Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVM
In allusion to solve the issue of fault diagnosis for bearing and other rotatory machinery, a technique based on fined-grained multi-scale Kolmogorov entropy and whale optimized multi-class support vector machine (abbreviated as FGMKE-WOA-MSVM) is proposed. Firstly, vibration signals are decomposed...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024040179 |
| _version_ | 1797224160566444032 |
|---|---|
| author | Bing wang Huimin li Xiong Hu Cancan Wang Dejian Sun |
| author_facet | Bing wang Huimin li Xiong Hu Cancan Wang Dejian Sun |
| author_sort | Bing wang |
| collection | DOAJ |
| description | In allusion to solve the issue of fault diagnosis for bearing and other rotatory machinery, a technique based on fined-grained multi-scale Kolmogorov entropy and whale optimized multi-class support vector machine (abbreviated as FGMKE-WOA-MSVM) is proposed. Firstly, vibration signals are decomposed by fine-grained multi-scale decomposition, and the Kolmogorov entropy of the sub-signals at different analysis scales is calculated as the multi-dimension feature vector, which quantitatively characterize the complexity of the signal at multi-scales. Aiming at the problem of sensitive parameters selection for multi-class support vector machine model (abbreviated as MSVM), the whale optimization algorithm (abbreviated as WOA) is introduced to optimize the penalty factor and kernel function parameter, and constructing optimal WOA-MSVM model. Finally, an instance analysis is carried out with Jiangnan University bearing datasets to verify the effectiveness and superiority of this technique. The results show that compared with different feature vectors and models such as K nearest neighbors (abbreviated as KNN) and Decision Tree (abbreviated as RF), the proposed technique is superior with fast computation speed and high diagnostic efficiency. |
| first_indexed | 2024-04-24T13:48:42Z |
| format | Article |
| id | doaj.art-d4115bce81d94091aa7f6e2242367eba |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-04-24T13:48:42Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-d4115bce81d94091aa7f6e2242367eba2024-04-04T05:06:33ZengElsevierHeliyon2405-84402024-03-01106e27986Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVMBing wang0Huimin li1Xiong Hu2Cancan Wang3Dejian Sun4Shanghai Maritime University, Shanghai, 201306, ChinaShanghai Maritime University, Shanghai, 201306, ChinaShanghai Maritime University, Shanghai, 201306, China; Corresponding author.Shanghai Maritime University, Shanghai, 201306, ChinaShanghai Maritime University, Shanghai, 201306, ChinaIn allusion to solve the issue of fault diagnosis for bearing and other rotatory machinery, a technique based on fined-grained multi-scale Kolmogorov entropy and whale optimized multi-class support vector machine (abbreviated as FGMKE-WOA-MSVM) is proposed. Firstly, vibration signals are decomposed by fine-grained multi-scale decomposition, and the Kolmogorov entropy of the sub-signals at different analysis scales is calculated as the multi-dimension feature vector, which quantitatively characterize the complexity of the signal at multi-scales. Aiming at the problem of sensitive parameters selection for multi-class support vector machine model (abbreviated as MSVM), the whale optimization algorithm (abbreviated as WOA) is introduced to optimize the penalty factor and kernel function parameter, and constructing optimal WOA-MSVM model. Finally, an instance analysis is carried out with Jiangnan University bearing datasets to verify the effectiveness and superiority of this technique. The results show that compared with different feature vectors and models such as K nearest neighbors (abbreviated as KNN) and Decision Tree (abbreviated as RF), the proposed technique is superior with fast computation speed and high diagnostic efficiency.http://www.sciencedirect.com/science/article/pii/S2405844024040179Rolling bearingFault diagnosisSVMKolmogorov entropy |
| spellingShingle | Bing wang Huimin li Xiong Hu Cancan Wang Dejian Sun Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVM Heliyon Rolling bearing Fault diagnosis SVM Kolmogorov entropy |
| title | Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVM |
| title_full | Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVM |
| title_fullStr | Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVM |
| title_full_unstemmed | Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVM |
| title_short | Rolling bearing fault diagnosis based on fine-grained multi-scale Kolmogorov entropy and WOA-MSVM |
| title_sort | rolling bearing fault diagnosis based on fine grained multi scale kolmogorov entropy and woa msvm |
| topic | Rolling bearing Fault diagnosis SVM Kolmogorov entropy |
| url | http://www.sciencedirect.com/science/article/pii/S2405844024040179 |
| work_keys_str_mv | AT bingwang rollingbearingfaultdiagnosisbasedonfinegrainedmultiscalekolmogoroventropyandwoamsvm AT huiminli rollingbearingfaultdiagnosisbasedonfinegrainedmultiscalekolmogoroventropyandwoamsvm AT xionghu rollingbearingfaultdiagnosisbasedonfinegrainedmultiscalekolmogoroventropyandwoamsvm AT cancanwang rollingbearingfaultdiagnosisbasedonfinegrainedmultiscalekolmogoroventropyandwoamsvm AT dejiansun rollingbearingfaultdiagnosisbasedonfinegrainedmultiscalekolmogoroventropyandwoamsvm |