Transformer winding hot-spot temperature (HST) is one of the important factors affecting transformer oil-paper insulation deterioration. This study presents a three-dimensional coupled electromagnetic-fluid-thermal analysis method for HST calculation in a 10 kV oil-immersed distribution transformer, the influence of the transformer internal metal structure parts on the HST of the winding is considered in the simulation. Combining electromagnetic-field calculation with no-load test and load test of the transformer provides a more accurate method to determine internal losses of the transformer. Taking those power losses as heat sources, the transformer fluid-thermal field analysis is conducted with the finite volume method. The variation of physical parameters of transformer oil with temperature is considered in the simulation. On the basis of the equivalent thermal resistance theory, the equivalent thermal conductivities of transformer windings are obtained. The simulation results deduced from the proposed method agree well with the experimental ones, which are obtained with fibre optic temperature sensors during the transformer temperature rise test, the maximum temperature difference is <3°C. The results validated the validity and accuracy of the proposed transformer HST calculation method.

A quasi-3D coupled-field method is introduced and applied on a ventilated dry-type transformer to study temperature rise of windings in this study. A simplified 3D model was first established to calculate energy loss of core and velocity distribution in a plane above the lower yoke. Then two accurate 2D models were built up to figure out energy losses in the windings. With a combination of indirect and sequential coupling, energy losses of both windings and core were used as heat source, and velocities for both 2D models were applied as boundary condition for analysing fluid-thermal field. Final results of temperature rise were calculated with temperature rise of two 2D models. In the end, numerical results were compared with experimental data to prove the effectiveness of this method.

This paper proposed a prediction method to predict a 10-kV oil-immersed transformer hot spot temperature (HST). A set of feature temperature points on the transformer iron shell is proposed based on fluid-thermal field calculation. These feature points, as well as transformer load rate, are taken as the input parameters of a machine learning model established by support vector regression (SVR), thus to describe their relationships with the HST. This model is trained by nine samples selected by L 9 (3 4 ) orthogonal array and applied to predict the HST of 20 test samples. The training samples are all obtained by simulation, and the test samples have consisted of simulation and transformer temperature rise test results. With effective parameter optimization of the SVR model, the predicted results agree well with the experimental and simulation data, the mean absolute percentage error (MAPE) is 1.55%, and the maximum temperature difference is less than 3 • C. The results validated the validity and the generalization performance of the prediction model. INDEX TERMSHot spot temperature, oil-immersed transformer, support vector regression, multi-physical field analysis.