<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Andrew Kenyon</style></author><author><style face="normal" font="default" size="100%">Victoria Catterson</style></author><author><style face="normal" font="default" size="100%">Stephen MacArthur</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Design of an Intelligent Diagnostic Architecture to Support the Condition Monitoring of Power Generation Assets.</style></title><secondary-title><style face="normal" font="default" size="100%">Proceedings of the 44th International Universities Power Engineering Conference</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Diagnostics and Measurements in Power Systems</style></keyword><keyword><style  face="normal" font="default" size="100%">Monitoring and communications</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2009</style></year><pub-dates><date><style  face="normal" font="default" size="100%">September</style></date></pub-dates></dates><number><style face="normal" font="default" size="100%"></style></number><edition><style face="normal" font="default" size="100%"></style></edition><publisher><style face="normal" font="default" size="100%"></style></publisher><pub-location><style face="normal" font="default" size="100%">University of Strathclyde</style></pub-location><volume><style face="normal" font="default" size="100%"></style></volume><pages><style face="normal" font="default" size="100%"></style></pages><isbn><style face="normal" font="default" size="100%"></style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">Detailed, timely and accurate condition monitoring and diagnostic capability for generation assets is important for safely operating a power plant. Often, a software system will be developed to perform this function. Each generating unit will include several assets, with several different types of sensors recording real-time data. In addition, it is often desirable to have access to historic data. To provide comprehensive support to asset managers and condition monitoring engineers a successful software system should utilise this heterogeneous data to form a meaningful overview of the plant condition, while diagnosing any perceived faults. If the software must handle data from several power plants over a large geographic area, the volume of data may become too great for manual inspection. This requires a greater emphasis on the extraction and presentation of important information, to reduce the unnecessary data that is presented to busy engineers. The large area the software must operate over also introduces additional requirements common to all distributed software. A multi-agent system (MAS) is proposed to allow the condition monitoring and fault diagnosis of several power plants for a major UK utility. A MAS is a collection of intelligent agents that work together to achieve a common goal. An intelligent agent must display three key characteristics: reactivity, pro-activeness, and social ability. An agent is considered reactive when it can perceive and react to changes in the surrounding environment. Pro-activeness is achieved by agents being goal orientated, and actively seeking out the means to achieve those goals. Social ability refers to an agents ability to co-operate with other agents to achieve common goals. These three properties allow a condition monitoring system to intelligently integrate multiple data sources and interpretation techniques towards the common goal of plant health analysis. In addition, the agents run on a standardised platform that allows deployment over a network, providing a means for distributed deployment. The system will automate data interpretation and the extraction of relevant information, with an emphasis on the efficient presentation of this information to a small number of specialists. While systems have been developed that analyse a specific variable, this system will use multiple diverse parameters to diagnose faults. Several artificial intelligence approaches are considered for data interpretation, including knowledge based systems, data mining and online learning. The system will provide diagnostics and decision support for the specialists without the need for manual detailed analysis. This paper will focus on the development of the User Requirements Specification and Functional Specification of the architecture. The specifications will be validated by experts in the fields of asset management and condition monitoring from the utility. The paper will conclude with an outline of the proposed architecture, including appropriate data interpretation algorithms and a definition of the interface and support mechanisms for the engineers.</style></abstract><issue><style face="normal" font="default" size="100%"></style></issue><work-type><style face="normal" font="default" size="100%"></style></work-type><accession-num><style face="normal" font="default" size="100%"></style></accession-num><call-num><style face="normal" font="default" size="100%"></style></call-num><notes><style face="normal" font="default" size="100%"></style></notes><custom1><style face="normal" font="default" size="100%"></style></custom1><custom2><style face="normal" font="default" size="100%"></style></custom2><custom3><style face="normal" font="default" size="100%"></style></custom3><custom4><style face="normal" font="default" size="100%"></style></custom4><custom5><style face="normal" font="default" size="100%"></style></custom5><custom6><style face="normal" font="default" size="100%"></style></custom6><custom7><style face="normal" font="default" size="100%"></style></custom7><research-notes><style face="normal" font="default" size="100%"></style></research-notes><num-vols><style face="normal" font="default" size="100%"></style></num-vols><orig-pub><style face="normal" font="default" size="100%"></style></orig-pub><reprint-edition><style face="normal" font="default" size="100%"></style></reprint-edition><section><style face="normal" font="default" size="100%"></style></section><auth-address><style face="normal" font="default" size="100%"></style></auth-address><remote-database-name><style face="normal" font="default" size="100%"></style></remote-database-name><remote-database-provider><style face="normal" font="default" size="100%"></style></remote-database-provider><label><style face="normal" font="default" size="100%"></style></label><access-date><style face="normal" font="default" size="100%"></style></access-date></record></records></xml>
