Power Transformer Winding Deformation Diagnosis Based on the Sum of Two‐Way Shortest Distance

Abstract

Frequency response analysis (FRA) method has been widely used in the world, but the interpretation of its signatures is still a hard problem to solve. This paper introduces a method of the sum of two‐way shortest distance for transformer winding deformation fault diagnosis, which is based on trajectory similarity between FRA signatures. Compared with most existing methods, it does not need order preservation; however, it focuses more on the trajectory itself. The geometric principle of the sum of two‐way shortest distance is introduced and analyzed in detail. By using the circuit analysis software, the equivalent circuit model of the transformer is established, a group of the FRA signatures of three types of transformer winding fault, including axial displacement, radial deformation, and disk space variation fault, are obtained. The distribution of different type of faults is studied by using the sum of two‐way shortest distance to process the FRA signatures in three different frequency bands. Using the sum of two‐way shortest distance as input, the support vector machine (SVM) is employed to train a predictive engine for transformer winding deformation fault diagnosis. Result shows that the proposed method can well classify and diagnose transformer winding deformation fault. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.