Abstract
Remaining useful life (RUL) prediction is a key aspect of prognostics and health management. It is essential for ensuring the reliability and operational safety of mechanical equipment. Graph Attention Networks (GATs) are an emerging approach for RUL prediction through the innovative integration of graph structures and attention mechanisms. However, existing graph structures fail to establish the correlations between different sensors at different timestamps. Furthermore, the attention mechanism of traditional GATs exhibits insufficient capability in capturing complex nonlinear dependencies between nodes. To overcome these limitations, this paper proposes a nonlinear coupling spatiotemporal graph attention network (NCST-GAT) for RUL prediction. First, a spatiotemporal graph structure construction method is designed to integrate sensor nodes across timestamps. Then, a multiplicative Kolmogorov-Arnold attention mechanism is proposed to replace the standard multilayer perceptron in attention scoring functions, significantly enhancing the modeling of nonlinear interactions among nodes and yielding more expressive feature representations to predict RUL. Experimental results on the CMAPSS and PHM2010 datasets demonstrate that the proposed NCST-GAT achieves an average improvement of 6.1% and 15.6% for RMSE and prognostic Score metrics respectively over state-of-the-art methods, exhibiting strong predictive performance and generalization capability.
Funding Information
  • Science and Technology Project of Hebei Education Department (QN2024107)
  • National Key Research and Development Program of China (2022YFB3303803)
  • National Key Research and Development Program of China (2024YFB3310900)
  • National Natural Science Foundation of China (52405100)
  • National Natural Science Foundation of China (62073118)

This publication has 41 references indexed in Scilit: