基于WKPCA与IEDO-XGBoost的变压器故障诊断方法研究

扫码查看

原文链接

万方数据
维普

中文摘要：针对变压器故障的特点,将加权核主成分分析技术与IEDO-XGBoost相结合,提出了一种新的变压器故障诊断模型.该方法主要将溶解气体分析技术与无编码比值法相结合,获取变压器的故障特征,利用WKPCA对其进行降维处理,并将归一化处理后的故障样本数据作为IEDO-XG-Boost模型的输入,输出变压器故障诊断类型及其诊断准确率.选取 20 维变压器故障特征数据进行 WKPCA降维处理,加快了模型的收敛速度;采用自适应正余弦策略和高斯变异策略对指数分布优化器算法进行改进,并用10 个典型测试函数对改进后的指数分布优化算法性能进行了测试,结果表明改进后的指数分布优化算法具有更快的收敛速度和全局搜索能力.然后,利用改进的指数分布算法来确定 XGBoost 模型中的多个最优参数.仿真结果表明,该模型的诊断准确率为91.82%,分别比 EDO-XGBoost、NGO-XGBoost、GJO-XGBoost、GWO-XGBoost 和 WOA-XGBoost 故障诊断模型高 2.73%、3.64%、5.46%、8.18%和 10.91%,验证了本文所提方法能够有效提高变压器故障诊断性能.

外文标题：Transformer fault diagnosis method based on weighted kernel principal component analysis with improved exponential distribution optimization XGBoost

外文摘要：Aiming at the characteristics of transformer faults,a new transformer fault diagnosis model is proposed by combining the Weighted Kernel Principal Component Analysis(WKPCA)technique with IEDO-XGBoost.The method mainly combines the dissolved gas analysis technique with the non-coded ratio method to obtain the fault characteristics of the transformer,use WKPCA to reduce its dimension,and use the processed normalized fault sample data as the input of the IEDO-XGBoost model to output the transformer fault diagnosis type and its diagnostic accuracy.The 20-dimensional transformer fault feature data are selected for WKPCA dimension reduction process-ing,which accelerates the convergence speed of the model;the exponential distribution optimizer algorithm is im-proved by using the adaptive sine-cosine strategy and Gaussian variance strategy,and the performance of the im-proved exponential distribution optimization algorithm is tested by using 10 typical test functions.The results show that the improved exponential distribution optimization algorithm has faster convergence speed and global search a-bility.Then,the improved exponential distribution algorithm is used to determine multiple optimal parameters in the XGBoost model.Simulation results show that the diagnostic accuracy of the model is 91.82%,which is 2.73%,3.64%,5.46%,8.18%and 10.91%higher than that of EDO-XGBoost,NGO-XGBoost,GJO-XGBoost,GWO-XGBoost and WOA-XGBoost fault diagnosis models,respectively,which verifies that the proposed method can effectively improve transformer fault diagnosis performance.

外文关键词：

transformerweighted kernel principal component analysisfault diagnosisdissolved gas analysisexponential distribution optimization algorithmextreme gradient boosting(XGBoost)

作者：

张容槟、徐耀松、牛元平

展开 >

作者单位：

辽宁工程技术大学电气与控制工程学院,辽宁葫芦岛 125105

关键词：

变压器加权核主成分分析故障诊断溶解气体分析指数分布优化算法极端梯度提升

基金：

国家自然科学基金项目辽宁省教育厅重点实验室项目辽宁省教育厅辽宁省高等学校基本科研项目辽宁省教育厅科技项目

项目编号：

51974151LJZS003LJ2017QL012LJ2019QL015

出版年：

2024

DOI：

10.12067/ATEEE2403014

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(10)