Domain Adaptation via Simulation Parameter and Data Perturbation for Predictive Maintenance

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 27, 2024
Kiavash Fathi Fabio Corradini Marcin Sadurski Marco Silvestri Marko Ristin Afrooz Laghaei Davide Valtorta Tobias Kleinert Hans Wernher van de Venn

Abstract

Conventional data-driven predictive maintenance (PdM) solutions learn from samples of run-to-failures (R2F) to estimate the remaining useful life of an asset. In practice, such samples are scarce or completely missing. Simulation models can be oftentimes used to generate R2F samples as a replacement. However, due to the complexity of the assets, creating realistic simulation models is tedious, or even impossible. Thus generated R2F data cannot be used to create reliable PdM models as they are highly sensitive to noises in the sensors or small deviations in system working condition. To address this, we present a new concept of simulation data generation based on supervised domain adaptation for a regression problem where the remaining useful life (RUL) or the health index (HI) of the system is predicted. Apart from input and output domain shift, given the changes in the dominant failing component and its degradation process, the function mapping sensor readings to RUL and/or HI is also prone to changes and thus is a random process itself. Therefore, we aim to generate R2F training data from different working conditions and possible failure types using parameter randomization in the simulation model. By sampling from various configurations within simulation model's parameter space, we ensure that the trained data-driven PdM model's performance is not impacted by the initial conditions and/or the changes in the degradation of the system's condition indicators. Our results indicate that the model is robust to signal reading manipulation and showcases a more spread-out feature importance across a wider range of sensor readings for making predictions. We also demonstrate its applicability on the real-world factory physical system whilst our models were mainly trained using generated data.

How to Cite

Fathi, K., Corradini, F., Sadurski, M., Silvestri, M., Ristin, M., Laghaei, A., Valtorta, D., Kleinert, T., & van de Venn, H. W. (2024). Domain Adaptation via Simulation Parameter and Data Perturbation for Predictive Maintenance. PHM Society European Conference, 8(1), 11. https://doi.org/10.36001/phme.2024.v8i1.3985
Abstract 227 | PDF Downloads 120

##plugins.themes.bootstrap3.article.details##

Keywords

Domain adaptation, Simulation-to-real transfer, Predictive maintenance, Industry 4.0

References
Belforte, G., Raparelli, T., & Mazza, L. (1992). Analysis of typical component failure situations for pneumatic cylinders under load. Lubrication engineering, 48(11), 840–845. Bonomi, N., Cardoso, F., Confalonieri, M., Daniele, F., Ferrario, A., Foletti, M., . . . Pedrazzoli, P. (2021). Smart quality control powered by machine learning algorithms. 2021 IEEE 17th International Conference on Automation Science and Engineering (CASE), 764770. Chang, Y., Fang, H., & Zhang, Y. (2017). A new hybrid method for the prediction of the remaining useful life of a lithium-ion battery. Applied energy, 206, 15641578. Chen, D., Meng, J., Huang, H., Wu, J., Liu, P., Lu, J., & Liu, T. (2022). An empirical-data hybrid driven approach for remaining useful life prediction of lithiumion batteries considering capacity diving. Energy, 245, 123222. Chen, J., Zio, E., Li, J., Zeng, Z., & Bu, C. (2018). Accelerated Life Test for Reliability Evaluation of Pneumatic Cylinders. IEEE Access, 6, 75062–75075. (Conference Name: IEEE Access) Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785–794). Cortes, C., & Mohri, M. (2011). Domain adaptation in regression. In International conference on algorithmic learning theory (pp. 308–323). Cui, L., Du, S., & Hawkes, A. G. (2012). A study on a single-unit repairable system with state aggregations. IIE Transactions, 44(11), 1022–1032. Didona, D., & Romano, P. (2014). On bootstrapping machine learning performance predictors via analytical models.arXiv preprint arXiv:1410.5102.

Farahani, A., Voghoei, S., Rasheed, K., & Arabnia, H. R.

(2021). A brief review of domain adaptation. Advances in data science and information engineering: proceedings from ICDATA 2020 and IKE 2020, 877–894. Fathi, K., Sadurski, M., Kleinert, T., & van de Venn, H. W.

(2023). Source component shift detection classification for improved remaining useful life estimation in alarm-based predictive maintenance. In 2023 23rd international conference on control, automation and systems (iccas) (p. 975-980). doi: 10.23919/ICCAS59377.2023.10316874 Fathi, K., van de Venn, H. W., & Honegger, M. (2021). Predictive maintenance: an autoencoder anomaly-based approach for a 3 dof delta robot. Sensors, 21(21), 6979.

