模型与数据混合驱动的IGBT寿命预测方法

doi:10.7527/S1000-6893.2024.30173

Abstract

Abstract:

As a key module of aviation inverter， Insulated Gate Bipolar Transistor （IGBT） plays a decisive role in its safety and reliability. Considering the complex operating conditions of aviation inverter and the fact that IGBT is one of the most vulnerable components for failure， this paper analyzes the failure mechanism and key characteristic parameters of IGBT in aviation inverter. Based on this， an IGBT life prediction method is proposed by combing Long Short-Term Memory （LSTM） network with physical analytical model. The relationship is established for IGBT between its state monitoring data and junction temperature， and the cumulative damage of IGBT is obtained from the physical model， so as to achieve the real-time life prediction of IGBT. Finally， the IGBT accelerated aging experimental dataset provided by the NASA PCoE Center is applied to validate the prediction model. The corresponding results show that the LSTM network combined with the cumulative damage model can effectively predict the lifespan of IGBT， thereby contributing to improving the reliability and reducing the daily maintenance cost of aviation inverters.

Key words: aviation inverter, Insulated Gate Bipolar Transistor (IGBT), Long Short-Term Memory (LSTM) network, life prediction, cumulative damage

CLC Number:

V240.2

Guishuang TIAN, Shaoping WANG, Jian SHI, Mo TAO. IGBT life prediction method driven by model and data[J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(15): 630173.

Figures/Tables 19

Fig.1

Fig.2

Table 1

Switching state of two⁃level aerial inverter

模式	$S a b c$	$u a n$	$u b n$	$u c n$	$u a b$	$u b c$	$u c a$
0	000	0	0	0	0	0	0
1	001	$- 13 U d$	$- 13 U d$	$23 U d$	0	$- U d$	$U d$
2	010	$- 13 U d$	$23 U d$	$- 13 U d$	$- U d$	$U d$	0
3	011	$- 13 U d$	$13 U d$	$13 U d$	$- U d$	0	$U d$
4	100	$23 U d$	$- 13 U d$	$- 13 U d$	$U d$	0	$- U d$
5	101	$13 U d$	$- 23 U d$	$13 U d$	$U d$	$- U d$	0
6	110	$13 U d$	$13 U d$	$- 23 U d$	0	$U d$	$- U d$
7	111	0	0	0	0	0	0

