Skip to main content
SpringerLink
Log in

Machine learning approach for sorting SiC MOSFET devices for paralleling

  • Original Article
  • Published:
Journal of Power Electronics Aims and scope Submit manuscript

Abstract

This paper presents the development of a machine learning model for sorting SiC MOSFET devices for paralleling. A multivariate linear regression model is developed and trained with device parameter data (as input) and current imbalance data (as label). Each of the training devices is successively paralleled with one reference device to generate the current imbalance (label) data. Devices with close values of current imbalance when individually paralleled with the reference device are expected to have relatively balanced current sharing when paralleled among themselves. This model is trained with 40 devices and tested with 20 devices. The model shows accuracies of 87.93% and 97.48% in predicting transient and steady state current imbalances, respectively. These accuracy values are obtained by comparing the model’s prediction for the 20 testing devices with the actual current imbalance values when these devices are paralleled with a reference device. Based on current imbalance predictions made by these models, the devices are grouped into classes for paralleling applications. The selection of devices for paralleling based on predictions from these models result in a satisfactorily balanced current distribution. The model’s performance at higher temperatures is also satisfactory.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

References

  1. Majumdar, G.: Recent technologies and trends of power devices. In: 2007 International Workshop on Physics of Semiconductor Devices, Mumbai, pp. 787–792 (2007)

  2. Baliga, B.J.: Trends in power semiconductor devices. IEEE Trans. Electron Devices 43(10), 1717–1731 (1996)

    Article  Google Scholar 

  3. Hefner, A., Berning, D., McNutt, T., Mantooth, A., Lai, J., Singh, R.: Characterization and modeling of silicon-carbide power devices. In: 2001 International Semiconductor Device Research Symposium. Symposium Proceedings (Cat. No. 01EX497), Washington, DC, USA, pp. 568–571 (2001)

  4. Cui, Y., Chinthavali, M.S., Xu, F., Tolbert, L.M.: Characterization and modeling of silicon carbide power devices and paralleling operation. In: 2012 IEEE International Symposium on Industrial Electronics, Hangzhou, pp. 228–233 (2012)

  5. Biela, J., Schweizer, M., Waffler, S., Kolar, J.W.: SiC versus Si—evaluation of potentials for performance improvement of inverter and DC–DC converter systems by SiC power semiconductors. IEEE Trans. Ind. Electron. 58(7), 2872–2882 (2011)

    Article  Google Scholar 

  6. Hazra, S., et al.: High switching performance of 1700-V, 50-A SiC power MOSFET over Si IGBT/BiMOSFET for advanced power conversion applications. IEEE Trans. Power Electron. 31(7), 4742–4754 (2016)

    Google Scholar 

  7. Sarnago, H., Lucía, Ó., Burdío, J.M.: A comparative evaluation of SiC power devices for high-performance domestic induction heating. IEEE Trans. Ind. Electron. 62(8), 4795–4804 (2015)

    Article  Google Scholar 

  8. Xue, Y., Lu, J., Wang, Z., Tolbert, L.M., Blalock, B.J., Wang, F.: Active current balancing for parallel-connected silicon carbide MOSFETs. In: 2013 IEEE Energy Conversion Congress and Exposition, Denver, pp. 1563–1569 (2013)

  9. Li, H., Munk-Nielsen, S., Pham, C., Bęczkowski, S.: Circuit mismatch influence on performance of paralleling silicon carbide MOSFETs. In: 2014 16th European Conference on Power Electronics and Applications, Lappeenranta, pp. 1–8 (2014)

  10. Chen, H., Divan, D.: High speed switching issues of high power rated silicon-carbide devices and the mitigation methods. In: 2015 IEEE Energy Conversion Congress and Exposition (ECCE), Montreal, QC, pp. 2254–2260 (2015)

  11. Zhang, H., Tolbert, L.M., Ozpineci, B.: Impact of SiC devices on hybrid electric and plug-in hybrid electric vehicles. IEEE Trans. Ind. Appl. 47(2), 912–921 (2011)

