Abstract ▼ AI-Helper

With the fast growing number of skyscrapers and large ultrahigh apartment complexes, the concerns on fire caused by electricity also grow. Among about 30,000 fires recorded annually, roughly one third of them are hewn to be caused by electricity. If one of such high and densely populated buildings o...

With the fast growing number of skyscrapers and large ultrahigh apartment complexes, the concerns on fire caused by electricity also grow. Among about 30,000 fires recorded annually, roughly one third of them are hewn to be caused by electricity. If one of such high and densely populated buildings or apartments catches a fire, the consequence can potentially be quite catastrophic. However, with the rapid development of the techniques in the fields of communications and computers, electric power distribution systems for such buildings and apartments have been largely digitalized in recent years. More detailed informations on the operating status are now available, which enables more sophisticated monitoring and early detection of potential fire caused by electricity. In this paper, we present an inference technique that can be used as one of the basic techniques in building intelligent distribution panel systems that can effectively monitor, prevent and detect the occurrence of fire caused by electricity. The technique can accommodate production rules in linguistic expressions on high abstraction levels. Fire finding strategies can be easily modified to provide more effective countermeasures. Simulation results show that inference capabilities and thus the capability of fire monitoring in power distribution panel systems can be significantly enhanced with our approach.