Bias magnetic characteristic analysis and condition identification of transformers under DC bias magnetism conditions based on electromagnetic vibration and convolutional neural network

Abstract

Abnormal vibration of transformers under DC bias magnetism may cause permanent damage to its mechanical structure. Considering the magnetostrictive effect of the core is the main source of vibration in transformers, this paper proposes a method called 2DWT-CNN for identifying DC bias magnetism conditions in transformers by studying the magnetostrictive effect of ferromagnetic materials and analyzing the dynamic process of core deformation. Specifically, the electromagnetic vibration signals of the core and the shell of the transformer were acquired separately on the experimental platform. Then, based on the expansion and contraction characteristics of the core under DC bias magnetism conditions, the magnetic vibration features were extracted using the 2D wavelet transform. Finally, a bias magnetism recognition method called two-dimensional wavelet-convolutional neural network (2DWT-CNN) was established by combining convolutional neural networks as the classifier. The experimental results show that the recognition model has a classification accuracy of almost 100% for the core test points and a prediction accuracy of around 97% for the points located in the transformer's shell. Therefore, the 2DWT-CNN, which takes magnetostrictive effects into account, is an effective method for identifying bias magnetic conditions and can successfully apply the microscopic process of magnetostriction to the macroscopic and practical detection of transformer bias magnetic conditions.