A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention Transformer

Bearings are essential rotational components that enable mechanical equipment to operate effectively. In real-world industrial environments, bearings are subjected to high temperatures and loads, making failure prediction and health management critical for ensuring stable equipment operations and sa...

Full description

Saved in:
Bibliographic Details
Main Authors: Li Zhang, Ying Zhang, Hao Luo, Tongli Ren, Hongsheng Li
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Actuators
Subjects:
Online Access:https://www.mdpi.com/2076-0825/14/5/255
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327709574922240
author Li Zhang
Ying Zhang
Hao Luo
Tongli Ren
Hongsheng Li
author_facet Li Zhang
Ying Zhang
Hao Luo
Tongli Ren
Hongsheng Li
author_sort Li Zhang
collection DOAJ
description Bearings are essential rotational components that enable mechanical equipment to operate effectively. In real-world industrial environments, bearings are subjected to high temperatures and loads, making failure prediction and health management critical for ensuring stable equipment operations and safeguarding both personnel and property. To address long-tail defect identification, we propose a coupled time–frequency attention model that accounts for the long-tail distribution and pervasive noise present in production environments. The model efficiently learns amplitude and phase information by first converting the time-domain signal into the frequency domain with the Fast Fourier Transform (FFT) and then processing the data using a real–imaginary attention mechanism. To capture dependencies in long sequences, a multi-head self-attention mechanism is then implemented in the time domain. Furthermore, the model’s ability to fully learn features is enhanced through the linear coupling of time–frequency domain attention, which effectively mitigates noise interference and corrects imbalances in data distribution. The performance of the proposed model is compared with that of advanced models under the conditions of imbalanced label distribution, cross-load, and noise interference, proving its superiority. The model is evaluated using the Case Western Reserve University (CWRU) and laboratory bearing datasets.
format Article
id doaj-art-3eb3ef24541f488eb9276be0a0a58d32
institution Kabale University
issn 2076-0825
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Actuators
spelling doaj-art-3eb3ef24541f488eb9276be0a0a58d322025-08-20T03:47:48ZengMDPI AGActuators2076-08252025-05-0114525510.3390/act14050255A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention TransformerLi Zhang0Ying Zhang1Hao Luo2Tongli Ren3Hongsheng Li4College of Information, Liaoning University, Shenyang 110036, ChinaCollege of Information, Liaoning University, Shenyang 110036, ChinaCollege of Information, Liaoning University, Shenyang 110036, ChinaCollege of Information, Liaoning University, Shenyang 110036, ChinaCollege of Information, Liaoning University, Shenyang 110036, ChinaBearings are essential rotational components that enable mechanical equipment to operate effectively. In real-world industrial environments, bearings are subjected to high temperatures and loads, making failure prediction and health management critical for ensuring stable equipment operations and safeguarding both personnel and property. To address long-tail defect identification, we propose a coupled time–frequency attention model that accounts for the long-tail distribution and pervasive noise present in production environments. The model efficiently learns amplitude and phase information by first converting the time-domain signal into the frequency domain with the Fast Fourier Transform (FFT) and then processing the data using a real–imaginary attention mechanism. To capture dependencies in long sequences, a multi-head self-attention mechanism is then implemented in the time domain. Furthermore, the model’s ability to fully learn features is enhanced through the linear coupling of time–frequency domain attention, which effectively mitigates noise interference and corrects imbalances in data distribution. The performance of the proposed model is compared with that of advanced models under the conditions of imbalanced label distribution, cross-load, and noise interference, proving its superiority. The model is evaluated using the Case Western Reserve University (CWRU) and laboratory bearing datasets.https://www.mdpi.com/2076-0825/14/5/255bearing fault diagnosislong-tail distributioncoupling time–frequency attentionreal–imaginary attention
spellingShingle Li Zhang
Ying Zhang
Hao Luo
Tongli Ren
Hongsheng Li
A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention Transformer
Actuators
bearing fault diagnosis
long-tail distribution
coupling time–frequency attention
real–imaginary attention
title A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention Transformer
title_full A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention Transformer
title_fullStr A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention Transformer
title_full_unstemmed A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention Transformer
title_short A Long-Tail Fault Diagnosis Method Based on a Coupled Time–Frequency Attention Transformer
title_sort long tail fault diagnosis method based on a coupled time frequency attention transformer
topic bearing fault diagnosis
long-tail distribution
coupling time–frequency attention
real–imaginary attention
url https://www.mdpi.com/2076-0825/14/5/255
work_keys_str_mv AT lizhang alongtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT yingzhang alongtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT haoluo alongtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT tongliren alongtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT hongshengli alongtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT lizhang longtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT yingzhang longtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT haoluo longtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT tongliren longtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer
AT hongshengli longtailfaultdiagnosismethodbasedonacoupledtimefrequencyattentiontransformer