Logo image
Bearing Remaining Useful Life Prediction Based on Regression Shapalet and Graph Neural Network
期刊文章   同儕審查

Bearing Remaining Useful Life Prediction Based on Regression Shapalet and Graph Neural Network

Xiaoyu Yang, Ying Zheng, Yong Zhang, David Shan-Hill WongWeidong Yang
IEEE Transactions on Instrumentation and Measurement
2022

摘要

graph evolution Graph Neural Network regression shapelet Remaining Useful Life prediction Instrumentation Electrical and Electronic Engineering
Remaining useful life (RUL) prediction of bearing is essential to guarantee its safe operation. In recent years, Deep learning (DL) based methods attract lots of research attention for accurate RUL prediction. However, the weak interpretability of the DL models prevents their wide use in practical systems. In this paper, the graph is used to represent the degradation state of bearings, and Graph Neural Network (GNN) is applied for their RUL prediciton. Specifically, regression shapelet is proposed to transform the bearings time series data into graph structure firstly. Then, with the proposed distance matrix/adjacency matrix as the input and smoothed nonlinear health index(SNHI) as the output, a deep GNN model combining Graph Convolutional Neural-network (GCN) and Gated Recurrent Unit (GRU) is set up in both spatial and temporal perspective to predict the bearing RUL. Meanwhile, graph evolution is adopted to monitor the graph changes with time, and offer the explanation for the bearing degradation procedure. Experiment study on the PRONOSTIA platform is used to evaluate the proposed method. The results show that the proposed method can well explain the bearing degradation process from the graph perspective, and will achieve superior performance to the existing methods.

相關連結

指標

1 檢視次數

詳細資料

Logo image