Remaining Useful Life Prediction for Bearing Based on Coupled Diffusion Process and Temporal Attention
- 15 February 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-10
Abstract
Remaining Useful Life (RUL) prediction is one of the difficulties in prognostics and system health management (PHM) of bearings. Moreover, due to the limitations of test cost and equipment, it isn’t easy to obtain abundant full life cycle experimental samples of bearings, which cannot provide enough training samples to further improve the accuracy of RUL prediction. To address these problem, this paper proposes a rolling bearing RUL prediction method based on coupled diffusion probabilistic model and time attention mechanism (CDTA). This method first augments the original sequence with the coupled diffusion process, which preserves its randomness and reduces the difficulty of training the subsequent inference network. Then, it introduces a time attention unit (TAU) to enhance the network’s ability to extract and fuse temporal features and dependencies within and between samples, which improves prediction accuracy. This paper conducts experimental verification on PHM2012 datasets and shows that the proposed method achieves significant improvement in prediction accuracy compared with existing RUL prediction methods.Keywords
Funding Information
- National Natural Science Foundation of China (62071001)
- Nature Science Foundation of Anhui (2008085MF183, 2208085QF206, 2308085QF224)
- Key Science Project of Anhui Education Department of China (KJ2021A0013)
- China Postdoctoral Science Foundation (2023M730009)
This publication has 37 references indexed in Scilit:
- Towards prognostic generalization: a domain conditional invariance and specificity disentanglement network for remaining useful life predictionJournal of Intelligent Manufacturing, 2023
- Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning2023
- Spatio-temporal degradation modeling and remaining useful life prediction under multiple operating conditions based on attention mechanism and deep learningReliability Engineering & System Safety, 2022
- A review of vibration-based gear wear monitoring and prediction techniquesMechanical Systems and Signal Processing, 2022
- Remaining Useful Life Prediction via Improved CNN, GRU and Residual Attention Mechanism With Soft ThresholdingIEEE Sensors Journal, 2022
- Joint decision-making of parallel machine scheduling restricted in job-machine release time and preventive maintenance with remaining useful life constraintsReliability Engineering & System Safety, 2022
- Recurrent convolutional neural network: A new framework for remaining useful life prediction of machineryNeurocomputing, 2020
- Reliable multiple combined fault diagnosis of bearings using heterogeneous feature models and multiclass support vector MachinesReliability Engineering & System Safety, 2019
- Complex network approaches to nonlinear time series analysisPhysics Reports, 2019
- Prediction of Bearing Remaining Useful Life With Deep Convolution Neural NetworkIEEE Access, 2018