HFDF-EffNetV2: A Lightweight, Noise-Robust Model for Fault Diagnosis in Rolling Bearings
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Fault Detection and Control Systems · Gear and Bearing Dynamics Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Advanced Manufacturing and Automation Technology (Guilin University of Technology), Education Department of Guangxi Zhuang Autonomous Region, Guilin 541006, China
Guangxi Engineering Research Center of Intelligent Rubber Equipment, Guilin University of Technology, Guilin 541006, China
Funding
Guangxi Key Research and Development Program Project
References (45)
Show source-provided references
1. Deep Transfer Learning for Bearing Fault Diagnosis: A Systematic Review Since 2016
2. Unsupervised cross-domain rolling bearing fault diagnosis based on time-frequency information fusion10.1016/j.jfranklin.2022.11.004 ↗
3. BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration10.1109/TIM.2023.3346517 ↗
4. MgNet: A fault diagnosis approach for multi-bearing system based on auxiliary bearing and multi-granularity information fusion10.1016/j.ymssp.2023.110253 ↗
5. Product envelope spectrum optimization-gram: An enhanced envelope analysis for rolling bearing fault diagnosis10.1016/j.ymssp.2023.110270 ↗
6. Review of research on signal decomposition and fault diagnosis of rolling bearing based on vibration signal10.1088/1361-6501/ad4eff ↗
7. Feature Mode Decomposition: New Decomposition Theory for Rotating Machinery Fault Diagnosis10.1109/TIE.2022.3156156 ↗
8. Cheng, Z., Yang, Y., Hu, N., Cheng, Z., and Cheng, J. (2024). All time-scale decomposition method and its application in gear fault diagnosis. Struct. Health Monit., 14759217241289873.10.1177/14759217241289873 ↗
9. Zheng, X., Cheng, Z., Cheng, J., Yang, Y., and Yang, X. (2025). Blaschke mode decomposition: Algorithm and application. Struct. Health Monit., 14759217241310576.10.1177/14759217241310576 ↗
10. A high-accuracy intelligent fault diagnosis method for aero-engine bearings with limited samples10.1016/j.compind.2024.104099 ↗
11. Adaptive Multiscale Convolution Manifold Embedding Networks for Intelligent Fault Diagnosis of Servo Motor-Cylindrical Rolling Bearing Under Variable Working Conditions10.1109/TMECH.2023.3314215 ↗
12. Model-Assisted Multi-source Fusion Hypergraph Convolutional Neural Networks for intelligent few-shot fault diagnosis to Electro-Hydrostatic Actuator10.1016/j.inffus.2023.102186 ↗
13. WCNN-RSN: A novel fault diagnosis method for rolling bearing using multimodal feature fusion10.1088/1361-6501/ad7e48 ↗
14. MT-ConvFormer: A Multitask Bearing Fault Diagnosis Method Using a Combination of CNN and Transformer10.1109/TIM.2024.3502821 ↗
15. Song, Q., Wang, J., Song, Q., Li, K., Hao, W., and Jiang, H. (2024). Fault diagnosis of HVCB via the subtraction average based optimizer algorithm optimized multi channel CNN-SABO-SVM network. Sci. Rep., 14.10.1038/s41598-024-80954-6 ↗
16. A Lightweight Rolling Bearing Fault Diagnosis Method Based on Multiscale Depth-Wise Separable Convolutions and Network Pruning10.1109/ACCESS.2024.3441232 ↗
17. A Lightweight Network With Adaptive Input and Adaptive Channel Pruning Strategy for Bearing Fault Diagnosis
18. Fan Fault Diagnosis Based on Lightweight Multiscale Multiattention Feature Fusion Network
19. Lightweight CNN Architecture Design Based on Spatial–Temporal Tensor and Its Application in Bearing Fault Diagnosis
20. Teta, A., Korich, B., Bakria, D., Hadroug, N., Rabehi, A., Alsharef, M., Bajaj, M., Zaitsev, I., and Ghoneim, S.S.M. (2024). Fault detection and diagnosis of grid-connected photovoltaic systems using energy valley optimizer based lightweight CNN and wavelet transform. Sci. Rep., 14.10.1038/s41598-024-69890-7 ↗
