Dissolved Gas Analysis of Insulating Oil for Power Transformer State Evaluation Based on Entropy Weight and TOPSIS Method

The transformer state evaluation involves a lot of indexes and fuzzy classification of state grade. In order to improve the accuracy and efficiency of transformer fault diagnosis and evaluate the state of transformer reasonably, a transformer state evaluation based on entropy weight and TOPSIS method is proposed. Firstly, the transformer state evaluation index system is established, and the entropy weight method is used to mine the data information of transformer dissolved gas in insulating oil under different conditions to determine the weight of each index; At the same time, TOPSIS method is used to obtain the closeness of quantitative index to each state grade of transformer, and finally the evaluation result is determined according to the closeness. The experimental results show that the evaluation results of the transformer based on the key index system established in this paper are consistent with the actual running state of the transformer compared with the results of the SVM method and the IEC three ratio method, which proves the effectiveness of the method.