|
|
|
| IGBT aging failure prediction method based on Bo-BiLSTM network |
| WAN Qingzhu1, YU Jiasong1, TONG Qingbin2, MIN Xianjuan1 |
1. School of Electric and Control Engineering, North China University of Technology, Beijing 100144;
2. School of Electrical Engineering, Beijing Jiaotong University, Beijing 100044 |
|
|
|
|
Abstract Aiming at the low accuracy of aging failure prediction for insulated gate bipolar transistor (IGBT) after thermal stress impact, a bi-directional long short term memory (BiLSTM) network based on Bayesian optimization (Bo) is proposed to predict the aging failure of IGBTs. Firstly, the aging failure principle of IGBT module is analyzed, the failure characteristic database is established based on NASA aging experiment data set, and finally the Bo-BiLSTM network is constructed to predict the failure characteristic parameters by using Matlab software. Commonly used regression prediction performance evaluation indexes are selected to compare and analyze the prediction results of long short term memory (LSTM) network model, BiLSTM network model and Bo-BiLSTM network model. The results show that the model fitting accuracy of Bo-BiLSTM network is higher, so the IGBT aging failure prediction method based on Bo-BiLSTM network has better prediction effect and can be applied to IGBT failure prediction.
|
|
Received: 11 December 2023
|
|
|
|
| Cite this article: |
|
WAN Qingzhu,YU Jiasong,TONG Qingbin等. IGBT aging failure prediction method based on Bo-BiLSTM network[J]. Electrical Engineering, 2024, 25(3): 1-10.
|
|
|
|
| URL: |
|
https://dqjs.cesmedia.cn/EN/Y2024/V25/I3/1
|
[1] 郝良收, 王丰, 李宁, 等. 一种适用于柔直换流阀功率模块的改进型测试装置[J]. 电气技术, 2020, 21(6): 102-105, 110.
[2] 丁雪妮, 陈民铀, 赖伟, 等. 多芯片并联IGBT模块老化特征参量甄选研究[J]. 电工技术学报, 2022, 37(13): 3304-3316.
[3] 陈雨晨, 陈凯楠, 郑树轩, 等. 无线电能传输磁耦合机构磁心解析模型与设计方法[J]. 电气技术, 2022, 23(6): 83-92.
[4] JIA Yingjie, XIAO Fei, DUAN Yaoqiang, et al.PSpice-COMSOL-based 3-D electrothermal-mechanical modeling of IGBT power module[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics, 2020, 8(4): 4173-4185.
[5] SHI Yunming, AI Yu, CHEN Shaoyong, et al.A health state prediction method of traction converter IGBT based on optimized particle filter[J]. Microelectronics Reliability, 2022, 139: 114840.
[6] 张经纬, 邓二平, 赵志斌, 等. 压接型IGBT器件单芯片子模组疲劳失效的仿真[J]. 电工技术学报, 2018, 33(18): 4277-4285.
[7] WU Xinlong, YANG Xin, DAI Xingyu, et al.A physical lifetime prediction methodology for IGBT module by explicit emulation of solder layer degradation[J]. Microelectronics Reliability, 2021, 127: 114384.
[8] LI Wanpihng, WANG Bixuan, LIU Jingcun, et al.IGBT aging monitoring and remaining lifetime prediction based on long short-term memory (LSTM) networks[J]. Microelectronics Reliability, 2020, 114: 113902.
[9] 任宏宇, 余瑶怡, 杜雄, 等. 基于优化长短期记忆神经网络的IGBT寿命预测模型[J]. 电工技术学报, 2024, 39(4): 1074-1086.
[10] 罗哲雄, 周望君, 陆金辉, 等. 双面散热汽车IGBT模块热测试方法研究[J]. 电气技术, 2022, 23(12): 24-30.
[11] CHU Chengpeng, DONG Chao, DU Mingxing, et al.Aging monitoring of bond wires based on differential mode conducted interference spectrum for IGBT module[J]. IEEE Transactions on Electromagnetic Compatibility, 2021, 63(4): 1274-1283.
[12] 韩恒贵. 基于深度学习的IGBT故障预测研究[D]. 北京: 北京交通大学, 2019.
[13] 蒋林, 蒲晓珉, 边晓光, 等. 背靠背功率模块中IGBT的关断过电压抑制[J]. 东方电气评论, 2021, 35(2): 11-14.
[14] 孔梅娟, 李志刚, 李雄, 等. IGBT功率模块状态监测技术研究现状[J]. 半导体技术, 2017, 42(2): 145-152.
[15] 孙梓涵. 基于数据驱动的IGBT寿命预测研究[D]. 北京: 北京交通大学, 2020.
[16] 刘嘉诚. 基于机器学习算法的IGBT寿命预测研究[D]. 合肥: 合肥工业大学, 2020.
[17] 王晨苑, 何怡刚, 王传坤, 等. 高压多芯片并联IGBT模块故障监测方法[J]. 电子测量与仪器学报, 2020, 34(10): 98-106.
[18] 范迦羽, 李恬晨, 和峰, 等. IGBT器件关断能力提升的参数筛选方法研究[J/OL]. 华北电力大学学报(自然科学版), 1-9 [2024-02-06]. http://kns.cnki.net/kcms/detail/13.1212.TM.20230105.2129.002.html.
[19] 刘伯颖, 胡佳程, 李玲玲, 等. IGBT老化状态下基于BAS-SVM模型的结温预测方法[J]. 微电子学, 2020, 50(5): 664-668, 682.
[20] 刘人宽, 李辉, 于凯, 等. 焊接型IGBT器件封装状态监测方法分析[J]. 电工技术, 2022(15): 71-78, 82. |
|
|
|
2024, Vol. 25 
