Abstract
Effective fault data is the basis for intelligent fault diagnosis. In actual engineering applications, it is often impossible to obtain sufficiently effective fault signals. Moreover, relying on fault data makes it impossible to design supporting fault diagnosis models for equipment that is being designed and manufactured. In response to the above problems, a method of using digital twin training data to drive high-fidelity fault diagnosis models was proposed. Taking rolling bearings as the research object, the above method was verified. First, a dynamic analysis was performed on the rolling bearing and a bearing model in three states was constructed. Subsequently, a twin model of the rolling bearing was built based on the Modelica language. The vibration signal was obtained by running the model and compared with the theoretical fault characteristic frequency to verify the accuracy of the high-fidelity rolling bearing twin model. Finally, the convolutional neural network (CNN) was trained using the data of the digital twin model and tested using experiments under various working conditions. The results show that the method proposed in this article can achieve higher accuracy and is effective.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
Data are available upon reasonable request.
References
Liu, D., Zhou, J.B., Pan, D.W., et al.: Lithium-ion battery remaining useful life estimation with an optimized relevance vector machine algorithm with incremental learning. Measurement 63, 143–151 (2015)
Liu, J., Wang, W., Ma, F., et al.: A data-model-fusion prognostic framework for dynamic system state forecasting. Eng. Appl. Artif. Intell. 25(4), 814–823 (2012)
Olivier, J., Viktor, S., Bram, V., et al.: Convolutional neural network based fault detection for rotating machinery. J. Sound Vib. 377, 331–345 (2016)
Ren, S.Q., Zhu, W., Liao, B., et al.: Selection-based resampling ensemble algorithm for nonstationary imbalanced stream data learning. Knowl.-Based Syst. 163, 705–722 (2019)
Nagwa, E., Sherif, B., Amira, R.: A conditional GAN-based approach for enhancing transfer learning performance in few-shot HCR tasks. Sci. Rep. 12(1), 16271 (2022)
Zhang, W., Li, X., Jia, X.D., et al.: Machinery fault diagnosis with imbalanced data using deep generative adversarial networks. Measurement 152, 107377 (2020)
Glassgen, E. H., Stargel, D. S.: The digital twin paradigm for future NASA and US Air Force vehicles. In 53rd AIAA/ASME/ASCE/AHS/ASC structures, Structural Dynamics and Materials Conference 20th AIAA/ASME/AHS Adaptive Structures Conference 14th AIAA, Hawaii, 1818 (2012).
Botin-sanabria, D.M., Mihaita, A., Peimbert-garcia, R.E., et al.: Digital twin technology challenges and applications: a comprehensive review. Remote Sens. 14(6), 1335 (2022)
Lim, K.Y.H.L., Zheng, P., Chen, C.H.: A state-of-the-art survey of Digital Twin: techniques, engineering product lifecycle management and business innovation perspectives. J. Intell. Manuf. 31, 1313–1337 (2020)
Wang, J.J., Ye, L.K., Gao, R., et al.: Digital Twin for rotating machinery fault diagnosis in smart manufacturing. Int. J. Prod. Res. 57(12), 3920–3934 (2019)
Jain, P., Poon, J., Singh, J.P., et al.: A digital twin approach for fault diagnosis in distributed photovoltaic systems. IEEE Trans. Power Electron. 35(1), 940–956 (2019)
Xia, M., Shao, H.D., Williams, D., et al.: Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. Reliab. Eng. Syst. Saf. 215, 107938 (2021)
Zhang, H., Qi, Q.L., Tao, F.: A multi-scale modeling method for digital twin shop-floor. J. Manuf. Syst. 62, 417–428 (2022)
Mishra, C., Samantaray, A.K., Chakraborty, G.: Ball bearing defect models: a study of simulated and experimental fault signatures. J. Sound Vib. 400, 86–112 (2017)
Xu, G. H. Gear-bearing coupling dynamic modeling and vibration characteristics analysis in helical gear transmission system. Shanghai University (2021)
Tiller, M.: Introduction to Physical Modeling with Modelica, pp. 1–23. Springer Science & Business Media, Berlin (2012)
Otter, M., Reiner, M., Tobolar, J., et al.: Towards modelica models with credibility information. Electronics 17(11), 2728 (2022)
Delussu, F., Manzione, D., Meo, R., et al.: Experiments and comparison of digital twinning of photovoltaic panels by machine learning models and a cyber-physical model in modelica. IEEE Trans. Ind. Inf. 18(6), 4018–4028 (2021)
Aivaliotis, P., Georgoulias, K., Arkouli, Z., et al.: Methodology for enabling digital twin using advanced physics-based modelling in predictive maintenance. Proc. Cirp 81, 417–422 (2019)
Magargle, R., Johnson, L., Mandloi, P., et al.: A simulation-based digital twin for model-driven health monitoring and predictive maintenance of an automotive braking system. In: Proceedings of the 12th International Modelica Conference, Prague, (2017)
Zhu, Y.Y., Hu, C., Ma, Y., et al.: An equation-based method for fully coupled analyses of floating offshore wind turbine based on Modelica. Energy Convers. Manage. 277, 116653 (2023)
Yang, S., Sun, X. B., Chen, D. J.: Bearing fault diagnosis of two-dimensional improved Att-CNN2D neural network based on Attention mechanism. In 2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS), Dalian, pp. 81–85, (2020)
Ruan, D.W., Chen, Y., Guhmann, C., et al.: Dynamics modeling of bearing with defect in modelica and application in direct transfer learning from simulation to test bench for bearing fault diagnosis. Electronics 11(4), 622 (2022)
Cui, L.L., Chen, X., Chen, S.J.: Dynamics modeling and analysis of local fault of rolling element bearing. Adv. Mech. Eng. 7(1), 262351 (2015)
Wang, B., Lei, Y, G., Li, N. P., et al.: A hybrid prognostics approach for estimating remaining useful life of rolling element bearings. IEEE Trans. Reliab. 1–12, (2018)
Funding
This work was supported in part by the National Natural Science Foundation of China (No. 51875368), and the Liaoning Provincial Department of Science and Technology Applied Basic Research Funding Project (2022JH2/101300230), and the Liaoning Provincial Department of Education Basic Research Funding Project (LJKQZ20222448).
Author information
Authors and Affiliations
Contributions
Conceptualization: Jing-yuan Wu, Qi-lin Shu, Yong-he Wei, Geng Wang and Ming-hao Li; Data curation: Jing-yuan Wu and Yong-he Wei; Formal analysis: Jing-yuan Wu; Investigation: Jing-yuan Wu; Methodology: Jing-yuan Wu and Yong-he Wei; Project administration: Jing-yuan Wu; Resources: Jing-yuan Wu and Yong-he Wei; Software: Jing-yuan Wu; Validation: Jing-yuan Wu and Geng Wang; Visualization: Jing-yuan Wu; Writing – original draft: Jing-yuan Wu; Writing – review and editing: Jing-yuan Wu, Qi-lin Shu, Yong-he Wei and Ming-hao Li.
Corresponding author
Ethics declarations
Conflict of interest
The authors have declared that no competing interests exist.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jingyuan, W., Qilin, S., Minghao, L. et al. Research on deep learning rolling bearing fault diagnosis driven by high-fidelity digital twins. Int J Interact Des Manuf (2024). https://doi.org/10.1007/s12008-024-01859-2
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12008-024-01859-2