The Interference Cancellation of Radio Fuze Based on Hopfield Neural Network

Radio fuze needs to detect exactly target signal from the echo signal being polluted by noise in real-time. Traditional interference cancellation system cannot meet the needs. The Hopfield neural network not only has the ability of nonlinear mapping, but also has the ability of self-learning. So it can be used to possess a desired result against the effect of uncertainties and incomplete information in signal processing. In this paper, the authors unify the performance function of adaptive noise cancellation and the energy function of Hopfield neural network by the precise deduction. The model of radio fuze interference cancellation system based on Hopfield neural network was designed. And the concerned simulation indicates Hopfield neural networks will improve radio fuze capability of obtaining useful information from interfered noise.