RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samples

Abstract Convolutional Neural Networks, with their excellent capabilities for automatic feature discrimination and learning, have been widely applied in the field of mechanical fault diagnosis. However, in real-world operating environments, acquiring large amounts of fault data as training samples i...

Full description

Saved in:
Bibliographic Details
Main Authors: Sun Fenghao, Li Guofa, He Jialong, Liu Shaoyang
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02500-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849768654877491200
author Sun Fenghao
Li Guofa
He Jialong
Liu Shaoyang
author_facet Sun Fenghao
Li Guofa
He Jialong
Liu Shaoyang
author_sort Sun Fenghao
collection DOAJ
description Abstract Convolutional Neural Networks, with their excellent capabilities for automatic feature discrimination and learning, have been widely applied in the field of mechanical fault diagnosis. However, in real-world operating environments, acquiring large amounts of fault data as training samples is often challenging, which limits the applicability of traditional methods. To address this issue, this study proposes a frequency-adaptive fault diagnosis method for high-speed motors under small-sample scenarios. Specifically, this paper designs an innovative data augmentation technique that effectively expands the diversity and coverage of the training dataset and is seamlessly integrated into the fault diagnosis model. Furthermore, to enhance the richness of feature representations and strengthen information exchange between different feature channels, this paper proposes a frequency-adaptive convolutional layer (SCNET), which significantly optimizes the performance of Bidirectional Gated Recurrent Units (BiGRU) in fault feature extraction. Based on these technological improvements, we have constructed an efficient intelligent fault diagnosis model named RS-SCBiGRU. Experimental validation shows that, compared to various advanced fault diagnosis methods, the RS-SCBiGRU model achieves a significant improvement in accuracy and demonstrates stronger noise resistance capabilities.
format Article
id doaj-art-5d313d218fc44d3c9958b6c9bf010ba7
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-5d313d218fc44d3c9958b6c9bf010ba72025-08-20T03:03:42ZengNature PortfolioScientific Reports2045-23222025-07-0115111610.1038/s41598-025-02500-2RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samplesSun Fenghao0Li Guofa1He Jialong2Liu Shaoyang3Key Laboratory of CNC Equipment Reliability, Ministry of Education, Jilin UniversityKey Laboratory of CNC Equipment Reliability, Ministry of Education, Jilin UniversityKey Laboratory of CNC Equipment Reliability, Ministry of Education, Jilin UniversityKey Laboratory of CNC Equipment Reliability, Ministry of Education, Jilin UniversityAbstract Convolutional Neural Networks, with their excellent capabilities for automatic feature discrimination and learning, have been widely applied in the field of mechanical fault diagnosis. However, in real-world operating environments, acquiring large amounts of fault data as training samples is often challenging, which limits the applicability of traditional methods. To address this issue, this study proposes a frequency-adaptive fault diagnosis method for high-speed motors under small-sample scenarios. Specifically, this paper designs an innovative data augmentation technique that effectively expands the diversity and coverage of the training dataset and is seamlessly integrated into the fault diagnosis model. Furthermore, to enhance the richness of feature representations and strengthen information exchange between different feature channels, this paper proposes a frequency-adaptive convolutional layer (SCNET), which significantly optimizes the performance of Bidirectional Gated Recurrent Units (BiGRU) in fault feature extraction. Based on these technological improvements, we have constructed an efficient intelligent fault diagnosis model named RS-SCBiGRU. Experimental validation shows that, compared to various advanced fault diagnosis methods, the RS-SCBiGRU model achieves a significant improvement in accuracy and demonstrates stronger noise resistance capabilities.https://doi.org/10.1038/s41598-025-02500-2Fault diagnosisSmall sampleData augmentationSelf-calibrating convolutionBidirectional gated recurrent unit
spellingShingle Sun Fenghao
Li Guofa
He Jialong
Liu Shaoyang
RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samples
Scientific Reports
Fault diagnosis
Small sample
Data augmentation
Self-calibrating convolution
Bidirectional gated recurrent unit
title RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samples
title_full RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samples
title_fullStr RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samples
title_full_unstemmed RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samples
title_short RS-SCBiGRU: a noise-robust neural network for high-speed motor fault diagnosis with limited samples
title_sort rs scbigru a noise robust neural network for high speed motor fault diagnosis with limited samples
topic Fault diagnosis
Small sample
Data augmentation
Self-calibrating convolution
Bidirectional gated recurrent unit
url https://doi.org/10.1038/s41598-025-02500-2
work_keys_str_mv AT sunfenghao rsscbigruanoiserobustneuralnetworkforhighspeedmotorfaultdiagnosiswithlimitedsamples
AT liguofa rsscbigruanoiserobustneuralnetworkforhighspeedmotorfaultdiagnosiswithlimitedsamples
AT hejialong rsscbigruanoiserobustneuralnetworkforhighspeedmotorfaultdiagnosiswithlimitedsamples
AT liushaoyang rsscbigruanoiserobustneuralnetworkforhighspeedmotorfaultdiagnosiswithlimitedsamples