Abstract
The article deals with a designed neuronet model of the control unit for an audio frequency track circuit which makes it possible to increase its noise stability by using the fine tuning of a guard time during which track receivers do not receive disturbances. It can adapt long signal delays to the track circuit operating conditions by using neuronets integrated in the model, the neurons adjusting their synaptic weights. The division of the neuronet model into five functional components which depend on the frequency of the carrying signal allowed minimizing the root-mean-square error for a learning sample, and also reducing the number of neurons in a buried layer of the neuronet.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
