Research on fault diagnosis of rolling bearing based on MTA-LNN

To address the issue of rolling bearing vibration signals being obscured by noise, leading to unclear fault characteristics and low fault diagnosis accuracy, a rolling bearing fault diagnosis method based on the Multi-scale Temporal Attention Liquid Neural Network (MTA-LNN) optimized by multi-scale temporal attention mechanism is proposed. Firstly, the original vibration signals are constructed into multi-scale time series samples through different scale windows. Secondly, the temporal attention mechanism is introduced to perform adaptive weighting on fault signal features at different scales. Finally, the liquid neural network is introduced to construct a fault diagnosis model to achieve the fault diagnosis task. Experimental results show that the liquid neural network optimized by the multi-scale attention mechanism can still achieve a high fault diagnosis rate under complex working conditions, with a fault diagnosis accuracy of up to 98.99%.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-15
DOI
https://doi.org/10.1038/s41598-026-79950-9
Primary Topic
Machine Fault Diagnosis Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Research on fault diagnosis of rolling bearing based on MTA-LNN

Y. B. Liu, Weinan Zheng, Yuehui Wang, Ying Du et al.
Scientific Reports
Machine Fault Diagnosis Techniques
article

Research on fault diagnosis of rolling bearing based on MTA-LNN

Y. B. Liu, Weinan Zheng, Yuehui Wang, Ying Du, Jian Jin, Chunyu Liu, Junliang Sha, Miao Yu
article en

Abstract

To address the issue of rolling bearing vibration signals being obscured by noise, leading to unclear fault characteristics and low fault diagnosis accuracy, a rolling bearing fault diagnosis method based on the Multi-scale Temporal Attention Liquid Neural Network (MTA-LNN) optimized by multi-scale temporal attention mechanism is proposed. Firstly, the original vibration signals are constructed into multi-scale time series samples through different scale windows. Secondly, the temporal attention mechanism is introduced to perform adaptive weighting on fault signal features at different scales. Finally, the liquid neural network is introduced to construct a fault diagnosis model to achieve the fault diagnosis task. Experimental results show that the liquid neural network optimized by the multi-scale attention mechanism can still achieve a high fault diagnosis rate under complex working conditions, with a fault diagnosis accuracy of up to 98.99%.

Scientific Reports
Jilin University of Architecture and Technology (CN)
Machine Fault Diagnosis Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon