استفادۀ مؤثر از روش SVM جهت تشخیص معایب موتورهای الکتریکی به کمک آنالیز اجزای محدود

نوع مقاله : مقاله پژوهشی (کاربردی)

نویسندگان

1 دانشجوی دکتری، گروه مهندسی برق، دانشکده مهندسی برق، دانشگاه زنجان، زنجان، ایران.

2 استاد، گروه مهندسی برق، دانشکده مهندسی برق، دانشگاه زنجان، زنجان، ایران.

3 استادیار، گروه مهندسی برق، گروه مهندسی برق و کامپیوتر ،دانشگاه فنی و حرفه‌ای، تهران، ایران.

10.48301/kssa.2023.389534.2495

چکیده

مقالۀ حاضر حاوی رویکردی کاربردی برای استفاده از روش ماشین بردار پشتیبان (SVM) در تشخیص خطاهای ماشین‌های الکتریکی با استفاده از آنالیز اجزای محدود (FEA) است. لازمۀ استفاده از روش SVM در تشخیص خطاها، طی شدن فاز آموزش آن است که خود مستلزم دسترسی به داده‌های کافی می‌باشد. مجموعۀ داده‌ها براساس شبیه‌سازی، در همان بستر شبیه‌سازی محدود هستند و مجموعه داده‌های آزمایشگاهی نیازمند تهیه چندین موتور می‌باشند تا از یک موتور به‌صورت سالم داده‌برداری ‌شود و بقیۀ موتورها معیوب‌سازی شده و در شرایط معیوب داده‌برداری گردند. حال آن‌که در شرایط واقعی، مجموعۀ داده‌ای از موتور معیوب در دسترس نیست. از طرفی به دلیل زمان‌بری و هزینه‌بری، امکان معیوب‌سازی و داده‌برداری از موتور‌های الکتریکی منحصر به‌فرد، دائم‌کار در خطوط تولید و گران‌قیمت فراهم نمی‌باشد. روش پیشنهادی در این مقاله، استفاده از همان موتور واقعی سالم است و نیازی به هزینه‌های مرتبط با تهیۀ چندین موتور و معیوب‌سازی آنها را ندارد. مجموعۀ داده در این روش با تکیه بر شبیه‌سازی و ایجاد ارتباط بین محیط شبیه‌سازی و آزمایشگاهی فراهم می‌شود. در ابتدا، با استفاده از روش FEA عیوب اتصال حلقۀ استاتور، شکست میله روتور و ناهم‌محوری شبیه‌سازی شده و مجموعه داده آنها تهیه می‌شود. سپس با تحلیل اثر جریان موتور، شاخص‌های عیوب استخراج شده و در طراحی شبکه‌های SVM مناسب استفاده می‌شوند. با اعمال ضرایب اصلاحی، انطباق لازم در ورودی‌های شبکه‌های SVM آموزش‌دیده جهت تشخیص عیوب موتور واقعی مشابه فراهم می‌شود. نتایج حاکی از قابلیت بالای روش پیشنهادی جهت تفکیک عیوب در موتورهای آزمایشگاهی مشابه است. 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

The Effective Use of SVM to Detect Faults in Electric Machines by Finite Element Analysis

نویسندگان [English]

  • Seyed Hamid Rafiei 1
  • Mansour Ojaghi 2
  • Mahdi Sabouri 3
1 PhD Student, Department of Electrical Engineering, Zanjan University (ZNU), Zanjan, Iran.
2 Professor, Department of Electrical Engineering, Zanjan University (ZNU), Zanjan, Iran.
3 Assistant Professor, Department of Electrical & Computer Engineering, Technical and Vocational University (TVU), Tehran, Iran.
چکیده [English]

This article presents a new approach to using Support Vector Machine (SVM) in the diagnosis of machine faults by finite element analysis (FEA). The requirement of using SVM in fault diagnosis is to go through their initial training phase, which requires access to sufficient data. The simulation dataset has been limited only to that simulation platform, and the laboratory dataset requires several motors to prepare data. In addition to the data of the healthy motor, the faults must be introduced intentionally into other motors to collect data under faulty conditions. However, a dataset of the faulty motor is not available in natural situations. On the other hand, due to the time consumption and cost, it is not possible to use this method to collect data from the unique, expensive, and non-stopping motors. The proposed method only uses the healthy motor and does not consist of the costs associated with purchasing several motors and damaging them. The dataset in this method was provided from motor simulation and then used in the laboratory environment. First, the stator inter-turn short circuit, broken rotor bar, and eccentricity faults were simulated using the FEA to create a dataset for the considered motor. Then, the indicators were extracted by the motor current signature analysis to design suitable SVM models. By the correction factor, the inputs of the trained SVM models were adjusted to detect faults in a laboratory motor. The results confirmed the high capability of the proposed approach to distinguish defects in similar laboratory motors.

