The Research of Power Transformer Fault Diagnosis based on Bagging Algorithm

The power transformer is one of the most important electrical equipment in power system. It is of great importance for maintaining the normal operation of the power transformer to detect the latent faults and grasp its development trend early. In order to improve the accuracy of power transformer fault diagnosis, a new method to diagnose power transformer faults based on the Bagging algorithm is presented. The problem of the transformer fault diagnosis is abstracted into a classification problem in the method. The oil dissolved gas analysis technology is used to collect data samples. After normalization and numerical processing the data samples, the weak learning algorithm is called repeatedly to complete the training of the sample set to get strong learning machine, which is used as transformer fault diagnosis model. The final diagnostic conclusion is obtained by majority voting method within the initial fault diagnosis results of weak learning machine. The ball vector machine is used as the weak learning algorithm of the Bagging algorithm. Finally, the experiment shows that the proposed method has better adaptability and lower diagnostic errors in improving the power transformer fault diagnosis accuracy than the traditional intelligent fault diagnosis method.