Diagnosis of Disc Space Variation Fault Degree of Transformer Winding Based on K-Nearest Neighbor Algorithm

作     者：Song Wang Fei Xie Fengye Yang Shengxuan Qiu Chuang Liu Tong Li 

作者机构：Department of Power and Electrical EngineeringNorthwest A&F UniversityYangling712100China NARI GroupBeijing Kedong Electric Power Control System Co.Ltd.Beijing100000China Huangling Mining Group Co.Ltd.Shanxi Coal and Chemical Industry GroupHuangling716000China 

出 版 物：《Energy Engineering》 (能源工程（英文）)

年 卷 期：2023年第120卷第10期

页      面：2273-2285页

核心收录：

学科分类：080801[工学-电机与电器] 0808[工学-电气工程] 08[工学] 

基　　金：supported in part by Shaanxi Natural Science Foundation Project (2023-JC-QN-0438) in part by Fundamental Research Funds for the Central Universities (2452021050) 

主　　题：Transformer winding frequency response analysis(FRA)method K-Nearest Neighbor(KNN) disc space variation(DSV) 

摘      要：Winding is one of themost important components in power *** the health state of the winding is of great importance to the stable operation of the power *** efficiently and accurately diagnose the disc space variation(DSV)fault degree of transformer winding,this paper presents a diagnostic method of winding fault based on the K-Nearest Neighbor(KNN)algorithmand the frequency response analysis(FRA)***,a laboratory winding model is used,and DSV faults with four different degrees are achieved by changing disc space of the discs in the ***,a series of FRA tests are conducted to obtain the FRA results and set up the FRA ***,ten different numerical indices are utilized to obtain features of FRA curves of faulted ***,the 10-fold cross-validation method is employed to determine the optimal k-value of *** addition,to improve the accuracy of the KNN model,a comparative analysis is made between the accuracy of the KNN algorithm and k-value under four distance *** getting the most appropriate distance metric and kvalue,the fault classificationmodel based on theKNN and FRA is constructed and it is used to classify the degrees of DSV *** identification accuracy rate of the proposed model is up to 98.30%.Finally,the performance of the model is presented by comparing with the support vector machine(SVM),SVM optimized by the particle swarmoptimization(PSO-SVM)method,and randomforest(RF).The results show that the diagnosis accuracy of the proposed model is the highest and the model can be used to accurately diagnose the DSV fault degrees of the winding.