Two approaches to power transformer fault classification based on protection signals

Abstract

A large amount of data is generated when a fault triggers transformer protection. However, no precise information is obtained regarding where and what type of fault has occurred. Consequently, the operator must wait, sometimes for days, before he can switch on the transformer, which may not have been affected by the fault at all. As a result, the network suffers reduced security and transmission capacity. This paper presents two methods that enable the identification of faults affecting power transformer protection based on its signals. These methods should assist the operator in deciding whether the transformer should be left off or switched back into the system immediately after the event. The statistical data on faults and protection operation enable fault classification based on the Bayes' theorem. The probability could be used as a measure of the event occurrence likelihood regarding a set of alternative events. A second method is further proposed, which uses the norm in the Banach space as a measure for the most probable event. Tests of both methods showed that they yield a fast and successful identification of power transformer faults.