Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small Samples

Fault diagnosis is of great significance for the maintenance of rotating machinery. Deep learning is an intelligent diagnostic technique that is receiving increasing attention. To address the issues of industrial data with small samples and varying working conditions, a residual convolutional neural...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanlong Xu, Liming Zhang, Ling Chen, Tian Tan, Xiaolong Wang, Hongguang Xiao
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4772
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239809158021120
author Yanlong Xu
Liming Zhang
Ling Chen
Tian Tan
Xiaolong Wang
Hongguang Xiao
author_facet Yanlong Xu
Liming Zhang
Ling Chen
Tian Tan
Xiaolong Wang
Hongguang Xiao
author_sort Yanlong Xu
collection DOAJ
description Fault diagnosis is of great significance for the maintenance of rotating machinery. Deep learning is an intelligent diagnostic technique that is receiving increasing attention. To address the issues of industrial data with small samples and varying working conditions, a residual convolutional neural network based on the attention mechanism is put forward for the fault diagnosis of rotating machinery. The method incorporates channel attention and spatial attention simultaneously, implementing channel-wise recalibration for frequency-dependent feature adjustment and performing spatial context aggregation across receptive fields. Subsequently, a residual module is introduced to address the vanishing gradient problem of the model in deep network structures. In addition, LSTM is used to realize spatiotemporal feature fusion. Finally, label smoothing regularization (LSR) is proposed to balance the distributional disparities among labeled samples. The effectiveness of the method is evaluated by its application to the vibration signal data from the safe injection pump and the Case Western Reserve University (CWRU). The results show that the method has superb diagnostic accuracy and strong robustness.
format Article
id doaj-art-4b16f98e8c534be49d2d6a430745fc33
institution Kabale University
issn 1424-8220
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-4b16f98e8c534be49d2d6a430745fc332025-08-20T04:00:50ZengMDPI AGSensors1424-82202025-08-012515477210.3390/s25154772Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small SamplesYanlong Xu0Liming Zhang1Ling Chen2Tian Tan3Xiaolong Wang4Hongguang Xiao5School of Nuclear Science and Technology, Naval University of Engineering, Wuhan 430033, ChinaSchool of Nuclear Science and Technology, Naval University of Engineering, Wuhan 430033, ChinaSchool of Nuclear Science and Technology, Naval University of Engineering, Wuhan 430033, ChinaSchool of Nuclear Science and Technology, Naval University of Engineering, Wuhan 430033, ChinaSchool of Nuclear Science and Technology, Naval University of Engineering, Wuhan 430033, ChinaSchool of Nuclear Science and Technology, Naval University of Engineering, Wuhan 430033, ChinaFault diagnosis is of great significance for the maintenance of rotating machinery. Deep learning is an intelligent diagnostic technique that is receiving increasing attention. To address the issues of industrial data with small samples and varying working conditions, a residual convolutional neural network based on the attention mechanism is put forward for the fault diagnosis of rotating machinery. The method incorporates channel attention and spatial attention simultaneously, implementing channel-wise recalibration for frequency-dependent feature adjustment and performing spatial context aggregation across receptive fields. Subsequently, a residual module is introduced to address the vanishing gradient problem of the model in deep network structures. In addition, LSTM is used to realize spatiotemporal feature fusion. Finally, label smoothing regularization (LSR) is proposed to balance the distributional disparities among labeled samples. The effectiveness of the method is evaluated by its application to the vibration signal data from the safe injection pump and the Case Western Reserve University (CWRU). The results show that the method has superb diagnostic accuracy and strong robustness.https://www.mdpi.com/1424-8220/25/15/4772fault diagnosisattention mechanismresidual modulelabel smoothing regularizationconvolutional neural networksmall samples
spellingShingle Yanlong Xu
Liming Zhang
Ling Chen
Tian Tan
Xiaolong Wang
Hongguang Xiao
Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small Samples
Sensors
fault diagnosis
attention mechanism
residual module
label smoothing regularization
convolutional neural network
small samples
title Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small Samples
title_full Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small Samples
title_fullStr Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small Samples
title_full_unstemmed Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small Samples
title_short Attention-Guided Residual Spatiotemporal Network with Label Regularization for Fault Diagnosis with Small Samples
title_sort attention guided residual spatiotemporal network with label regularization for fault diagnosis with small samples
topic fault diagnosis
attention mechanism
residual module
label smoothing regularization
convolutional neural network
small samples
url https://www.mdpi.com/1424-8220/25/15/4772
work_keys_str_mv AT yanlongxu attentionguidedresidualspatiotemporalnetworkwithlabelregularizationforfaultdiagnosiswithsmallsamples
AT limingzhang attentionguidedresidualspatiotemporalnetworkwithlabelregularizationforfaultdiagnosiswithsmallsamples
AT lingchen attentionguidedresidualspatiotemporalnetworkwithlabelregularizationforfaultdiagnosiswithsmallsamples
AT tiantan attentionguidedresidualspatiotemporalnetworkwithlabelregularizationforfaultdiagnosiswithsmallsamples
AT xiaolongwang attentionguidedresidualspatiotemporalnetworkwithlabelregularizationforfaultdiagnosiswithsmallsamples
AT hongguangxiao attentionguidedresidualspatiotemporalnetworkwithlabelregularizationforfaultdiagnosiswithsmallsamples