Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature Extraction
Bearings are critical components in mechanical systems, and their degradation process typically exhibits distinct stages, making stage-based remaining useful life (RUL) prediction highly valuable. This paper presents a model that combines correlation analysis feature extraction with a Graph Neural N...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/13/1/43 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588070981992448 |
|---|---|
| author | Guangzhong Huang Wenping Lei Xinmin Dong Dongliang Zou Shijin Chen Xing Dong |
| author_facet | Guangzhong Huang Wenping Lei Xinmin Dong Dongliang Zou Shijin Chen Xing Dong |
| author_sort | Guangzhong Huang |
| collection | DOAJ |
| description | Bearings are critical components in mechanical systems, and their degradation process typically exhibits distinct stages, making stage-based remaining useful life (RUL) prediction highly valuable. This paper presents a model that combines correlation analysis feature extraction with a Graph Neural Network (GNN)-based approach for bearing degradation stage classification and RUL prediction, aiming to achieve accurate bearing life prediction. First, the proposed Pearson–Spearman correlation metric, along with Kernel Principal Component Analysis (KPCA) and autoencoders, is used to group and fuse health indicators (HIs), thereby obtaining a health indicator (HI) that effectively reflects the bearing degradation process. Then, a model combining Graph Convolutional Network (GCN) and Long Short-Term Memory (LSTM) networks is proposed for bearing degradation stage classification. Based on the classification results, the Adaptive Attention GraphSAGE–LSTM (AAGL) model, also introduced in this study, is employed to precisely predict the bearing’s remaining useful life. |
| format | Article |
| id | doaj-art-8725cc667e844457af53a3abc675eab4 |
| institution | Kabale University |
| issn | 2075-1702 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj-art-8725cc667e844457af53a3abc675eab42025-01-24T13:39:14ZengMDPI AGMachines2075-17022025-01-011314310.3390/machines13010043Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature ExtractionGuangzhong Huang0Wenping Lei1Xinmin Dong2Dongliang Zou3Shijin Chen4Xing Dong5School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, ChinaSchool of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, ChinaMCC5 Group Shanghai Corporation Limited, Shanghai 200400, ChinaMCC5 Group Shanghai Corporation Limited, Shanghai 200400, ChinaSchool of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001, ChinaBearings are critical components in mechanical systems, and their degradation process typically exhibits distinct stages, making stage-based remaining useful life (RUL) prediction highly valuable. This paper presents a model that combines correlation analysis feature extraction with a Graph Neural Network (GNN)-based approach for bearing degradation stage classification and RUL prediction, aiming to achieve accurate bearing life prediction. First, the proposed Pearson–Spearman correlation metric, along with Kernel Principal Component Analysis (KPCA) and autoencoders, is used to group and fuse health indicators (HIs), thereby obtaining a health indicator (HI) that effectively reflects the bearing degradation process. Then, a model combining Graph Convolutional Network (GCN) and Long Short-Term Memory (LSTM) networks is proposed for bearing degradation stage classification. Based on the classification results, the Adaptive Attention GraphSAGE–LSTM (AAGL) model, also introduced in this study, is employed to precisely predict the bearing’s remaining useful life.https://www.mdpi.com/2075-1702/13/1/43rolling bearingRUL predictionKPCAautoencoderstage classificationGNN |
| spellingShingle | Guangzhong Huang Wenping Lei Xinmin Dong Dongliang Zou Shijin Chen Xing Dong Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature Extraction Machines rolling bearing RUL prediction KPCA autoencoder stage classification GNN |
| title | Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature Extraction |
| title_full | Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature Extraction |
| title_fullStr | Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature Extraction |
| title_full_unstemmed | Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature Extraction |
| title_short | Stage-Based Remaining Useful Life Prediction for Bearings Using GNN and Correlation-Driven Feature Extraction |
| title_sort | stage based remaining useful life prediction for bearings using gnn and correlation driven feature extraction |
| topic | rolling bearing RUL prediction KPCA autoencoder stage classification GNN |
| url | https://www.mdpi.com/2075-1702/13/1/43 |
| work_keys_str_mv | AT guangzhonghuang stagebasedremainingusefullifepredictionforbearingsusinggnnandcorrelationdrivenfeatureextraction AT wenpinglei stagebasedremainingusefullifepredictionforbearingsusinggnnandcorrelationdrivenfeatureextraction AT xinmindong stagebasedremainingusefullifepredictionforbearingsusinggnnandcorrelationdrivenfeatureextraction AT dongliangzou stagebasedremainingusefullifepredictionforbearingsusinggnnandcorrelationdrivenfeatureextraction AT shijinchen stagebasedremainingusefullifepredictionforbearingsusinggnnandcorrelationdrivenfeatureextraction AT xingdong stagebasedremainingusefullifepredictionforbearingsusinggnnandcorrelationdrivenfeatureextraction |