Investigation of convolutional neural network U-net under small datasets in transformer magneto-thermal coupled analysis

Abstract

Purpose This paper aims to investigate the approach combine the deep learning (DL) and finite element method for the magneto-thermal coupled problem. Design/methodology/approach To achieve the DL of electrical device with the hypothesis of a small dataset, with ground truth data obtained from the FEM analysis, U-net, a highly efficient convolutional neural network (CNN) is used to extract hidden features and trained in a supervised manner to predict the magneto-thermal coupled analysis results for different topologies. Using part of the FEM results as training samples, the DL model obtained from effective off-line training can be used to predict the distribution of the magnetic field and temperature field of other cases. Findings The possibility and feasibility of the proposed approach are investigated by discussing the influence of various network parameters, in particular, the four most important factors are training sample size, learning rate, batch size and optimization algorithm respectively. It is shown that DL based on U-net can be used as an efficiency tool in multi-physics analysis and achieve good performance with only small datasets. Originality/value It is shown that DL based on U-net can be used as an efficiency tool in multi-physics analysis and achieve good performance with only small datasets.