It is a common belief that convolutional neural networks (CNN) are incapable of acquiring knowledge from domain experts for fault detection and diagnosis. To address the challenge, this paper proposes a knowledge-transfer scheme from computer-aided engineering (CAE) models to CNN models. Domain experts build the CAE models that emulate the faulty behavior of rotating machines by incorporating fault symptom and controlling the degree of fault severity. Fault data are hardly acquired from rotating machines in the field, while a sufficient number of fault data can be generated using the CAE models. Then, a domain adaption model is trained using synthetic data (i.e., normal and fault data) from the CAE models and real data (i.e., normal data only) from rotating machines. To evaluate the validity of the proposed method, a small-scale testbed is regarded as the target system that does not have any fault data. This study contributes to resolve the dearth of fault data from most safety-related engineering assets such as power plant steam turbines, wind turbines, and urban air mobility.
Deep learning, CAE-aided, Bearing diagnosis, Domain adaptation
Wang, J., Zhang, Z., Liu, Z., Han, B., Bao, H., & Ji, S. (2023). Digital twin aided adversarial transfer learning method for domain adaptation fault diagnosis. Reliability Engineering & System Safety, vol. 234, 109152.
Feng, K., Ji, J. C., Zhang, Y., Ni, Q., Liu, Z., & Beer, M. (2023). Digital twin-driven intelligent assessment of gear surface degradation. Mechanical Systems and Signal Processing, vol. 186, 109896.
Long, M., Cao, Z., Wang, J., & Jordan, M. I. (2018). Conditional adversarial domain adaptation. Proceedings of the Advances in Neural Information Processing Systems, Montreal, Canada, pp. 1645-1655.
Zhou, K., Yang, Y., Qiao, Y., & Xiang, T. (2021). Domain generalization with MixStyle. Proceedings of the International Conference on Learning Representations, May 3-7, Vienna, Austria.
This work is licensed under a Creative Commons Attribution 3.0 Unported License.