| Citation: | LI Heng, TANG Qian, CHEN Guowang, et al. Diagnosis of bearing and drive shaft faults in helicopter tail drive systems assisted by digital twin[J]. Journal of Aerospace Power, 2025, 40（6）：20230818 doi: 10.13224/j.cnki.jasp.20230818
|
Considering the problem of unbalanced fault data in the helicopter tail drive system, a fault diagnosis method of helicopter tail drive system based on digital twin and transfer learning was proposed. A rigid-flexible coupling dynamics simulation model of the helicopter tail drive system was established to obtain high-fidelity fault simulation data truly reflecting the operating state of the helicopter tail drive system. A residual network introducing coordinate separable convolution and attention mechanism was used for fault feature extraction and classification. The domain adaptive method based on Gaussian kernel function was used to reduce the distribution difference between simulation data and experimental data in the feature space. In order to improve the robustness of the decision boundary and enhance the differentiation between categories, the cross-entry loss with margin regularization was introduced. It was experimentally verified that the fault diagnosis method based on digital twin and transfer learning can address the issue of deteriorated training effect in deep learning fault diagnosis model caused by unbalanced data. This method significantly reduced model loss and improved model accuracy by at least 2.17%, reaching the performance level of the deep learning fault diagnosis model based on normal data.
| [1] |
HOANG D T,KANG H J. A survey on deep learning based bearing fault diagnosis[J]. Neurocomputing,2019,335(335): 327-335.
|
| [2] |
TANG S,YUAN S,ZHU Y. Deep learning-based intelligent fault diagnosis methods toward rotating machinery[J]. IEEE Access,2019,8: 9335-9346.
|
| [3] |
文成林,吕菲亚. 基于深度学习的故障诊断方法综述[J]. 电子与信息学报,2020,42(1): 234-248. WEN Chenglin,LYU Feiya. Review on deep learning based fault diagnosis[J]. Journal of Electronics & Information Technology,2020,42(1): 234-248. (in Chinese
WEN Chenglin, LYU Feiya. Review on deep learning based fault diagnosis[J]. Journal of Electronics & Information Technology, 2020, 42(1): 234-248. (in Chinese)
|
| [4] |
SUN M,QIAN H,ZHU K,et al. Ensemble learning and SMOTE based fault diagnosis system in self-organizing cellular networks[C]//GLOBECOM 2017-2017 IEEE Global Communications Conference. Piscataway,US: IEEE,2017: 1-6.
|
| [5] |
钟诗胜,李旭,张永健. 基于DBN的不均衡样本驱动民航发动机故障诊断[J]. 航空动力学报,2019,34(3): 708-716. ZHONG Shisheng,LI Xu,ZHANG Yongjian. Fault diagnosis of civil aero-engine driven by unbalanced samples based on DBN[J]. Journal of Aerospace Power,2019,34(3): 708-716. (in Chinese
ZHONG Shisheng, LI Xu, ZHANG Yongjian. Fault diagnosis of civil aero-engine driven by unbalanced samples based on DBN[J]. Journal of Aerospace Power, 2019, 34(3): 708-716. (in Chinese)
|
| [6] |
LIU S W,JIANG H,WU Z,et al. Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis[J]. Measurement,2021,168: 108371. doi: 10.1016/j.measurement.2020.108371
|
| [7] |
CHEN M,SHAO H,DOU H,et al. Data augmentation and intelligent fault diagnosis of planetary gearbox using ILoFGAN under extremely limited samples[J]. IEEE Transactions on Reliability,2023,72(3): 1029-1037. doi: 10.1109/TR.2022.3215243
|
| [8] |
YU Y,GUO L,GAO H,et al. PCWGAN-GP: a new method for imbalanced fault diagnosis of machines[J]. IEEE Transactions on Instrumentation and Measurement,2022,71: 3515711.
|
| [9] |
CUI Y,JIA M,LIN T Y,et al. Class-balanced loss based on effective number of samples[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway,US: IEEE,2019: 9260-9269.
