Prediction of iron losses of wound core distribution transformers based onartificial neural networks

This paper presents an artificial neural network (ANN) approach to predicti ng and classifying distribution transformer specific iron losses, i.e., los ses per weight unit. The ANN is trained to learn the relationship of severa l parameters affecting iron losses. For this reason, the ANN learning and t esting sets are formed using actual industrial measurements, obtained from previous completed transformer constructions. Data comprise grain oriented steel electrical characteristics, cores constructional parameters, quality control measurements of cores production line and transformers assembly lin e measurements. It is shown that an average absolute error of 2.32% has bee n achieved in the prediction of individual core specific iron losses and an error of 2.2% in case of transformer specific losses. This is compared wit h average errors of 5.7% and 4.0% in prediction of specific iron losses of individual core and transformer, respectively, obtained by the current prac tice applying the typical loss curve to the same data. (C) 1998 Elsevier Sc ience B.V. All rights reserved.