基于改进小波神经网络的IGBT时间序列预测算法研究

黄柯勋; 吴松荣; 向碧楠; 徐睿; 涂振威

doi:10.13890/j.issn.1000-128x.2021.05.026

您当前的位置：

首页 >

文章列表页 >

基于改进小波神经网络的IGBT时间序列预测算法研究

可靠性与失效分析 | 更新时间：2021-12-13

- 基于改进小波神经网络的IGBT时间序列预测算法研究
- Research on IGBT Sequentially Prediction Algorithm Based on Improved Wavelet Neural Network
- 机车电传动 2021年第5期页码：161-166
- 作者机构：
  
  1.磁浮技术与磁浮列车教育部重点实验室，四川　成都　610031
  2.西南交通大学　电气工程学院，四川　成都　611756
- 作者简介：
  
  黄柯勋（1998—），男，硕士研究生，主要从事电力电子器件可靠性研究工作；E-mail: 906266297@qq.com
- 基金信息：
  
  四川省重大科技专项资助项目(20QYCX0095)
- DOI：10.13890/j.issn.1000-128x.2021.05.026
  中图分类号：
扫描看全文
黄柯勋, 吴松荣, 向碧楠, 等. 基于改进小波神经网络的IGBT时间序列预测算法研究[J]. 机车电传动, 2021,(5):161-166.

Kexun HUANG, Songrong WU, Binan XIANG, et al. Research on IGBT Sequentially Prediction Algorithm Based on Improved Wavelet Neural Network[J]. Electric Drive for Locomotives, 2021,(5):161-166.
黄柯勋, 吴松荣, 向碧楠, 等. 基于改进小波神经网络的IGBT时间序列预测算法研究[J]. 机车电传动, 2021,(5):161-166. DOI： 10.13890/j.issn.1000-128x.2021.05.026.

Kexun HUANG, Songrong WU, Binan XIANG, et al. Research on IGBT Sequentially Prediction Algorithm Based on Improved Wavelet Neural Network[J]. Electric Drive for Locomotives, 2021,(5):161-166. DOI： 10.13890/j.issn.1000-128x.2021.05.026.

摘要

针对IGBT老化失效问题，提出一种基于遗传算法改进的小波神经网络时间序列预测方法。在分析IGBT失效原理的基础上，利用IGBT老化数据集，选取关断瞬时“集电极-发射极”尖峰电压为失效特征参数，采用滑动时间窗法构建训练集与测试集，然后在MATLAB中搭建遗传算法改进的小波神经网络预测模型进行预测，并与传统的小波神经网络预测模型对比分析。试验结果显示，遗传算法改进的小波神经网络预测方均误差为0.017 1，方均根误差为0.130 9，平均绝对误差为0.109 6，分别比传统小波神经网络预测模型降低了0.005 7, 0.020 0, 0.064 0，有效提升了IGBT时间预测的精度。

Abstract

Aiming at the aging failure of IGBT, an improved wavelet neural network sequentially prediction method based on genetic algorithm was proposed. Based on the analysis of IGBT failure mechanism, with the IGBT aging data, the instantaneous collector emitter peak voltage was selected as the failure characteristic parameter, the training set and test set were constructed by the sliding time window method, and then the wavelet neural network prediction model improved by genetic algorithm was built in MATLAB for prediction, which was compared with the traditional wavelet neural network prediction model. The experimental results show that the mean square error of the improved wavelet neural network is 0.017 1, the root square mean error is 0.130 9, and the average absolute error is 0.109 6, compared with the traditional wavelet neural network prediction model, they are reduced by 0.005 7,0.020 0 and 0.064 0 respectively, which effectively improves the accuracy of IGBT sequentially prediction.

关键词

绝缘栅双极型晶体管失效机理小波神经网络遗传算法时间序列预测

Keywords

IGBTfailure mechanismwavelet neural networkgenetic algorithmsequentially prediction

references

BALIGA B J. IGBT器件：物理、设计与应用[M]. 北京: 机械工业出版社, 2018.

BALIGA B J. The IGBT device: physics, design and applications of the insulated gate bipolar transistor[M]. Beijing: China Machine Press, 2018.

麻骁. HXD1C型电力机车牵引变流器电气原理及重点故障分析处理[D]. 北京: 中国铁道科学研究院, 2019.

MA Yao. Electrical principle and troubleshooting analysis on HXDlC type locomotive traction inverters[D]. Beijing: China Academy of Railway Sciences, 2019.

方鑫, 周雒维, 姚丹, 等. IGBT模块寿命预测模型综述[J]. 电源学报, 2014(3): 14-21.

FANG Xin, ZHOU Luowei, YAO Dan, et al. An overview of IGBT life prediction models[J]. Journal of Power Supply, 2014(3): 14-21.

KILINSKI T J, LESNIAK J R, SANDOR B I. Modern approaches to fatigue life prediction of SMT solder joints[M]. Boston: Springer, 1991.

SASAKI K, IWASA N, KUROSU T, et al. Thermal and structural simulation techniques for estimating fatigue life of an IGBT module[C]//IEEE. 2008 20th International Symposium on Power Semiconductor Devices and IC's. Orlando: IEEE, 2008. DOI: 10.1109/ISPSD.2008.4538928http://doi.org/10.1109/ISPSD.2008.4538928.

王彬, 曹琳. 轨道交通用IGBT器件寿命预测技术综述[J]. 机车电传动, 2020(1): 9-12.

WANG Bin, CAO Lin. IGBT module lifetime prediction technology for rail transit[J]. Electric Drive for Locomotives, 2020(1): 9-12.

