Research library / 2026 / Conference paper
A Transformer Approach for Remaining Useful Life Prediction and Fault Diagnosis of Mechanical Equipment
IOP Conference Series: Materials Science and Engineering · 012059 · 2026
Abstract
Original English abstract
Accurately estimating remaining useful life (RUL) and performing timely fault diagnosis are critical for ensuring the reliability and safety of industrial equipment. However, these tasks are often treated separately, reducing the effectiveness of maintenance decisions and limiting the use of sensor data. This study extends the Transformer architecture to simultaneously perform RUL prediction and multi-label fault classification within the same framework. Through a shared encoder using self-attention to capture temporal and cross-sensor dependencies, the model learns representations that capture machine health evolution and fault characteristics. Two output heads handle RUL regression and fault classification, while uncertainty-based loss weighting automatically balances the training of both tasks. The model is evaluated on the Microsoft Azure predictive maintenance dataset containing multi-sensor readings from 100 industrial machines. Results show that the proposed approach outperforms machine-learning and deep-learning baselines on both tasks, achieving high accuracy and strong robustness across test machines. By jointly predicting fault types and RUL within a single framework, the proposed method enhances maintenance planning, enables earlier and more reliable interventions, and provides a scalable solution for intelligent monitoring in smart manufacturing environments.
Original source: Chalmers Research ↗
In brief
Equipment lifetime prediction and fault diagnosis are often modeled separately. This Transformer shares a sensor-data encoder across both tasks and is evaluated on data from 100 industrial machines.
Key points
- Uses a shared self-attention encoder with separate RUL regression and fault-classification heads.
- Balances the two tasks with uncertainty-based loss weighting.
- Evaluates the joint model on the Microsoft Azure predictive maintenance dataset.
Cite this work
Yuchen Liu, Siyuan Chen, Ebru Turanoglu Bekar (2026). A Transformer Approach for Remaining Useful Life Prediction and Fault Diagnosis of Mechanical Equipment. IOP Conference Series: Materials Science and Engineering, 1342(1), 012059. https://doi.org/10.1088/1757-899X/1342/1/012059
@inproceedings{Chen2026TransformerRulFault,
title = {{A Transformer Approach for Remaining Useful Life Prediction and Fault Diagnosis of Mechanical Equipment}},
author = {Liu, Yuchen and Chen, Siyuan and Turanoglu Bekar, Ebru},
year = {2026},
booktitle = {The 12th Swedish Production Symposium (SPS 2026)},
series = {IOP Conference Series: Materials Science and Engineering},
volume = {1342},
number = {1},
pages = {012059},
doi = {10.1088/1757-899X/1342/1/012059},
url = {https://research.chalmers.se/en/publication/553219}
}
Abstract reproduced from the linked source record. The overview and key points are concise explanations of the study.