Neural Network of Fault Distinguishing Based on Halve Amplification
Gui Cun-bing · Electric Power Science and Engineering · 2006
An artificial neural network for fault distinguishing by sampling halve is presented,and the pretreatment data are amplified.The essential of this academic is similar with the principium of magnifying glass.It can subtly distinguish two faults with very little difference.It can be indicated by the experiment result that this neural network acts much more ideally comparing with the other networks using common sampling and pretreatment method.