What question did this study set out to answer?

The study aims to develop a robust framework for remaining useful life prediction of rolling bearings by constructing noise-resistant health indicators and enabling threshold-free detection of initial degradation.

September 18, 2026Quality and Reliability Engineering International

Autoregressive Semi‐Connected Autoencoder for Remaining Useful Life Prediction of Rolling Bearings With Threshold‐Free First Prediction Time Detection

View Full Paper

Ask AI

Bookmark

Authors

JPJiachen PangMinzu University of China THTian HanUniversity of Science and Technology Beijing WWWeizhong WangBeijing Institute of Petrochemical Technology

Discussion

Member takes

Implication

Experimental study demonstrates accurate remaining useful life estimation in rolling bearings, highlighting threshold-free degradation detection.

Key Points

The study aims to develop a robust framework for remaining useful life prediction of rolling bearings by constructing noise-resistant health indicators and enabling threshold-free detection of initial degradation.
Designed an Autoregressive Semi-Connected Autoencoder (ARSCAE) featuring a sparsified encoder with a lower-triangular weight mask to enforce temporal causality and autoregressive smoothing regularization.
Utilized the unilateral inhibition property of the ReLU activation function to keep the health indicator at zero during normal states and positive upon degradation for adaptive first prediction time detection.
Employed a gated recurrent unit (GRU) network to map health indicator sequences to remaining useful life, evaluating performance on the benchmark XJTU-SY dataset and a custom high-temperature dataset.
ARSCAE generated health indicators with superior monotonicity and trendability compared to traditional methods.
The framework achieved state-of-the-art precision in remaining useful life prediction across standard and high-temperature operating conditions.

Cite This Study

Pang et al. (2026) studied this question.

synapsesocial.com/papers/6aad0bb6de0393d728b8a1a4 https://doi.org/10.1002/qre.70396

View Full Paper

Ask AI

Bookmark

Implication

Experimental study demonstrates accurate remaining useful life estimation in rolling bearings, highlighting threshold-free degradation detection.

Autoregressive Semi‐Connected Autoencoder for Remaining Useful Life Prediction of Rolling Bearings With Threshold‐Free First Prediction Time Detection

Discussion

Member takes

Implication

Key Points

Cite This Study

Autoregressive Semi‐Connected Autoencoder for Remaining Useful Life Prediction of Rolling Bearings With Threshold‐Free First Prediction Time Detection

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider