湖南电力 ›› 2023, Vol. 43 ›› Issue (4): 125-132.doi: 10.3969/j.issn.1008-0198.2023.04.019

• 故障与分析 • 上一篇    下一篇

基于改进北方苍鹰算法优化混合核极限学习机的变压器故障诊断方法

王士彬1,2, 李多2, 赵娜2, 谢文龙2, 黄伟2, 季鸿宇2   

  1. 1.国网重庆市电力公司市南供电分公司,重庆 401336;
    2.重庆理工大学电气与电子工程学院,重庆 400054
  • 收稿日期:2023-04-11 修回日期:2023-05-23 出版日期:2023-08-25 发布日期:2023-09-07
  • 通信作者: 李多,男,硕士研究生,通信作者,主要从事电力设备在线监测与故障诊断等方面的研究。
  • 作者简介:王士彬,男,高级工程师,主要从事电力建设及设备安装维护管理等方面的研究。
  • 基金资助:
    国家社会科学基金项目(21BJL098)

Transformer Fault Diagnosis Method of Optimized Hybrid Kernel Extreme Learning Machine Based on Improved Northern Goshawk Optimization Algorithm

WANG Shibin1,2, LI Duo2, ZHAO Na2, XIE Wenlong2, HUANG Wei2, JI Hongyu2   

  1. 1. State Grid Chongqing Shinan Electric Power Supply Branch, Chongqing 401336, China;
    2. School of Electrical and Electronic Engineering, Chongqing University of Technology, Chongqing 400054, China
  • Received:2023-04-11 Revised:2023-05-23 Online:2023-08-25 Published:2023-09-07

摘要: 为提高变压器故障诊断精度,提出了一种基于改进北方苍鹰优化算法(improved northern goshawk optimization algorithm,INGO)优化混合核极限学习机(hybrid kernel extreme learning machine,HKELM)的变压器故障诊断方法。首先,利用ReliefF算法对19维变压器故障特征进行筛选降维;其次,引入Logistic-tent混沌映射、柯西变异算子和非线性递增权重三种策略改进北方苍鹰优化算法,提高全局寻优能力;然后使用改进后的INGO算法优化HKELM的初始参数,以提高HKELM的分类准确性和鲁棒性;最后,将经ReliefF优选后的特征作为模型的输入特征,并与不同变压器故障诊断模型进行对比实验。仿真结果表明,INGO-HKELM故障诊断模型相较于其他模型具有更高的故障诊断精度。

关键词: 变压器, 故障诊断, 北方苍鹰优化算法, 混合核极限学习机

Abstract: To improve the accuracy of transformer fault diagnosis, a transformer fault diagnosis method of optimized hybrid kernel extreme learning machine(HKELM)based on improved northern goshawk optimization algorithm(INGO) is proposed. Firstly, the ReliefF algorithm is used to filter and reduce the dimensionality of 19 dimensional transformer fault features. Secondly, three strategies of Logistic tent chaotic mapping, Cauchy mutation operator, and nonlinear increasing weight, are introduced to improve the Northern Hawk optimization algorithm and enhance its global optimization ability. Then, the improved INGO algorithm is used to optimize the initial parameters of HKELM to improve its classification accuracy and robustness. Finally, the features optimized by ReliefF are used as input features for the model and compared with different transformer fault diagnosis models. The simulation results show that the INGO-HKELM fault diagnosis model has higher fault diagnosis accuracy compared to other models.

Key words: transformer, fault diagnosis, northern goshawk optimization algorithm, hybrid kernel extreme learning machine

中图分类号: