Kalıcı Mıknatıs Destekli Senkron Relüktans Motor Sargı Arızasının Evrişimli Sinir Ağı ile Teşhisi

Year 2024, Volume: 19 Issue: 2, 415 - 425, 30.09.2024

Ayse Bayrak , Canan Taştimur , Erhan Akın

https://doi.org/10.55525/tjst.1463429

Abstract

Son yıllarda hata tespiti için makine öğrenmesi modellerinin kullanımı yaygınlaşmıştır. Amacı, kalıcı mıknatıs destekli senkron relüktans motor ilgili sorunları tanımlamak ve düzeltmektir. Bu araştırmanın temel amacı, hataları erken aşamalarında tanımlamak ve sınıflandırmaktır. Bağımsız Bileşen Analizi ve Derin Öğrenme modelleri gibi makine öğrenimi yaklaşımlarını kullanarak motor arızalarını sınıflandırdık. Bağımsız Bileşen Analizi (ICA) kullanarak titreşim ve akım sinyallerini motor sinyallerinden elde ettik. Sıfırdan tasarladığımız evrişimsel sinir ağı (CNN) mimarisini ve Transfer Öğrenme tekniğini kullanarak birden fazla mimari üzerinde denemeler yaptık ve elde ettiğimiz sinyalleri kullanarak oluşturduğumuz iki farklı veri setini test ettik. Deneysel bulgulara göre, önerilen sıfırdan CNN modeli, sınıflandırmada son derece iyi performans göstererek akım sinyallerle %98,7 ve titreşim sinyalleriyle %99,4’e ulaşmıştır.

Keywords

Devre arızaları, arıza tespiti, makine öğrenmesi, kalıcı mıknatıslı motorlar.

Diagnosis of Permanent Magnet Assisted Synchronous Reluctance Motor Winding Fault by Convolutional Neural Network

Abstract

In recent years, the use of machine learning models for fault detection has become commonplace. Its goal is to identify and fix problems with permanent magnet synchronous reluctance motors. This research’s primary goal is to identify and categorize errors in their early stages. We classified winding faults using machine learning approaches, such as Independent Component Analysis and Deep Learning models. We could distinguish between vibration and current signals from the engine signals by using Independent Component Analysis (ICA). We experimented on multiple architectures using the convolutional neural network (CNN) architecture we designed from scratch and the Transfer Learning technique, testing two distinct datasets we generated using the signals we got. According to experimental findings, the suggested scratch CNN model performed exceptionally well in classification, achieving 98.6% with current signals and 99.4% with vibration signals.

