Fast power transformer fault classification methods based on protection signals

A fast estimation of the operating status of the power transformer is essential for power system monitoring. Three methods are presented, which enable the classification of faults affecting power transformer protection, based on its signals. The first method is based on a modelled relationship between faults and protection action, which is formulated as a matrix function. A pseudoinversion is used to obtain the transformer diagnosis indices. The second method uses the norm in the Banach space as a measure for the most probable event. The third method exploits the Bayes probability calculation based on statistical data on faults and protection operation. Results of all these methods show that they yield a fast and successful identification of power transformer faults.