Table 1

Fig.3

Fig.4

Table 2

Fig.5

Fig.6

Fig.7

Table 3

Table 4

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Fig.13

Table 5

Fig.14

References 28

1	黄湛钧，董鑫，卢沐宇，等. 基于DRSN与电压幅值分析的航空HVDC系统逆变器故障诊断［J］. 航空学报， 2024， 45（3）： 328685.
	HUANG Z J， DONG X， LU M Y， et al. Fault diagnosis of inverter of aviation HVDC system based on DRSN and voltage amplitude analysis［J］. Acta Aeronautica et Astronautica Sinica， 2024， 45（3）： 328685 （in Chinese）.
2	邱立军，吴明辉. PHM技术框架及其关键技术综述［J］. 国外电子测量技术， 2018， 37（2）： 10-15.
	QIU L J， WU M H. Review on the framework and key technology of PHM［J］. Foreign Electronic Measurement Technology， 2018， 37（2）： 10-15 （in Chinese）.
3	左景航，王友仁，王景霖，等. 变工况下航空逆变器健康评估方法研究［J］. 电子测量技术， 2022， 45（6）： 30-35.
	ZUO J H， WANG Y R， WANG J L， et al. Research on health evaluation method of aviation inverter under variable working conditions［J］. Electronic Measurement Technology， 2022， 45（6）： 30-35 （in Chinese）.
4	HE Q C， CHEN W H， PAN J， et al. A prognostic method for predicting failure of dc/dc converter［J］. Microelectronics Reliability， 2017， 74： 27-33.
5	AL-MOHAMAD A， HOBLOS G， PUIG V. A hybrid system-level prognostics approach with online RUL forecasting for electronics-rich systems with unknown degradation behaviors［J］. Microelectronics Reliability， 2020， 111： 113676.
6	ABUELNAGA A， NARIMANI M， BAHMAN A S. A review on IGBT module failure modes and lifetime testing［J］. IEEE Access， 2021， 9： 9643-9663.
7	CZERNY B， LEDERER M， NAGL B， et al. Thermo-mechanical analysis of bonding wires in IGBT modules under operating conditions［J］. Microelectronics Reliability， 2012， 52（9-10）： 2353-2357.
8	WANG C L， TIAN Q H， YANG W H， et al. Analysis of characteristics of high voltage IGBT under low temperature［C］∥ 2019 IEEE International Conference on Electron Devices and Solid-State Circuits （EDSSC）. Piscataway： IEEE Press， 2019： 1-3.
9	陈华坤，章卫国，史静平，等. 航空电子设备故障预测特征参数提取方法研究［J］. 西北工业大学学报， 2017， 35（3）： 364-373.
	CHEN H K， ZHANG W G， SHI J P， et al. Research on feature extraction method for fault prediction of avionics［J］. Journal of Northwestern Polytechnical University， 2017， 35（3）： 364-373 （in Chinese）.
10	孔梅娟，李志刚，赵旺旺. IGBT键合线脱落故障特征分析［J］. 电工电能新技术， 2018， 37（10）： 87-92.
	KONG M J， LI Z G， ZHAO W W. Analysis of fault characteristics of IGBT bonding wire lift off［J］. Advanced Technology of Electrical Engineering and Energy， 2018， 37（10）： 87-92 （in Chinese）.
11	陈民铀，陈一高，高兵，等. 考虑老化进程对热参数影响的IGBT模块寿命评估［J］. 中国电机工程学报， 2017， 37（18）： 5427-5436， 5542.
	CHEN M Y， CHEN Y G， GAO B， et al. Lifetime estimation of IGBT module considering influence of aging process on thermal parameters［J］. Proceedings of the CSEE， 2017， 37（18）： 5427-5436， 5542 （in Chinese）.
12	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.
	LIU J C. IGBT life prediction based on machine learning algorithm［D］.Hefei： Hefei University of Technology， 2020 （in Chinese）.
13	郭子庆，王学华. 基于神经网络的IGBT模块剩余使用寿命预测模型［J］. 电测与仪表， 2023， 60（1）： 132-138.
	GUO Z Q， WANG X H. Prediction model of neural network-based IGBT module remaining service life［J］. Electrical Measurement & Instrumentation， 2023， 60（1）： 132-138 （in Chinese）.
14	GANGSAR P， TIWARI R. Signal based condition monitoring techniques for fault detection and diagnosis of induction motors： A state-of-the-art review［J］. Mechanical Systems and Signal Processing， 2020， 144： 106908.
15	XU Z Y， SALEH J H. Machine learning for reliability engineering and safety applications： Review of current status and future opportunities［J］. Reliability Engineering & System Safety， 2021， 211： 107530.
16	ZHANG J L， HU J B， YOU H L， et al. Characterization method of IGBT comprehensive health index based on online status data［J］. Microelectronics Reliability， 2021， 116： 114023.
17	FANG X C， LIN S， HUANG X J， et al. A review of data-driven prognostic for IGBT remaining useful life［J］. Chinese Journal of Electrical Engineering， 2018， 4（3）： 73-79.
18	LAI W， CHEN M Y， RAN L， et al. Study on lifetime prediction considering fatigue accumulative effect for die-attach solder layer in an IGBT module［J］. IEEJ Transactions on Electrical and Electronic Engineering， 2018， 13（4）： 613-621.
19	肖飞，罗毅飞，刘宾礼，等. 焊料层空洞对IGBT器件热稳定性的影响［J］. 高电压技术， 2018， 44（5）： 1499-1506.
	XIAO F， LUO Y F， LIU B L， et al. Influence of voids in solder layer on the temperature stability of IGBTs［J］. High Voltage Engineering， 2018， 44（5）： 1499-1506 （in Chinese）.
20	AHSAN M， STOYANOV S， BAILEY C. Data driven prognostics for predicting remaining useful life of IGBT［C］∥ 2016 39th International Spring Seminar on Electronics Technology （ISSE）. Piscataway： IEEE Press， 2016： 273-278.
21	ISMAIL A， SAIDI L， SAYADI M， et al. Gaussian process regression remaining useful lifetime prediction of thermally aged power IGBT［C］∥ IECON 2019 - 45th Annual Conference of the IEEE Industrial Electronics Society. Piscataway： IEEE Press， 2019： 6004-6009.
22	LI W P， WANG B X， LIU J C， et al. IGBT aging monitoring and remaining lifetime prediction based on long short-term memory （LSTM） networks［J］. Microelectronics Reliability， 2020， 114： 113902.
23	高伟，张琼洁，李长留，等. 基于LSTM网络的牵引变流器IGBT故障预测方法研究［J］. 电子器件， 2020， 43（4）： 804-808.
	GAO W， ZHANG Q J， LI C L， et al. A fault prediction method of IGBT in traction converter based on LSTM［J］. Chinese Journal of Electron Devices， 2020， 43（4）： 804-808 （in Chinese）.
24	刘宾礼，刘德志，唐勇，等. 基于加速寿命试验的IGBT模块寿命预测和失效分析［J］. 江苏大学学报（自然科学版）， 2013， 34（5）： 556-563.
	LIU B L， LIU D Z， TANG Y， et al. Lifetime prediction and failure analysis of IGBT module based on accelerated lifetime test［J］. Journal of Jiangsu University （Natural Science Edition）， 2013， 34（5）： 556-563 （in Chinese）.
25	PATIL N， CELAYA J， DAS D， et al. Precursor parameter identification for insulated gate bipolar transistor （IGBT） prognostics［J］. IEEE Transactions on Reliability， 2009， 58（2）： 271-276.
26	SHI Y M， LIU J Q， AI Y， et al. Lifetime prediction method of the traction converter IGBT based on plastic strain energy density［J］. IEEE Transactions on Transportation Electrification， 2024， 10（1）： 1286-1298.
27	YANG L， AGYAKWA P A， JOHNSON C M. Physics-of-failure lifetime prediction models for wire bond interconnects in power electronic modules［J］. IEEE Transactions on Device and Materials Reliability， 2013， 13（1）： 9-17.
28	CELAYA J， PHIL W， GOEBEL K. IGBT accelerated aging data set［Z］. 2009.

