基于改进NSGA-Ⅱ算法的风电机组变流器IGBT快速迭代优化设计

范佳; 赵峰; 刘一凡; 杨凡; 鄢继铨; 胡伟飞

doi:10.19912/j.0254-0096.tynxb.2024-2348

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

基于改进NSGA-Ⅱ算法的风电机组变流器IGBT快速迭代优化设计

更新时间：2026-07-22

- 基于改进NSGA-Ⅱ算法的风电机组变流器IGBT快速迭代优化设计
- Vol. 47, Issue 6, Pages: 221-229(2026)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.19912/j.0254-0096.tynxb.2024-2348
  CLC： TM614
- Online First：08 July 2026，
  
  Published：2026
- 稿件说明：
移动端阅览
范佳, 赵峰, 刘一凡, et al. 基于改进NSGA-Ⅱ算法的风电机组变流器IGBT快速迭代优化设计[J]. 2026, 47(6): 221-229.
DOI：

范佳, 赵峰, 刘一凡, et al. 基于改进NSGA-Ⅱ算法的风电机组变流器IGBT快速迭代优化设计[J]. 2026, 47(6): 221-229. DOI： 10.19912/j.0254-0096.tynxb.2024-2348.

摘要

绝缘栅双极型晶体管（IGBT）模块作为风电机组发电系统功率变流器的核心组件

优化其导电性能和制造成本意义重大。为解决这一问题

提出一种基于改进非支配排序遗传算法（NSGA-Ⅱ）的风电机组变流器IGBT模块快速迭代优化设计方法。首先

定义以其导电性能和制造成本为优化目标的优化问题

并构建了参数化热电耦合模型

实现了导电性能的精确快速求解;随后

提出基于核密度估计的改进NSGA-Ⅱ算法

通过与传统优化算法对比

改进算法显著提高了计算效率与优化精度。此外

为减轻计算负担

引入克里金（Kriging）代理模型技术构建了设计变量与优化目标间的高精度代理模型

从而实现了快速迭代优化设计。优化结果表明

该方法最多可将导电损耗减少20.00%

制造成本最多可节约27.63%。

Abstract

Insulated-gate bipolar transistor （IGBT） modules

as the core power components of wind turbine power converters

are crucial for achieving high operational efficiency and cost-effectiveness. Optimizing the electrical conductivity and manufacturing cost of these modules is essential. However

the demanding operational environments often cause performance degradation

and traditional design optimization methods incur high computational costs

making rapid iterative optimization difficult. To address these limitations

this study proposes a rapid iterative design optimization method for wind turbine converter IGBTs based on an improved NSGA-Ⅱ algorithm （Non-dominated Sorting Genetic Algorithm Ⅱ）. Firstly

the optimization problem is formulated with electrical conductivity and manufacturing cost as dual objectives. A parametric thermoelectric coupling model is developed to enable accurate and efficient evaluation of conductivity under varying design conditions. To further enhance the optimization process

an improved NSGA-Ⅱ algorithm based on kernel density estimation is proposed

significantly improving computational efficiency and optimization accuracy compared to traditional optimization algorithms. Additionally

a Kriging-based surrogate model is employed to construct high-fidelity mappings between design variables and optimization objectives

thereby reducing computational burdens and enabling rapid iterative optimization. Numerical experiments confirm the effectiveness and robustness of the proposed method

demonstrating reductions in electrical losses of up to 20.00% and decreases in manufacturing costs by as much as 27.63%. This study provides a practical and efficient design framework for IGBT modules

offering valuable insights into multi-objective optimization in the field of power electronics. By integrating advanced optimization algorithms with surrogate modeling

the proposed method addresses key challenges in the design and performance enhancement of wind turbine power systems.

关键词

Keywords

references

卓振宇, 张宁, 谢小荣,等. 高比例可再生能源电力系统关键技术及发展挑战[J]. 电力系统自动化, 2021, 45(9): 171-191.

胡姚刚, 李辉, 廖兴林, 等. 风电变流器IGBT模块有效工作芯片状态评估[J]. 太阳能学报, 2021, 42(5): 373-379.

