Abstract
In this paper we consider diagnostics of induction motor faults via measurement of startup current. Data collected has a form of time series of varying length and magnitude, as it strongly depends on voltage supply. In this work we focus on functional representation of those signals in time domain. We show that we can effectively model those signals with taking uncertainty under consideration and using those models create efficient classifier. For this purpose we have used Bayesian Gaussian mixture model classifier, which creates models of all healthy and faulty states and the entirety of population of possible cases. We show how our approach works and how it behaves under significant randomization.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
Aneiros, G., Cao, R., Fraiman, R., Genest, C., Vieu, P.: Recent advances in functional data analysis and high-dimensional statistics. J. Multivariate Anal. 170, 3–9 (2019), Special Issue on Functional Data Analysis and Related Topics
Baranowski, J.: Application of bayesian functional gaussian mixture model classifier for cable fault isolation. In: Kowalczuk, Z. (ed.) Intelligent and Safe Computer Systems in Control and Diagnostics, pp. 254–265. Springer International Publishing, Cham (2023). https://doi.org/10.1007/978-3-031-16159-9_21
Baranowski, J.: Application of bayesian functional gaussian mixture model classifier for cable fault isolation, vol. 545. LNNS, pp. 254–265 (2023). https://doi.org/10.1007/978-3-031-16159-9_21
Cai, B., et al.: Remaining useful life re-prediction methodology based on wiener process: Subsea christmas tree system as a case study. Compu. Industrial Eng. 151, 106983 (2021). https://doi.org/10.1016/j.cie.2020.106983. https://www.sciencedirect.com/science/article/pii/S0360835220306537
Cai, B., et al.: Fault detection and diagnostic method of diesel engine by combining rule-based algorithm and bns/bpnns. J. Manufact. Syst. 57, 148–157 (2020). https://doi.org/10.1016/j.jmsy.2020.09.001. https://www.sciencedirect.com/science/article/pii/S0278612520301618
Carpenter, B., et al.: Stan: A probabilistic programming language. J. Stat. Softw. Articles 76(1), 1–32 (2017)
Fireteanu, V., Leconte, V., Zidat, F.: Monitoring of the evolution of a squirrel-cage bar breakage through harmonics of the magnetic field outside the induction motor. In: 2016 International Symposium on Power Electronics, Electrical Drives, Automation and Motion (SPEEDAM), pp. 633–638 (2016). https://doi.org/10.1109/SPEEDAM.2016.7525834
Kawase, Y., Yamaguchi, T., Uozumi, H., Kawano, H., Watanabe, M., Kusadome, T.: Characteristics analysis of induction motor with broken rotor bars at steady state. In: 2020 23rd International Conference on Electrical Machines and Systems (ICEMS), pp. 1190–1193 (2020). https://doi.org/10.23919/ICEMS50442.2020.9290789
Kliman, G., Koegl, R., Stein, J., Endicott, R., Madden, M.: Noninvasive detection of broken rotor bars in operating induction motors. IEEE Trans. Energy Convers. 3(4), 873–879 (1988). https://doi.org/10.1109/60.9364
Luo, G., Hurwitz, J., Habetler, T.G.: The effect of broken rotor bar on the low frequency components in the axial stray flux of induction motors. In: 2019 IEEE 12th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (SDEMPED), pp. 227–231 (2019). https://doi.org/10.1109/DEMPED.2019.8864917
Poręba, J., Baranowski, J.: Functional logistic regression for motor fault classification using acoustic data in frequency domain. Energies 15(15) (2022)
Rad, M.: Squirrel cage motors automatic bar diagnostics based on startup current. Maszyny Elektryczne - zeszyty problemowe 79, 113–115 (2008)
Rad, M.: Induction motor cage diagnosis based on wavelet transform and self-training systems. Przegląd Elektrotechniczny = Electrical Review 86(5), 55–59 (2010)
Stief, A., Ottewill, J., Baranowski, J., Orkisz, M.: A pca and two-stage bayesian sensor fusion approach for diagnosing electrical and mechanical faults in induction motors. IEEE Trans. Industr. Electron. 66(12), 9510–9520 (2019)
Wan, H., Wang, H., Scotney, B., Liu, J.: A novel gaussian mixture model for classification. In: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC), pp. 3298–3303 (2019). https://doi.org/10.1109/SMC.2019.8914215
Wang, J.L., Chiou, J.M., Müller, H.G.: Functional data analysis. Annual Rev. Stat. Appli. 3(1), 257–295 (2016). https://doi.org/10.1146/annurev-statistics-041715-033624
Acknowledgements
Work partially realised in the scope of project titled ”Process Fault Prediction and Detection”. Project was financed by The National Centre for Research and Development on the base of decision no. UMO-2021/41/B/ST7/03851. Part of work was funded by AGH’s Research University Excellence Initiative under project “Interpretable methods of process diagnosis using statistics and machine learning”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jarzyna, K., Rad, M., Piątek, P., Baranowski, J. (2023). Bayesian Fault Diagnosis for Induction Motors During Startup in Frequency Domain. In: Pawelczyk, M., Bismor, D., Ogonowski, S., Kacprzyk, J. (eds) Advanced, Contemporary Control. PCC 2023. Lecture Notes in Networks and Systems, vol 709. Springer, Cham. https://doi.org/10.1007/978-3-031-35173-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-35173-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35172-3
Online ISBN: 978-3-031-35173-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)