A Survey on Graph Neural Networks for Remaining Useful Life Prediction: Methodologies, Evaluation and Future Trends

The prediction of Remaining Useful Life (RUL) is a critical component in the field of Prognostics and Health Management (PHM), which aims to predict the future state of a system to ensure timely maintenance and prevent unexpected failures (Wang, Xu, Li, Ren, Dong, Chen, Du, Wang, Shi and Zhang, 2024f; Karatzinis, Boutalis and Van Vaerenbergh, 2024; Zhang, Yuan, Jiang and Zhao, 2024b). Accurate RUL prediction enable predictive maintenance, which can significantly reduce downtime, improve safety, and optimize the lifecycle management of machinery and equipment. Additionally, effective RUL prediction can enhance decision-making processes, improve resource allocation, and reduce maintenance costs. In recent years, deep learning has become increasingly important in RUL prediction due to its ability to model complex patterns and dependencies, providing more accurate and reliable predictions compared to traditional methods, such as statistical approaches (Si, Wang, Hu and Zhou, 2011) and physicsbased models (Lei, Li, Gontarz, Lin, Radkowski and Dybala, 2016; Sikorska, Hodkiewicz and Ma, 2011; Li, Zhang, Li and Si, 2024). Existing studies in RUL prediction have primarily focused on utilizing temporal encoders such as Temporal Convolutional Networks (TCN) (Qiu, Niu, Shang, Gao and Xu, 2023), Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN) (Shang, Xu, Qiu, Gao, Jiang and Yi, 2024), and Long Short-Term Memory (LSTM) networks. These methods have achieved strong performance due to their ability to capture temporal information, which refers to the time-based patterns and sequences within the data, such as trends and periodic behaviors. However, they are not effective at capturing spatial information, which limits their performance in RUL prediction.