Application of data mining techniques in synthetic data for predictive maintenance: a case study

• Rafael Schena Federal University of Rio Grande do Sul
• João Cesar Netto Federal University of Rio Grande do Sul
• Karin Becker Federal University of Rio Grande do Sul https://orcid.org/0000-0003-4967-1027

DOI: https://doi.org/10.5753/sbbd.2022.224627

Abstract

This paper presents a case study of application data mining techniques in synthetic data for predictive maintenance of a naval propulsion system, with the objective of analyzing its applicability and suitability in the construction of predictive models for maintenance. In the first stage, we applied data mining techniques to the original dataset, and raised hypotheses about the results obtained with synthetic data. In the second and third stages, respectively, we tested the hypotheses raised in the initial stage by inserting class imbalance and measurement uncertainties. The results show ways to enrich synthetic data in order to build models more similar to real industrial scenarios.

Keywords: predictive maintenance, synthetic data, data mining

References

Brun, K. and Kurz, R. (1998). Measurement uncertainties encountered during gas turbine driven compressor field testing. In Turbo Expo: Power for Land, Sea, and Air, volume 78644, page V003T07A001. American Society of Mechanical Engineers.

Carchiolo, V., Longheu, A., Di Martino, V., and Consoli, N. (2019). Power plants failure reports analysis for predictive maintenance. In WEBIST, pages 404-410.

Coraddu, A., Oneto, L., Ghio, A., Savio, S., Anguita, D., and Figari, M. (2016). Machine learning approaches for improving condition-based maintenance of naval propulsion plants. Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, 230(1):136-153.

Dalheim, and Steen, S. (2021). Uncertainty in the real-time estimation of ship speed through water. Ocean Engineering, 235:109423.

Mahmoodzadeh, Z., Wu, K.-Y., Lopez Droguett, E., and Mosleh, A. (2020). Condition-based maintenance with reinforcement learning for dry gas pipeline subject to internal corrosion. Sensors, 20(19):5708.

Mathew, V., Toby, T., Singh, V., Rao, B. M., and Kumar, M. G. (2017). Prediction of remaining useful lifetime (rul) of turbofan engine using machine learning. In 2017 IEEE International Conference on Circuits and Systems (ICCS), pages 306-311.

Mauthe, F., Hagmeyer, S., and Zeiler, P. (2021). Creation of publicly available data sets for prognostics and diagnostics addressing data scenarios relevant to industrial applications. International Journal of Prognostics and Health Management, 12(2).

Mobley, R. K. (2002). An introduction to predictive maintenance. Elsevier. Rao, S. V. (2020). Using a digital twin in predictive maintenance. Journal of Petroleum Technology, 72(08):42-44.

Schröer, C., Kruse, F., and Gómez, J. M. (2021). A systematic literature review on applying crisp-dm process model. Procedia Computer Science, 181:526-534.

Susto, G. A., Schirru, A., Pampuri, S., McLoone, S., and Beghi, A. (2015). Machine learning for predictive maintenance: A multiple classifier approach. IEEE Transactions on Industrial Informatics, 11(3):812-820.

Wirth, R. and Hipp, J. (2000). Crisp-dm: Towards a standard process model for data mining. In Proceedings of the 4th international conference on the practical applications of knowledge discovery and data mining, volume 1, pages 29-40. Manchester.

Zhang, W., Yang, D., and Wang, H. (2019). Data-driven methods for predictive maintenance of industrial equipment: A survey. IEEE Systems Journal, 13(3):2213-2227.