Document Type : Research Paper


1 Department of Electrical Drives and Controls, Bosch Rexroth AG, Ulm, Germany.

2 Department of Applied Computer Science, Fulda University of Applied Sciences, Fulda, Germany.

3 Department of Electrical Engineering, Fulda University of Applied Sciences, Fulda, Germany.


This study proposes a framework for the automated hyperparameter optimization of a bearing fault detection pipeline for Permanent Magnet Synchronous Motors (PMSMs) without the need for external sensors. An Automated Machine Learning (AutoML) pipeline search is performed through genetic optimization to reduce human-induced bias due to inappropriate parameterizations. A search space is defined, which includes general methods of signal processing and manipulation as well as methods tailored to the respective task and domain. The proposed framework is evaluated on the bearing fault detection use case under real-world conditions. Considerations on the generalization of the deployed fault detection pipelines are also considered. Likewise, attention was paid to experimental studies for evaluations of the robustness of the fault detection pipeline to variations of the motors working condition parameters between the training and test domain.


Main Subjects

[1]      Imoru, O., Jimoh, A. A., & Hamam, Y. (2014). Origin and manifestation of electrical machine faults-a review. The 2nd IEEE conference on power engineering and renewable energy (ICPERE) 2014 (pp. 189–194). IEEE.
[2]      Mbo’O, C. P., Herold, T., & Hameyer, K. (2014). Impact of the load in the detection of bearing faults by using the stator current in pmsm’s. Proceedings - 2014 international conference on electrical machines, icem 2014 (pp. 1621–1627). IEEE. DOI: 10.1109/ICELMACH.2014.6960399
[3]      Schoen, R. R., Habetler, T. G., Kamran, F., & Bartheld, R. G. (1994). Motor bearing damage detection using stator current monitoring. Proceedings of 1994 IEEE industry applications society annual meeting (Vol. 1, pp. 110–116). IEEE.
[4]      Eren, L., & Devaney, M. J. (2004). Bearing damage detection via wavelet packet decomposition of the stator current. IEEE transactions on instrumentation and measurement, 53(2), 431–436.
[5]      Kao, I. H., Wang, W. J., Lai, Y. H., & Perng, J. W. (2019). Analysis of permanent magnet synchronous motor fault diagnosis based on learning. IEEE transactions on instrumentation and measurement, 68(2), 310–324. DOI:10.1109/TIM.2018.2847800
[6]      Leite, V. C. M. N., Silva, J. G. B. da, Torres, G. L., Veloso, G. F. C., Silva, L. E. B. da, Bonaldi, E. L., & Oliveira, L. E. de L. de. (2017). Bearing fault detection in induction machine using squared envelope analysis of stator current. In Bearing technology. IntechOpen.
[7]      Lessmeier, C., Kimotho, J. K., Zimmer, D., & Sextro, W. (2016). Condition monitoring of bearing damage in electromechanical drive systems by using motor current signals of electric motors: a benchmark data set for data-driven classification [presentation]. Third european conference of the prognostics and health management society 2016 (Vol. 3, pp. 152–156).
[8]      Milkovic, D. (2015). Brief review of motor current signature analysis. HDKBR info magazin, 5(5(1)), 14–26.
[9]      Picot, A., Obeid, Z., Régnier, J., Poignant, S., Darnis, O., & Maussion, P. (2014). Statistic-based spectral indicator for bearing fault detection in permanent-magnet synchronous machines using the stator current. Mechanical systems and signal processing, 46(2), 424–441.
[10]    Zhang, W., Li, C., Peng, G., Chen, Y., & Zhang, Z. (2018). A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mechanical systems and signal processing, 100, 439–453. DOI:10.1016/j.ymssp.2017.06.022
[11]    Jin, G., Zhu, T., Akram, M. W., Jin, Y., & Zhu, C. (2020). An adaptive anti-noise neural network for bearing fault diagnosis under noise and varying load conditions. IEEE access, 8, 74793–74807.
[12]    Wagner, T., & Sommer, S. (2020). Bearing fault detection using deep neural network and weighted ensemble learning for multiple motor phase current sources. INISTA 2020 - 2020 international conference on innovations in intelligent systems and applications, proceedings (pp. 1–7). IEEE. DOI: 10.1109/INISTA49547.2020.9194618
[13]    Tong, Z., Li, W., Zhang, B., Jiang, F., & Zhou, G. (2018). Bearing fault diagnosis under variable working conditions based on domain adaptation using feature transfer learning. IEEE access, 6, 76187–76197. DOI:10.1109/ACCESS.2018.2883078
