Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding
In many practical fault diagnosis applications, the acquisition of fault data labels requires substantial manpower and resources, which are sometimes impossible to achieve. To address this, an unsupervised bearing fault diagnosis method based on deep clustering is proposed. In this method, an autoen...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9354608/ |
| id |
doaj-543a41a5f3114f67ae5cbe67661b51e6 |
|---|---|
| record_format |
Article |
| spelling |
doaj-543a41a5f3114f67ae5cbe67661b51e62021-03-30T15:06:09ZengIEEEIEEE Access2169-35362021-01-019301543016810.1109/ACCESS.2021.30594599354608Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded EmbeddingJing An0https://orcid.org/0000-0002-4028-4277Ping Ai1https://orcid.org/0000-0003-3132-7236Cong Liu2Sen Xu3Dakun Liu4School of Mechanical Engineering, Yancheng Institute of Technology, Yancheng, ChinaCollege of Computer and Information Engineering, Hohai University, Nanjing, ChinaSchool of Mechanical Engineering, Yancheng Institute of Technology, Yancheng, ChinaSchool of Information Engineering, Yancheng Institute of Technology, Yancheng, ChinaSchool of Mechanical Engineering, Yancheng Institute of Technology, Yancheng, ChinaIn many practical fault diagnosis applications, the acquisition of fault data labels requires substantial manpower and resources, which are sometimes impossible to achieve. To address this, an unsupervised bearing fault diagnosis method based on deep clustering is proposed. In this method, an autoencoder is initially applied to the signal spectrum to learn the initial representation. Then, its potential manifold is further searched, and a Gaussian mixture model is finally used for clustering. Experiments conducted on the Case Western Reserve University bearing datasets show that the proposed method can find the optimal clusterable manifold. Moreover, its clustering performance is better than those of the current advanced baseline methods, and it is only slightly complex. Thus, the effectiveness of the proposed method is verified.https://ieeexplore.ieee.org/document/9354608/Bearing fault diagnosisautoencoded embedding representationlocal manifold learningmanifold re-embeddingdeep clusteringclusterable manifold |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Jing An Ping Ai Cong Liu Sen Xu Dakun Liu |
| spellingShingle |
Jing An Ping Ai Cong Liu Sen Xu Dakun Liu Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding IEEE Access Bearing fault diagnosis autoencoded embedding representation local manifold learning manifold re-embedding deep clustering clusterable manifold |
| author_facet |
Jing An Ping Ai Cong Liu Sen Xu Dakun Liu |
| author_sort |
Jing An |
| title |
Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding |
| title_short |
Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding |
| title_full |
Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding |
| title_fullStr |
Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding |
| title_full_unstemmed |
Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding |
| title_sort |
deep clustering bearing fault diagnosis method based on local manifold learning of an autoencoded embedding |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2021-01-01 |
| description |
In many practical fault diagnosis applications, the acquisition of fault data labels requires substantial manpower and resources, which are sometimes impossible to achieve. To address this, an unsupervised bearing fault diagnosis method based on deep clustering is proposed. In this method, an autoencoder is initially applied to the signal spectrum to learn the initial representation. Then, its potential manifold is further searched, and a Gaussian mixture model is finally used for clustering. Experiments conducted on the Case Western Reserve University bearing datasets show that the proposed method can find the optimal clusterable manifold. Moreover, its clustering performance is better than those of the current advanced baseline methods, and it is only slightly complex. Thus, the effectiveness of the proposed method is verified. |
| topic |
Bearing fault diagnosis autoencoded embedding representation local manifold learning manifold re-embedding deep clustering clusterable manifold |
| url |
https://ieeexplore.ieee.org/document/9354608/ |
| work_keys_str_mv |
AT jingan deepclusteringbearingfaultdiagnosismethodbasedonlocalmanifoldlearningofanautoencodedembedding AT pingai deepclusteringbearingfaultdiagnosismethodbasedonlocalmanifoldlearningofanautoencodedembedding AT congliu deepclusteringbearingfaultdiagnosismethodbasedonlocalmanifoldlearningofanautoencodedembedding AT senxu deepclusteringbearingfaultdiagnosismethodbasedonlocalmanifoldlearningofanautoencodedembedding AT dakunliu deepclusteringbearingfaultdiagnosismethodbasedonlocalmanifoldlearningofanautoencodedembedding |
| _version_ |
1724179977900916736 |