A method that integrates the motif difference field (MDF) with an improved EfficientNet was proposed for gearbox fault diagnosis to address the difficulty of diagnosing gearbox faults under complex operating conditions. Firstly, the original fault feature signal was transformed from one-dimensional data into a two-dimensional feature image by using the motif difference field. Then, the two-dimensional feature image was input into a neural network that was based on the EfficientNet framework. This network was further optimized by incorporating the coordinate attention (CA) mechanism, channel concatenation operations, channel shuffle operations, and group convolutions to enhance its feature extraction and expression capabilities, thereby improving the accuracy of gearbox fault diagnosis. In line with the experimental results, the proposed method is shown to be suitable for diagnosing gearbox faults under complex operating conditions, with a fault recognition accuracy being achieved of up to 98.9%. Moreover, the recognition accuracy can still be reached of over 90% even when Gaussian white noise with a signal-to-noise ratio of -10 dB is added.
FENG Peng-fan, HAO Ru-jiang, SHANG Teng-long, LOU Hai-yang, WANG Tian-chi, YAO Bo-yu.
Gearbox Fault Diagnosis Based on MDF and Improved EfficientNet[J].
Science Technology and Engineering, 2026, 26(3): 1038-1045 DOI:10.12404/j.issn.1671-1815.2501240
DengFeiyue, WangHongli, GaoRuiyang, et al. Characteristic analysis of vibration characteristics of axlebox bearing inner ring failure under wheel track excitation[J]. Journal of Hebei University (Natural Science Edition), 2023, 43(6): 561-570.
WangYangyang, TangJian, DaiJuying, et al. A rolling bearing fault diagnosis method based on 1DCNN[J]. Machinery Management Development, 2019, 34(10): 141-144, 159.
HanZhengjie, NiuRongjun, MaZikui, et al. Improved residual neural network based on attention mechanism for bearing fault diagnosis[J]. Vibration and Shock, 2023, 42(16): 82-91.
ZhengXincheng, HaoRujiang, YaoBoyu, et al. Optimisation of sin geometry modal decomposition and improved ResNeXt neural network for gearbox fault diagnosis[J]. Science Technology and Engineering, 2025, 25(7): 2792-2799.
ZhangLifeng, WangZhi. Flow characterisation and flow pattern identification of two-phase flow based on recurrence diagrams[J]. Journal of Metrology, 2022, 43(11): 1438-1444.
[13]
SunW. Markov transition field enhanced deep domain adaptation network for milling tool condition monitoring[J]. Micromachines, 2022, 13(6): 873.
[14]
ZhangY, GanF, ChenX. Motif difference field:an effective image-based time series classification and applications in machine malfunction detection[C]//2020 IEEE 4th Conference on Energy Internet and Energy System Integration (EI2). New York: IEEE, 2020: 3079-3083.
[15]
HouQ, ZhouD, FengJ. Coordinate attention for efficient mobile network design[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2021: 13713-13722.
[16]
KrizhevskyA, SutskeverI, HintonG E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[17]
ZhangX, ZhouX, LinM, et al. Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 6848-6856.
DengFeiyue, LüHaoyang, GuXiaohui, et al. Fault diagnosis method of axlebox bearings in high-speed locomotives based on lightweight neural network Shuffle-SENet[J]. Journal of Jilin University(Engineering Edition), 2022, 52(2): 474-482.
[20]
TanM, LeQ. Efficientnet: rethinking model scaling for convolutional neural networks[C]// International Conference on Machine Learning. New York: PMLR, 2019: 6105-6114.
[21]
ZhangX, ZhouX, LinM, et al. Shufflenet: an extremely efficient convolutional neural network for mobile devices[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. New York: IEEE, 2018: 6848-6856.