Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning

Han Zhang; Wenxia Sima; Ming Yang

doi:10.17775/CSEEJPES.2021.05660

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning

Regular Papers | 更新时间：2026-10-16

- Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning
- Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning
- 中国电机工程学会电力与能源系统学报(英文) 2025年11卷第5期页码：2178-2188
- 作者机构：
  
  State Key Laboratory of Power Transmission Equipment & System Security and New Technology, Chongqing University,Chongqing,China
- 作者简介：
- 基金信息：
- DOI：10.17775/CSEEJPES.2021.05660
  中图分类号：
- 纸质出版：2025-09-01
- 稿件说明：
移动端阅览
Han Zhang, Wenxia Sima, Ming Yang. Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning[J]. 中国电机工程学会电力与能源系统学报(英文), 2025,11(5):2178-2188.

Han Zhang, Wenxia Sima, Ming Yang. Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning[J]. CSEE Journal of Power and Energy Systems, 2025, 11(5): 2178-2188.
Han Zhang, Wenxia Sima, Ming Yang. Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning[J]. 中国电机工程学会电力与能源系统学报(英文), 2025,11(5):2178-2188. DOI： 10.17775/CSEEJPES.2021.05660.

Han Zhang, Wenxia Sima, Ming Yang. Data-Driven Approach for Electromagnetic Transient Recognition Using Transfer Learning[J]. CSEE Journal of Power and Energy Systems, 2025, 11(5): 2178-2188. DOI： 10.17775/CSEEJPES.2021.05660.

摘要

Abstract

Recognition methods of electromagnetic transients (EMT) have been widely used in power systems with the assumption that training and testing data are drawn from the same probability distribution. However

that assumption is hard to satisfy in industrial applications because the distribution of measured EMT testing data generally changes over time. The performance of these methods gradually deteriorates with the distribution shift. The phenomenon limits application of EMT recognition methods. Therefore

this paper proposes a transfer learning-based recognition network (TLRN) for EMT to break the limitation. It consists of a feature extractor

EMT recognizer

domain recognizer

and maximum mean discrepancy (MMD). The feature extractor is constructed to learn features of EMT automatically. The domain recognizer and MMD make features learned by the feature extractor domain invariant. Based on domain invariant features

the EMT recognizer achieves accurate EMT recognition

despite the distribution discrepancy between EMT training and testing data. TLRN maintains satisfactory EMT recognition performance by updating periodically with an unsupervised learning strategy. Using EMT datasets measured from different substations

scenario experiments

and experiment comparisons are conducted

and the recognition performance of the proposed TLRN is demonstrated.

关键词

Keywords

references

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

Detection Framework for Few-Shot Voltage Disturbances in Power Systems Using Evaluation Learning

Power Grid Fault Diagnosis Based on Deep Pyramid Convolutional Neural Network

Efficient Execution Method of Edge Intelligent Models for Abnormal Target Detection in Transmission Lines Based on Low Bit Shift Quantization

Temporal Convolutional Auto-Encoder for Residential Non-Intrusive Load Monitoring

Faulty-Feeder Detection Based on Sparse Waveform Encoding and Simple Convolutional Neural Network with Multi-Scale Filters and One Layer of Convolution