电动汽车IGBT剩余使用寿命预测

兰州理工大学学报 ›› 2024, Vol. 50 ›› Issue (2): 77-86.

• 自动化技术与计算机技术 • 上一篇下一篇

电动汽车IGBT剩余使用寿命预测

杜先君^*1,2, 王紫阳¹

1.兰州理工大学电气工程与信息工程学院, 甘肃兰州 730050;
2.兰州理工大学甘肃省工业过程控制重点实验室, 甘肃兰州 730050

收稿日期:2022-03-02 出版日期:2024-04-28 发布日期:2024-04-29
通讯作者: 杜先君(1979-),男,浙江杭州人,博士,副教授.Email:xdu@lut.edu.cn
基金资助:
国家自然科学基金(61563032),甘肃省教育厅创新基金(2021A-027)

Remaining useful life prediction of IGBT in electric vehicles

DU Xian-jun^1,2, WNAGZi-yang¹

1. College of Electrical and Information Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China;
2. Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2022-03-02 Online:2024-04-28 Published:2024-04-29

摘要/Abstract

摘要： 引入一种基于贝叶斯优化(BOA)的双向长短时记忆网络(Bi-LSTM),同时结合注意力机制,应用于绝缘栅双极型晶体管(IGBT)剩余使用寿命预测,所提方法可有效提高IGBT剩余使用寿命预测的准确性.通过IGBT加速老化试验收集V_CE-on,验证了其作为失效特征参数的可行性,并将其作为实验数据集对所提方法进行仿真验证.实验分析结果表明,所提的混合预测模型与经典LSTM及其他预测模型相比,有更低的退化预测误差,具备较高的理论意义和实践价值.

关键词: 电动汽车IGBT, 剩余寿命预测, 贝叶斯优化算法, 注意力机制, 双向长短时记忆网络

Abstract: As one of the core components of electric vehicles, IGBTs' health monitoring and remaining life prediction play a vital role in proactive maintenance. The Bi-LSTM model based on Bayesian optimization and attention mechanism is proposed to predict the remaining useful life of IGBT in this paper. The proposed method can effectively improve the accuracy of IGBT remaining service life prediction. V_CE-on through IGBT accelerated aging test is collected in this study, verifying its feasibility as a failure characteristic parameter. This data is used as an experimental data set to validate the proposed method through simulation. The experimental analysis results show that the proposed hybrid prediction model has lower degradation prediction error than the classical LSTM and other prediction models, demonstrating significant theoretical and practical value.

Key words: electric vehicles of IGBT, remaining life prediction, Bayesian optimization algorithm, attention mechanism, bidirectional long short-term memory

中图分类号:

TN322.8

杜先君, 王紫阳. 电动汽车IGBT剩余使用寿命预测[J]. 兰州理工大学学报, 2024, 50(2): 77-86.

DU Xian-jun, WNAGZi-yang. Remaining useful life prediction of IGBT in electric vehicles[J]. Journal of Lanzhou University of Technology, 2024, 50(2): 77-86.