试验条件	参数设置
开关频率/kHz	1
栅极电压/V	10
占空比/%	40
温度/℃	330
保护温度/℃	345
循环次数	3 291 800 000

序号	参数设置	取值
1	优化次数	1 200
2	最大优化时间/s	2 161
3	最大迭代次数	300
4	隐含层层数	1
5	单层隐含层细胞数	160
6	第1层隐含层细胞数	32
7	第2层隐含层细胞数	64
8	第3层隐含层细胞数	128
9	初始学习率	5×10^-3
10	遗弃率	0.2

序号	Batch size	LSTM网络层数1		LSTM网络层数2		LSTM网络层数3		GRU网络
序号	Batch size	RMSE	训练时长/s	RMSE	训练时长/s	RMSE	训练时长/s	RMSE	训练时长/s
1	10	0.508	688.54	0.682	1 156.56	0.818	2 161.46	0.739	552.17
2	20	0.432	672.99	0.728	1 151.21	0.741	1 856.17	0.504	459.02
3	40	0.448	673.29	0.656	1 142.97	0.825	1 768.68	0.532	464.87
4	60	0.448	672.16	0.658	1 148.09	0.855	1 767.04	0.688	458.50
5	80	0.498	676.75	0.609	1 153.34	0.729	1 858.63	0.614	464.17
6	100	0.636	688.71	0.703	1 136.68	0.839	1 864.22	0.758	466.85
7	120	0.595	692.14	0.652	1 159.75	0.759	1 789.73	0.576	474.51
8	150	0.467	684.09	0.667	1 160.93	0.774	1 689.43	0.607	484.17
9	200	0.452	744.00	0.710	1 279.06	0.717	1 774.78	0.591	562.06
10	300	0.553	807.06	0.687	1 500.94	0.879	1 946.57	0.618	587.62

