Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network
Abstract Existing bearing fault diagnosis methods have some disadvantages, one being that most methods cannot completely consider all specific fault attributes. Another disadvantage is that the qualitative diagnosis method considers different fault types as a whole, and qualitative diagnosis of a si...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-12-01
|
| Series: | Cognitive Computation and Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/ccs2.12016 |
| _version_ | 1818515656535965696 |
|---|---|
| author | Shixin Zhang Qin Lv Shenlin Zhang Jianhua Shan |
| author_facet | Shixin Zhang Qin Lv Shenlin Zhang Jianhua Shan |
| author_sort | Shixin Zhang |
| collection | DOAJ |
| description | Abstract Existing bearing fault diagnosis methods have some disadvantages, one being that most methods cannot completely consider all specific fault attributes. Another disadvantage is that the qualitative diagnosis method considers different fault types as a whole, and qualitative diagnosis of a single fault attribute is complicated. A convolutional neural network is proposed for application in the multi‐attribute quantitative bearing fault diagnosis. Multiple combinations of convolutional layers are adopted to directly extract features from one‐dimensional vibration signals. In addition, a softmax layer is designed to realise the simultaneous recognition of different fault attributes. The advantage of this approach is that it can realise diagnostic results for any combination of fault attributes and corresponding types, which overcomes the disadvantage of single attribute recognition in the traditional method. The method is simple but has strong generalisation ability with average diagnostic accuracy of more than 95%. According to bearing data from Case Western Reserve University and laboratory experiments by the authors, the results verify that the method can accurately and quantitatively diagnose bearing faults. |
| first_indexed | 2024-12-11T00:31:38Z |
| format | Article |
| id | doaj.art-a55dde9b749f4fa2b20e69f53c298dbf |
| institution | Directory Open Access Journal |
| issn | 2517-7567 |
| language | English |
| last_indexed | 2024-12-11T00:31:38Z |
| publishDate | 2021-12-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cognitive Computation and Systems |
| spelling | doaj.art-a55dde9b749f4fa2b20e69f53c298dbf2022-12-22T01:27:20ZengWileyCognitive Computation and Systems2517-75672021-12-013428729610.1049/ccs2.12016Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural networkShixin Zhang0Qin Lv1Shenlin Zhang2Jianhua Shan3Anhui Province Key Laboratory of Special Heavy Load Robot College of Mechanical Engineering Anhui University of Technology Ma'anshan Anhui ChinaAnhui Province Key Laboratory of Special Heavy Load Robot College of Mechanical Engineering Anhui University of Technology Ma'anshan Anhui ChinaAnhui Province Key Laboratory of Special Heavy Load Robot College of Mechanical Engineering Anhui University of Technology Ma'anshan Anhui ChinaAnhui Province Key Laboratory of Special Heavy Load Robot College of Mechanical Engineering Anhui University of Technology Ma'anshan Anhui ChinaAbstract Existing bearing fault diagnosis methods have some disadvantages, one being that most methods cannot completely consider all specific fault attributes. Another disadvantage is that the qualitative diagnosis method considers different fault types as a whole, and qualitative diagnosis of a single fault attribute is complicated. A convolutional neural network is proposed for application in the multi‐attribute quantitative bearing fault diagnosis. Multiple combinations of convolutional layers are adopted to directly extract features from one‐dimensional vibration signals. In addition, a softmax layer is designed to realise the simultaneous recognition of different fault attributes. The advantage of this approach is that it can realise diagnostic results for any combination of fault attributes and corresponding types, which overcomes the disadvantage of single attribute recognition in the traditional method. The method is simple but has strong generalisation ability with average diagnostic accuracy of more than 95%. According to bearing data from Case Western Reserve University and laboratory experiments by the authors, the results verify that the method can accurately and quantitatively diagnose bearing faults.https://doi.org/10.1049/ccs2.12016machine bearingsfeature extractionfault diagnosisvibrationsvibrational signal processingconvolutional neural nets |
| spellingShingle | Shixin Zhang Qin Lv Shenlin Zhang Jianhua Shan Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network Cognitive Computation and Systems machine bearings feature extraction fault diagnosis vibrations vibrational signal processing convolutional neural nets |
| title | Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network |
| title_full | Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network |
| title_fullStr | Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network |
| title_full_unstemmed | Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network |
| title_short | Multi‐attribute quantitative bearing fault diagnosis based on convolutional neural network |
| title_sort | multi attribute quantitative bearing fault diagnosis based on convolutional neural network |
| topic | machine bearings feature extraction fault diagnosis vibrations vibrational signal processing convolutional neural nets |
| url | https://doi.org/10.1049/ccs2.12016 |
| work_keys_str_mv | AT shixinzhang multiattributequantitativebearingfaultdiagnosisbasedonconvolutionalneuralnetwork AT qinlv multiattributequantitativebearingfaultdiagnosisbasedonconvolutionalneuralnetwork AT shenlinzhang multiattributequantitativebearingfaultdiagnosisbasedonconvolutionalneuralnetwork AT jianhuashan multiattributequantitativebearingfaultdiagnosisbasedonconvolutionalneuralnetwork |