کلیدواژه‌ها [English]

  • Support Vector Machine
  • Fault Detection
  • Finite Element
  • Current Signature
[1] Solodkiy, E., Dadenkov, D., & Salnikov, S. (2019 January 30- February 02). Detection of stator inter-turn short circuit in three-phase induction motor using current coordinate transformation. 2019 26th International Workshop on Electric Drives: Improvement in Efficiency of Electric Drives, Moscow, Russia.  https://doi.org/10.1109/IWED.20 19.8664353
[2] Abad, H. B. B., Ojaghi, M., & Taheri, A. (2021). Efficient index for detecting the stator winding interturn fault in six-phase squirrel-cage induction motors. Measurement, 184, 109912. https://doi.org/10.1016/j.measurement.2021.109912
[3] Ojaghi, M., Sabouri, M., & Faiz, J. (2018). Performance analysis of squirrel-cage induction motors under broken rotor bar and stator inter-turn fault conditions using analytical modeling. Institute of Electrical and Electronics Engineers Transactions on Magnetics, 54(11), 1-5. https://doi.org/10.1109/TMAG.2018.2842240.
[4] Sridhar, S., Rao, K. U., Umesh, R., & Harish, K. (2016 November 22-25). Condition monitoring of Induction Motor using statistical processing. 2016 Institute of Electrical and Electronics Engineers Region 10 Conference (TENCON), Singapore, Asia.  https://doi.org/10.1 109/TENCON.2016.7848597
[5] Seshadrinath, J., Singh, B., & Panigrahi, B. K. (2013). Incipient turn fault detection and condition monitoring of induction machine using analytical wavelet transform. Institute of Electrical and Electronics Engineers Transactions on Industry Applications, 50(3), 2235-2242. https://doi.org/10.1109/IAS.2012.6374026
[6] Das, S., Koley, C., Purkait, P., & Chakravorti, S. (2010, July 25-29). Wavelet aided SVM classifier for stator inter-turn fault monitoring in induction motors. Institute of Electrical and Electronics Engineers Power and Energy Society general meeting, Minneapolis, Minnesota, United States. https://doi.org/10.1109/PES.2010.5589595
[7] Jagadanand, G., & Dias, F. L. (2015, February 19-21). ARM based induction motor fault detection using wavelet and support vector machine. 2015 Institute of Electrical and Electronics Engineers International Conference on Signal Processing, Informatics, Communication and Energy Systems, Kozhikode, India. https://doi.org/10.1109/SP ICES.2015.7091503
[8] Das, S., Purkait, P., Koley, C., & Chakravorti, S. (2014). Performance of a load-immune classifier for robust identification of minor faults in induction motor stator winding. Institute of Electrical and Electronics Engineers Transactions on Dielectrics and Electrical Insulation, 21(1), 33-44. https://doi.org/10.1109/TDEI.2013.003549
[9] Mohamed, M., Mohamed, E., Mohamed, A-A., Abdel-Nasser, M., & Hassan, M. M. (2020). Detection of inter turn short circuit faults in induction motor using artificial neural network. 2020 26th Conference of Open Innovations Association (FRUCT), Yaroslavl, Russia.  https://doi.org/10.23919/FRUCT48808.2020.9087535
[10] Shih, K-J., Hsieh, M-F., Chen, B-J., & Huang, S-F. (2022). Machine Learning for Inter-Turn Short-Circuit Fault Diagnosis in Permanent Magnet Synchronous Motors. Institute of Electrical and Electronics Engineers Transactions on Magnetics, 58(8), 1-7. http s://doi.org/10.1109/TMAG.2022.3169173
[11] Vinayak, B. A., Uddin, R., & Jagadanaand, G. (2017, November 16-18). Inter phase fault detection in inverter fed induction motor using wavelet transform. 2017 3rd International Conference on Condition Assessment Techniques in Electrical Systems, Rupnagar, India. https://doi.org/10.1109/CATCON.2017.8280193
[12] Husari, F., & Seshadrinath, J. (2021). Incipient Interturn fault detection and severity evaluation in electric drive system using hybrid HCNN-SVM based model. Institute of Electrical and Electronics Engineers Transactions on Industrial Informatics, 18(3), 1823-1832. https://doi.org/10.1109/TII.2021.3067321
