Journal of the Korean Society of Manufacturing Process Engineers (한국기계가공학회지)

The Korean Society of Manufacturing Process Engineers (한국기계가공학회)
권호 표지
DOI QR코드

DOI QR Code

Fault Prognostics of a SMPS based on PCA-SVM

PCA-SVM 기반의 SMPS 고장예지에 관한 연구

  • Yoo, Yeon-Su (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Kim, Dong-Hyeon (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Kim, Seol (Department of Mechanical System Engineering, Kumoh National institute of Technology) ;
  • Hur, Jang-Wook (Department of Mechanical System Engineering, Kumoh National institute of Technology)
  • 유연수 (금오공과대학교 기계시스템공학과) ;
  • 김동현 (금오공과대학교 기계시스템공학과) ;
  • 김설 (금오공과대학교 기계시스템공학과) ;
  • 허장욱 (금오공과대학교 기계시스템공학과)
  • Received : 2020.06.03
  • Accepted : 2020.07.06
  • Published : 2020.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

With the 4th industrial revolution, condition monitoring using machine learning techniques has become popular among researchers. An overload due to complex operations causes several irregularities in MOSFETs. This study investigated the acquired voltage to analyze the overcurrent effects on MOSFETs using a failure mode effect analysis (FMEA). The results indicated that the voltage pattern changes greatly when the current is beyond the threshold value. Several features were extracted from the collected voltage signals that indicate the health state of a switched-mode power supply (SMPS). Then, the data were reduced to a smaller sample space by using a principal component analysis (PCA). A robust machine learning algorithm, the support vector machine (SVM), was used to classify different health states of an SMPS, and the classification results are presented for different parameters. An SVM approach assisted by a PCA algorithm provides a strong fault diagnosis framework for an SMPS.

Keywords

References

  1. Choi, H., Kim, T. K., Heo, G. R., Hur, J. W., Choi, S. D., "Study of Fuel Pump Failure Prognostic Based on Machine Learning Using Artificial Neural Network", Journal of the Korean Society of Manufacturing Process Engineers, Vol. 18 No. 9, pp. 52-57, 2019.
  2. Yun, B. D., "Cases of Fault Diagnosis and Prediction Technology Application to the Energy Industry", The Korean Society of Mechanical Engineers International Journal, Vol. 53 No. 7, pp. 44-52, 2013.
  3. Zheng, X., Wu, L., Guan, Y., and Li, X., "Analysis of the Degradation of MOSFETs in Switching Mode Power Supply by Characterizing Source Oscillator Signals", Mathematical Problems in Engineering, Vol. 2013, Special Issue, pp. 1-7, 2013.
  4. Ye, X., Chen, C., Wang, Y., Zhou, Y. and Vachtsevanos, G., "Health-assessment methodology research for SMPS based on simulation", 2015 Annual Reliability and Maintainability Symposium (RAMS), Palm Harbor, FL, pp. 1-7, 2015.
  5. Jang, I. H., "A Study on the Design and Analysis of Degradation Test for LED Lamp SMPS", Ph. D. dissertation, Chosun University, Republic of Korea. 2016.
  6. Hayes, J. H., "Modeling and Tracking Degradation in Electronic Components", Ph. D. dissertation, Clemson University, United States of America, 2017.
  7. Yun, S. H., Park, B. H., Lee, C. W., "A Study on Fault Diagnosis Algorithm for Rotary Machine using Data Mining Method and Empirical Mode Decomposition". Journal of the Korean Society of Manufacturing Process Engineers, Vol. 15, No. 4 pp. 23-29 2016. https://doi.org/10.14775/ksmpe.2016.15.4.023
  8. Kim, S. J., "A Wavelet-based Profile Classification using Support Vector Machine", Journal of Korean Institute of Intelligent Systems, Vol. 18 No. 5, pp. 718-723, 2008. https://doi.org/10.5391/JKIIS.2008.18.5.718
  9. Kim, S. Y., Park, S. H., "Multi-class Classification of Database Workloads using PCA-SVM Classifier", Journal of Korean Institute of Information Scientists and Engineers : Databases, Vol. 38, No. 1, pp. 1-8, 2011.
  10. Jung, H., Kim, J. W., "A Machine Learning Approach for Mechanical Motor Fault Diagnosis," Journal of the Society of Korea Industrial and Systems Engineering, Vol. 40, No. 1, pp. 57-64, 2017. https://doi.org/10.11627/jkise.2017.40.1.057