姚芳, 胡洋, 李铮, 等. 风电变流器IGBT瞬态电热特性测试及其应用研究[J]. 太阳能学报, 2018, 39(2): 369-376.

何伟冬, 王学梅. 用于风电的模块化多电平变流器IGBT的定制化设计[J]. 电力工程技术, 2021, 40(4): 10-17.

王红庆, 梁媛. 基于NSGA权值修正的MPC方法及其在光氢系统应用[J]. 太阳能学报, 2024, 45(11): 131-140.

曹阳, 房永亮, 刘珍, 等. 基于RSM和NSGA-Ⅱ法的风电系统经济优化研究[J]. 太阳能学报, 2022, 43(1): 161-168.

DEB K, PRATAP A, AGARWAL S,et al.A fast and elitist multiobjective genetic algorithm: NSGA-Ⅱ[J]. IEEE transactions on evolutionary computation, 2002, 6(2): 182-197.

ZHANG Q, LI H.MOEA/D: a multiobjective evolutionary algorithm based on decomposition[J]. IEEE transactions on evolutionary computation, 2007, 11(6): 712-731.

QI Y, MA X, LIU F,et al.MOEA/D with adaptive weight adjustment[J]. Evolutionary computation, 2014, 22(2): 231-264.

ALAVI O, ABDOLLAH M, VIKI A H.Thermal optimization of IGBT modules based on finite element method and particle swarm optimization[J]. Journal of computational electronics, 2017, 16(3): 930-938.

LIU H, XU S L, MA Y,et al.An adaptive Bayesian sequential sampling approach for global metamodeling[J]. Journal of mechanical design, 2015, 138(1): 011404.

HU W F, ZHAO F, DENG X Y,et al.A new sequential sampling method for surrogate modeling based on a hybrid metric[J]. Journal of mechanical design, 2024, 146(6): 061705.

MO S, LU D, SHI X,et al.A Taylor expansion-based adaptive design strategy for global surrogate modeling with applications in groundwater modeling[J]. Water resources research, 2017, 53(12): 10802-10823.

于梦阁, 潘振宽, 蒋荣超, 等. 基于近似模型的高速列车头型多目标优化设计[J]. 机械工程学报, 2019, 55(24): 178-186.

赵峰, 胡伟飞, 李光, 等. 基于混合指标自适应采样代理模型的多目标优化设计方法[J]. 机械工程学报, 2024, 60(13): 81-91.

BEZERRA M, SANTELLI R, OLIVEIRA E,et al.Response surface methodology (RSM) as a tool for optimization in analytical chemistry[J]. Talanta, 2008, 76(5): 965-977.

ZHOU Q, JIANG P, SHAO X,et al.A variable fidelity information fusion method based on radial basis function[J]. Advanced engineering informatics, 2017, 32: 26-39.

KLEIJNEN J P C. Kriging metamodeling in simulation: a review[J]. European journal of operational research, 2009, 192(3): 707-716.

TIAN Y, CHENG R, ZHANG X,et al.PlatEMO: a Matlab platform for evolutionary multi-objective optimization [educational forum][J]. IEEE computational intelligence magazine, 2017, 12(4): 73-87.

VIANA F A C. A tutorial on Latin hypercube design of experiments[J]. Quality and reliability engineering international, 2016, 32(5): 1975-1985.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

基于GSS的RIME-CNN-LSTM-Attention光伏出力组合预测模型

基于WOA-GWO算法优化的光伏组件最佳倾角实验研究

基于改进鱼鹰优化算法与VMD-LSTM的超短期风电功率预测

基于混合神经网络的风电场测风数据插补方法的研究

各代生物乙醇生产工艺碳减排潜力研究

Related Author

袁越

苗安康

马一力

黄毅

蔡伟华

陈嘉祥

王力

朱彪

Related Institution

华北电力大学自动化系北京102206

Department of Automatic Control,North China Electric Power University

Wind Energy Institute,Shenyang University of Technology,Shen Yang

School of Electrical Engineering, Shenyang University of Technology

Tianshui Electric Drive Research Institute Group Co., Ltd.

AI问答

⁰