Abnormality Diagnosis O F Gis Using Adaptive Resonance Theory

?‘lie paper presents an artificial neural network(ANN) approach using ARTS(Adaptive Resonance Theory 2) to a diagnostic system for a Gas Insulated Switchgear(G1S). To begin with, we will show the background of abnormality diagnosis of GISs from the view point of predictive maintenance of them. Then, we will discuss the necessity of ART-t,ype ANNs, as an unsupervised learning method, in which neuron(s) are self-organized and self-created when detecting unexpected signals even if un-trained by ANNs through a sensor. Finally, we will present our brief simula tion results and their evaluation.