The use of a multi-agent paradigm in electrical plant condition monitoring

Electrical utilities need to operate their equipment closer to their design limits and require to extend their operating life through automatic condition monitoring systems. This paper introduces a multi agent paradigm for data interpretation in electrical plant monitoring. Data interpretation is of significant importance to infer the state of the equipment by converting the condition monitoring data into appropriate information. The vast amount of data and the complex processes behind on-line fault detection indicate the need for an automated solution. The classification of partial discharge signatures from gas insulated substations, as a result of applying different artificial intelligence techniques within a multi agent system, is described in this paper. A multi agent system that views the problem as an interaction of simple independent software entities, for effective use of the available data, is presented. The overall solution is derived from the combination of solutions provided by the components of the multi-agent system. This multi-agent system can employ various intelligent system techniques and has been implemented using the ZEUS Agent Building Toolkit