinganddeepmultikernelextremelearningmachine
AT luoguoqing bearingfaultdiagnosismethodbasedonimprovedcompressedsensinganddeepmultikernelextremelearningmachine
AT tanweimin bearingfaultdiagnosismethodbasedonimprovedcompressedsensinganddeepmultikernelextremelearningmachine