[14]    Zhou, J., Zheng, L. Y., Wang, Y., & Gogu, C. (2020). A multistage deep transfer learning method for machinery fault diagnostics across diverse working conditions and devices. IEEE access, 8, 80879–80898. DOI:10.1109/ACCESS.2020.2990739
[15]    Michau, G., & Fink, O. (2021). Unsupervised transfer learning for anomaly detection: application to complementary operating condition transfer. Knowledge-based systems, 216, 106816. DOI:10.1016/j.knosys.2021.106816
[16]   Kefalas, M., Baratchi, M., Apostolidis, A., Van Den Herik, D., & Back, T. (2021). Automated machine learning for remaining useful life estimation of aircraft engines. 2021 IEEE international conference on prognostics and health management, ICPHM 2021 (pp. 1–9). IEEE. DOI: 10.1109/ICPHM51084.2021.9486549
[17]    Larocque-Villiers, J., Dumond, P., & Knox, D. (2021). Automating predictive maintenance using state-based transfer learning and ensemble methods. 2021 IEEE international symposium on robotic and sensors environments (ROSE) (pp. 1-7). IEEE. DOI: 10.1109/ROSE52750.2021.9611768
[18]    Kang, S., Ma, D., Wang, Y., Lan, C., Chen, Q., & Mikulovich, V. I. (2017). Method of assessing the state of a rolling bearing based on the relative compensation distance of multiple-domain features and locally linear embedding. Mechanical systems and signal processing, 86, 40–57. DOI:10.1016/j.ymssp.2016.10.006
[19]    Cerrada, M., Sánchez, R. V., Cabrera, D., Zurita, G., & Li, C. (2015). Multi-stage feature selection by using genetic algorithms for fault diagnosis in gearboxes based on vibration signal. Sensors (Switzerland), 15(9), 23903–23926. DOI:10.3390/s150923903
[20]    Eckmann, J. P., Kamphorst, S. O., & Ruelle, D. (1995). Recurrence plots of dynamical systems. Europhysics letters (EPL), 4(9), 973–977.
[21]    Wang, Z., Oates, T. (2015). Encoding time series as images for visual inspection and classification using tiled convolutional neural networks. Workshops at the twenty-ninth aaai conference on artificial intelligence (Vol. 1). AAAI Menlo Park, CA, USA.
[22]    Wagner, T., & Sommer, S. (2021). Feature based bearing fault detection with phase current sensor signals under different operating conditions [presentation]. PHM society european conference (pp. 448–456).
[23]    Kimotho, J. K. (2016). Development and performance evaluation of prognostic approaches for technical systems (Ph.D Thesis, University Paderborn of German).
[24]    Pearson, K. (1901).  LIII. On lines and planes of closest fit to systems of points in space . The London, edinburgh, and dublin philosophical magazine and journal of science, 2(11), 559–572. DOI:10.1080/14786440109462720
[25]    Peng, H., Long, F., & Ding, C. (2005). Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE transactions on pattern analysis and machine intelligence, 27(8), 1226–1238. DOI:10.1109/TPAMI.2005.159
[26]    Rações, H. D. L., Ferreira, F. J. T. E., Pires, J. M., & Damásio, C. V. (2019). Application of different machine learning strategies for current-and vibration-based motor bearing fault detection in induction motors. IECON 2019-45th annual conference of the ieee industrial electronics society (Vol. 1, pp. 68–73). IEEE.
[27]    Javel, I. M., Salvador, R. C., Dadios, E., Vicerra, R. R. P., & Teologo, A. T. (2019). Epileptic seizure detection via eeg using tree-based pipeline optimization tool. 2019 IEEE 11th international conference on humanoid, nanotechnology, information technology, communication and control, environment, and management, hnicem 2019 (pp. 1–5). IEEE. DOI: 10.1109/HNICEM48295.2019.9073465
[28]    De Sa, F. P. G., Brandao, D. N., Ogasawara, E., Coutinho, R. D. C., & Toso, R. F. (2020). Wind turbine fault detection: a semi-supervised learning approach with automatic evolutionary feature selection. International conference on systems, signals, and image processing (Vol. 2020-July, pp. 323–328). IEEE.
[29]    Shukla, A., Tiwari, R., & Kala, R. (2010). Towards hybrid and adaptive computing: a perspective (Vol. 307). Springer.
[30]    Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation, 6(2), 182–197. DOI:10.1109/4235.996017
[31]    Maćkiewicz, A., & Ratajczak, W. (1993). Principal components analysis (PCA). Computers & geosciences, 19(3), 303–342.
[32]    Shahana, A. H., & Preeja, V. (2016). Survey on feature subset selection for high dimensional data. 2016 international conference on circuit, power and computing technologies (ICCPCT) (pp. 1–4). IEEE.