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

作     者：Yunhe Liu Tengfei Guo Jinda Li Chunxing Pei Jianqiang Liu Yunhe Liu;Tengfei Guo;Jinda Li;Chunxing Pei;Jianqiang Liu

作者机构：School of Electrical EngineeringBeijing Jiaotong UniversityBeijing 100044China 

出 版 物：《High-Speed Railway》 (高速铁路（英文）)

年 卷 期：2024年第2卷第1期

页      面：64-70页

学科分类：08[工学] 082304[工学-载运工具运用工程] 080204[工学-车辆工程] 0802[工学-机械工程] 0823[工学-交通运输工程] 

基　　金：supported by the Science and Technology Project of the Headquarters of the State Grid Corporation of China(52199922001U) 

主　　题：IGBT Electro-thermal coupling model Junction temperature monitoring Loss model Neural networks 

摘      要：The power module of the Insulated Gate Bipolar Transistor(IGBT)is the core component of the traction transmission system of high-speed *** module s junction temperature is a critical factor in determining device *** temperature monitoring methods based on the electro-thermal coupling model have limitations,such as ignoring device interactions and high computational *** 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 *** with the traditional electricalthermal coupling model method,it requires fewer monitoring parameters and eliminates the complex loss calculation and equivalent thermal resistance network establishment *** simulation model of a highspeed train traction system has been established to explore the accuracy and efficiency of MMALSTM-based prediction methods for IGBT power module junction *** 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.