    Article  Google Scholar 

  12. Liu, T., Ning, R., Wong, T.T.Y., Shen, Z.J.: Modeling and analysis of SiC MOSFET switching oscillations. IEEE J. Emerg. Select. Top. Power Electron. 4(3), 747–756 (2016)

    Google Scholar 

  13. Sadik, D., Colmenares, J., Peftitsis, D., Lim, J., Rabkowski, J., Nee, H.: Experimental investigations of static and transient current sharing of parallel-connected silicon carbide MOSFETs. In: 15th European Conference on Power Electronics and Applications (EPE), Lille, pp. 1–10 (2013)

  14. Peftitsis, D., Baburske, R., Rabkowski, J., Lutz, J., Tolstoy, G., Nee, H.: Challenges regarding parallel connection of SiC JFETs. IEEE Trans. Power Electron. 28(3), 1449–1463 (2013)

    Article  Google Scholar 

  15. Li, H., Munk-Nielsen, S., Bęczkowski, S., Wang, X.: A novel DBC layout for current imbalance mitigation in SiC MOSFET multichip power modules. IEEE Trans. Power Electron. 31(12), 8042–8045 (2016)

    Article  Google Scholar 

  16. Rabkowski, J., Peftitsis, D., Nee, H.: Parallel-operation of discrete SiC BJTs in a 6-kW/250-kHz DC/DC boost converter. IEEE Trans. Power Electron. 29(5), 2482–2491 (2014)

    Article  Google Scholar 

  17. Wang, M., Luo, F., Xu, L.: A double-end sourced wire-bonded multichip SiC MOSFET power module with improved dynamic current sharing. IEEE J. Emerg. Select. Top. Power Electron. 5(4), 1828–1836 (2017)

    Article  Google Scholar 

  18. Wood, R.A., Salem, T.E.: Evaluation of a 1200-V, 800-A All-SiC dual module. IEEE Trans. Power Electron. 26(9), 2504–2511 (2011)

    Article  Google Scholar 

  19. Li, H., et al.: Influences of device and circuit mismatches on paralleling silicon carbide MOSFETs. IEEE Trans. Power Electron. 31(1), 621–634 (2016)

    Article  Google Scholar 

  20. Lim, J., Peftitsis, D., Rabkowski, J., Bakowski, M., Nee, H.: Analysis and experimental verification of the influence of fabrication process tolerances and circuit parasitics on transient current sharing of parallel-connected SiC JFETs. IEEE Trans. Power Electron. 29(5), 2180–2191 (2014)

    Article  Google Scholar 

  21. Mao, Y., Miao, Z., Wang, C., Ngo, K.D.T.: Balancing of peak currents between paralleled SiC MOSFETs by drive-source resistors and coupled power-source inductors. IEEE Trans. Ind. Electron. 64(10), 8334–8343 (2017)

    Article  Google Scholar 

  22. Li, H., et al.: Influence of paralleling dies and paralleling half-bridges on transient current distribution in multichip power modules. IEEE Trans. Power Electron. 33(8), 6483–6487 (2018)

    Article  Google Scholar 

  23. Ao, J., Wang, Z., Chen, J., Peng, L., Chen, Y.: The cost-efficient gating drivers with master–slave current sharing control for parallel SiC MOSFETs. In: 2018 IEEE Transportation Electrification Conference and Expo, Asia-Pacific (ITEC Asia-Pacific), Bangkok, pp. 1–5 (2018)

  24. Mao, Y., Miao, Z., Wang, C., Ngo, K.D.T.: Passive balancing of peak currents between paralleled MOSFETs with unequal threshold voltages. IEEE Trans. Power Electron. 32(5), 3273–3277 (2017)

    Article  Google Scholar 

  25. Bertelshofer, T., Maerz, A., Bakran, M.: Derating of parallel SiC MOSFETs considering switching imbalances. In: PCIM Europe 2018; International Exhibition and Conference for Power Electronics, Intelligent Motion, Renewable Energy and Energy Management, Nuremberg, Germany, pp. 1–8 (2018)

