Neural solution to the target intercept problems in a gun fire control system

Time delay neural networks trained with the backpropagation algorithm are derived for the gun fire control system to correct the miss distance between a target and the projectiles from the gun. Its performance is compared to optimum linear filter based on minimum mean square error [R.E. Kalman, A new approach to linear filtering and prediction problems, J. Basic Eng. 82D (1960) 35–44.]. The structure of the proposed neural controller is described and performance results are shown.