Diagnosis of power transformers using modified self organizing map

Substation facilities have become large and complex in the electric power systems. Development of condition monitoring and diagnosis techniques has been very important to improve the security of substation transformers. This paper presents a method to analyze the cause, the degree, and process of aging of power transformers by self organizing map (SOM). Dissolved gas data were non-linearly transformed by the sigmoid function in SOM that works close to the process of how humans make a decision. The potential of failure and the degree of aging of normal transformers are identified by using the proposed quantitative criterion. Furthermore, the transformer aging is monitored by the proposed criterion for a set of transformers. To demonstrate the validity of the proposed method, a case study is performed and its results are presented.