A Novel Method of Transformer Fault Diagnosis Based on Extension Theory and Information Fusion in Wireless Sensor Networks

Abstract

Wireless Sensor Networks (WSN) produce a large amount of data that need to be processed, delivered and assessed according to the application objectives. A WSN may be designed to monitor the working state of power transformer timely, efficiently and remotely by virtue of the sensor nodes placed in transformer oil, gathering the real-time data of the dissolved multi-component gases in oil. The way these data are manipulated by the sensor nodes is a fundamental issue and information fusion arises to process data gathered by sensor nodes and benefits from their processing capability. This paper presents a novel method to diagnose transformer fault making comprehensive use of extension theory and multivariate optimization of fusion theory, which can effectively and intelligently diagnose transformer fault types, providing more convenience for the workers on remote monitoring and improving the intelligent degree of the fault diagnosis.