Solution of Switching Loss of IGBT Module Based on Back Propagation Neural Network

TANG Bo; LIU Ren; JIANG Haotian; SUN Rui; WU Zhuo

doi:10.13296/j.1001-1609.hva.2019.07.005

您当前的位置：

首页 >

文章列表页 >

Solution of Switching Loss of IGBT Module Based on Back Propagation Neural Network

更新时间：2025-04-26

- Solution of Switching Loss of IGBT Module Based on Back Propagation Neural Network
- High VoltageApparatus Vol. 55, Issue 7, Pages: 27-32(2019)
- 作者机构：
  
  三峡大学电气与新能源学院
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2019.07.005
  CLC： TM564;TP183
- Published：2019
- 稿件说明：
移动端阅览
[1]唐波,刘任,江浩田,孙睿,吴卓.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.

TANG Bo, LIU Ren, JIANG Haotian, et al. Solution of Switching Loss of IGBT Module Based on Back Propagation Neural Network[J]. High VoltageApparatus, 2019, 55(7): 27-32.
[1]唐波,刘任,江浩田,孙睿,吴卓.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 VoltageApparatus, 2019, 55(7): 27-32. 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 performanceand lifetime studies of power converter. Aiming at the disadvantages that the existing IGBT switching loss solvingmodels are difficult to accurately solve the switching loss value

the error back propagation（BP）neural network mod-el 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 IGBTmodule switching loss as the input vector

and optimizing the initial weight and threshold of BP neural network bythe particle swarm algorithm

the exact solution of the switching loss is obtained accordingly. The model realizes thereliable prediction of the switching loss of the IGBT module on various working conditions in the rated range

and themaximum error rate in 100 sets of validation samples is 3.85%.

关键词

Keywords

references

Views

208

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Simulation Design and Optimization of Permanent-magnet-motor Operating Mechanism for Vacuum Circuit Breaker with Long Clearance

Fault Diagnosis Algorithm on Spring Operating Mechanism for High Voltage Circuit Breaker and Load Switch Based on Motor Current

Design Simulation and Optimization of Fast Electromagnetic Repulsion Mechanism for Mechanical DC Circuit Breaker

Research on Key Technologies of PMA Based Synchronous Switching

Pattern Recognition of Partial Discharge in Oil-paper Insulation Based on Time Series

Related Author

LI Jinqi

DING Yiling

WANG Zhoulin

DING Can

HE Zhipeng

JI Yiwei

ZHAO Lihua

WU Yuezheng

Related Institution

State Key Laboratory of Electrical Insulation and Power Equipment, Xi'an Jiaotong University

School of Automation, Northwest University of Technology

School of Electrical Engineering, Sichuan University

Lijiang Power Supply Bureau of Yunnan Power Grid Co., Ltd.

Electric Power Research Institute of State Grid Jibei Electric Power Co, Ltd

⁰