A remaining useful life prediction method based on PSR-former
Abstract The non-linear and non-stationary vibration data generated by rotating machines can be used to analyze various fault conditions for predicting the remaining useful life(RUL). It offers great help to make prognostic and health management(PHM) develop. However, the complexity of the mechanica...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-22941-3 |
| _version_ | 1811257027880550400 |
|---|---|
| author | Huang Zhang Shuyou Zhang Lemiao Qiu Yiming Zhang Yang Wang Zili Wang Gaopeng Yang |
| author_facet | Huang Zhang Shuyou Zhang Lemiao Qiu Yiming Zhang Yang Wang Zili Wang Gaopeng Yang |
| author_sort | Huang Zhang |
| collection | DOAJ |
| description | Abstract The non-linear and non-stationary vibration data generated by rotating machines can be used to analyze various fault conditions for predicting the remaining useful life(RUL). It offers great help to make prognostic and health management(PHM) develop. However, the complexity of the mechanical working environment makes the vibration data collected easily affected, so it is hard to form an appropriate health index(HI) to predict the RUL. In this paper, a PSR-former model is proposed including a Phase space reconstruction(PSR) layer and a Transformer layer. The PSR layer is utilized as an embedding to deepen the understanding of vibration data after feature fusion. In the Transformer layer, an attention mechanism is adopted to give different assignments, and a layer-hopping connection is used to accelerate the convergence and make the structure more stable. The effectiveness of the proposed method is validated through the Intelligent Maintenance Systems (IMS) bearing dataset. Through analysis, the prediction accuracy is judged by the parameter RMSE which is 1.0311. Some state-of-art methods such as LSTM, GRU, and CNN were also analyzed on the same dataset to compare. The result indicates that the proposed method can effectively establish a precise model for RUL predictions. |
| first_indexed | 2024-04-12T17:50:03Z |
| format | Article |
| id | doaj.art-82b98cb891044eca84725982e52cfa61 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T17:50:03Z |
| publishDate | 2022-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-82b98cb891044eca84725982e52cfa612022-12-22T03:22:31ZengNature PortfolioScientific Reports2045-23222022-10-0112111710.1038/s41598-022-22941-3A remaining useful life prediction method based on PSR-formerHuang Zhang0Shuyou Zhang1Lemiao Qiu2Yiming Zhang3Yang Wang4Zili Wang5Gaopeng Yang6The State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang UniversityThe State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang UniversityThe State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang UniversityThe State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang UniversityThe State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang UniversityThe State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang UniversityThe State Key Laboratory of Fluid Power and Mechatronic System, Zhejiang UniversityAbstract The non-linear and non-stationary vibration data generated by rotating machines can be used to analyze various fault conditions for predicting the remaining useful life(RUL). It offers great help to make prognostic and health management(PHM) develop. However, the complexity of the mechanical working environment makes the vibration data collected easily affected, so it is hard to form an appropriate health index(HI) to predict the RUL. In this paper, a PSR-former model is proposed including a Phase space reconstruction(PSR) layer and a Transformer layer. The PSR layer is utilized as an embedding to deepen the understanding of vibration data after feature fusion. In the Transformer layer, an attention mechanism is adopted to give different assignments, and a layer-hopping connection is used to accelerate the convergence and make the structure more stable. The effectiveness of the proposed method is validated through the Intelligent Maintenance Systems (IMS) bearing dataset. Through analysis, the prediction accuracy is judged by the parameter RMSE which is 1.0311. Some state-of-art methods such as LSTM, GRU, and CNN were also analyzed on the same dataset to compare. The result indicates that the proposed method can effectively establish a precise model for RUL predictions.https://doi.org/10.1038/s41598-022-22941-3 |
| spellingShingle | Huang Zhang Shuyou Zhang Lemiao Qiu Yiming Zhang Yang Wang Zili Wang Gaopeng Yang A remaining useful life prediction method based on PSR-former Scientific Reports |
| title | A remaining useful life prediction method based on PSR-former |
| title_full | A remaining useful life prediction method based on PSR-former |
| title_fullStr | A remaining useful life prediction method based on PSR-former |
| title_full_unstemmed | A remaining useful life prediction method based on PSR-former |
| title_short | A remaining useful life prediction method based on PSR-former |
| title_sort | remaining useful life prediction method based on psr former |
| url | https://doi.org/10.1038/s41598-022-22941-3 |
| work_keys_str_mv | AT huangzhang aremainingusefullifepredictionmethodbasedonpsrformer AT shuyouzhang aremainingusefullifepredictionmethodbasedonpsrformer AT lemiaoqiu aremainingusefullifepredictionmethodbasedonpsrformer AT yimingzhang aremainingusefullifepredictionmethodbasedonpsrformer AT yangwang aremainingusefullifepredictionmethodbasedonpsrformer AT ziliwang aremainingusefullifepredictionmethodbasedonpsrformer AT gaopengyang aremainingusefullifepredictionmethodbasedonpsrformer AT huangzhang remainingusefullifepredictionmethodbasedonpsrformer AT shuyouzhang remainingusefullifepredictionmethodbasedonpsrformer AT lemiaoqiu remainingusefullifepredictionmethodbasedonpsrformer AT yimingzhang remainingusefullifepredictionmethodbasedonpsrformer AT yangwang remainingusefullifepredictionmethodbasedonpsrformer AT ziliwang remainingusefullifepredictionmethodbasedonpsrformer AT gaopengyang remainingusefullifepredictionmethodbasedonpsrformer |