A study on temperature monitoring method for inverter IGBT based on memory recurrent neural network

Abstract

The power module of the Insulated Gate Bipolar Transistor (IGBT) is the core component of the traction transmission system of high-speed trains. The module's junction temperature is a critical factor in determining device reliability. Existing temperature monitoring methods based on the electro-thermal coupling model have limitations, such as ignoring device interactions and high computational complexity. To address these issues, an analysis of the parameters influencing IGBT failure is conducted, and a temperature monitoring method based on the Macro-Micro Attention Long Short-Term Memory (MMALSTM) recursive neural network is proposed, which takes the forward voltage drop and collector current as features. Compared with the traditional electrical-thermal coupling model method, it requires fewer monitoring parameters and eliminates the complex loss calculation and equivalent thermal resistance network establishment process. The simulation model of a high-speed train traction system has been established to explore the accuracy and efficiency of MMALSTM-based prediction methods for IGBT power module junction temperature. The simulation outcomes, which deviate only 3.2% from the theoretical calculation results of the electric-thermal coupling model, confirm the reliability of this approach for predicting the temperature of IGBT power modules.

Keywords

IGBT / Electro-thermal coupling model / Junction temperature monitoring / Loss model / Neural networks

Declaration of Competing Interest

The authors declare that they have no competing interests.

Acknowledgment

This work was supported by the Science and Technology Project of the Headquarters of the State Grid Corporation of China (52199922001U).

References

[1] U. Choi, F. Blaabjerg, K. Lee, et al., Study and handling methods of power IGBT module failures in power electronic converter systems. IEEE Trans. Power Electron., 30(5)(2015), pp. 2517-2533.

[2] S. Yang, A. Bryant, P. Mawby, et al., An industry-based survey of reliability in power electronic converters. IEEE Trans. Ind. Appl., 47(3)(2011), pp. 1441-1451.

[3] B. Du, J.L. Hudgins, E. Santi, et al., Transient electro-thermal simulation of power semiconductor devices. IEEE Trans. Power Electron., 25(1)(2010), pp. 237-248.

[4] Y. Yang, Q. Zhang, P. Zhang. A fast IGBT junction temperature estimation approach based on ON-state voltage drop. IEEE Trans. Ind. Appl., 57(1)(2020), pp. 685-693.

[5] H. Luo, J. Mao, C. Li, et al., Online junction temperature and current simultaneous extraction for SiC MOSFETs with electroluminescence effect. IEEE Trans. Power Electron., 37(1)(2022), pp. 21-25.

[6] M. Sathik, J. Pou, S. Prasanth, et al., Comparison of IGBT junction temperature measurement and estimation methods-a review, 2017 Asian Conference on Energy, Power and Transportation Electrification (ACEPT), IEEE, (2017) 1–8.

[7] Y. Tian, T. An, F. Qin, et al., A thermal network model for thermal analysis in automotive IGBT modules, 2021 22nd International Conference on Electronic Packaging Technology (ICEPT), IEEE, (2021) 1–5.

[8] U.M. Choi, F. Blaabjerg, F. Iannuzzo, et al., Junction temperature estimation method for a 600V,30A IGBT module during converter operation. Microelectron. Reliab., 55(9–10)(2015), pp. 2022-2026.

[9] H. Yu, X. Jiang, J. Chen, et al., Comparative study of temperature sensitive electrical parameters for junction temperature monitoring in SiC MOSFET and Si IGBT, 2020 IEEE 9th International Power Electronics and Motion Control Conference (IPEMC2020-ECCE Asia), IEEE, (2020) 905–909.

[10] N. Baker, L. Dupont, S. Munk-Nielsen, et al., IR camera validation of IGBT junction temperature measurement via peak gate current. IEEE Trans. Power Electron., 32(4)(2016), pp. 3099-3111.

[11] A.S. Bahman, K. Ma, P. Ghimire, et al., A 3D lumped thermal network model for long-term load profiles analysis in high power IGBT modules. IEEE J. Emerg. Sel. Top. Power Electron. (2016), pp. 1050-1063.

[12] X. Yang, K. Heng, X. Dai, et al., A temperature-dependent Cauer model simulation of IGBT module with analytical thermal impedance characterization. IEEE J. Emerg. Sel. Top. Power Electron., 10(3)(2022), pp. 3055-3065.

[13] Y. Dou. An improved prediction model of IGBT junction temperature based on backpropagation neural network and Kalman filter. Complexity, 2021(7)(2021), pp. 1-10.

[14] Q. Wang, X. Zhang, W. Zhang, et al., Fast and accurate temperature estimation of three-level IGBT converter based on 3-D coupled thermal model, 2020 IEEE 1st China International Youth Conference on Electrical Engineering, IEEE, (2020) 1–7.

[15] F. Gao, B. Bilgin, J. Bauman, Junction temperature estimation based on updating RC network for different liquid cooling conditions, 2019 IEEE Transportation Electrification Conference and Expo, (2019) 1–6.

[16] M. Xu, K. Ma, X. Cai, et al., Lumped thermal coupling model of multichip power module enabling case temperature as reference node. IEEE Trans. Power Electron., 37(10)(2022), pp. 11502-11506.

[17] M. Ma, W. Guo, X. Yan, et al., A three-dimensional boundary-dependent compact thermal network model for IGBT modules in new energy vehicles. IEEE Trans. Ind. Electron., 68(6)(2021), pp. 5248-5258.

[18] J. Li, A. Castellazzi, M.A. Eleffendi, et al., A physical RC network model for electro-thermal analysis of a multichip SiC power module. IEEE Trans. Power Electron., 33(3)(2018), pp. 2494-2508.

[19] S. Zheng, X. Du, J. Zhang, et al., Measurement of thermal parameters of SiC MOSFET module by case temperature. IEEE J. Emerg. Sel. Top. Power Electron., 8(1)(2020), pp. 311-322.

[20] S. Hochreiter, J. Schmidhuber. Long short-term memory. Neural Comput., 9(8)(1997), pp. 1735-1780.