HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings

In rolling bearing intelligent fault diagnosis (FD), lightweight models are constrained by issues such as noise interference and the scarcity of fault data, making it challenging to achieve real-time, high-accuracy diagnosis on resource-limited devices. To address these challenges, this study propos...

Full description

Saved in:
Bibliographic Details
Main Authors: Donglei Zhang, Jiafang Pan, Tianping Huang, Junlin Niu, Faguo Huang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4902
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155750621446144
author Donglei Zhang
Jiafang Pan
Tianping Huang
Junlin Niu
Faguo Huang
author_facet Donglei Zhang
Jiafang Pan
Tianping Huang
Junlin Niu
Faguo Huang
author_sort Donglei Zhang
collection DOAJ
description In rolling bearing intelligent fault diagnosis (FD), lightweight models are constrained by issues such as noise interference and the scarcity of fault data, making it challenging to achieve real-time, high-accuracy diagnosis on resource-limited devices. To address these challenges, this study proposes a lightweight model that combines the hierarchical fine-grained decision fusion (HFDF) strategy with an improved EfficientNetV2 architecture (HFDF-EffNetV2). The model optimizes depth and width multiplicity factors to enhance parameter utilization efficiency. It uses pyramidal convolution (PyConv) combined with Fused-MBConv (Fused-MBPyConv) to obtain multi-scale time-frequency information. Additionally, an enhanced MBConv, termed BSMB-Conv-MLCA, integrates subspace blueprint separable convolution (BSConv-S) with mixed local channel attention (MLCA) extract deep-grained fault features. The HFDF strategy outputs confidence in stages and updates weights to prevent the model from falling into local overfitting when handling confusable samples. Experimental results on Case 1 and Case 2 show that HFDF-EffNetV2 achieved 100% accuracy with diagnostic times of 18.67 millisecond (ms) and 17.56 ms, respectively, and 1.85 million (M) parameters. Under noisy conditions, average accuracies reached 98.19% and 85.68%, respectively. Additionally, the model performed well with small samples, yielding accuracies of 98.69% and 97.51%. These results highlight its superior robustness to noise and lightweight performance compared with other advanced models.
format Article
id doaj-art-0b7c8a2803ed444ba19e674b94266def
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-0b7c8a2803ed444ba19e674b94266def2025-08-20T02:24:47ZengMDPI AGApplied Sciences2076-34172025-04-01159490210.3390/app15094902HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling BearingsDonglei Zhang0Jiafang Pan1Tianping Huang2Junlin Niu3Faguo Huang4Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, ChinaKey Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, ChinaKey Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, ChinaKey Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, ChinaKey Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, ChinaIn rolling bearing intelligent fault diagnosis (FD), lightweight models are constrained by issues such as noise interference and the scarcity of fault data, making it challenging to achieve real-time, high-accuracy diagnosis on resource-limited devices. To address these challenges, this study proposes a lightweight model that combines the hierarchical fine-grained decision fusion (HFDF) strategy with an improved EfficientNetV2 architecture (HFDF-EffNetV2). The model optimizes depth and width multiplicity factors to enhance parameter utilization efficiency. It uses pyramidal convolution (PyConv) combined with Fused-MBConv (Fused-MBPyConv) to obtain multi-scale time-frequency information. Additionally, an enhanced MBConv, termed BSMB-Conv-MLCA, integrates subspace blueprint separable convolution (BSConv-S) with mixed local channel attention (MLCA) extract deep-grained fault features. The HFDF strategy outputs confidence in stages and updates weights to prevent the model from falling into local overfitting when handling confusable samples. Experimental results on Case 1 and Case 2 show that HFDF-EffNetV2 achieved 100% accuracy with diagnostic times of 18.67 millisecond (ms) and 17.56 ms, respectively, and 1.85 million (M) parameters. Under noisy conditions, average accuracies reached 98.19% and 85.68%, respectively. Additionally, the model performed well with small samples, yielding accuracies of 98.69% and 97.51%. These results highlight its superior robustness to noise and lightweight performance compared with other advanced models.https://www.mdpi.com/2076-3417/15/9/4902fault diagnosislightweightEfficientNetV2robustness
spellingShingle Donglei Zhang
Jiafang Pan
Tianping Huang
Junlin Niu
Faguo Huang
HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings
Applied Sciences
fault diagnosis
lightweight
EfficientNetV2
robustness
title HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings
title_full HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings
title_fullStr HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings
title_full_unstemmed HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings
title_short HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings
title_sort hfdf effnetv2 a lightweight noise robust model for fault diagnosis in rolling bearings
topic fault diagnosis
lightweight
EfficientNetV2
robustness
url https://www.mdpi.com/2076-3417/15/9/4902
work_keys_str_mv AT dongleizhang hfdfeffnetv2alightweightnoiserobustmodelforfaultdiagnosisinrollingbearings
AT jiafangpan hfdfeffnetv2alightweightnoiserobustmodelforfaultdiagnosisinrollingbearings
AT tianpinghuang hfdfeffnetv2alightweightnoiserobustmodelforfaultdiagnosisinrollingbearings
AT junlinniu hfdfeffnetv2alightweightnoiserobustmodelforfaultdiagnosisinrollingbearings
AT faguohuang hfdfeffnetv2alightweightnoiserobustmodelforfaultdiagnosisinrollingbearings