|
| [10] |
FERNANDO K R M,TSOKOS C P. Dynamically weighted balanced loss: class imbalanced learning and confidence calibration of deep neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems,2022,33(7): 2940-2951. doi: 10.1109/TNNLS.2020.3047335
|
| [11] |
DUAN A,GUO L,GAO H,et al. Deep focus parallel convolutional neural network for imbalanced classification of machinery fault diagnostics[J]. IEEE Transactions on Instrumentation and Measurement,2020,69(11): 8680-8689. doi: 10.1109/TIM.2020.2998233
|
| [12] |
HOU R,CHEN J,FENG Y,et al. Contrastive-weighted self-supervised model for long-tailed data classification with vision transformer augmented[J]. Mechanical Systems and Signal Processing,2022,177: 109174. doi: 10.1016/j.ymssp.2022.109174
|
| [13] |
陈果,杨默晗,于平超. 基于深度学习的航空发动机不平衡故障部位识别[J]. 航空动力学报,2020,35(12): 2602-2615. CHEN Guo,YANG Mohan,YU Pingchao. Aero-engine unbalanced fault location identification method based on deep learning[J]. Journal of Aerospace Power,2020,35(12): 2602-2615. (in Chinese
CHEN Guo, YANG Mohan, YU Pingchao. Aero-engine unbalanced fault location identification method based on deep learning[J]. Journal of Aerospace Power, 2020, 35(12): 2602-2615. (in Chinese)
|
| [14] |
董绍江,朱朋,朱孙科,等. 基于仿真数据驱动和领域自适应的滚动轴承故障诊断方法[J]. 中国机械工程,2023,34(6): 694-702. DONG Shaojiang,ZHU Peng,ZHU Sunke,et al. Fault diagnosis method of rolling bearings based on simulation data drive and domain adaptation[J]. China Mechanical Engineering,2023,34(6): 694-702. (in Chinese
DONG Shaojiang, ZHU Peng, ZHU Sunke, et al. Fault diagnosis method of rolling bearings based on simulation data drive and domain adaptation[J]. China Mechanical Engineering, 2023, 34(6): 694-702. (in Chinese)
|
| [15] |
ZHANG Qinglei,HE Qunshan,QIN Jiyun,et al. Application of fault diagnosis method combining finite element method and transfer learning for insufficient turbine rotor fault samples[J]. Entropy,2023,25(3): 414. doi: 10.3390/e25030414
|
| [16] |
陈书辉. 基于仿真数据与深度迁移学习的液压泵故障诊断研究[D]. 武汉: 华中科技大学,2021. CHEN Shuhui. Research on fault diagnosis of hydraulic pump based on simulation data and deep transfer learning[D]. Wuhan: Huazhong University of Science and Technology,2021. (in Chinese
CHEN Shuhui. Research on fault diagnosis of hydraulic pump based on simulation data and deep transfer learning[D]. Wuhan: Huazhong University of Science and Technology, 2021. (in Chinese)
|
| [17] |
SHEN Y,ZHONG X,SHAO H,et al. Digital twin-assisted imbalanced fault diagnosis framework using subdomain adaptive mechanism and margin-aware regularization[J]. Reliability Engineering & System Safety,2023,239: 109522.
|
| [18] |
LIU R,LEHMAN J,MOLINO P,et al. An intriguing failing of convolutional neural networks and the CoordConv solution[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. New York: ACM,2018: 9628-9639.
|
| [19] |
LU G,ZHANG W,WANG Z. Optimizing depthwise separable convolution operations on GPUs[J]. IEEE Transactions on Parallel and Distributed Systems,2022,33(1): 70-87. doi: 10.1109/TPDS.2021.3084813
|
| [20] |
YE R,WANG W,REN Y,et al. Bearing fault detection based on convolutional self-attention mechanism[C]//2020 IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT). Piscataway,US: IEEE,2020: 869-873.
|
| [21] |
ZHONG H,LYU Y,YUAN R,et al. Bearing fault diagnosis using transfer learning and self-attention ensemble lightweight convolutional neural network[J]. Neurocomputing,2022,501: 765-777. doi: 10.1016/j.neucom.2022.06.066
|
| [22] |
PARK J,KIM J K,JUNG S,et al. ECG-signal multi-classification model based on squeeze-and-excitation residual neural networks[J]. Applied Sciences,2020,10(18): 6495. doi: 10.3390/app10186495
|
| [23] |
LI A,YAO D,YANG J,et al. Bearing diagnosis using an anti-noise neural network based on selectable branch multiscale modules and attention mechanisms[J]. IEEE Sensors Journal,2024,24(5): 5830-5840. doi: 10.1109/JSEN.2023.3326439
|
DownLoad:
