Journal of Power Electronics

The Korean Institute of Power Electronics (전력전자학회)
권호 표지
DOI QR코드

DOI QR Code

Open-circuit fault diagnosis of three-phase PWM rectifier circuits based on transient characteristics and random forest classification

  • RenZhong Shan (Hebei Key Laboratory of Safety Monitoring of Mining Equipment) ;
  • JingBo Yang (School of Emergency Equipment, North China Institute of Science and Technology) ;
  • ShengLi Huang (School of Emergency Equipment, North China Institute of Science and Technology)
  • Received : 2023.01.26
  • Accepted : 2023.09.20
  • Published : 2024.01.20
⟨ Previous Next ⟩

Abstract

Fault diagnosis is becoming increasingly important in improving the reliability of power electronic devices. The research in this paper focuses on the issue of the faulty operation that can occur after partial IGBT open-circuit faults in three-phase PWM rectifier circuits. To promptly and effectively diagnose faults and to determine their locations, a fault diagnosis method based on transient characteristics and random forest classification is proposed. First, the characteristics of single and double IGBT open-circuit faults in three-phase PWM rectifier circuits are analyzed. It is discovered that these faults do not immediately manifest. Instead, they exhibit fault characteristics in the corresponding time sequence. Then the random forest classifier is trained using transient fault samples from the three-phase PWM rectifier circuit. Finally, generalized testing is performed on data that was not involved in the training process, with an accuracy rate of over 98%. The use of frequency distribution graphs for visual analysis of the diagnostic results solves the problem of diagnosing multiple IGBT open-circuit faults.

Keywords

Acknowledgement

The research work of this paper has been supported by North China Institute of Science and Technology Fund Project Intramural Fund-Class A; project number: 3142020015.

