Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm
In this paper, a novel composite fault diagnosis method combining adaptive feature mode decomposition (FMD) and minimum noise amplitude deconvolution (MNAD) is proposed. Firstly, chaos mapping and leader mutation selection strategy were introduced to improve the Northern Goshawk algorithm (NGO), and...
Published in: | Processes |
---|---|
Main Authors: | , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/pr10122532 |
id |
ftmdpi:oai:mdpi.com:/2227-9717/10/12/2532/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2227-9717/10/12/2532/ 2023-08-20T04:08:44+02:00 Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm Sen Yu Jie Ma agris 2022-11-29 application/pdf https://doi.org/10.3390/pr10122532 EN eng Multidisciplinary Digital Publishing Institute Advanced Digital and Other Processes https://dx.doi.org/10.3390/pr10122532 https://creativecommons.org/licenses/by/4.0/ Processes; Volume 10; Issue 12; Pages: 2532 chaotic leadership Northern Goshawk optimization feature mode decomposition minimum noise amplitude deconvolution feature extraction sparse pulse and cyclicstationarity composite fault Text 2022 ftmdpi https://doi.org/10.3390/pr10122532 2023-08-01T07:33:29Z In this paper, a novel composite fault diagnosis method combining adaptive feature mode decomposition (FMD) and minimum noise amplitude deconvolution (MNAD) is proposed. Firstly, chaos mapping and leader mutation selection strategy were introduced to improve the Northern Goshawk algorithm (NGO), and a chaotic leadership Northern Goshawk optimization (CLNGO) algorithm was proposed. The advantages of the CLNGO algorithm in convergence accuracy and speed were verified by 12 benchmark functions. Then, a new index called sparse pulse and cyclicstationarity (SPC) is proposed to evaluate signal sparsity. Finally, SPC is used as the fitness function of CLNGO to optimize FMD and MNAD. The optimal decomposition mode n and filter length of FMD, and filter length L and noise ratio ρ of MNAD are selected. The CLNGO-FMD is used to decompose signal into different modes. The signal is reconstructed based on the kurtosis criterion and the CLNGO-MNAD method is used to reduce the noise of the reconstructed signal twice. The experimental results show that the proposed method can achieve the enhancement of weak features and the removal of noise to extract the fault feature frequency adaptively. Compared with EMD, VMD, MOMEDA, MCKD and other methods, the proposed method has better performance in fault feature frequency extraction, and it is effective for the diagnosis of single faults and composite faults. Text Northern Goshawk MDPI Open Access Publishing Processes 10 12 2532 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
chaotic leadership Northern Goshawk optimization feature mode decomposition minimum noise amplitude deconvolution feature extraction sparse pulse and cyclicstationarity composite fault |
spellingShingle |
chaotic leadership Northern Goshawk optimization feature mode decomposition minimum noise amplitude deconvolution feature extraction sparse pulse and cyclicstationarity composite fault Sen Yu Jie Ma Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm |
topic_facet |
chaotic leadership Northern Goshawk optimization feature mode decomposition minimum noise amplitude deconvolution feature extraction sparse pulse and cyclicstationarity composite fault |
description |
In this paper, a novel composite fault diagnosis method combining adaptive feature mode decomposition (FMD) and minimum noise amplitude deconvolution (MNAD) is proposed. Firstly, chaos mapping and leader mutation selection strategy were introduced to improve the Northern Goshawk algorithm (NGO), and a chaotic leadership Northern Goshawk optimization (CLNGO) algorithm was proposed. The advantages of the CLNGO algorithm in convergence accuracy and speed were verified by 12 benchmark functions. Then, a new index called sparse pulse and cyclicstationarity (SPC) is proposed to evaluate signal sparsity. Finally, SPC is used as the fitness function of CLNGO to optimize FMD and MNAD. The optimal decomposition mode n and filter length of FMD, and filter length L and noise ratio ρ of MNAD are selected. The CLNGO-FMD is used to decompose signal into different modes. The signal is reconstructed based on the kurtosis criterion and the CLNGO-MNAD method is used to reduce the noise of the reconstructed signal twice. The experimental results show that the proposed method can achieve the enhancement of weak features and the removal of noise to extract the fault feature frequency adaptively. Compared with EMD, VMD, MOMEDA, MCKD and other methods, the proposed method has better performance in fault feature frequency extraction, and it is effective for the diagnosis of single faults and composite faults. |
format |
Text |
author |
Sen Yu Jie Ma |
author_facet |
Sen Yu Jie Ma |
author_sort |
Sen Yu |
title |
Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm |
title_short |
Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm |
title_full |
Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm |
title_fullStr |
Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm |
title_full_unstemmed |
Adaptive Composite Fault Diagnosis of Rolling Bearings Based on the CLNGO Algorithm |
title_sort |
adaptive composite fault diagnosis of rolling bearings based on the clngo algorithm |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2022 |
url |
https://doi.org/10.3390/pr10122532 |
op_coverage |
agris |
genre |
Northern Goshawk |
genre_facet |
Northern Goshawk |
op_source |
Processes; Volume 10; Issue 12; Pages: 2532 |
op_relation |
Advanced Digital and Other Processes https://dx.doi.org/10.3390/pr10122532 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/pr10122532 |
container_title |
Processes |
container_volume |
10 |
container_issue |
12 |
container_start_page |
2532 |
_version_ |
1774721198900379648 |