The invention discloses a
radar main lobe interference suppression method based on a neural network and belongs to the technical field of
radar. The method comprises a step of determining a steering vector of a received
signal according to a geometric model of a
radar array element arrangement after a
main lobe interference direction is known and constructing a received
signal model of the targetsignal and an interference
signal, a step of constructing an ideal low
side lobe null steering directional diagram according to the known
main lobe interference direction, a step of creating a training sample through an input signal, taking the ideal low
side lobe null steering directional diagram as an expected signal sample, establishing a suitable neural
network model on the above basis and training, and a step of applying the trained neural network and verifying the input signal to obtain an output directional diagram. According to the method, the neural network is employed to suppress themain lobe interference, compared with the conventional method, the method of the invention has the advantages that
null steering is formed at an interference position, the shape preserving of a mainlobe directional diagram and a low
side lobe level are achieved, an ideal directional diagram is obtained, the accuracy of the angle measurement is improved, the
energy loss of a
target signal is reduced, the stability of a
system is improved, the requirements of angle measurement can be satisfied well, and therefore, the
system performance is improved.