[13] Ishkova, I., & Vítek, O. (2015, May 20-22). Diagnosis of eccentricity and broken rotor bar related faults of induction motor by means of motor current signature analysis. 2015 16th international scientific conference on electric power engineering, Kouty nad Desnou, Czech Republic. https://doi.org/10.1109/EPE.2015.7161130
[14] Fireteanu, V., Constantin, A-I., Zorig, A., & Chouder, A. (2018, October 4-6). Impact of the Stator Short-circuit, Rotor Broken Bar and Eccentricity Faults on Rotor Force for Loaded and No-load Induction Motors Operation. 2018 International Conference on Applied and Theoretical Electricity, Craiova, Romania. https://doi.org/10.1109/ICATE.201 8.8551471
[15] Fireteanu, V., Constantin, A., & Popa, M. (2018, September 3-6). Influence of single or multiple faults short-circuit, broken rotor bar and eccentricity on the torque and rotor force in induction motors. 2018 XIII International Conference on Electrical Machines, Alexandroupoli, Greece. https://doi.org/10.1109/ICELMACH.2018.8507008
[16] Seghiour, A., Seghier, T., & Zegnini, B. (2015, May 25-27). Diagnostic of the simultaneous of dynamic eccentricity and broken rotor bars using the magnetic field spectrum of the air-gap for an induction machine. 2015 3rd International Conference on Control, Engineering & Information Technology, Tlemcen, Algeria https://doi.org/10.1109/ CEIT.2015.7233158
[17] Antonino-Daviu, J., Quijano-López, A., Climente-Alarcon, V., & Razik, H. (2017, October 1-5). Evaluation of the detectability of rotor faults and eccentricities in induction motors via transient analysis of the stray flux. 2017 Institute of Electrical and Electronics Engineers Energy Conversion Congress and Exposition, Cincinnati, Ohio, United States. https://doi.org/10.1109/ECCE.2017.8096633
[18] Luo, G., Habetler, T. G., & Hurwitz, J. (2019, September 29- October 03). A multi-sensor fusion scheme for broken rotor bar and air-gap eccentricity detection of induction machines. 2019 Institute of Electrical and Electronics Engineers  Energy Conversion Congress and Exposition, Baltimore, Maryland, United States. https://doi.org/10.11 09/ECCE.2019.8912275
[19] Zgarni, S. E., & Braham, A. (2016, March 21-23). Intelligent induction motor diagnosis system: A new challenge. 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing, Monastir, Tunisia. https://doi.org/10.1109/ATSIP. 2016.7523125
[20] Keskes, H., & Braham, A. (2015). Recursive undecimated wavelet packet transform and DAG SVM for induction motor diagnosis. Institute of Electrical and Electronics Engineers Transactions on Industrial Informatics, 11(5), 1059-1066. https://doi.org/10.1109/T II.2015.2462315
[21] Pezzani, C. M., Fontana, J. M., Donolo, P. D., De Angelo, C. H., Bossio, G. R., & Silva, L. I. (2018, August 22-24). Svm-based system for broken rotor bar detection in induction motors. 2018 Institute of Electrical and Electronics Engineers ANDESCON, Santiago de Cali, Colombia. https://doi.org/10.1109/ANDESCON.2018.8564627
[22] Vishwakarma, H. O., Sajan, K., Maheshwari, B., & Dhiman, Y. D. (2015, August 12-14). Intelligent bearing fault monitoring system using support vector machine and wavelet packet decomposition for induction motors. 2015 international conference on power and advanced control engineering, Bengaluru, India. https://doi.org/10.1109/ICPA CE.2015.7274969
[23] Zarei, J., Arefi, M. M., & Hassani, H. (2015, May 27-29). Bearing fault detection based on interval type-2 fuzzy logic systems for support vector machines. 2015 6th International Conference on Modeling, Simulation, and Applied Optimization, Istanbul, Turkey. https://doi.org/10.1109/ICMSAO.2015.7152214
