Remaining Useful Life Prediction Combining Advanced Anomaly Detection and Graph Isomorphic Network
IEEE Sensors Journal · 15.11.2024 · 24 (22) · 38365-38376
DOI: 10.1109/jsen.2024.3470231 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 15.11.2024. Verfasst von Junyu Qi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 29-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic and Applied Basic Research Foundation of Guangdong Province, Young Talent Support Project of Guangzhou Association for Science and Technology.
Abstract (Originalsprache)
Condition monitoring (CM) has garnered extensive attention in the era of Industry 4.0 and digital manufacturing. It is crucial to monitor the health status of machinery to ensure reliability, safety, production quality, and effectiveness. Advanced predictive maintenance strategies increase equipment availability and effectiveness by accurately predicting failures, thus facilitating maintenance engineering decisions and preventing unplanned machinery breakdowns. In this research, a novel predictive maintenance strategy is proposed by integrating anomaly detection and fault prognostics, two significant challenges in smart maintenance, into one CM system. For anomaly detection, we developed an intelligent methodology based on the skip convolution generative adversarial network (SCGAN). This network combines a convolutional autoencoder (CAE), generative adversarial network (GAN), and skip connections, forming a robust system to construct health indicators (HIs), effectively and efficiently tracking the degradation status of rolling element bearings with fault identified using the $3\sigma $ criterion. Validation on real experimental datasets demonstrates that the developed HIs show a stable trend during the healthy stage and a marked increase when deterioration is detected. Subsequently, we employ an advanced graph isomorphic network (GIN) for remaining useful life (RUL) prediction. GIN utilizes graph data and graph convolutions (GCs) to map complex relationships between degradation evolution and RUL. This approach outperforms existing deep learning models, such as convolutional neural networks (CNNs), long short-term memory (LSTM) networks, and CNN-LSTM, providing more accurate RUL prediction.
Förderung
- National Natural Science Foundation of China
- Basic and Applied Basic Research Foundation of Guangdong Province
- Young Talent Support Project of Guangzhou Association for Science and Technology
Zitieren
APA
Qi, J., Chen, Z., Song, Y., Xia, J., & Li, W. (2024). Remaining Useful Life Prediction Combining Advanced Anomaly Detection and Graph Isomorphic Network. IEEE Sensors Journal, 24(22), 38365-38376. https://doi.org/10.1109/jsen.2024.3470231
Vancouver
Qi J, Chen Z, Song Y, Xia J, Li W. Remaining Useful Life Prediction Combining Advanced Anomaly Detection and Graph Isomorphic Network. IEEE Sensors Journal. 2024;24(22):38365-38376. doi:10.1109/jsen.2024.3470231
BibTeX
@article{Qi2024,
author = {Qi, Junyu and Chen, Zhuyun and Song, Yuchen and Xia, Jingyan and Li, Weihua},
title = {Remaining Useful Life Prediction Combining Advanced Anomaly Detection and Graph Isomorphic Network},
journal = {IEEE Sensors Journal},
year = {2024},
volume = {24},
number = {22},
pages = {38365--38376},
doi = {10.1109/jsen.2024.3470231}
}
EUVIMED