[1]唐 波,刘 任,江浩田,等.基于BP神经网络的IGBT模块开关损耗求解[J].高压电器,2019,55(07):27-32.[doi:10.13296/j.1001-1609.hva.2019.07.005]
 TANG Bo,LIU Ren,JIANG Haotian,et al.Solution of Switching Loss of IGBT Module Based on Back Propagation Neural Network[J].High Voltage Apparatus,2019,55(07):27-32.[doi:10.13296/j.1001-1609.hva.2019.07.005]
点击复制

基于BP神经网络的IGBT模块开关损耗求解()
分享到:

《高压电器》[ISSN:1001-1609/CN:61-11271/TM]

卷:
第55卷
期数:
2019年07期
页码:
27-32
栏目:
研究与分析
出版日期:
2019-07-15

文章信息/Info

Title:
Solution of Switching Loss of IGBT Module Based on Back Propagation Neural Network
作者:
唐 波 刘 任 江浩田 孙 睿 吴 卓
(三峡大学电气与新能源学院, 湖北 宜昌  443002)
Author(s):
TANG Bo LIU Ren JIANG Haotian SUN Rui WU Zhuo
(College of Electrical Engineering & New Energy, China Three Gorges University, Hubei Yichang 443002, China)
关键词:
IGBT模块 开关损耗 损耗影响因素 BP神经网络 粒子群算法
Keywords:
IGBT module switching loss loss factor BP neural network particle swarm algorithm
DOI:
10.13296/j.1001-1609.hva.2019.07.005
摘要:
如何准确求解绝缘栅双极晶体管(IGBT)模块的开关损耗值,是电力变换器性能和寿命研究中的关键问题之一。针对现有IGBT开关损耗模型难以准确求解开关损耗值的缺陷,引入了基于粒子群算法优化的误差反向传播(BP)前馈神经网络模型。将影响开关损耗的5个主要因素(集射工作电压、集电极电流、驱动电压、驱动电阻、结温)作为BP神经网络的输入向量,并采用粒子群算法优化网络的初始权值与阀值,通过共轭梯度法的学习规则加速收敛,从而获得开关损耗的精确求解值。该模型实现了在额定值范围内对各种工况下的IGBT模块开关损耗值的可靠预测,其在100组测试验证样本下所出现的最大误差比率为3.85%。
Abstract:
How to solve the switching loss value of the IGBT module accurately is a key problem in the performance and lifetime studies of power converter. Aiming at the disadvantages that the existing IGBT switching loss solving models are difficult to accurately solve the switching loss value, the error back propagation (BP) neural network model optimized by the particle swarm algorithm is proposed. With taking the 5 main factors (Collector-emitter voltage, collector current, gate drive voltage, gate drive resistance, junction temperature) that affect the press-contact IGBT module switching loss as the input vector, and optimizing the initial weight and threshold of BP neural network by the particle swarm algorithm, the exact solution of the switching loss is obtained accordingly. The model realizes the reliable prediction of the switching loss of the IGBT module on various working conditions in the rated range, and the maximum error rate in 100 sets of validation samples is 3.85%.

参考文献/References:

[1] 吴 锐,温家良,于坤山,等. 电压源换流器开关器件损耗建模[J]. 中国电机工程学报,2012,32(21):1-7. WU Rui, WEN Jianliang, YU Kunshan, et al. Power loss modeling of switching devices in voltage source converters[J]. Proceedings of the CSEE,2012, 32(21): 1-7.
[2] AGHDAM M G, FATHI S H, GHASEMI A. The analysis of conduction and switching losses in three-phase OHSW multilevel and switching losses in switching functions[C]// IEEE PEDS.[S.l.]:IEEE, 2005: 209-218.
[3] HEFNER A R. Analytical modeling of device-circuit interactions for the power insulated gate bipolar transistor(IGBT)[J]. IEEE Transactions on Industry Applications, 1990, 26(6): 995-1005.
[4] HEFNER A R. A dynamic electro-thermal model for the IGBT[J]. IEEE Transactions on Industry Applications, 1994, 30(2): 394-405.
[5] MATTAUSH K. Status and trends of power semiconductor device models for circuit simulation[J]. IEEE Transactions on Power Electronics, 1998, 13(3): 452-465.
[6] LU L, BRANT A, HUDGINS J L, et al. Physics-based model of planar-gate IGBT including MOS side two-dimensional effects[J]. IEEE Transactions on Industry Applications, 2010, 46(6): 2556-2567.
[7] BLAABJERG F, JAEGER U, MUNK-NIELSEN S, et al. Power losses in PWM-VSI inverter using NPT or PT IGBTs devices[J]. IEEE Transactions on Power Electronics,1995,10(3): 358-367.
[8] 熊 妍,沈燕群,江 剑,等. IGBT损耗计算和损耗模型研究[J]. 电源技术应用,2006,9(5):55-60. XIONG Yan, SHEN Yanqun, JIANG Jian, et al. Study on loss calculation and model for IGBT[J]. Power Supply Technologies and Applications, 2006, 9(5): 55-60.
[9] 潘武略,徐 政,张 静,等. 电压源换流器型直流输电换流器损耗分析[J]. 中国电机工程学报,2008,28(15):72-78. PAN Wunüe,XU Zheng,ZHANG Jing,et al. Loss analysis of voltage source converter based HVDC converter[J]. Proceedings of the CSEE,2008,28(15):72-78.
[10] 毛 鹏,谢少军,许泽刚.IGBT模块的开关暂态模型及损耗分析[J].中国电机工程学报,2010,33(15):40-47. MAO Peng, XIE Shaojun, XU Zegang. Switching transients model and loss analysis of IGBT module[J]. Proceedings of the CSEE,2010, 33(15): 40-47.
[11] RAJAPAKSE A D, GOLE A M, WILSON P L. Electromagnetic transient simulation models for accurate representation of switching losses and thermal performance in power electronic systems[J]. IEEE Transactions on Power Delivery, 2005, 20(1): 319-327.
[12] RCICHL J V. Inverter dynamic electro-thermal simulation with experiment verification[D]. Blacksburg:Virginia Polytechnic Institute and State University,2005.
[13] DU B, HUDGINS J L, ENRICO S, et al. Transient electrothermal simulation of power semiconductor devices[J]. IEEE Transactions on Power Electron, 2010, 25(1): 237-248.
[14] CODECASA L,VINCENZO D A,MAGNANI A,et al. Circuit-Based electrothermal simulation of power devices by an ultra fast nonlinear MOR approach[J]. IEEE Transactions on Power Electron,2015,30(99): 1-13.
[15] DUONG T H, HEFNER A R, ORTIZ-RODRIGUEZ J M, et al. Physics-based electro-thermal saber model and parameter extraction for high-voltage SiC buffer-layer IGBTs[C]// IEEE Energy Conversation Congression Exposition. [S.l.]:IEEE, 2014: 460-467.
[16] 王兆安,黄 俊. 电力电子技术[M]. 北京:机械工业出版社,2000. WANG Zhao’an,HUANG Jun. Electronic power technology[M]. Beijing:Machinery Industry Press,2000.
[17] 范高锋,王伟胜,刘 纯. 基于人工神经网络的风电功率预测[J]. 中国电机工程学报,2008,28(34):118-123. FAN Gaofeng, WANG Weisheng, LIU Chun. Wind power prediction based on artificial neural network[J]. Proceedings of the CSEE, 2008, 28(34): 118-123.
[18] 陈 娜. 中高压功率IGBT模块开关特性测试及建模[D]. 杭州:浙江大学,2012. CHEN Na. Switching characteristics testing and modeling of medium and high voltage igbt power module[D]. Hangzhou: Zhejiang University, 2012.
[19] CVETKOVIC I, BOROYEVICH D, MATTAVELLI P, et al. Nonlinear, hybrid terminal behavioral modeling of a DC-based nanogrid system[C]//IEEE Applied Power Electronics Conference.[S.l.]:IEEE,2011:1251-1258.
[20] LU L, BRYANT A, HUDGINS J L, et al. Physics-based model of planar-gate IGBT including MOS side two-dimensional effects[J]. IEEE Transactions on Industry Applications, 2010, 46(6): 2556-2567.

备注/Memo

备注/Memo:
唐 波(1978—),男,博士,教授,主要研究方向为输变电系统电磁环境。 刘 任(1990—),男,硕士研究生,主要研究方向为输变电系统电磁环境(通讯作者)。 江浩田(1990—),男,硕士研究生,主要研究方向为输变电系统电磁环境。 孙 睿(1993—),男,硕士研究生,主要研究方向为输变电系统电磁环境。 吴 卓(1990—),男,硕士研究生,主要研究方向为输变电系统电磁环境。 收稿日期:2018-11-04; 修回日期:2019-01-19 基金项目:国家自然科学基金项目(51307098)。 Project Supported by National Natural Science Foundation of China(51307098).
更新日期/Last Update: 2019-07-15