[24] Choudhary, A., Goyal, D., & Letha, S. S. (2020). Infrared thermography-based fault diagnosis of induction motor bearings using machine learning. Institute of Electrical and Electronics Engineers Sensors Journal, 21(2), 1727-1734. https://doi.org/10.1109/JSEN.2020.3 015868
[25] Abid, F. B., Zgarni, S., & Braham, A. (2016, October 23-26). Bearing fault detection of induction motor using SWPT and DAG support vector machines. IECON 2016-42nd Annual Conference of the Institute of Electrical and Electronics Engineers Industrial Electronics Society, Florence, Italy. https://doi.org/10.1109/IECON.2016.7793237
[26] Gunasekaran, S., Pandarakone, S. E., Asano, K., Mizuno, Y., & Nakamura, H. (2018, September 23-26). Condition monitoring and diagnosis of outer raceway bearing fault using support vector machine. 2018 Condition Monitoring and Diagnosis, Perth, Western Australia, Australia. https://doi.org/10.1109/CMD.2018.8535744
[27] Abid, F. B., Zgarni, S., & Braham, A. (2018). Distinct bearing faults detection in induction motor by a hybrid optimized SWPT and aiNet-DAG SVM. Institute of Electrical and Electronics Engineers transactions on Energy Conversion, 33(4), 1692-1699. https://doi.org/10.1109/TEC.2018.2839083
[28] Pandarakone, S. E., Akahori, K., Matsumura, T., Mizuno, Y., & Nakamura, H. (2017, March 22-25). Development of a methodology for bearing fault scrutiny and diagnosis using SVM. 2017 Institute of Electrical and Electronics Engineers International Conference on Industrial Technology, Toronto, Ontario, Canada. https://doi.org/10.1109/ICIT.2 017.7913097
[29] Georgoulas, G., Climente-Alarcon, V., Antonino-Daviu, J. A., Stylios, C. D., Arkkio, A., & Nikolakopoulos, G. (2016, July 19-21). A multi-label classification approach for the detection of broken bars and mixed eccentricity faults using the start-up transient. 2016 Institute of Electrical and Electronics Engineers 14th International Conference on Industrial Informatics, Poitiers, France. https://doi.org/10.1109/INDIN.2016.78 19198
[30] Singh, H., Seera, M., & Abdullah, M. Z. (2013, August 4-9). Detection and diagnosis of broken rotor bars and eccentricity faults in induction motors using the fuzzy min-max neural network. The 2013 international joint conference on neural networks, Dallas, Texas, United States. https://doi.org/10.1109/IJCNN.2013.6707003
[31] Silva, V. A., & Pederiva, R. (2013, October 29-30). Fault detection in induction motors based on artificial intelligence. Proceedings of the International Conference on Surveillance, Chartres, France. https://www.semanticscholar.org/paper/Fault-detect ion-in-induction-motors-based-on-Silva-Pederiva/6d9793d397cf6d9f8359c6e7930 ed083f25d0833
[32] Smart, E., Brown, D., & Axel-Berg, L. (2013, September 22-25). Comparing one and two class classification methods for multiple fault detection on an induction motor. 2013 Institute of Electrical and Electronics Engineers Symposium on Industrial Electronics & Applications, Kuching, Malaysia. https://doi.org/10.1109/ISIEA.2013.6738982
[33] Valencia, J. B., Sanchez, M. P., Roman, J. M., Panadero, R. P., & Bano, A. S. (2014, November 18-20). Study of performance of several techniques of fault diagnosis for induction motors in steady-state with svm learning algorithms. 2014 2nd International Conference on Artificial Intelligence, Modelling and Simulation, Madrid, Spain. https://doi.org/ 10.1109/AIMS.2014.47
[34] Kandukuri, S. T., Senanyaka, J. S. L., Huynh, V. K., & Robbersmyr, K. G. (2019). A two-stage fault detection and classification scheme for electrical pitch drives in offshore wind farms using support vector machine. Institute of Electrical and Electronics Engineers Transactions on Industry Applications, 55(5), 5109-5118. https://doi.org/10.1109/T IA.2019.2924866