Fei, C. (2022). Lithium-ion battery data set. IEEE Dataport. Retrieved from https://dx.doi.org/10.21227/fh1g-8k11 doi: 10.21227/fh1g-8k11 Ferrario, A., Confalonieri, M., Barni, A., Izzo, G., Landolfi, G., & Pedrazzoli, P. (2019). A Multipurpose Small-Scale Smart Factory For Educational And Research Activities. Procedia Manufacturing, 38, 663–670. Gao, Y., Liu, X., Huang, H., & Xiang, J. (2021). A hybrid of fem simulations and generative adversarial networks to classify faults in rotor-bearing systems. ISA transactions, 108, 356–366.

Hanachi, H., Liu, J., Banerjee, A., Chen, Y., & Koul, A.

(2014). A physics-based modeling approach for performance monitoring in gas turbine engines. IEEE Transactions on Reliability, 64(1), 197–205.

Kaufmann, E., Loquercio, A., Ranftl, R., M¨uller, M., Koltun, V., & Scaramuzza, D. (2020). Deep drone acrobatics. arXiv preprint arXiv:2006.05768.

Lei, Y., Li, N., Gontarz, S., Lin, J., Radkowski, S., & Dybala, J. (2016). A model-based method for remaining useful life prediction of machinery. IEEE Transactions on reliability, 65(3), 1314–1326.

Lin, R., Yu, Y., Wang, H., Che, C., & Ni, X. (2022). Remaining useful life prediction in prognostics using multiscale sequence and long short-term memory network. Journal of computational science, 57, 101508.

Liu, J., Wang, W., Ma, F., Yang, Y., & Yang, C. (2012). A data-model-fusion prognostic framework for dynamic system state forecasting. Engineering Applications of Artificial Intelligence, 25(4), 814–823.

Motiian, S., Piccirilli, M., Adjeroh, D. A., & Doretto, G.

(2017). Unified deep supervised domain adaptation and generalization. In Proceedings of the ieee international conference on computer vision (pp. 5715–5725).

Nakutis, ˇ Zilvinas., & Kaˇskonas, P. (2008). An approach to pneumatic cylinder on-line conditions monitoring. Mechanics, 72(4), 41–47.

Nejjar, I., Geissmann, F., Zhao, M., Taal, C., & Fink, O.

(2024). Domain adaptation via alignment of operation profile for remaining useful lifetime prediction. Reliability Engineering & System Safety, 242, 109718. Peng, X. B., Andrychowicz, M., Zaremba, W., & Abbeel, P.

(2018). Sim-to-real transfer of robotic control with dynamics randomization. In 2018 ieee international conference on robotics and automation (icra) (pp. 38033810).

Ragab, M., Chen, Z., Wu, M., Kwoh, C. K., & Li, X. (2020).

Adversarial transfer learning for machine remaining useful life prediction. In 2020 ieee international conference on prognostics and health management (icphm) (pp. 1–7).

Rahat, M., Mashhadi, P. S., Nowaczyk, S., Rognvaldsson, T., Taheri, A., & Abbasi, A. (2022). Domain adaptation in predicting turbocharger failures using vehicle’s sensor measurements. In Phm society european conference (Vol. 7, pp. 432–439).

Saxena, A. (2023). Nasa turbofan jet engine data set. IEEE Dataport. Retrieved from https://dx.doi.org/10.21227/pjh5-p424 doi: 10.21227/pjh5-p424 Si, X.-S., Wang, W., Hu, C.-H., Zhou, D.-H., & Pecht, M. G.

(2012). Remaining useful life estimation based on a nonlinear diffusion degradation process. IEEE Transactions on reliability, 61(1), 50–67.

Thelen, A., Li, M., Hu, C., Bekyarova, E., Kalinin, S., & Sanghadasa, M. (2022). Augmented model-based framework for battery remaining useful life prediction. Applied Energy, 324, 119624.

Tiboni, G., Arndt, K., & Kyrki, V. (2023). Dropo: Sim-to-real transfer with offline domain randomization. Robotics and Autonomous Systems, 166, 104432.

Wang, Q., Taal, C., & Fink, O. (2021). Integrating expert knowledge with domain adaptation for unsupervised fault diagnosis. IEEE Transactions on Instrumentation and Measurement, 71, 1–12.

Yang, B., Lei, Y., Jia, F., & Xing, S. (2019). An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mechanical Systems and Signal Processing, 122, 692706.

Yu, K., Fu, Q., Ma, H., Lin, T. R., & Li, X. (2021). Simulation data driven weakly supervised adversarial domain adaptation approach for intelligent cross-machine fault diagnosis. Structural Health Monitoring, 20(4), 21822198.
Section
Technical Papers