ALGHASSI A, PERINPANAYAGAM S, JENNIONS I K. A simple state-based prognostic model for predicting remaining useful life of IGBT power module[C]//IEEE. 2013 15th European Conference on Power Electronics and Applications (EPE). Lille: IEEE, 2013. DOI: 10.1109/EPE.2013.6634482http://doi.org/10.1109/EPE.2013.6634482.

白梁军, 黄萌, 饶臻, 等. 基于GARCH模型的IGBT寿命预测[J]. 中国电机工程学报, 2020, 40(18): 5787-5795.

BAI Liangjun, HUANG Meng, RAO Zhen, et al. Lifetime prediction of IGBT based on GARCH model[J]. Proceedings of the CSEE, 2020, 40(18): 5787-5795.

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.

LIU Ziying, ZHU Chenlei. IGBT life prediction based on Elman neural network model[J]. Semiconductor Technology, 2019, 44(5): 395-400.

忻力, 荣智林, 窦泽春, 等. IGBT在轨道交通牵引应用中的可靠性研究[J]. 机车电传动, 2015(5): 1-5.

XIN Li, RONG Zhilin, DOU Zechun, et al. Study on IGBT reliability of rail transit traction converter application[J]. Electric Drive for Locomotives, 2015(5): 1-5.

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]. 半导体检测与设备, 2017, 42(2): 145-152.

KONG Meijuan, LI Zhigang, LI Xiong, et al. Research status of condition monitoring technology in IGBT power module[J]. Semiconductor Testing and Equipment, 2017, 42(2): 145-152.

JI B, PICKERT V, CAO W, et al. In situ diagnostics and prognostics of wire bonding faults in IGBT modules for electric vehicle drives[J]. IEEE Transactions on Power Electronics, 2013, 28(12): 5568-5577. DOI: 10.1109/TPEL.2013.2251358http://doi.org/10.1109/TPEL.2013.2251358.

杜雄, 李高显, 李腾飞, 等. 风电变流器IGBT 模块的多时间尺度寿命评估[J]. 中国电机工程学报, 2015, 35(23): 6152-6166.

DU Xiong, LI Gaoxian, LI Tengfei, et al. Multi-time scale lifetime evaluation of IGBT modules in the wind power converter[J]. Proceedings of the CSEE, 2015, 35(23): 6152-6166.

龚灿, 孙鹏菊, 杜雄, 等. 基于键合线压降的IGBT模块内部缺陷监测研究[J]. 电源学报, 2016, 14(6): 153-162.

GONG Can, SUN Pengju, DU Xiong, et al. Research on condition monitoring for defects inside IGBT modules based on voltage drop of bond wires[J]. Journal of Power Supply, 2016, 14(6): 153-162.

丁荣军, 刘国友. 轨道交通用高压IGBT技术特点及其发展趋势[J]. 机车电传动, 2014(1): 1-6.

DING Rongjun, LIU Guoyou. Technical features and development trend of high-voltage IGBT for rail transit traction application[J]. Electric Drive for Locomotives, 2014(1): 1-6.

GAO B, YANG F, CHEN M, et al. Thermal lifetime estimation method of IGBT module considering solder fatigue damage feedback loop[J]. Microelectronics Reliability, 2018, 82(3): 51-61. DOI: 10.1016/j.microrel.2017.12.046http://doi.org/10.1016/j.microrel.2017.12.046.

史业照, 郭斌, 郑永军. 基于LSTM网络的IGBT寿命预测研究[J/OL]. 中国测试: 1-6. [2021-04-17].

SHI Yezhao, GUO Bin, ZHENG Yongjun. Research on IGBT life prediction based on LSTM network[J/OL]. China Measurement & Test: 1-6. [2021-04-17].

Watanabe A, Tsukuda M, Omura I. Real time degradation monitoring system for high power IGBT module under power cycling test[J]. Microelectronics Reliability, 2013, 53(9/10/11): 1692-1696.

黄晓慧, 张翠芳. 布谷鸟算法优化小波神经网络的短时交通流预测[J]. 计算机应用与软件, 2017, 34(3): 238-242.

HUANG Xiaohui, ZHANG Cuifang. Prediction for short-term traffic flow based on wavelet neural network optimised by Cuckoo search algorithm[J]. Computer Applications and Software, 2017, 34(3): 238-242.

李会超, 李鸿, 张博. 基于遗传算法优化小波神经网络的短时交通流量预测[J]. 计算机应用与软件, 2018, 35(7): 148-152.

LI Huichao, LI Hong, ZHANG Bo. Short-term traffic flow forecasting based on wavelet neural network optimised by genetic algorithm[J]. Computer Applications and Software, 2018, 35(7): 148-152.

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.

HAN Henggui. Research on fault prediction of IGBT based on deep learning[D]. Beijing: Beijing Jiaotong University, 2019.

AHSAN M, STOYANOV S, BAILEY C. Data driven prognostics for predicting remaining useful life of IGBT[C]//IEEE. 2016 39th International Spring Seminar on Electronics Technology (ISSE). Pilsen: IEEE, 2016. DOI: 10.1109/ISSE.2016.7563204http://doi.org/10.1109/ISSE.2016.7563204.

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. DOI: 10.1109/TIE.2017.2740856http://doi.org/10.1109/TIE.2017.2740856.

HUANG Q, PENG C, WANG L, et al. Effects of current and bonding wires damage on high-power IGBT module reliability by electro-thermo-mechanical simulation[C]//IEEE. 2020 21st International Conference on Electronic Packaging Technology (ICEPT). Guangzhou: IEEE, 2020. DOI: 10.1109/ICEPT50128.2020.9202868http://doi.org/10.1109/ICEPT50128.2020.9202868.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于迭代诱导遗传算法的列车自适应节能策略研究

功率模块铜线键合工艺参数优化设计

跨座式单轨走行轮胎模型参数辨识研究

基于遗传算法的轨道车辆参数优化设计