参考文献

[1] 王丹,续丹,曹秉刚.电动汽车关键技术发展综述 [J].中国工程科学,2013,15(1):68-72.
[2] NGWENDSON L,SWEET M R,NARAYANAN E M S.An overview of the recent developments in high-voltage powersemiconductor MOS-controlled bipolar devices [C/OL].[2021-10-20].https://ieeexplore.ieee.org/document/5314159.
[3] 钱照明,张军明,盛况.电力电子器件及其应用的现状和发展 [J].中国电机工程学报,2014,34(29):5149-5161.
[4] 何湘宁,宗升,吴建德,等.配电网电力电子装备的互联与网络化技术 [J].中国电机工程学报,2014,34(29):5162-5170.
[5] YANG S,XIANG D,BRYANT A,et al.Condition monitoring for device reliability in power electronic converters:a review [J].IEEE Transactions on Power Electronics,2010,25(11):2734-2752.
[6] 李志星,张鑫宇,平恩顺.基于PFA的IGBT键合线失效机理及寿命预测 [J].半导体技术,2013,38(9):681-684.
[7] FANG X,LIN S,HUAG X,et al.A review of data-driven prognostic for IGBT remaining useful life [J].Chinese Journal of Electrical Engineering,2018,4(3):73-79.
[8] DENG E,ZHAO Z,XIN Q,et al.Analysis on the difference of the characteristic between high power IGBT modules and press pack IGBTs [J].Microelectronics Reliability,2017,78:25-37.
[9] JIANG M,FU G,CECCARELLI L,et al.Finite element modeling of IGBT modules to explore the correlation between electric parameters and damage in bond wires [C]//2019 IEEE Energy Conversion Congress and Exposition (ECCE).Baltimore:IEEE,2019:839-844.
[10] 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.
[11] DOU Y.An improved prediction model of IGBT junction temperature based on backpropagation neural network and Kalman filter [J].Complexity,2021(2):1-10.
[12] SMET V,FOREST F,USELSTEIN J J,et al.Ageing and failure modes of IGBT modules in high-temperature power cycling [J].IEEE Transactions on Industrial Electronics,2011,58(10):4931-4941.
[13] LI W,WANG B,LIU J,et al.IGBT aging monitoring and remaining lifetime prediction based on long short-term memory (LSTM) networks [J].Microelectronics Reliability,2020,114:113902.
[14] WU H,YE C,ZHANG Y,et al.Remaining useful life prediction of an IGBT module in electric vehicles statistical analysis [J].Symmetry,2020,12(8):1325.
[15] 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,2012,13(1):9-17.
[16] GGIMIRE P,PEDERSEN K B,DD VEGA A R,et al.A real time measurement of junction temperature variation in high power IGBT modules for wind power converter application [C]//CIPS 2014 8th International Conference on Integrated Power Electronics Systems.Nuremberg:VDE,2014:1-6.
[17] 刘子英,朱琛磊.基于Elman神经网络模型的IGBT寿命预测 [J].半导体技术,2019,44(5):395-400.
[18] 史业照,郭斌,郑永军.基于LSTM网络的IGBT寿命预测研究 [J].中国测试,2024,50(2):54-58.
[19] SCHEUERMANN U,SCHMIDT R.Investigations on the VCE (T)-method to determine the junction temperature by using the chip itself as sensor [C]//International Exhibition and Conference on Power Electronics,Intelligent Motion and Power Quality.Nuremberg:[s.n.],2009:802-807.
[20] BECZKOWSKI S,GHIMIE P,DE VEGA A R,et al.Online Vce measurement method for wear-out monitoring of high power IGBT modules [C]//2013 15th European Conference on Power Electronics and Applications (EPE).Lille:IEEE,2013:1-7.
[21] CHOI U M,MA K,BLAABJERG F.Validation of lifetime prediction of IGBT modules based on linear damage accumulation by means of superimposed power cycling tests [J].IEEE Transactions on Industrial Electronics,2017,65(4):3520-3529.
[22] ZHANG J,WANG P,YAN R,et al.Long short-term memory for machine remaining life prediction [J].Journal of Manufacturing Systems,2018,48:78-86.
[23] XU K,BA J,KIROS R,et al.Show,attend and tell:neural image caption generation with visual attention [J].Computer Science,2015,37:2048-2057.
[24] BAHDANAU D,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate [C]//3rd International Conference on Learning Representations.San Diego:[s.n.],2015:14090473.
[25] VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need [C]//Advances in Neural Information Processing Systems.Long Beach:[s.n.],2017:5998-6008.
[26] QIN Y,SONG D,CHEN H,et al.A dual-stage attention-based recurrent neural network for time series prediction [C/OL].[2021-12-10].https://www.ijcai.org/proceedings/2017/0366.pdf.
[27] CHEN Z,WU M,ZHAO R,et al.Machine remaining useful life prediction via an attention-based deep learning approach [J].IEEE Transactions on Industrial Electronics,2020,68(3):2521-2531.
[28] LI C,HOU Y,WANG P,et al.Joint distance maps based action recognition with convolutional neural networks [J].IEEE Signal Processing Letters,2017,24(5):624-628.
[29] JIN X B,ZHENG W Z,KONG J L,et al.Deep-learning forecasting method for electric power load via attention-based encoder-decoder with Bayesian optimization [J].Energies,2021,14(6):1596.
[30] PELIKAN M,GOLDBERG D,CANTÚ-PAZ E.BOA:the Bayesian optimization algorithm [C]//Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-99).Orlando:Morgan Kaufmann,1999:525-532.
[31] SHAHRIARI B,SWERSKY K,WANG Z,et al.Taking the human out of the loop:a review of Bayesian optimization [J].Proceedings of the IEEE,2015,104(1):148-175.
[32] EKER O F,CAMCI F,JENNIONS I K.Major challenges in prognostics:study on benchmarking prognostics datasets [C]//Proceedings of the 1st European Conference of the Prognostics and Health Management Society.Dresden:PHM Society,2012:148-155.

电动汽车IGBT剩余使用寿命预测

Remaining useful life prediction of IGBT in electric vehicles

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	陈辉, 牛丽丽, 付辉, 张天佑, 席磊. 基于多尺度残差和注意力机制的图像去雾算法[J]. 兰州理工大学学报, 2024, 50(2): 69-76.
[2]	杜先君, 邱小彧. 基于改进LSTM神经网络的化工过程故障诊断[J]. 兰州理工大学学报, 2023, 49(6): 72-79.
[3]	王星, 晏榕璟. 深度可分卷积结合多通道注意力的垃圾图像快速分类模型[J]. 兰州理工大学学报, 2023, 49(3): 88-93.
[4]	王燕, 赵妮妮, 范林. 基于图神经网络特征交叉的协同过滤算法[J]. 兰州理工大学学报, 2023, 49(1): 94-102.
[5]	赵宏, 傅兆阳, 王乐. 基于特征融合的中文文本情感分析方法[J]. 兰州理工大学学报, 2022, 48(3): 94-102.