Intelligent Design of Power Electronics: Technical Roadmap Overview and Frontier Exploration

陈宇; 祝之森; 白敬波; 商毅; 康勇

doi:10.13334/j.0258-8013.pcsee.241598

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Intelligent Design of Power Electronics: Technical Roadmap Overview and Frontier Exploration

更新时间：2026-01-08

- Intelligent Design of Power Electronics: Technical Roadmap Overview and Frontier Exploration
- Vol. 46, Issue 1, Pages: 339-356(2026)
- 作者机构：
  
  华中科技大学电气与电子工程学院,湖北省,武汉市,430074
- 作者简介：
- 基金信息：
- DOI：10.13334/j.0258-8013.pcsee.241598
  CLC：
- Published：2026
- 稿件说明：
移动端阅览
陈宇, 祝之森, 白敬波, et al. Intelligent Design of Power Electronics: Technical Roadmap Overview and Frontier Exploration[J]. 2026, 46(1): 339-356.
DOI：

陈宇, 祝之森, 白敬波, et al. Intelligent Design of Power Electronics: Technical Roadmap Overview and Frontier Exploration[J]. 2026, 46(1): 339-356. DOI： 10.13334/j.0258-8013.pcsee.241598.

摘要

该文对人工智能(artificial intelligence，AI)技术和电力电子设计结合的相关研究进行全面综述，从时间、技术和发展趋势等多个视角进行分析。首先，回顾AI发展关键节点对电力电子设计领域的影响；对AI在电力电子设计领域的应用进行了分类，对比分析传统AI、深度监督学习、深度强化学习3类算法在电力电子设计中的需求、应用思路和效果；在此基础上，提出电力电子设计智能化下一阶段的发展方向，是解决传统设计工具和AI工具之间、各种设计工具与人之间的交互问题，给出基于大语言模型的电力电子智能代理前沿探索；最后，给出关于该领域的若干思考。

Abstract

This paper provides a comprehensive review of the integration of artificial intelligence (AI) technology and power electronics design

analyzing the topic from multiple perspectives including time

technology

and development trend. First

the impact of key milestones in AI development on the field of power electronics design is reviewed; then

the research on AI in power electronics design is classified

and the requirements

application ideas

and effects of traditional AI

deep supervised learning

and deep reinforcement learning algorithms in power electronics design are comparatively analyzed. Based on this foundation

the paper proposes that the next stage of intelligent power electronics design needs to focus on solving the interaction problems between traditional design tools and AI tools and also between design tools and humans

and offers several frontier explorations of power electronics intelligent agents based on large language models; Finally

several thoughts about this field are provided.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

传统方法与人工智能:潮流控制优化算法的现状、挑战与未来方向

Energy Management Strategy of Urban Rail Wayside Energy Storage System Based on Improved Deep Deterministic Policy Gradient Algorithm

Decentralized Coordinated Control Strategy for Power Quality in Low Voltage Distribution Networks Based on Multi-agent Deep Reinforcement Learning

Zonal Voltage Control Strategy Based on Graph Deep Reinforcement Learning With Spatial-temporal Pseudo-twin Network

Two-stage Distributed Generators Optimization Based on Deep Reinforcement Learning With Parameter Sharing

Related Author

王甜婧

汤涌

王兵

黄彦浩

郭强

陈兴雷

文晶

李文臣

Related Institution

电网安全与节能国家重点实验室(中国电力科学研究院有限公司)

北京交通大学电气工程学院, 北京市海淀区

College of Electrical Engineering and Automation, Fuzhou University

Electric Power Research Institute, State Grid Fujian Electric Power Co., Ltd.

Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education (Northeast Electric Power University)

AI问答

⁰