Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention Mechanism

Gearbox condition monitoring is essential for ensuring the reliability of power transmission systems. However, the existing methods are constrained by shallow feature extraction and unidirectional temporal modeling. To address these limitations, this study proposes a novel fault diagnosis framework...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoteng Ma, Kejia Zhai, Nana Luo, Yehui Zhao, Guangming Wang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/10/2978
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850256422096338944
author Xiaoteng Ma
Kejia Zhai
Nana Luo
Yehui Zhao
Guangming Wang
author_facet Xiaoteng Ma
Kejia Zhai
Nana Luo
Yehui Zhao
Guangming Wang
author_sort Xiaoteng Ma
collection DOAJ
description Gearbox condition monitoring is essential for ensuring the reliability of power transmission systems. However, the existing methods are constrained by shallow feature extraction and unidirectional temporal modeling. To address these limitations, this study proposes a novel fault diagnosis framework that integrates multiscale depthwise separable convolution, bidirectional gated recurrent units, and a squeeze-and-excitation attention mechanism. This approach enables multiscale feature extraction from vibration signals, bidirectional temporal modeling, and the enhancement of critical fault-related information. The experimental results demonstrate that the proposed method significantly outperforms conventional models in terms of fault diagnosis accuracy, noise robustness, and adaptability to varying operating conditions. The attention mechanism effectively suppresses noise interference, while bidirectional temporal modeling accurately captures fault propagation characteristics, thereby improving adaptability to dynamic conditions. This research provides a highly robust solution for intelligent gearbox fault diagnosis in complex industrial environments.
format Article
id doaj-art-2cf2d66db84b446399677dea7ba742ba
institution OA Journals
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-2cf2d66db84b446399677dea7ba742ba2025-08-20T01:56:39ZengMDPI AGSensors1424-82202025-05-012510297810.3390/s25102978Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention MechanismXiaoteng Ma0Kejia Zhai1Nana Luo2Yehui Zhao3Guangming Wang4College of Information Science and Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Information Science and Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaCollege of Engineering, Ocean University of China, Qingdao 266404, ChinaCollege of Mechanical and Electronic Engineering, Shandong Agricultural University, Taian 271018, ChinaGearbox condition monitoring is essential for ensuring the reliability of power transmission systems. However, the existing methods are constrained by shallow feature extraction and unidirectional temporal modeling. To address these limitations, this study proposes a novel fault diagnosis framework that integrates multiscale depthwise separable convolution, bidirectional gated recurrent units, and a squeeze-and-excitation attention mechanism. This approach enables multiscale feature extraction from vibration signals, bidirectional temporal modeling, and the enhancement of critical fault-related information. The experimental results demonstrate that the proposed method significantly outperforms conventional models in terms of fault diagnosis accuracy, noise robustness, and adaptability to varying operating conditions. The attention mechanism effectively suppresses noise interference, while bidirectional temporal modeling accurately captures fault propagation characteristics, thereby improving adaptability to dynamic conditions. This research provides a highly robust solution for intelligent gearbox fault diagnosis in complex industrial environments.https://www.mdpi.com/1424-8220/25/10/2978gearboxfault diagnosisconvolutional neural networkgated recurrent unitattention mechanism
spellingShingle Xiaoteng Ma
Kejia Zhai
Nana Luo
Yehui Zhao
Guangming Wang
Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention Mechanism
Sensors
gearbox
fault diagnosis
convolutional neural network
gated recurrent unit
attention mechanism
title Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention Mechanism
title_full Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention Mechanism
title_fullStr Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention Mechanism
title_full_unstemmed Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention Mechanism
title_short Gearbox Fault Diagnosis Under Noise and Variable Operating Conditions Using Multiscale Depthwise Separable Convolution and Bidirectional Gated Recurrent Unit with a Squeeze-and-Excitation Attention Mechanism
title_sort gearbox fault diagnosis under noise and variable operating conditions using multiscale depthwise separable convolution and bidirectional gated recurrent unit with a squeeze and excitation attention mechanism
topic gearbox
fault diagnosis
convolutional neural network
gated recurrent unit
attention mechanism
url https://www.mdpi.com/1424-8220/25/10/2978
work_keys_str_mv AT xiaotengma gearboxfaultdiagnosisundernoiseandvariableoperatingconditionsusingmultiscaledepthwiseseparableconvolutionandbidirectionalgatedrecurrentunitwithasqueezeandexcitationattentionmechanism
AT kejiazhai gearboxfaultdiagnosisundernoiseandvariableoperatingconditionsusingmultiscaledepthwiseseparableconvolutionandbidirectionalgatedrecurrentunitwithasqueezeandexcitationattentionmechanism
AT nanaluo gearboxfaultdiagnosisundernoiseandvariableoperatingconditionsusingmultiscaledepthwiseseparableconvolutionandbidirectionalgatedrecurrentunitwithasqueezeandexcitationattentionmechanism
AT yehuizhao gearboxfaultdiagnosisundernoiseandvariableoperatingconditionsusingmultiscaledepthwiseseparableconvolutionandbidirectionalgatedrecurrentunitwithasqueezeandexcitationattentionmechanism
AT guangmingwang gearboxfaultdiagnosisundernoiseandvariableoperatingconditionsusingmultiscaledepthwiseseparableconvolutionandbidirectionalgatedrecurrentunitwithasqueezeandexcitationattentionmechanism