Abductive network model-based diagnosis system for power transformer incipient fault detection

Abstract

An abductive network model (ANM)-based diagnosis system for power transformers fault detection is presented that enhances the diagnostic accuracy of the power transformer incipient fault. The ANM formulates the diagnosis problem into a hierarchical architecture with several layers of function nodes of simple low-order polynomials. The ANM links the complicated and numerical knowledge relationships of diverse dissolved gas contents in the transformer oil with their corresponding fault types. The proposed ANM has been tested on the Taipower company diagnostic records and compared with the previous fuzzy diagnosis system, artificial neural networks as well as with the conventional method. The test results confirm that the ANM possesses far superior diagnosis accuracy and requires less effort to develop.