Domain Adaptation based Fault Diagnosis under Variable Operating Conditions of a Rock Drill
Jin Uk Ko
Fault diagnosis using a data-driven approach is an essential technology for the safety and maintenance of a rock drill. However, since the signals acquired from the rock drill have different distributions due to variable operating conditions, the classification performance of the data-driven method decreases; this is called the domain shift issue. This paper proposes a new domain adaptation-based fault diagnosis scheme to solve the problem. The proposed method introduces a data cropping technique to mitigate the difference in the length of the data measured from the rock drill for each impact cycle. To extract invariant features for all operating conditions, the proposed method combines two methods: the domain adversarial neural network and minimization of the maximum mean discrepancy (MMD) between the features from different domains. In addition, a soft voting ensemble is used to reduce the model uncertainty. The proposed method shows superior performance when validated with the rock drill dataset and ranked 2nd place in the 2022 PHM Conference Data Challenge.
How to Cite
Rock Drill, Fault Diagnosis, Domain Adaptation, Deep-learning
Li, B., Chow, MY., Tipsuwan, Y., & Hung, J.C. (2000) Neural-network-based motor rolling bearing fault diagnosis. IEEE transactions on industrial electronics, vol.47(5), pp. 1060-1069. doi.org/10.1109/41.873214
Guo, X., Chen, L., & Shen, C. (2016). Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis. Measurement, vol. 93, pp. 490-502. doi.org/10.1016/j.measurement.2016.07.054
Ganin, Y., Ustinova, E., Ajakan, H., Germain, P., Larochelle, H., Laviolette, F., Marchand, M., & Lempitsky, V. (2016). Domain-adversarial training of neural networks. The journal of machine learning research, vol.17(1), pp. 2096-2030. doi.org/10.48550/arXiv.1505.07818
Jiao, J., Zhao, M., & Lin, J. (2019). Unsupervised adversarial adaptation network for intelligent fault diagnosis. IEEE Transactions on Industrial Electronics, vol. 67(11), pp. 9904-9913. doi.org/10.1109/TIE.2019.2956366
Guo, L., Lei, Y., Xing, S., Tan, T., & Li, N. (2018). Deep convolutional transfer learning network: A new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Transactions on Industrial Electronics, vol.66(9) pp. 7316-7325. doi.org/10.1109/TIE.2018.2877090
Borgwardt, KM., Gretton, A., Rasch, MJ., Kriegel, HP., Schölkopf, B., Karsten M., & Smola, AJ. (2006) Integrating structured biological data by kernel maximum mean discrepancy. Bioinformatics, vol.22(14) pp. 49-57. doi.org/10.1093/bioinformatics/btl242
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.