References

  1. Degioanni, F., Zurbriggen, I.G., Ordonez, M.: Characterization of the minimum recovery time transients for three-phase PWM rectifiers. In: 2021 IEEE Applied Power Electronics Conference and Exposition (APEC), Phoenix, AZ, USA, 2021, pp. 2503-2509 (2021), https://doi.org/10.1109/APEC42165.2021.9486984
  2. Degioanni, F., Zurbriggen, I.G.. Ordonez, M.: Fast and reliable geometric-based controller for three-phase PWM rectifiers. In: 2020 IEEE Applied Power Electronics Conference and Exposition (APEC), New Orleans, LA, USA, 2020, pp. 1891-1896 (2020), https://doi.org/10.1109/APEC39645.2020.9124287
  3. Mohandoss, D.P., Shi, Y., Suo, K.: Outlier prediction using random forest classifier. In: 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC), NV, USA, pp. 0027- 0033 (2021), https://doi.org/10.1109/CCWC51732.2021.9376077
  4. Xun, W., fang, C.T., Shu, et al.: An online diagnostic method based on output current locus for open-circuit faults of inverters. Trans. China Electrotech. Soc. 32(2), 87-95 (2017). (in Chinese)
  5. Barcenas, E., Espinoza Trejo Trejo, D., Loredo Flores, A.: Fault diagnosis scheme for open circuit IGBT faults on a three-phase PWM rectifier. IEEE Lat. Am. Trans. 13(8), 2524-2528 (2015). https://doi.org/10.1109/TLA.2015.7331907
  6. Lamb, J., Mirafzal, B.: Open-circuit IGBT fault detection and location isolation for cascaded multilevel converters. IEEE Trans. Ind. Electron. 64(6), 4846-4856 (2017). https://doi.org/10.1109/TIE.2017.2674629
  7. Wu, F., Zhao, J., Liu, Y., Zhou, D., Luo, H.: Primary source inductive energy analysis based real-time multiple open-circuit fault diagnosis in two-level three-phase PWM boost rectifier. IEEE Trans. Power Electron. 33(4), 3411-3423 (2018). https://doi.org/10.1109/TPEL.2017.2704589
  8. Gui, Y., Li, M., Lu, J., Golestan, S., Guerrero, J.M., Vasquez, J.C.: A voltage modulated DPC approach for three-phase PWM rectifier. IEEE Trans. Industr. Electron. 65(10), 7612-7619 (2018). https://doi.org/10.1109/TIE.2018.2801841
  9. Abuelnaga, A., Narimani, M.: Open circuit IGBT fault classification using phase current in a CHB converter. In: IECON 2019-45th Annual Conference of the IEEE Industrial Electronics Society, Lisbon, Portugal, 2019, pp. 4636-4641, (2019), https://doi.org/10.1109/IECON.2019.8927101
  10. Bae, C.-J., Lee, S.-M., Lee, D.-C.: Diagnosis of multiple IGBT open-circuit faults for three-phase PWM inverters. In: 2016 IEEE 8th International Power Electronics and Motion Control Conference (IPEMC-ECCE Asia), Hefei, pp. 2504-2509 (2016). https://doi.org/10.1109/IPEMC.2016.7512692
  11. Jung, S.-M., Park, J.-S., Kim, H.-W., Cho, K.-Y., Youn, M.-J.: An MRAS-based diagnosis of open-circuit fault in PWM voltagesource inverters for PM synchronous motor drive systems. IEEE Trans. Power Electron. 28(5), 2514-2526 (2013). https://doi.org/10.1109/TPEL.2012.2212916
  12. Chand, S.S., Kumar, R.R., Prasad, R., Cirrincione, M., Raj, KK..: Open Circuit (OC) and Short Circuit (SC) IGBT switch fault detection in three-phase standalone photovoltaic inverters using shallow neural networks. In: 2022 25th International Conference on Electrical Machines and Systems (ICEMS), Chiang Mai, Thailand, pp. 1-5 (2022), https://doi.org/10.1109/ICEMS56177.2022.9983112
  13. Huang, Z., Wang, Z., Zhang, H.: A Diagnosis algorithm for multiple open-circuited faults of microgrid inverters based on main fault component analysis. IEEE Trans. Energy Convers. 33(3), 925-937 (2018). https://doi.org/10.1109/TEC.2018.2822481
  14. Miah, M.O., Shahriar Khan, S., Shatabda, S., Farid, D.M.: Improving detection accuracy for imbalanced network intrusion classification using cluster-based under-sampling with random forests. In: 2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT), Dhaka, Bangladesh, pp. 1-5 (2019), https://doi.org/10.1109/ICASERT.2019.8934495
  15. Reddy, P.D., Parvathy, L.R.: Prediction analysis using random forest algorithms to forecast the air pollution level in a particular location. In: 2022 3rd International Conference on Smart Electronics and Communication (ICOSEC), Trichy, India, pp. 1585-1589 (2022), https://doi.org/10.1109/ICOSEC54921.2022.9952138
  16. Shah, A.M., Bhalja, B.R.: Fault discrimination scheme for power transformer using random forest technique. IET Gener. Transm. Distrib. 10(6), 1431-1439 (2016) https://doi.org/10.1049/iet-gtd.2015.0955
  17. Gang, Xu., Yuanpeng, T., Tenghui, D.: Sparse random forest based abnormal behavior pattern detection of electric power user side. Power System Technol. 41(06), 1964-1973 (2017). (in Chinese)
  18. Jianzhang, He., Haibo, W., Zhixiang, Ji., et al.: Heavy overload forecasting of distribution transformers based on random forest theory. Power System Technol. 41(08), 2593-2597 (2017). (in Chinese)
  19. Mohammadhassani, A., Mehrizi-Sani, A.: Open-circuit submodule fault diagnosis in MMCs using support vector machines. IET Gener. Transm. Distrib. 16(24), 5015-5025 (2022). https://doi.org/10.1049/gtd2.12652
  20. Ali, N., Gao, Q., Ma, K.: Diagnosis of power transistors open-and short-circuit faults in SRM drives through current error analysis. In: IEEE 13th International Symposium on Diagnostics for Electrical Machines, Power Electronics and Drives (SDEMPED). Dallas, TX, USA, pp. 221-226 (2021). https://doi.org/10.1109/SDEMPED51010.2021.9605498
  21. Li, B., Shi, S., Wang, B., Wang, G., Wang, W., Xu, D.: fault diagnosis and tolerant control of single IGBT open-circuit failure in modular multilevel converters. IEEE Trans. Power Electron. 31(4), 3165-3176 (2016). https://doi.org/10.1109/TPEL.2015.2454534
  22. Mansouri, M., Fezai, R., Trabelsi, M., Nounou, H., Nounou, M., Bouzrara, K.: Reduced Gaussian process regression based random forest approach for fault diagnosis of wind energy conversion systems. IET Renew. Power Gener. 15(15), 3612-3621 (2021). https://doi.org/10.1049/rpg2.12255
  23. Kou, L., Liu, C., Cai, G.W., Zhang, Z., Zhou, J.N., Wang, X.M.: Fault diagnosis for three-phase PWM rectifier based on deep feedforward network with transient synthetic features. ISA Trans. 101, 399-407 (2020) https://doi.org/10.1016/j.isatra.2020.01.023