Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation Strategy
The remaining useful life (RUL) of bearings based on deep learning methods has been increasingly used. However, there are still two obstacles in deep learning RUL prediction: (1) the training process of the deep learning model requires enough data, but run-to-failure data are limited in the actual i...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/12/21/11086 |
| _version_ | 1797469226964877312 |
|---|---|
| author | Ran Wang Fucheng Yan Ruyu Shi Liang Yu Yingjun Deng |
| author_facet | Ran Wang Fucheng Yan Ruyu Shi Liang Yu Yingjun Deng |
| author_sort | Ran Wang |
| collection | DOAJ |
| description | The remaining useful life (RUL) of bearings based on deep learning methods has been increasingly used. However, there are still two obstacles in deep learning RUL prediction: (1) the training process of the deep learning model requires enough data, but run-to-failure data are limited in the actual industry; (2) the mutual dependence between RUL predictions at different time instants are commonly ignored in existing RUL prediction methods. To overcome these problems, a RUL prediction method combining the data augmentation strategy and Wiener–LSTM network is proposed. First, the Sobol sampling strategy is implemented to augment run-to-failure data based on the degradation model. Then, the Wiener–LSTM model is developed for the RUL prediction of bearings. Different from the existing LSTM-based bearing RUL methods, the Wiener–LSTM model utilizes the Wiener process to represent the mutual dependence between the predicted RUL results at different time instants and embeds the Wiener process into the LSTM to control the uncertainty of the result. A joint optimization strategy is applied in the construction of the loss function. The efficacy and superiority of the proposed method are verified on a rolling bearing dataset obtained from the PRONOSTIA platform. Compared with the conventional bearing RUL prediction methods, the proposed method can effectively augment the bearing run-to-failure data and, thus, improve the prediction results. Meanwhile, fluctuations of the bearing RUL prediction result are significantly suppressed by the proposed method, and the prediction errors of the proposed method are much lower than other comparative methods. |
| first_indexed | 2024-03-09T19:17:24Z |
| format | Article |
| id | doaj.art-aaa4105dc5ba4580a886fa1fb79c6ace |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-09T19:17:24Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-aaa4105dc5ba4580a886fa1fb79c6ace2023-11-24T03:37:49ZengMDPI AGApplied Sciences2076-34172022-11-0112211108610.3390/app122111086Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation StrategyRan Wang0Fucheng Yan1Ruyu Shi2Liang Yu3Yingjun Deng4College of Logistics Engineering, Shanghai Maritime University, Shanghai 201306, ChinaCollege of Logistics Engineering, Shanghai Maritime University, Shanghai 201306, ChinaAVIC Shanghai Aero Measurement & Controlling Research Institute, Shanghai 201601, ChinaState Key Laboratory of Mechanical System and Vibration, Institute of Vibration, Shock and Noise, Shanghai Jiao Tong University, Shanghai 200240, ChinaCenter for Applied Mathematics, Tianjin University, Tianjin 300072, ChinaThe remaining useful life (RUL) of bearings based on deep learning methods has been increasingly used. However, there are still two obstacles in deep learning RUL prediction: (1) the training process of the deep learning model requires enough data, but run-to-failure data are limited in the actual industry; (2) the mutual dependence between RUL predictions at different time instants are commonly ignored in existing RUL prediction methods. To overcome these problems, a RUL prediction method combining the data augmentation strategy and Wiener–LSTM network is proposed. First, the Sobol sampling strategy is implemented to augment run-to-failure data based on the degradation model. Then, the Wiener–LSTM model is developed for the RUL prediction of bearings. Different from the existing LSTM-based bearing RUL methods, the Wiener–LSTM model utilizes the Wiener process to represent the mutual dependence between the predicted RUL results at different time instants and embeds the Wiener process into the LSTM to control the uncertainty of the result. A joint optimization strategy is applied in the construction of the loss function. The efficacy and superiority of the proposed method are verified on a rolling bearing dataset obtained from the PRONOSTIA platform. Compared with the conventional bearing RUL prediction methods, the proposed method can effectively augment the bearing run-to-failure data and, thus, improve the prediction results. Meanwhile, fluctuations of the bearing RUL prediction result are significantly suppressed by the proposed method, and the prediction errors of the proposed method are much lower than other comparative methods.https://www.mdpi.com/2076-3417/12/21/11086remaining useful life predictionbearinglong short-term memory (LSTM)sequence-wise uncertainty controlWiener process |
| spellingShingle | Ran Wang Fucheng Yan Ruyu Shi Liang Yu Yingjun Deng Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation Strategy Applied Sciences remaining useful life prediction bearing long short-term memory (LSTM) sequence-wise uncertainty control Wiener process |
| title | Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation Strategy |
| title_full | Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation Strategy |
| title_fullStr | Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation Strategy |
| title_full_unstemmed | Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation Strategy |
| title_short | Uncertainty-Controlled Remaining Useful Life Prediction of Bearings with a New Data-Augmentation Strategy |
| title_sort | uncertainty controlled remaining useful life prediction of bearings with a new data augmentation strategy |
| topic | remaining useful life prediction bearing long short-term memory (LSTM) sequence-wise uncertainty control Wiener process |
| url | https://www.mdpi.com/2076-3417/12/21/11086 |
| work_keys_str_mv | AT ranwang uncertaintycontrolledremainingusefullifepredictionofbearingswithanewdataaugmentationstrategy AT fuchengyan uncertaintycontrolledremainingusefullifepredictionofbearingswithanewdataaugmentationstrategy AT ruyushi uncertaintycontrolledremainingusefullifepredictionofbearingswithanewdataaugmentationstrategy AT liangyu uncertaintycontrolledremainingusefullifepredictionofbearingswithanewdataaugmentationstrategy AT yingjundeng uncertaintycontrolledremainingusefullifepredictionofbearingswithanewdataaugmentationstrategy |