Prediction Approach for the Oil Temperature of Transformers by a Grey Method with Grouping Strategy

Converter transformer is an important part of UHVDC transmission system, which undertakes the work of energy transfer and energy conversion. In addition, the prediction of the oil temperature is significant for the performance evaluation of the transformer body. In this paper, the mechanism of the prediction approach is introduced particularly, and the prediction of the oil temperature for a converter transformer is presented as an example to verify the effectiveness of the proposed grey method with grouping strategy. From the results, it can be clearly seen that the prediction error declines obviously with increasing of the grouping number. To details, prediction error declines about three-fifths from the grouping number 1 to number 2. Particularly, the prediction error declines slowly after the grouping number is 9 and the prediction error is basically maintained at about 10%. This paper provides a technical support for other kind predictions of oil temperature.