Self-Interference Cancellation in Radar Jammer Based on Deep Neural Networks

In the radar electronic warfare, the problem in the transmitter-receiver isolation of the radar jammer will affect the detection and reception of the jammer itself seriously. Adaptive algorithms are often used to solve the problem. The weights of the filter in the algorithms are updated according to the minimum mean square error when it works. This method cannot effectively eliminate the nonlinear components of the self-interference signal in some special cases. In order to solve this problem, a method of self - interference cancellation based on deep neural networks is proposed in this paper. The networks simulate the behavior model of the nonlinear amplifier through training. And then it reconstructs the nonlinear components of the self-interference signal, so that this part can be effectively eliminated.