DOI QR코드

DOI QR Code

Fault Diagnosis Algorithm of Electronic Valve using CNN-based Normalized Lissajous Curve

CNN기반 정규화 리사주 도형을 이용한 전자식 밸브 고장진단알고리즘

  • Park, Seong-Mi (Dept. of Lift Engineering, Korea Lift College) ;
  • Ko, Jae-Ha (Green Energy Institute, Energy Innovative Industry R&D Department) ;
  • Song, Sung-Geun (Korea Electronics Technology Institute, Energy Conversion Research Center) ;
  • Park, Sung-Jun (Dept. Electrical Engineering, Chonnam National University) ;
  • Son, Nam Rye (Dept. of Information & Communication Engineering, Honam University)
  • 박성미 (한국승강기대학교 승강기공학부) ;
  • 고재하 (녹색에너지연구원,에너지신산업연구실) ;
  • 송성근 (한국전자기술연구원, 에너지변환연구센터) ;
  • 박성준 (전남대학교 전기공학과) ;
  • 손남례 (호남대학교, 정보통신공학과)
  • Received : 2020.08.16
  • Accepted : 2020.08.26
  • Published : 2020.10.31

Abstract

Currently, the K-Water uses various valves that can be remotely controlled for optimal water management. Valve system fault can be classified into rotor defects, stator defects, bearing defects, and gear defects of induction motors. If the valve cannot be operated due to a gear fault, the water management operation can be greatly affected. For effective water management, there is an urgent need for preemptive repairs to determine whether gear is damaged through failure prediction diagnosis.. Recently, deep learning algorithms are being applied for valve failure diagnosis. However, the method currently applied has a disadvantage of attaching a vibration sensor to the valve. In this paper, propose a new algorithm to determine whether a fault exists using a convolutional neural network (CNN) based on the voltage and current information of the valve without additional sensor mounting. In particular, a normalized Lisasjous diagram was used to maximize the fault classification performance in the CNN-based diagnostic system.

References

  1. Park, Jae-Ho, Kim Jong-Hoon, Lee Gyeong-Bae, " A Case Study on Pressure Reducing Valve for Stability Assurance of Long Pipeline," KOREAN SOCIETY OF CIVIL ENGINEERS, 10, pp. 31-32, (2015).
  2. Byung-Hoon Chung, Dae-Chul Shin, "A Development of the Algorithm to Detect the Fault of the Induction Motor Using Motor Current Signature Analysis," Transactions of the Korean Society for Noise and Vibration Engineering 14(8), pp. 675-683, (2004). https://doi.org/10.5050/KSNVN.2004.14.8.675
  3. Lark-Kyo Kim, Jung-Hwan Lim, "Online Fault Diagnosis of Motor Using Electric Signatures," The transactions of The Korean Institute of Electrical Engineers 59(10), pp. 1882-1888, (2010). https://doi.org/10.5370/KIEE.2010.59.10.1882
  4. Han Hyung-Seob, Cho Sang-Jin, Chong Ui-Pil, "Feature Vector Decision Method of Various Fault Signals for Neural-network-based Fault Diagnosis System," Transactions of the Korean Society for Noise and Vibration Engineering 20(11), pp. 1009-1017, (2010). https://doi.org/10.5050/KSNVE.2010.20.11.1009
  5. Dong-Jin Choi, Ji-Hoon Han, Hyeuong-Seob Kim, Min-joon Choi, Chan-woo Kwon, Sun-Ki Hong," Study on Motor Fault Diagnosis Considering Noise Disturbance Based on Machine Learning," The Korean Institute of Electrical Engineers, 10, pp. 29-30, (2018).
  6. S. K.Hong, K. S.Kim, Y. H.Cho, I, H Ka, "A study on Application for Signal Acquisition and Analysis for Motor Fault Diagnosis" KIEE.IThe Transactions of the Korean Institute of Electrical Engineers, pp. 876-877, (2015).
  7. W Sun, R Zhao, R Yan, S Shao and X Chen, "Convolutional Discriminative Feature Learning for Induction Motor Fault Diagnosis", IEEE Trans. on Industrial Informatics, Vol. 13, Issue:3, pp.1350-1359, (2017). https://doi.org/10.1109/TII.2017.2672988
  8. Jae-soo Lee, In-Ho Choi, Hong Kwon Eui, Hak-Yun Choi, Roh, Hee Jung, Ahn Jeongkeun, "An Efficient Water Pressure Measurement System of the Water Pipes using IoT," J. Korea Inst. Intell. Transp. Syst. vol. 17, no.1, pp. 114-122, (2018). https://doi.org/10.12815/kits.2018.17.1.114
  9. Park Chang-Ha, "Combination of In-circuit Test and Lissajous Pattern for Circuit Card Failure Analysis," Dept. of Avionics Engineering Graduate School of Aeronautics, Information and Industry,Hanseo University, (2020).
  10. Ian Goodfellow, Yoshua Bengio, Aaron Courville, "Deep Learning," MIT Press. p. 326, (2016).
  11. M.V. Valueva, N.N. Nagornov, P.A. Lyakhov, G.V. Valuev, N.I. Chervyakov, "Application of the residue number system to reduce hardware costs of the convolutional neural network implementation," Mathematics and Computers in Simulation, Elsevier, Vol.177, pp.232-243, (2020). https://doi.org/10.1016/j.matcom.2020.04.031
  12. Tensorflow.org: Deep Learning Library Developed by Google. Available online: https://www.tensorflow.org/ (accessed on 7 March (2020).
  13. Keras.io: The Python Deep Learning Library. Available online: https://keras.io/ (accessed on 7 March (2020).