Aging Prediction of IGBT Based on Improved Support Vector Regression

doi:10.11930/j.issn.1004-9649.202201008

Abstract

Abstract: In order to accurately predict the aging state of insulated gate bipolar transistor (IGBT), a novel IGBT aging prediction method is proposed based on improved whale optimization algorithm (IWOA) and optimized support vector regression (SVR). In this method, the time-frequency domain characteristics of IGBT collector-emitter voltage signals are extracted and are integrated into a comprehensive index to characterize the aging state of IGBT through dimension reduction of kernel principal component analysis (KPCA); Against the deficiency of the whale optimization algorithm (WOA), the Sobol sequence population initialization, inertia weight and reverse learning strategy are introduced to enhance the local search ability and convergence speed of WOA; The IWOA is used to optimize the penalty factor and kernel parameters of SVR, and an IGBT prediction model is constructed based on the comprehensive index. The proposed IWOA-SVR method is verified by using the IGBT aging data set of the NASA Ames laboratory. The results show that the constructed IWOA-SVR prediction model can more accurately predict the aging of IGBT.

Key words: insulated gate bipolar transistor, aging prediction, support vector regression, whale optimization algorithm, nuclear principal component analysis

CHEN Zhengxiong, PAZILAI Mahemuti, SHEN Wei. Aging Prediction of IGBT Based on Improved Support Vector Regression[J]. Electric Power, 2022, 55(7): 1-10.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202201008

https://www.electricpower.com.cn/EN/Y2022/V55/I7/1

References

[1] SMET V, FOREST F, HUSELSTEIN J J, et al. Aging and failure modes of IGBT modules in high-temperature power cycling[J]. IEEE Transactions on Industrial Electronics, 2011, 58(10): 4931–4941.
[2] 王希平, 丁祥宽, 姚芳, 等. IGBT模块失效机理及状态监测研究综述[J]. 中国电力, 2019, 52(9): 61–72
WANG Xiping, DING Xiangkuan, YAO Fang, et al. Review of failure mechanism and state monitoring technology for IGBT modules[J]. Electric Power, 2019, 52(9): 61–72
[3] YANG S, BRYANT A, MAWBY P, et al. An industry-based survey of reliability in power electronic converters[J]. IEEE Transactions on Industry Applications, 2011, 47(3): 1441–1451.
[4] 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 Jiacheng. Research on IGBT life prediction based on machine learning algorithm[D]. Hefei: Hefei University of technology, 2020.
[5] RAJAGURU P, LU H, BAILEY C, et al. Impact of underfill and other physical dimensions on silicon lateral IGBT package reliability using computer model with discrete and continuous design variables[J]. Microelectronics Reliability, 2018, 83: 146–156.
[6] LI L L, LIU Z F, TSENG M L, et al. Prediction of IGBT power module remaining lifetime using the aging state approach[J]. Microelectronics Reliability, 2019, 102: 113–476.
[7] 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
ZHANG Jingwei, DENG Erping, ZHAO Zhibin, et al. Simulation on fatigue failure of single IGBT chip module of press-pack IGBTs[J]. Transactions of China Electrotechnical Society, 2018, 33(18): 4277–4285
[8] 冯静波, 吕铮, 邓卫华, 等. 柔性直流换流阀IGBT过流失效研究[J]. 中国电力, 2021, 54(1): 70–77
FENG Jingbo, LV Zheng, DENG Weihua, et al. Study on the IGBT overcurrent failure of VSC-HVDC converter valve[J]. Electric Power, 2021, 54(1): 70–77
[9] 陈剑, 王海风. 模型-数据混合驱动的直驱风机VSC等效建模方法[J]. 电力系统保护与控制, 2021, 49(2): 10–17
CHEN Jian, WANG Haifeng. A model-data hybrid driven method of VSC equivalent modeling of a permanent magnetic synchronous generator[J]. Power System Protection and Control, 2021, 49(2): 10–17
[10] 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 Wei, ZHANG Qiongjie, LI Changliu, 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
[11] CHEN M, XU S, RAN L, et al. Prediction of case temperature for monitoring IGBT power module using artificial neural network[J]. International Review of Electrical Engineering (IREE), 2012, 7(1): 3240–3247.
[12] HAQUE M S, CHOI S, BAEK J. Auxiliary particle filtering-based estimation of remaining useful life of IGBT[J]. IEEE Transactions on Industrial Electronics, 2018, 65(3): 2693–2703.
[13] ASTIGARRAGA D, IBANEZ F M, GALARZA A, et al. Analysis of the results of accelerated aging tests in insulated gate bipolar transistors[J]. IEEE Transactions on Power Electronics, 2016, 31(11): 7953–7962.
[14] SONNENFELD G, GOEBEL K, CELAYA J R. An agile accelerated aging, characterization and scenario simulation system for gate controlled power transistors[C]//2008 IEEE AUTOTESTCON. IEEE, 2008: 208–215.
[15] CHOI U M, J?RGENSEN S, BLAABJERG F. Advanced accelerated power cycling test for reliability investigation of power device modules[J]. IEEE Transactions on Power Electronics, 2016, 31(12): 8371–8386.
[16] 吴广宁, 袁海满, 高波, 等. 基于特征评估与核主元分析的电力变压器故障诊断[J]. 高电压技术, 2017, 43(8): 2533–2540
WU Guangning, YUAN Haiman, GAO Bo, et al. Fault diagnosis of power transformer based on feature evaluation and kernel principal component analysis[J]. High Voltage Engineering, 2017, 43(8): 2533–2540
[17] MIRJALILI S, LEWIS A. The whale optimization algorithm[J]. Advances in Engineering Software, 2016, 95: 51–67.
[18] BRATLEY P, FOX B L. Implementing sobols quasirandom sequence generator (algorithm 659)[J]. ACM Transactions on Mathematical Software, 2003, 29(1): 49–57.
[19] 张顶学, 关治洪, 刘新芝. 一种动态改变惯性权重的自适应粒子群算法[J]. 控制与决策, 2008(11): 1253–1257
ZHANG Dingxue, GUAN Zhihong, LIU Xinzhi. An adaptive particle swarm optimization algorithm with dynamically changing inertia weight[J]. Control and Decision, 2008(11): 1253–1257
[20] BEN SALEM S, BACHA K, CHAARI A. Support vector machine based decision for mechanical fault condition monitoring in induction motor using an advanced Hilbert-Park transform[J]. ISA Transactions, 2012, 51(5): 566–572.