Switching Unscented Kalman Filters With Unknown Transition Probabilities for Remaining Useful Life Prediction of Bearings
- 26 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (20) , 32577-32595
Abstract
Since bearings are critical components of mechanical equipment, timely fault detection and accurate prediction of remaining useful life (RUL) are essential for ensuring sufficient time for maintenance and replacement. Switching multi-model prognostics have been extensively studied to better describe the entire degradation process. However, existing studies typically assume that model transition probabilities are known and constant, which is unrealistic in practical applications. To address this research gap, this study proposes the SUKF-EM algorithm. This algorithm first introduces a novel method for integrating health indicators. Subsequently, to resolve the issue of real-time estimation of model transition probabilities, an objective function for evaluating these probabilities is constructed based on the expectation maximization algorithm. Following this, an algorithmic framework for real-time identification using stochastic approximation is derived. Finally, the switching unscented Kalman filtering algorithm is integrated to achieve RUL prediction for bearings. The effectiveness of the proposed method has been validated using run-to-failure experimental data from the Intelligent System Maintenance Center at the University of Cincinnati and XJTU-SY.Keywords
Funding Information
- National Natural Science Foundation of China (NSFC61773039)
This publication has 51 references indexed in Scilit:
- A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery RUL predictionAdvanced Engineering Informatics, 2023
- Remaining useful life re-prediction methodology based on Wiener process: Subsea Christmas tree system as a case studyComputers & Industrial Engineering, 2021
- LSTM networks based on attention ordered neurons for gear remaining life predictionISA Transactions, 2020
- A novel deep learning method based on attention mechanism for bearing remaining useful life predictionApplied Soft Computing, 2020
- A multimodal and hybrid deep neural network model for Remaining Useful Life estimationComputers in Industry, 2019
- A novel Switching Unscented Kalman Filter method for remaining useful life prediction of rolling bearingMeasurement, 2019
- Enhanced particle filter for tool wear predictionJournal of Manufacturing Systems, 2015
- Real-time Reliability Evaluation for an Individual Product Based on Change-point Gamma and Wiener ProcessQuality and Reliability Engineering International, 2013
- An online sequential algorithm for the estimation of transition probabilities for jump Markov linear systemsAutomatica, 2006
- Wavelet filter-based weak signature detection method and its application on rolling element bearing prognosticsJournal of Sound and Vibration, 2006