The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Activation Function Selection of CNN for Inductive Motor Static Fault Diagnosis

유도전동기의 고정자 고장 진단을 위한 CNN의 활성화 함수 선정

  • Kim, Kyoung-Min (Dept. of Electrical and Semiconductor Eng. Chonnam National Univ.) ;
  • Kim, Yong-Hyeon (Dept. of Electrical and Semiconductor Eng. Chonnam National Univ.) ;
  • Park, Guen-Ho (Dept. of Electrical and Semiconductor Eng. Chonnam National Univ.) ;
  • Lee, Buhm (Dept. of Electrical and Semiconductor Eng. Chonnam National Univ.) ;
  • Lee, Sang-Ro (WP Co., ltd.) ;
  • Goh, Yeong-Jin (Dept. of Electrical Eng. Tongmyeong University)
  • 김경민 (전남대학교 전기및반도체공학과) ;
  • 김용현 (전남대학교 전기및반도체공학과) ;
  • 박근호 (전남대학교 전기및반도체공학과) ;
  • 이범 (전남대학교 전기및반도체공학과) ;
  • 이상로 ;
  • 고영진 (동명대학교 전기공학과)
  • Received : 2021.03.01
  • Accepted : 2021.04.17
  • Published : 2021.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose an efficient CNN application method by analyzing the effect of activation function on the failure diagnosis of the inductive motor stator. Generally, the main purpose of the inductive motor stator failure diagnosis is to prevent the failure by rapidly diagnosing the minute turn short. In the application of activation function, experiments show that the Sigmoid function is 23.23% more useful in accuracy of diagnosis than the ReLu function, although it is shown that ReLu has superiority in overall fixer failure in utilizing the activation function.

본 논문에서는 유도전동기 고정자 고장 진단에 있어서 활성화 함수가 미치는 영향을 분석하여 효율적인 CNN 활용 방법을 제안하였다. 일반적으로 유도전동기 고정자 고장 진단의 주된 목적은 미세한 턴 단락을 빠르게 진단함으로 고장을 미리 방지함에 있다. 이에 활성화 함수 활용에 있어서 전반적인 고정자 고장에는 ReLu가 우수성을 보임을 알 수 있었으나, 미세한 턴 단락인 2턴 단락에 있어서는 Sigmoid 함수가 ReLu 함수보다 진단의 정확도에 있어서 23.23% 유용함을 실험을 통해 확인할 수 있었다.

Keywords

References

  1. A. Boum, N. Y. J. Maurice, L. N. Nneme, and L. M. Mbumda, "Fault Diagnosis of an Induction Motor based on Fuzzy Logic, Artificial Neural Network and Hybrid System," Int J of Control, vol. 8, no. 2, 2018, pp. 42-51.
  2. S. E. Pandarakone, Y. Mizuno, and H. Nakamura, "A Comparative Study between Machine Learning Algorithm and Artificial Intelligence Neural Network in Detecting Minor Bearing Fault of Induction Motors," Energies, vol. 12, no. 11, 2019, pp. 2105. https://doi.org/10.3390/en12112105
  3. J. C. Quiroz, N. Mariun, M. R. Mehrjou, M. Izadi, N. Misron, and M. A. M. Radzi, "Fault detection of broken rotor bar in LS-PMSM using random forests," Measurement, vol. 116, 2018, pp. 273-280. https://doi.org/10.1016/j.measurement.2017.11.004
  4. F. Filippetti, G. Frauceschini, C. Tassoni, and P. vas, "Recent developments of induction motor drives fault diagnosis using AI techniques," IEEE Trans. on Enegy Conversion, vo1. 21, 2006, pp. 1-8. https://doi.org/10.1109/TEC.2005.847964
  5. T. Khan, P. Alekhya, and J. Seshadrinath, "Incipient inter-turn fault diagnosis in induction motors using CNN and LSTMbased methods," IEEE Industry Applications Society Annual Meeting, IEEE, 2018, pp. 1-6.
  6. M. Skowron, T. Kowalska, M. Wolkiewicz, and C. T. Kowalski, "Convolutional neural network-based stator current data-driven incipient stator fault diagnosis of inverter-fed induction motor," Energies, vol. 13, 2020, pp. 1-21. https://doi.org/10.3390/en13010001
  7. P. Chattopadhyay, N. Saha, C. Delpha, and J. Sil, "Deep learning in fault diagnosis of induction motor drives," Prognostics and System Health Management Conf.2018, pp. 1068-1073.
  8. J. H. Han, D. J. Choi, S. K. Hong, and J. S. Kim, "Motor fault diagnosis using CNN based deep learning algorithm considering motor rotating speed," IEEE 6th Int. Conf. on Industrial Engineering and Applications (ICIEA). IEEE, pp. 440-445, 2019.
  9. Y.. J. Goh, G. N. Kim, Y. H. Kim, B. Lee, and K. M. Kim, "Diagnosis Method for Stator-Faults in Induction Motor using Park's Vector Pattern and Convolution Neural Network," Institute of Korean Electrical and Electronics Engineers, vol. 24, no. 3, 2020, pp. 883-889.
  10. S. W. Park and D. Y. Kim, "Comparison of Image Classification Performance by Activation Functions in Convolutional Neural Networks," Korea Multimedia Society, vol. 21, no. 10, 2018, pp. 1142-1149.
  11. Y. J. Goh and K. M. Kim "Inter-turn Short Circuit Diagnosis Using New D-Q Synchronous Min- Max Coordinate System and Linear Discriminant Analysis" applied science, vol. 24, no. 3, Mar. 2020, pp. 추가해주세요.