基于神经网络的绝缘栅双极型晶体管开关损耗预测

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1522 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要针对级联储能应用领域大量绝缘栅双极型晶体管（IGBT）的开关损耗难以准确在线测量的问题,引入误差反向传播神经网络,建立IGBT开关损耗预测模型。首先采用级联H桥功率模块搭建开关损耗动态测试系统,通过调整直流母线电压、交流电流及冷却液温度,获得大量测试数据;然后将影响IGBT开关损耗的3个主要因素——集射极电压、集电极电流、结温作为预测模型的输入,采用粒子群优化算法优化开关损耗预测模型的初始权值和阈值,以提升预测开通损耗、关断损耗及二极管反向关断损耗的准确度并加速学习规律的收敛;最后与随机给定初始权值及阈值的开关损耗预测模型进行对比分析。结果表明,引入粒子群优化算法所建立的开关损耗预测模型的预测准确度更高,针对50组随机验证数据的最大百分误差为3.3%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	王长华
	李祥雄
	梁顺发
	陈荣东

关键词 ：绝缘栅双极型晶体管（IGBT）, 开关损耗预测, 神经网络, 粒子群优化算法

Abstract：Aiming at the disadvantages that numerous insulated gate bipolar transistor (IGBT) switching loss are difficult to accurately measure online in the cascaded energy storage application area, switching loss prediction model is established based on the error back propagation neural network. Firstly, dynamic test system of switching loss is built with cascaded H bridge power module, the massive switching loss data is obtained with changing the direct current bus voltage, alternating current and coolant temperature of power module. 3 main factors including collector-emitter voltage, collector current and device junction temperature are taken as the input of IGBT switching loss prediction model. The particle swarm optimization is used to optimize the initial weight and threshold of prediction model, improving prediction accuracy and accelerating the convergence of learning laws. The optimized performance of this model is compared and analyzed with the prediction model that the initial weight and threshold are given randomly. The results show that the prediction accuracy of the model proposed in this paper is higher. The maximum percentage error for 50 sets of random validation data is 3.3%.

Key words： insulated gate bipolar transistor (IGBT) switching loss prediction neural network particle swarm optimization

收稿日期: 2024-09-19

作者简介: 王长华（1983—）,男,湖南省邵阳市人,硕士,工程师,主要从事电力电子技术与电池储能研发工作。

引用本文:

王长华, 李祥雄, 梁顺发, 陈荣东. 基于神经网络的绝缘栅双极型晶体管开关损耗预测[J]. 电气技术, 2025, 26(3): 42-48. WANG Changhua, LI Xiangxiong, LIANG Shunfa, CHEN Rongdong. Insulated gate bipolar transistor switching loss prediction based on neural network. Electrical Engineering, 2025, 26(3): 42-48.

链接本文:

https://dqjs.cesmedia.cn/CN/Y2025/V26/I3/42

[1] 蔡旭, 李睿, 李征. 储能功率变换与并网技术[M].北京: 科学出版社, 2019.
[2] 张午宇, 齐磊, 张翔宇, 等. 计及金属化薄膜电容器与IGBT模块退化过程相关性的柔直换流阀组件可靠性评估方法[J].电工技术学报, 2024, 39(14): 4508-4518.
[3] 李雨泽, 张秀敏, 袁文迁, 等. 基于电参数的IGBT开关瞬态过程耦合关系分析[J].高电压技术, 2024, 50(3): 1252-1263.
[4] 邹毅军, 魏明洋. 模块化多电平换流器子模块故障模拟方法[J].电气技术, 2022, 23(4): 96-101.
[5] AN Yang, SUN Xiangdong, REN Biying, et al.A data-driven method for IGBT open-circuit fault diagnosis for the modular multilevel converter based on a modified Elman neural network[J].Energy Reports, 2022, 8: 80-88.
[6] SIVAPRIYA A, KALAIARASI N.A novel enhanced deep learning-based fault diagnosis approach for cascaded multilevel inverter[J].e-Prime-Advances in Electrical Engineering, Electronics and Energy, 2023, 5: 100253.
[7] 李志刚, 梅霜. 基于神经网络的功率模块开关损耗预测[J].现代电子技术, 2016, 39(20): 101-103.
[8] LIU Yunhe, GUO Tengfei, LI Jinda, et al.A study on temperature monitoring method for inverter IGBT based on memory recurrent neural network[J].High- speed Railway, 2024, 2(1): 64-70.
[9] 普靖, 罗毅飞, 肖飞, 等. 针对高压IGBT的改进瞬态模型[J].高电压技术, 2018, 44(2): 448-455.
[10] 杨立敏, 王晖, 韩志勇, 等. 全桥型模块化多电平换流器损耗简化计算模型研究[J].电工电能新技术, 2019, 38(8): 53-62.
[11] 黄李奔. 基于BP神经网络模型的智慧杆电源热稳定性评估方法[J].电气技术, 2023, 24(6): 47-56.
[12] 徐扬, 张紫涛. 基于遗传模拟退火算法改进BP神经网络的中长期电力负荷预测[J].电气技术, 2021, 22(9): 70-76.
[13] 任宏宇, 余瑶怡, 杜雄, 等. 基于优化长短期记忆神经网络的IGBT寿命预测模型[J].电工技术学报, 2024, 39(4): 1074-1086.
[14] 唐圣学, 张继欣, 姚芳, 等. IGBT模块寿命预测方法研究综述[J].电源学报, 2023, 21(1): 177-194.
[15] 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.
[16] 万庆祝, 于佳松, 佟庆彬, 等. 基于Bo-BiLSTM网络的IGBT老化失效预测方法[J].电气技术, 2024, 25(3): 1-10.
[17] 陈娜, 李鹏, 江剑, 等. 中高压IGBT开关特性的遗传神经网络预测[J].电工技术学报, 2013, 28(2): 239-247, 254.
[18] 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(7): 27-32.
[19] 田安民, 孙光淼, 卢文冰, 等. 大容量变流器中IGBT关断过电压抑制技术研究[J].电力电子技术, 2023, 57(10): 13-16.