半月刊

ISSN 1000-1026

CN 32-1180/TP

+高级检索 English
基于多模型选择性融合的变压器在线故障诊断
作者:
作者单位:

1.东北大学信息科学与工程学院,辽宁省沈阳市 110819;2.国网辽宁省电力有限公司,辽宁省沈阳市 110006

摘要:

在线智能化故障诊断是变压器故障诊断的发展趋势,为发挥不同征兆子集及诊断算法的性能优势,实现多元诊断模型的互补决策,文中通过对智能诊断算法的性能进行多维对比分析,选取综合性能优的诊断算法用于征兆子集优选,使用优选子集与诊断算法训练多个诊断模型,通过模型间差异性分析有选择地对模型进行融合并用于最终决策。实例验证结果表明,融合模型泛化性能及均衡诊断能力均有提升。

关键词:

基金项目:

国家自然科学基金资助项目(61673093)。

通信作者:

作者简介:


On-line Fault Diagnosis for Transformer Based on Selective Fusion of Multiple Models
Author:
Affiliation:

1.College of Information Science and Engineering, Northeastern University, Shenyang 110819, China;2.State Grid Liaoning Electric Power Limited Company, Shenyang 110006, China

Abstract:

Online intelligent fault diagnosis is the development trend of transformer fault diagnosis. In order to make use of the performance advantages of different symptom subsets and diagnosis algorithms, and realize the complementary decision-making of multiple diagnosis models, this paper conducts multi-dimensional comparative analysis on the performance of intelligent diagnosis algorithms, and selects the diagnosis algorithms with excellent comprehensive performance for the selection of the symptom subset. The selecteded subsets and diagnosis algorithms are used to train multiple diagnosis models, and the models are selectively fused and used for final decision-making through analysis of differences between models.The example verification results show that the generalization performance and balance diagnosis ability of the fusion model are improved.

Keywords:

Foundation:
This work is supported by National Natural Science Foundation of China (No. 61673093).
引用本文
[1]张育杰,李典阳,冯健,等.基于多模型选择性融合的变压器在线故障诊断[J/OL].电力系统自动化,http://doi. org/10.7500/AEPS20200519002.
ZHANG Yujie, LI Dianyang, FENG Jian, et al. On-line Fault Diagnosis for Transformer Based on Selective Fusion of Multiple Models[J/OL]. Automation of Electric Power Systems, http://doi. org/10.7500/AEPS20200519002.
复制
分享
历史
  • 收稿日期:2020-05-19
  • 最后修改日期:2020-10-29
  • 录用日期:2020-10-20
  • 在线发布日期:
  • 出版日期:
相关附件