Power transformer DGA data processing and alarming tool for on-line monitors

A combined artificial neural network and expert system algorithm (ANNEPS) was developed over the years as both offline and on-line diagnosis tools for power transformers based on dissolved gas analysis (DGA). ANNEPS takes advantage of the inherent positive features of each method and offers a further refinement of present techniques. An updated automated diagnosis system, ANNEPS v5.0, is presented in this paper. The new system has updated the existing expert system according to the new IEEE standard and extends it with new interface, automated database interactions, and alarm notification functions. Though the earlier version was integrated and used by Arizona Public Service (APS) for Serveron online monitors, the ANNEPS v5.0 could be tailored for any type of on-line DGA monitor with a database interface. The combined neural network and expert system engine validates data, detects the faults, and recommends appropriate action. When the result indicates an ldquoabnormalrdquo condition, a notification of the diagnosis results is sent to transformer maintenance personnel through email. It also performs an automatic daily backup of both the input database and the output file.