SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments
Among the smart factory studies, we describe defect detection research conducted on bearings, which are elements of mechanical facilities. Bearing research has been consistently conducted in the past; however, most of the research has been limited to using existing artificial intelligence models. In...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/9/1504 |
| _version_ | 1797505106427510784 |
|---|---|
| author | Seoyeong Lee Jongpil Jeong |
| author_facet | Seoyeong Lee Jongpil Jeong |
| author_sort | Seoyeong Lee |
| collection | DOAJ |
| description | Among the smart factory studies, we describe defect detection research conducted on bearings, which are elements of mechanical facilities. Bearing research has been consistently conducted in the past; however, most of the research has been limited to using existing artificial intelligence models. In addition, previous studies assumed the factories situated in the bearing defect research were insufficient. Therefore, a recent research was conducted that applied an artificial intelligence model and the factory environment. The transformer model was selected as state-of-the-art (SOTA) and was also applied to bearing research. Then, an experiment was conducted with Gaussian noise applied to assume a factory situation. The swish-LSTM transformer (Sl transformer) framework was constructed by redesigning the internal structure of the transformer using the swish activation function and long short-term memory (LSTM). Then, the data in noise were removed and reconstructed using the singular spectrum analysis (SSA) preprocessing method. Based on the SSA-Sl transformer framework, an experiment was performed by adding Gaussian noise to the Case Western Reserve University (CWRU) dataset. In the case of no noise, the Sl transformer showed more than 95% performance, and when noise was inserted, the SSA-Sl transformer showed better performance than the comparative artificial intelligence models. |
| first_indexed | 2024-03-10T04:13:52Z |
| format | Article |
| id | doaj.art-335d9c83341f4684a2e017540e5283d9 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T04:13:52Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-335d9c83341f4684a2e017540e5283d92023-11-23T08:04:31ZengMDPI AGElectronics2079-92922022-05-01119150410.3390/electronics11091504SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory EnvironmentsSeoyeong Lee0Jongpil Jeong1Department of Smart Factory Convergence, Sungkyunkwan University, Suwon 16419, KoreaDepartment of Smart Factory Convergence, Sungkyunkwan University, Suwon 16419, KoreaAmong the smart factory studies, we describe defect detection research conducted on bearings, which are elements of mechanical facilities. Bearing research has been consistently conducted in the past; however, most of the research has been limited to using existing artificial intelligence models. In addition, previous studies assumed the factories situated in the bearing defect research were insufficient. Therefore, a recent research was conducted that applied an artificial intelligence model and the factory environment. The transformer model was selected as state-of-the-art (SOTA) and was also applied to bearing research. Then, an experiment was conducted with Gaussian noise applied to assume a factory situation. The swish-LSTM transformer (Sl transformer) framework was constructed by redesigning the internal structure of the transformer using the swish activation function and long short-term memory (LSTM). Then, the data in noise were removed and reconstructed using the singular spectrum analysis (SSA) preprocessing method. Based on the SSA-Sl transformer framework, an experiment was performed by adding Gaussian noise to the Case Western Reserve University (CWRU) dataset. In the case of no noise, the Sl transformer showed more than 95% performance, and when noise was inserted, the SSA-Sl transformer showed better performance than the comparative artificial intelligence models.https://www.mdpi.com/2079-9292/11/9/1504bearing fault diagnosissingular spectrum analysistransformerunder noisy factory environments |
| spellingShingle | Seoyeong Lee Jongpil Jeong SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments Electronics bearing fault diagnosis singular spectrum analysis transformer under noisy factory environments |
| title | SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments |
| title_full | SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments |
| title_fullStr | SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments |
| title_full_unstemmed | SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments |
| title_short | SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments |
| title_sort | ssa sl transformer for bearing fault diagnosis under noisy factory environments |
| topic | bearing fault diagnosis singular spectrum analysis transformer under noisy factory environments |
| url | https://www.mdpi.com/2079-9292/11/9/1504 |
| work_keys_str_mv | AT seoyeonglee ssasltransformerforbearingfaultdiagnosisundernoisyfactoryenvironments AT jongpiljeong ssasltransformerforbearingfaultdiagnosisundernoisyfactoryenvironments |