[35] Liang, X., Ali, M. Z., & Zhang, H. (2019). Induction motors fault diagnosis using finite element method: A review. Institute of Electrical and Electronics Engineers Transactions on Industry Applications, 56(2), 1205-1217. https://doi.org/10.1109/TIA.2019.2958908
[36] Gyftakis, K. N., & Cardoso, A. M. (2017, April 20-21). A new space vector approach to detect stator faults in induction motors. 2017 Institute of Electrical and Electronics Engineers Workshop on Electrical Machines Design, Control and Diagnosis, Nottingham, United Kingdom. https://doi.org/10.1109/WEMDCD.2017.7947752
[37] Halder, S., Bhat, S., & Dora, B. (2022). Prediction of broken rotor bar in induction motor using spectral entropy features and tlbo optimized svm. Turkish Journal of Electrical Engineering and Computer Sciences, 30(5), 1962-1979. https://doi.org/10.55730/13 00-0632.3916
[38] Mazouji, R., Khaloozadeh, H., & Arasteh, M. (2020, February 4-6). Fault Diagnosis of Broken Rotor Bars in Induction Motors Using Finite Element Analysis. 2020 11th Power Electronics, Drive Systems, and Technologies Conference, Tehran, Iran https://doi. org/10.1109/PEDSTC49159.2020.9088429
[39] Polat, A., Yilmaz, A., & Ergene, L. T. (2018). Investigation of The Effects of Eccentricity on Induction Motor via Multi-Resolution Wavelet Analysis. Electrica, 18(2), 187-197. https://doi.org/10.5152/iujeee.2018.1821
[40] Tian, K., Zhang, T., Ai, Y., & Zhang, W. (2018). Induction motors dynamic eccentricity fault diagnosis based on the combined use of WPD and EMD-simulation study. Applied Sciences, 8(10), 1709. https://doi.org/10.3390/app8101709
[41] Fantin Irudaya Raj, E., & Appadurai, M. (2022). Static 2D-Finite Element Analysis of Eccentricity Fault in Induction Motor. In: M, L. Kolhe, S. B. Jaju, & P. M. Diagavane (Eds.) Smart Technologies for Energy, Environment and Sustainable Development, Vol 1. Springer. https://doi.org/10.1007/978-981-16-6875-3_33
[42] Priya, B. H., Karthick, R., Lokprakash, B., Vasanth, S., & Praveen, N. K. (2020, April 9-10). Static eccentricity fault analysis in inverter fed induction motor using finite element method. Institute of Physics Conference Series: Materials Science and Engineering: Second International Conference on Materials Science and Manufacturing Technology, Hotel Aloft, Coimbatore, Tamil Nadu, India.  https://doi.org/10.1088/1757-899X/87 2/1/012049
[43] Kuczmann, M., Gadó, K., Horváth, S., Vajda, I., Marcsa, D., & Belahcen, A. (2018). Analysis of an Induction Machine by the Finite Element Method. Recent Innovations in Mechatronics, 5(1), 1-5. https://doi.org/10.17667/riim.2018.1/5
[44] Ding, Z., Bu, W., Cai, X., Wu, X., & Liu, S. (2019, October 12-13). Finite Element Analysis and Modeling of Three-Phase Induction Motor. Institute of Physics Conference Series: Materials Science and Engineering, Melbourne, Australia. http://dx.doi.org/10.1088 /1757-899X/677/5/052055  
[45] Pascual, D. G. (2015). Artificial intelligence tools: decision support systems in condition monitoring and diagnosis. Crc Press. https://www.routledge.com/Artificial-Intellig ence-Tools-Decision-Support-Systems-in-Condition-Monitoring/Pascual/p/book/9 780367738358
[46] Martinez-Herrera, A. L., Ferrucho-Alvarez, E. R., Ledesma-Carrillo, L. M., Mata-Chavez, R. I., Lopez-Ramirez, M., & Cabal-Yepez, E. (2022). Multiple fault detection in induction motors through homogeneity and kurtosis computation. Energies, 15(4), 1541. https ://doi.org/10.3390/en15041541
[47] Garcia-Calva, T., Morinigo-Sotelo, D., Fernandez-Cavero, V., & Romero-Troncoso, R. (2022). Early Detection of Faults in Induction Motors—A Review. Energies, 15(21), 7855. https://doi.org/10.3390/en15217855