21. Neural-transformer: A brain-inspired lightweight mechanical fault diagnosis method under noise10.1016/j.ress.2024.110409 ↗
22. Lightweight pyramid attention residual network for intelligent fault diagnosis of machine under sharp speed variation10.1016/j.ymssp.2024.111824 ↗
23. Shin, J., and Lee, S. (2023). Robust and lightweight deep learning model for industrial fault diagnosis in low-quality and noisy data. Electronics, 12.10.3390/electronics12020409 ↗
24. FRFconv-TDSNet: Lightweight, Noise-Robust Convolutional Neural Network Leveraging Full-Receptive-Field Convolution and Time-Domain Statistics for Intelligent Machine Fault Diagnosis10.1109/TIM.2024.3450065 ↗
25. A Novel Lightweight Rotating Mechanical Fault Diagnosis Framework With Adaptive Residual Enhancement and Multigroup Coordinate Attention
26. DPCCNN: A new lightweight fault diagnosis model for small samples and high noise problem10.1016/j.neucom.2025.129526 ↗
27. A novel approach for bearings multiclass fault diagnosis fusing multiscale deep convolution and hybrid attention networks10.1088/1361-6501/ad1c47 ↗
28. Wavelet transform for rotary machine fault diagnosis: 10 years revisited10.1016/j.ymssp.2023.110545 ↗
29. Duta, I.C., Liu, L., Zhu, F., and Shao, L. (2020). Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition. arXiv.
30. Haase, D., and Amthor, M. (2020). Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets. arXiv.10.1109/CVPR42600.2020.01461 ↗
31. Mixed local channel attention for object detection10.1016/j.engappai.2023.106442 ↗
32. Gao, S., He, J., Pan, H., and Gong, T. (2022). A multi-scale and lightweight bearing fault diagnosis model with small samples. Symmetry, 14.10.3390/sym14050909 ↗
33. Xie, F., Li, G., Song, C., and Song, M. (2023). The Early Diagnosis of Rolling Bearings’ Faults Using Fractional Fourier Transform Information Fusion and a Lightweight Neural Network. Fractal and Fractional, 7.10.3390/fractalfract7120875 ↗
34. Multi-sensor fusion rolling bearing intelligent fault diagnosis based on VMD and ultra-lightweight GoogLeNet in industrial environments10.1016/j.dsp.2023.104306 ↗
35. Tan, M., and Le, Q. (2021). Efficientnetv2: Smaller Models and Faster Training. arXiv.
36. Misra, D. (2019). Mish: A Self Regularized Non-Monotonic Activation Function. arXiv.
37. Chen, J., Wang, P., Liu, J., and Qian, Y. (2022, January 18–24). Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00481 ↗
38. Müller, R., Kornblith, S., and Hinton, G.E. (2019). When Does Label Smoothing Help?. arXiv.
39. Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Dollr, P. (2017). Focal Loss for Dense Object Detection. arXiv.10.1109/ICCV.2017.324 ↗
40. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study10.1016/j.ymssp.2015.04.021 ↗
41. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
42. Wang, A., Chen, H., Lin, Z., Han, J., and Ding, G. (2024, January 16–22). Repvit: Revisiting Mobile CNN From ViT Perspective. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.01506 ↗
43. Iandola, F.N., Han, S., Moskewicz, M.W., Ashraf, K., Dally, W.J., and Keutzer, K. (2016). SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size. arXiv.
44. MPNet: A lightweight fault diagnosis network for rotating machinery10.1016/j.measurement.2024.115498 ↗
45. Howard, A., Sandler, M., Chu, G., Chen, L.-C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., and Vasudevan, V. (November, January 27). Searching for Mobilenetv3. Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Republic of Korea.10.1109/ICCV.2019.00140 ↗