Keywords

Circuit Faults, Fault Detection, Machine Learning, Permanent Magnet Motors

References

• Jung W, Yun SH, Lim YS, Cheong S, Park H. Vibration and current dataset of three-phase permanent magnet synchronous motors with stator faults. Data in Brief 2023; 47, 108952.
• Arafat AKM, Choi S. Optimal Phase Advance Under Fault-Tolerant Control of a Five-Phase Permanent Magnet Assisted Synchronous Reluctance Motor. IEEE Trans Ind Electron 2018; 65(4): 2915-2924.
• Soualhi A, Clerc G, Razik H, & Ondel O. Detection of induction motor faults by an improved artificial ant clustering. In: IECON 2011-37th Annual Conference of the IEEE Industrial Electronics Society; 10 November 2011; Melbourne, VIC, Australia: IEEE. pp. 3446-3451.
• Glowacz A, & Glowacz Z. Diagnosis of stator faults of the single-phase induction motor using acoustic signals. Appl Acoust 2017; 117: 20-27.
• Glowacz A. Diagnostics of rotor damages of three-phase induction motors using acoustic signals and SMOFS-20-EXPANDED. Arch Acoust 2016; 41(3): 507-515.
• Glowacz A, & Glowacz Z. Diagnostics of stator faults of the single-phase induction motor using thermal images, MoASoS and selected classifiers. Meas 2016; 93: 86-93.
• López TC, Riba JR., Garcia A, & Romeral L. Detection of eccentricity faults in five-phase ferrite-PM assisted synchronous reluctance machines. Appl Sci 2017; 7(6): 565.
• Pazouki E, Islam MZ, Bonthu SSR, & Choi S. Eccentricity fault detection in multiphase permanent magnet assisted synchronous reluctance motor. In: 2015 IEEE International Electric Machines & Drives Conference (IEMDC); 13 May 2015; United States: IEEE. pp. 240-246.
• Moradi CH, & Behroozi L. Analytical design, electromagnetic field analysis and parametric sensitivity analysis of an external rotor permanent magnet-assisted synchronous reluctance motor. Electr Eng 2020; 102(4): 1947-1957.
• Wang B, Wang J, Sen B, Griffo A, Sun Z, & Chong E. A fault-tolerant machine drive based on permanent magnet-assisted synchronous reluctance machine. IEEE Trans Ind Appl 2017; 54(2): 1349-1359.
• Zine W. HF signal injection and Machine Learning for the sensorless control of IPMSM-based EV drives. Ph. D. thesis, 2017.
• Luo Y, Qiu J, & Shi C. Fault detection of permanent magnet synchronous motor based on deep learning method. In: 2018 21st International Conference on Electrical Machines and Systems (ICEMS); 10 October 2018; Jeju, Korea (South): IEEE. pp. 699-703.
• Kao IH, Wang WJ, Lai Y. H, & Perng JW. Analysis of permanent magnet synchronous motor fault diagnosis based on learning. IEEE Trans Instrum Meas 2018; 68(2): 310-324.
• Chen Y, Liang S, Li W, Liang H, & Wang C. Faults and diagnosis methods of permanent magnet synchronous motors: A review. Appl Sci 2019; 9(10): 2116.
• Ebrahimi BM, Faiz J, & Roshtkhari MJ. Static-, dynamic-, and mixed-eccentricity fault diagnoses in permanent-magnet synchronous motors. IEEE Trans Ind Electron 2009; 56(11): 4727-4739.
• Xu X, Qiao X, Zhang N, Feng J, & Wang X. Review of intelligent fault diagnosis for permanent magnet synchronous motors in electric vehicles. Adv Mech Eng 2020; 12(7): 1687814020944323.
• Jung W, Yun S. H, Lim YS, Cheong S, & Park YH. Vibration and current dataset of three-phase permanent magnet synchronous motors with stator faults. Data in Brief 2023; 47, 108952.
• Copeland BJ, & Proudfoot D. Artificial intelligence: History, foundations, and philosophical issues. Philosophy of psychology and cognitive science, North-Holland: press, 2007.
• Verma M. Artificial intelligence and its scope in different areas with special reference to the field of education. Int J Adv Educ Res 2018; 3(1): 5-10.
• Mukhamediev RI, Popova Y, Kuchin Y, Zaitseva E, Kalimoldayev A, Symagulov A, & Yelis M. Review of artificial intelligence and machine learning technologies: Classification, restrictions, opportunities and challenges. Mathematics 2022; 10(15), 2552.
• Izonin I, Tkachenko R, Peleshko D, Rak T, & Batyuk D. Learning-based image super-resolution using weight coefficients of synaptic connections. In; 2015 Xth International Scientific and Technical Conference Computer Sciences and Information Technologies (CSIT); 17 Sept. 2015; Lviv, Ukraine: IEEE. pp. 25-29.
• Shen D, Wu G, & Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng 2017; 19: 221-248.
• Panetto H, Iung B, Ivanov D, Weichhart G, & Wang X. Challenges for the cyber-physical manufacturing enterprises of the future. Annu Rev Control 2019; 47: 200-213.
• Tuncer T, Ertam F, Dogan S, Aydemir E, & Pławiak P. Ensemble residual network-based gender and activity recognition method with signals. J Supercomput 2020; 76: 2119-2138.
• Barakhnin VB, Duisenbayeva AN, Kozhemyakina OY, Yergaliyev Y. & Muhamedyev RI. The automatic processing of the texts in natural language. Some bibliometric indicators of the current state of this research area. Journal of physics. Conference series 2018; 1117(1).
• Hirschberg J, & Manning CD. Advances in natural language processing. Science 2015; 349(6245): 261-266.
• Abdullahi M, Baashar Y, Alhussian H, Alwadain A, Aziz N, Capretz LF. & Abdulkadir S. J. Detecting cybersecurity attacks in Internet of things using artificial intelligence methods: A systematic literature review. Electronics 2022; 11(2), 198.
• Lennartsson A. & Blomberg M. Fault Detection in Permanent Magnet Synchronous Motors using Machine Learning. 2021.
• Bohm T. How precise has fault detection to be? Answers from an economical point of view. In; Proceedings of the 26th International Congress on Condition Monitoring and Diagnostics Engineering Management; 5 July 2018; Rustenburg, South Africa; pp. 460-466.