Journal Article10.1109/TIM.2022.3151169
Bearing Remaining Useful Life Prediction Based on Regression Shapalet and Graph Neural Network
Xiao Yang,Ying Zheng,Yong Zhang,David Shan-Hill Wong,Weidong Yang +4 more
- Vol. 71, pp 1-12
44
TL;DR: 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.
read more
Abstract: Remaining useful life (RUL) prediction of bearing is essential to guarantee its safe operation. In recent years, deep learning (DL)-based methods attract a lot of research attention for accurate RUL prediction. However, the weak interpretability of the DL models prevents their wide use in practical systems. In this article, the graph is used to represent the degradation state of bearings, and a graph neural network (GNN) is applied for their RUL prediction. Specifically, regression shapelet is proposed to transform the bearings time series data into graph structure first. 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 gate recurrent unit (GRU) is set up in both spatial and temporal perspectives to predict the bearing RUL. Meanwhile, graph evolution is adopted to monitor the graph changes with time and offer an explanation for the bearing degradation procedure. The 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.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A gated graph convolutional network with multi-sensor signals for remaining useful life prediction
TL;DR: In this article , a gated graph convolutional network (GGCN) is developed for multi-sensor signal fusion and RUL prediction, and the extracted features are fed into a quantile regression layer to estimate the RUL and its confidence interval.
66
Spatio-Temporal Fusion Attention: A Novel Approach for Remaining Useful Life Prediction Based on Graph Neural Network
TL;DR: A graph neural network (GNN)-based spatio-temporal fusion attention (STFA) approach that can combine the information in time and space at the same time and utilize a priori knowledge about the equipment’s structure is developed.
42
Remaining Useful Life Prediction Method Based on the Spatiotemporal Graph and GCN Nested Parallel Route Model
Liuyang Song,Ye Jin,Tianjiao Lin,Shengkai Zhao,Zhicheng Wei,Huaqing Wang +5 more
TL;DR: A spatiotemporal graph and GCN nested parallel route model for remaining useful life prediction based on high-dimensional time series data. The model incorporates spatial and temporal patterns to improve prediction accuracy and generalization ability.
20
Light convolutional neural network by neural architecture search and model pruning for bearing fault diagnosis and remaining useful life prediction
TL;DR: In this article , a cell-based light convolutional neural network (LBS-CNN) with Neural Architecture Search (NAS) and weights-ranking-based model pruning was proposed for bearing fault diagnosis and remaining useful life prediction.
Comprehensive Dynamic Structure Graph Neural Network for Aero-Engine Remaining Useful Life Prediction
Hongfei Wang,Zhuo Zhang,Xiang Li,Xinyang Deng,Wen Jiang +4 more
TL;DR: A new RUL prediction method based on GNN, which is named comprehensive dynamic structure GNN (CDSG), which not only fully exploits the health information hidden in the condition monitoring data but also takes into account the structural characteristics of the aero-engine.
14
References
Deep-Convolution-Based LSTM Network for Remaining Useful Life Prediction
TL;DR: A novel deep neural network named convolution-based long short-term memory (CLSTM) network is proposed to predict the RUL of rotating machineries mining the in situ vibration data, and the proposed algorithm outperforms the current deep learning algorithms in URL prediction and system prognosis with respect to better accuracy and computation efficiency.
364
Deep separable convolutional network for remaining useful life prediction of machinery
TL;DR: The experimental results show that the proposed deep separable convolutional network (DSCN) is able to provide accurate RUL prediction results based on the raw multi-sensor data and is superior to some existing data-driven prognostics approaches.
333
A novel deep learning method based on attention mechanism for bearing remaining useful life prediction
TL;DR: A recurrent neural network based on encoder–decoder framework with attention mechanism is proposed to predict HI values, which are designed closely related with the RUL values in this paper.
316
Sensory-Updated Residual Life Distributions for Components With Exponential Degradation Patterns
TL;DR: A stochastic degradation modeling framework is developed for computing and continuously updating residual life distributions of partially degraded components by combining population-specific degradation characteristics with component-specific sensory data acquired through condition monitoring in order to compute and continuously update remaining life distributions.
298
Remaining Useful Life Estimation in Rolling Bearings Utilizing Data-Driven Probabilistic E-Support Vectors Regression
TL;DR: A data-driven approach for the remaining useful life (RUL) estimation of rolling element bearings based on ε-Support Vector Regression, with Wiener entropy utilized for the first time in the condition monitoring of rolling bearings.
284