A neural fuzzy network approach to Radar pulse compression

To make good range resolution and accuracy compatible with a high detection capability while maintaining the low average transmitted power, pulse compression processing giving low-range sidelobes is necessary. The traditional algorithms such as the direct autocorrelation filter (ACF), least squares (LS) inverse filter, and linear programming (LP) filter based on three-element Barker code (B13 code) have been developed. Recently, the neural network algorithms were issued. However, the traditional algorithms cannot achieve the requirements of high signal-to-sidelobe ratio and low integrated sidelobe level (ISL), and the normal neural networks such as the backpropagation (BP) network usually produce the extra problems of low convergence speed and are sensitive to the Doppler frequency shift. To overcome these defects, a new approach using a neural fuzzy network to deal with pulse compression in a radar system is presented. Two different Barker codes are carried out by a six-layer self-constructing neural fuzzy network (SONFIN). Simulation results show that this neural fuzzy network pulse compression (NFNPC) algorithm has significant advantages in noise rejection performance, range resolution ability, and Doppler tolerance, which are superior to the traditional and BP algorithms.