Periodical Update of Loss of Offsite Power Frequency

In Nuclear Power Reactors, a fault can occur in a few milliseconds, so locating the fault might be of the utmost importance due to safety, and other reasons. . When a plant malfunction occurs, a great data influx is occurred, so the cause of the malfunction cannot be easily or promptly identified. A typical NPP may have around 2,000 alarms in the Main Control Room (MCR) in addition to the display of analogue data. During plant transients, hundreds of alarms may be activated in a short time. Accordingly, there is an increasing demand for automated systems to diagnose such failures. The objective of this research is serving in the designing, constructing, operating, testing, and evaluating a prototype integrated monitoring and diagnostic system for a NPP. We proposed a new support system based on unsupervised neural network, called Adaptive Resonance network (ART), that assists alarming and diagnosis systems. ART is a neural network, which is an important family of competitive neural learning model. Its memory mode is very similar to that of biological one, and memory capacity can increase while the learning patterns increase. It can perform real-time online learning, and can work under non stationary world. A software simulation implementation of ART had been obtained to diagnosis a (NPPs) accidents patterns, to avoid the risk of occurrence of a nuclear accident. The new proposed algorithm is a classifier based on ART, achieved preferable results than several other classifier or neural algorithms. (author)