A Hybrid Prognostic Approach Combining a Stacked Multihead Self-Attention Autoencoder and Multimodal Relevance Sampling Particle Filter
- 23 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-22
Abstract
Accurate prediction of the Remaining Useful Life (RUL) of bearings is critical for optimizing maintenance strategies, preventing unexpected failures, and enhancing repair management. Despite the increasing interest in hybrid-driven prognostic methods, several challenges remain: (i) Constructing a high-quality Health Indicator (HI) is essential for accurate prognostics, but existing methods are hindered by feature redundancy and insufficient extraction of deep latent information, resulting in unreliable HIs. (ii) The Particle Filter (PF), a widely used RUL estimation method, can degrade into a prior estimation technique when measurement data are missing during prediction, leading to particle impoverishment and reduced accuracy. To address these challenges, this study introduces an innovative hybrid-driven framework for predicting the RUL, comprising two main components: HI construction and a closed-loop RUL prediction algorithm. For robust HI construction, a heuristic search method based on the Minimum Redundancy Maximum Relevance (mRMR) criterion is used to select optimal features, effectively mitigating redundancy. These features are then used as guiding labels to train a Stacked Multi-Head Self-Attention Autoencoder (SMSAE), which extracts deep, latent features from raw data, going beyond the shallow representations of the guiding labels. The framework further employs Bayesian Transformer models for one-step state predictions, which serve as virtual measurements in the Multi-Modal Relevance Sampling Particle Filter (MRSPF) algorithm, alleviating particle impoverishment and refining posterior distributions. Experimental validation on benchmark datasets demonstrates the superior predictive accuracy and reliability of the proposed framework.Keywords
Funding Information
- National Natural Science Foundation of China (NSFC61773039)
This publication has 50 references indexed in Scilit:
- Unsupervised construction of health indicator for rotating machinery via multi-criterion feature selection and attentive variational autoencoderScience China Technological Sciences, 2024
- Data-model linkage prediction of tool remaining useful life based on deep feature fusion and Wiener processJournal of Manufacturing Systems, 2024
- A new supervised multi-head self-attention autoencoder for health indicator construction and similarity-based machinery RUL predictionAdvanced Engineering Informatics, 2023
- A hybrid approach to predict battery health combined with attention-based transformer and online correctionJournal of Energy Storage, 2023
- A hybrid multi-stage methodology for remaining useful life prediction of control system: Subsea Christmas tree as a case studyExpert Systems with Applications, 2022
- Construction of health indicators for condition monitoring of rotating machinery: A review of the researchExpert Systems with Applications, 2022
- A comprehensive survey of clustering algorithms: State-of-the-art machine learning applications, taxonomy, challenges, and future research prospectsEngineering Applications of Artificial Intelligence, 2022
- Surface fatigue crack growth under variable amplitude loadingEngineering Fracture Mechanics, 2020
- A novel Switching Unscented Kalman Filter method for remaining useful life prediction of rolling bearingMeasurement, 2019
- Wavelet filter-based weak signature detection method and its application on rolling element bearing prognosticsJournal of Sound and Vibration, 2006