首页|基于MIWOA优化SCN的变压器故障诊断研究

基于MIWOA优化SCN的变压器故障诊断研究

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
针对变压器故障诊断精确度低的问题,本文提出了一种多策略改进的鲸鱼优化算法(MI-WOA)优化随机配置网络(SCN)的变压器故障诊断模型.首先,对变压器冗杂繁多的原始故障数据进行核主成分分析(KPCA)降维处理,降低无效特征的影响;其次,利用Tent混沌映射、动态自适应权重和初级知识获取共享算法对鲸鱼算法(WOA)进行改进,提高其优化能力;然后,在SCN中引入L2 范数惩罚项进行正则化处理,并使用改进后的MIWOA算法对SCN惩罚项系数C进行寻优求解,提高SCN分类精度和泛化能力;最后,将降维的数据输入到MIWOA-SCN故障诊断模型中,提高模型收敛速度.结果表明,本文所提出的模型诊断精度为 93.1%,与WOA-SCN、GWO-SCN和PSO-SCN诊断模型相比,分别提高了 6.89%、9.48%、14.65%,证明MIWOA-SCN诊断模型在变压器故障诊断上具有良好的诊断效果.
Research on transformer fault diagnosis based on MIWOA optimized SCN
To address the problem of low accuracy of transformer fault diagnosis,a multi-strategy improved whale optimization algorithm(MIWOA)is proposed to optimize the transformer fault diagnosis model of stochastic configu-ration network(SCN).First,the raw transformer redundant and extensive fault data are subjected to kernel princi-pal component analysis(KPCA)to reduce the influence of invalid features.Secondly,the whale optimization algo-rithm(WOA)is improved by using tent chaos mapping,dynamic adaptive weighting and primary knowledge acqui-sition sharing algorithm to improve its optimization capability.Then,the L2 parametric penalty term is introduced in the SCN for regularization and the improved MIWOA algorithm solves the SCN penalty term coefficients C in an optimal way to improve the SCN classification accuracy and generalization ability.Finally,in order to accelerate the convergence speed of the model,degraded data are input into the MIWOA-SCN fault diagnosis model.The results show that the diagnostic accuracy of the model is 93.1%,which is 6.89%and 9.48%higher than the WOA-SCN,GWO-SCN,and PSO-SCN diagnostic models,respectively.This is 14.65%higher.This proves that the MIWOA-SCN diagnostic model has good diagnostic performance for transformer fault diagnosis.

transformerwhale optimizaton algorithmkernel principal component analysisdynamic adaptive weightsprimary knowledge acquisition and sharing algorithmstochastic configuration network

丰胜成、张宗瑞、付华、韩猛

展开 >

辽宁工程技术大学电气与控制工程学院,辽宁 葫芦岛 125105

山西潞安环保能源开发股份有限公司王庄煤矿,山西 长治 046204

变压器 鲸鱼优化算法 核主成分分析 动态自适应权重 初级知识获取共享算法 随机配置网络

国家自然科学基金辽宁高等学校创新团队项目辽宁高等学校国(境)外培养项目

51974151LT20190072019GJWZD002

2024

10.12067/ATEEE2303015

电工电能新技术
中国科学院电工研究所

电工电能新技术

CSTPCD北大核心
影响因子：0.716
ISSN：1003-3076
年,卷(期)：2024.43(6)