Bayesian temporal factorization and improved transformer architecture for the prediction of aero-engine remaining useful life
Authors:
- 2 July 2026
- journal article
- Published by Emerald Publishing in Engineering Computations
- Vol. 43 (10) , 4779-4802
Abstract
Purpose: The purpose of this paper is to propose a comprehensive model that skillfully interpolates missing values without introducing potential bias, and performs high-precision prediction of the remaining useful life (RUL) of an engine using an improved transformer model. Design/methodology/approach: This paper proposes a method that integrates Bayesian temporal factorization with improved transformer architecture. By integrating low-rank matrix factorization and vector autoregressive (VAR) processes into a unified probabilistic graphical model, which enables the framework to capture both global and local consistency within large-scale time series data, is essential for robust RUL prediction. Additionally, a tailored Gibbs sampling algorithm is developed to impute missing spatiotemporal engine data effectively. Following the estimation of missing values, an improved transformer model is employed for RUL prediction, which leverages gated convolutional units to enhance its ability to fuse local contextual information at each time step, and harnesses bespoke gated attention units further to improve the computational efficiency of transformer models. Findings: Extensive experimentation on a turbofan engine dataset validates the efficacy of the proposed method. Results demonstrate that our approach either outperforms or is comparable to the best existing approaches in RUL estimation. Originality/value: The method proposed in this study addresses the problem of poor RUL prediction capability of traditional deep learning (DL) models when engine data are partially missing.Keywords
Funding Information
- the Fundamental Research Funds for the Central Universities (ILA22032-1A)
- the Joint Fund of National Natural Science Foundation of China and Civil Aviation Administration of China (No. U2033202)
- the Joint Fund of National Natural Science Foundation of China and Civil Aviation Administration of China (U1333119)
- The National Natural Science Foundation of China (No.52172387)
- the Aeronautical Science Foundation of China (2022Z071052001)
This publication has 27 references indexed in Scilit:
- A novel similarity-based remaining useful life prediction method under multiple failure modes with variable sensorsMeasurement, 2025
- Bayesian gated-transformer model for risk-aware prediction of aero-engine remaining useful lifeExpert Systems with Applications, 2023
- Variational encoding approach for interpretable assessment of remaining useful life estimationReliability Engineering & System Safety, 2022
- A deep attention residual neural network-based remaining useful life prediction of machineryMeasurement, 2021
- Remaining useful life estimation via transformer encoder enhanced by a gated convolutional unitJournal of Intelligent Manufacturing, 2021
- A dual-LSTM framework combining change point detection and remaining useful life predictionReliability Engineering & System Safety, 2021
- Transferable convolutional neural network based remaining useful life prediction of bearing under multiple failure behaviorsMeasurement, 2021
- A Bayesian tensor decomposition approach for spatiotemporal traffic data imputationTransportation Research Part C: Emerging Technologies, 2019
- Remaining useful life estimation in prognostics using deep convolution neural networksReliability Engineering & System Safety, 2018
- Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life2016