Identification Method of Transformer Winding Material Based on Support Vector Machine

The use of “aluminium instead of copper” transformers poses a safety risk to the operation of the grid. In order to achieve rapid detection of transformer winding materials, this paper proposes an identification method of transformer winding material based on support vector machine. Firstly, according to the difference of copper aluminum transformer under harmonic excitation, the theoretical basis of identification method is given. Then, based on this principle a winding material identification test system is established, and copper aluminum transformer is tested separately. Finally, support vector machine is used to classify the test data and predict the measurement of unknown transformers using the classification results. The experimental results show that the identification method proposed in this paper can effectively screen out aluminum winding transformers quickly and has high application value in engineering fields such as transformer grid-connected testing and full pre-screening.