Research Progress on Big Data Feature Mining of Electromagnetic Induction Effects in Electric Motors
DOI:
https://doi.org/10.61173/c06f1k45Keywords:
Electromagnetic induction effect, big data feature extraction, anomaly detection, intelligent designAbstract
With the rapid development of Industry 4.0 and intelligent manufacturing, electromagnetic induction effects in motors, such as eddy current effects, harmonic distortion, and hysteresis losses, have become key factors affecting the energy efficiency and lifespan of motors. However, traditional analytical methods are highly dependent on limited working condition simulations and experimental data. This paper systematically reviews the application progress of big data technology in the study of electromagnetic induction effects in motors, with a focus on analyzing the advantages and disadvantages of traditional simulation, machine learning, and deep learning methods in feature extraction, anomaly detection, and optimization design. Research shows that data-driven technologies have significantly enhanced the accuracy and efficiency of energy efficiency optimization, fault diagnosis, and intelligent control. Future research needs to further integrate multi-source data with physical models to provide theoretical support and practical guidance for intelligent design, predictive maintenance, and energy efficiency optimization.
References
[1] Li Junqing et al. Motor Bearing Fault Diagnosis Method Based on current signals and deep reinforcement learning, Electric Power Science and Engineering,2003,3,(39),pp.61-70
[2] Hyeon Bae, Sungshin Kim, Yon Tae Kim, et al. Application of Time-Series Data Mining for Fault Diagnosis of Induction Motors, Journal of Mechanical Science and Technology,volume 19,issue 6, pp.1770-1778
[3] R. Leidhold, D. Kalugin, O. Tolochko, Experimental research of the magnetization and demagnetization process of the vector-controlled induction motor, IEEE Transactions on Energy Conversion, early access, May 2024, doi: 10.1109/ TEC.2024.3385437
[4] Shi Jie, Wu Xing, Liu Tao. Diagnosis of Bearing Recheck Faults using HHT Algorithm and Convolutional Neural Network. Transactions of the Chinese Society of Agricultural Engineering, 2020,2,vol.36,No.4
[5] Li Weili, Zhang Xiaolei, Wang Yuhang. Temperature rise characteristics of rotor with sheath permanent magnet servo motor under current-time harmonic action. Proceedings of the CSEE, 2023,43*(12), 4567-4580
[6] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536.
[7] Wang Manxi, Lu Keyu, Wang Jiabao, et al. Small Sample Recognition Technology Based on Data Augmentation and Ensemble Learning [J]. Mobile Communications, 2022,46(7): 02-09.
[8] WANG Xiang, DENG Wen, LIU Shixiong, HUANG Zhitao. Anomaly detection method of electromagnetic time series based on attention mechanism[J]. Journal of Terahertz Science and Electronic Information Technology, 2021, 19(4): 581-588
[9] Yongji Zhang. “Electrical Engineering and Intelligent Control Strategies in Renewable Energy Integration: Enhancing Energy Sustainability.” Journal of Theory and Practice of Management Science,2024.04(05).06, issn:2790-1491
[10] D. Gheorghe, Mihai Ioan. “ASPECTS REGARDING DATA MINING APPLIED TO FAULT DETECTION.” Annals of the Oradea University: Fascicle Management and Technological Engineering, Volume IX(XIX),2010,NR2
[11] Shanghai Electric Corporation Limited, Predictive maintenance of intelligent high-end equipment in industrial Internet. http://www.yrdcpcn.com/upload/2023/0822/89710010- 6c9d-46ef-917d-5e6135fccfe6.pdf
Downloads
Published
Issue
Section
License
Copyright (c) 2025 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