  26. Wang, G., Mookken, J., Rice, J., Schupbach, M.: Dynamic and static behavior of packaged silicon carbide MOSFETs in paralleled applications. In: 2014 IEEE applied power electronics conference and exposition—APEC 2014, Fort Worth, TX, pp. 1478–1483 (2014)

  27. Kelner, G., Shur, M.S., Binari, S., Sleger, K.J., Kong, H.: High-transconductance beta-SiC buried-gate JFETs. IEEE Trans. Electron Devices 36(6), 1045–1049 (1989)

    Article  Google Scholar 

  28. Kokosis, S.G., Andreadis, I.E., Kampitsis, G.E., Pachos, P., Manias, S.: Forced current balancing of parallel-connected SiC JFETs during forward and reverse conduction mode. IEEE Trans. Power Electron. 32(2), 1400–1410 (2017)

    Article  Google Scholar 

  29. Baliga, B.J.: Fundamentals of power semiconductor devices. Springer, North Carolina (2008)

    Book  Google Scholar 

  30. Alpaydin, E.: Introduction to machine learning: selected papers of Lionel W. McKenzie, Chapter 1–2, pp. 2–47. MIT Press, Cumberland (2016)

    Google Scholar 

  31. Müller, A.C., Guido, S.: Introduction to machine learning with Python: a guide for data scientists. Chapter 2, pp. 33–55. Oreilly, Sebastopol (2017)

    Google Scholar 

  32. Bishop, C.M.: Pattern recognition and machine learning. Chapter 3, pp. 137–147. Springer Science+Business Media, LLC, Singapore (2006)

    Google Scholar 

  33. Andrew, N.: Class Lecture, Topic: “Supervised learning”. CS229, Computer Science Department, Stanford University, Stanford, California, Fall 2018 [pdf document], pp. 3–11. Retrieved from http://cs229.stanford.edu/notes/cs229-notes1.pdf

  34. Kim, P.: Matlab deep learning with machine learning, neural networks and artificial intelligence. Chapter 1, pp. 1–17. Apress, Seoul (2017)

    Google Scholar 

  35. Haihong, Q., et al.: Influences of circuit mismatch on paralleling silicon carbide MOSFETs. In: 2017 12th IEEE Conference on Industrial Electronics and Applications (ICIEA), Siem Reap, pp. 556–561 (2017)

  36. Abuogo, J., Zhao, Z., Ke, J.: Linear regression model for screening SiC MOSFETs for paralleling to minimize transient current imbalance. In: 2019 The 5th International Conference on Electrical Engineering, Control and Robotics, Guangzhou, China (2019)

  37. Ke, J., Zhao, Z., Sun, P., Huang, H., Abuogo, J., Cui, X.: Chips classification for suppressing transient current imbalance of parallel-connected silicon carbide MOSFETs. In: IEEE Transactions on Power Electronics

  38. La Mantia, S., Abbatelli, L., Brusca, C., Melito, M., Nania, M.: Design rules for paralleling of silicon carbide power MOSFETs. In: PCIM Europe 2017, Nuremberg, Germany, pp. 1–6 (2017)

Download references

Author information

Authors and Affiliations

  1. Department of Electrical and Electronic Engineering, Dedan Kimathi University of Technology, Nyeri, Kenya

    James Opondo Abuogo

  2. State Key Laboratory of Alternate Electrical Power System with Renewable Energy Source, North China Electric Power University, Beijing, China

    Zhibin Zhao

Authors
  1. James Opondo Abuogo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhibin Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhibin Zhao.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Abuogo, J.O., Zhao, Z. Machine learning approach for sorting SiC MOSFET devices for paralleling. J. Power Electron. 20, 329–340 (2020). https://doi.org/10.1007/s43236-019-00028-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s43236-019-00028-z

Keywords

Search

Navigation