Detection of Transformer Internal Faults by Using Dynamic Principle Component Analysis

Abstract

In this paper; a method is proposed to detect parameter faults in nonlinear systems. The proposed method is called a dynamic principal component analysis approach. In this approach, the detection is based on the manipulation of input and output data without assuming any model for the system. The approach is based on the principal component analysis of the system input-output correlation data on a horizon going a specified number of steps backward. This method is applied to a custom-built transformer in order to detect internal short circuit faults. It is observed through various application examples that the proposed method leads to satisfactory results in the sense of detecting parameter faults in non-linear dynamical systems.