IGBT编号	T_m/℃	E_a/（10^-19J·mol^-1）	ΔT_j/℃	D/10^-7
1	338.82	0.99	5.70	0.547 0
2	338.87	0.99	5.71	0.539 8
3	338.79	0.99	5.83	0.573 8
4	338.88	0.99	5.87	0.538 6
5	338.84	0.99	5.84	0.553 3
6	338.82	0.99	6.05	0.561 2

[1]	Kaishang LI, Haoqi FAN, Runzi WANG, Xiancheng ZHANG, Shantung TU. Life design method of high-temperature equipment based on dual-scale damage theory [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(5): 531706-531706.
[2]	Mengwei ZHANG, Weiping HU, Haibin XU, Zhanqi MA, Zhixin ZHAN, Qingchun MENG. Experimental and theoretical model study on influence of scratch defects on fatigue life of 30Ni4CrMoA sample [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(3): 230743-230743.
[3]	Zhiguang HUA, Shiyuan PAN, Dongdong ZHAO, Xianglong LI, Manfeng DOU. Lifespan prediction of hydrogen fuel cell based on decomposition optimization parallel ESN [J]. Acta Aeronautica et Astronautica Sinica, 2025, 46(2): 330696-330696.
[4]	Tongzhou GAO, Xiaofan HE, Xiaolei WANG, Ziguang LI, Zhentao ZHU, Zhixin ZHAN. Fatigue life prediction of 2014-T6 aluminum alloy based on CDM theory and SVM model [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(7): 228952-228952.
[5]	Binjie MOU, Jinsong JIANG, Kun YANG, Huanbing FU, Dehong MENG, Wei JIN. Acoustic fatigue design method for fighter inlet structure [J]. Acta Aeronautica et Astronautica Sinica, 2024, 45(14): 229603-229603.
[6]	Jiaxin YANG, Shengjin TANG, Liang LI, Xiaoyan SUN, Shuai QI, Xiaosheng SI. Remaining useful life prediction of implicit nonlinear Wiener degradation process based on multi-source information [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(12): 227662-227662.
[7]	Xiurui WANG, Kaishang LI, Hanghang GU, Yong ZHANG, Tiwen LU, Runzi WANG, Xiancheng ZHANG. A unified criterion for high⁃low cycle fatigue life prediction based on crystal plasticity theory [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2023, 44(10): 427300-427300.
[8]	ZHANG Shengfei, LI Tianmei, HU Changhua, DU Dangbo, SI Xiaosheng. Missing data generation method and its application in remaining useful life prediction based on deep convolutional generative adversarial network [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(8): 225708-225708.
[9]	MU Hanxiao, ZHENG Jianfei, HU Changhua, ZHAO Ruixing, DONG Qing. Remaining useful life prediction of multivariate degradation equipment based on CDBN and BiLSTM [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(7): 325403-325403.
[10]	CHEN Keming, TIAN Ruozhou, GUO Sujuan, WANG Runzi, ZHANG Chengcheng, CHEN Haofeng, ZHANG Xiancheng, TU Shandong. Creep fatigue life prediction of aero-engine turbine disc under cyclic thermal load [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(5): 225290-225290.
[11]	LEI Shiying, SUN Jianzhong, LIU He. Cumulative damage index model and service reliability evaluation of turbine blade [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(3): 225064-225064.
[12]	WANG Shaoping, GENG Yixuan, SHI Cun. Life estimation of aircraft hydraulic pump based on failure physics and data driven [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2022, 43(10): 527347-527347.
[13]	XIAO Yang, QIN Haiqin, XU Kejun, JIA Mingming, ZHANG Zhuzhu. Low cycle fatigue life prediction of FGH96 alloy based on modified SWT model [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(5): 524360-524360.
[14]	ZHANG Junrui, ZHENG Xitao, YUAN Lin, ZHONG Guiyong, LI Guochen. Fatigue life prediction method for hybrid multi-bolted joints based on damage weight [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(5): 524306-524306.
[15]	LI Qian, ZHANG Fulu, ZHAO Zihua. Very high cycle fatigue of nickel-based single-crystal and directionally solidified superalloys: Review [J]. ACTA AERONAUTICAET ASTRONAUTICA SINICA, 2021, 42(5): 524340-524340.

IGBT life prediction method driven by model and data

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 19

References 28

Related Articles 15

Recommended Articles

Metrics

Comments