A neural network sidelobe suppression filter for a pulse-compression radar with powers-of-two weights

Abstract

A new compression filter for binary coded wideband digital signals with sidelobe reduction capabilities using a feedforward time-delay neural network is considered. This filter uses powers-of-two synaptic weights and the backpropagation learning algorithm. Using digital hardware implementation of such a filter for pulse compression is easier owing to elimination of multipliers. The simulation results showed that the time sidelobes of the output signal can be reduced up to about 60 dB. The quantization of the filter weights causes additional losses of about 6-14 dB depending on the input signal to noise ratio.