Adaptive leakage suppression based on recurrent wavelet neural network

A novel adaptive leakage suppression method based on recurrent wavelet neural network (RWNN) in phase-coded modulation continuous wave (PCM-CW) radar is proposed in this paper. In the proposed model, the orthogonalized received signals do cross multiplication with the orthogonal local reference signals. Based on the characteristics of trigonometric function, the differencing output of the two channels effectively suppresses the leakage from transmitter while retains the interested target echoes. Considering rigorous requirements in military, blind channel equalization based on RWNN is applied to compensate the inequality in the two channels in phase property and amplitude gain to achieve suppression ratio higher than MO. The small size and high efficiency of RWNN make it is well suited to be utilized in the real time leakage suppression. The results of theoretical analysis and simulation on the detecting performance of the radar both show the validity and practicability of the proposed method.