|
|
|
| Bearing fault diagnosis based on deep dynamic domain adaptation |
| WANG Junhui, LEI Wenping, LIU Huajie， WEI Lijun， HAN Dongyang |
| School of Mechanical and Power Engineering, Zhengzhou University, Zhengzhou 450001,China |
|
|
|
|
Abstract Aiming at the problem that the data distribution of source domain and target domain in transfer learning is very different, and it is difficult to adapt to the dynamic changes of marginal distribution and conditional distribution in traditional learning, a bearing fault diagnosis method based on deep dynamic domain adaptation is proposed. In the domain adaptation layer, a dynamic distribution adaptation method is introduced, and edge distribution alignment and conditional distribution alignment are performed by domain classifiers, and dynamic domain adaptation is performed by dynamically measuring the contribution of conditional distribution and edge distribution to the domain according to the balance factor. Through the migration diagnosis test and comparative analysis of bearing data sets of Case Western Reserve University and Jiangnan University under variable working conditions, the accuracy of cross-domain diagnosis is effectively improved, and the effectiveness and excellence of the proposed method are verified.
|
|
Received: 23 May 2022
Published: 28 July 2023
|
|
|
|
[1] 李涛，段礼祥，张东宁，等. 自适应卷积神经网络在旋转机械故障诊断中的应用[J]. 振动与冲击，2020, 39(16): 275-282.
LI Tao, DUAN Lixiang, ZHANG Dongning, et al. Application of adaptive convolutional neural network in rotating machinery fault diagnosis [J]. Journal of Vibration and Shock, 2020, 39(16): 275-282.
[2] TZENG E, HOFFMAN J, ZhANG N, et al. Deep domain confusion: Maximizing for domain invariance[J]. arXiv preprint arXiv, 2014, 1412: 3474-3482.
[3] PAN S J, Yang Q. A survey on transfer learning[J]. IEEE Transactions on knowledge and data engineering, 2010, 22(10): 1345-1359.
[4] 雷亚国，杨彬，杜兆钧，等. 大数据下机械装备故障的深度迁移诊断方法[J]. 机械工程学报，2019, 55(07): 1-8.
LEI Yaguo, YANG Bin, DU ZhaoJNU, et al. Deep migration diagnosis method of mechanical equipment fault under big data [J]. Journal of mechanical engineering, 2019, 55 (07): 1-8.
[5] 谭俊杰，杨先勇，徐增丙，等. 基于无监督迁移成分分析和深度信念网络的轴承故障诊断方法[J]. 武汉科技大学学报，2019, 42(06):456-462.
TAN JNUjie, YANG Xianyong, XU Zengbing, et al. Bearing fault diagnosis method based on unsupervised transfer component analysis and deep belief network [J]. Journal of Wuhan University of Science and Technology, 2019, 42(06): 456-462.
[6] 吴静然，刘建华，崔冉. 子域适应无监督轴承故障诊断[J]. 振动与冲击，2021, 40(15):34-40.
WU Jingran, LIU Jianhua, CUI Ran. Subdomain adaptive unsupervised bearing fault diagnosis[J]. Journal of Vibration and Shock, 2021, 40(15): 34-40.
[7] WANG J, CHEN Y, FENG W, et al. Transfer learning with dynamic distribution adaptation[J]. ACM Transactions on Intelligent Systems and Technology (TI, 2020, 11(1): 1-25.
[8] BEN-David S, BLITZER J, CRAMMER K, et al. Analysis of representations for domain adaptation[J]. Advances in neural information processing systems, 2006, 19(1): 137-144
[9] GOODFELLOW I, POUGET-Abadie J, MIRZA M, et al. Generative adversarial nets In: Advances in Neural Information Processing Systems[J]. 2014, 27(1): 2672-2680.
[10] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// in: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016, 770-778.
[11] 李可. 江南大学轴承故障数据集[EB/OL]. http://mad- net.org:8765/explore.html?t=0.%205831516555847212．
[12] LONG M, CAO Y, WANG J, et al. Learning transferable features with deep adaptation networks[C]// in: International conference on machine learning, PMLR. 2015, 97-105.
[13] GANIN Y, USTINOVA E, AJAKAN H, et al. Domain-adversarial training of neural networks[J]. The journal of machine learning research, 2016, 17(1): 2096-2030.
[14] LONG M, ZHU H, WANG J, et al. Deep transfer learning with joint adaptation networks[C]// in: International conference on machine learning, PMLR. 2017, 2208-2217.
|
|
|
|
