Suboptimal control of neutral systems

Abstract

The usual approach for obtaining the optimal control for a neutral system with quadratic cost consists of first deriving a set of necessary conditions for optimality and then using conventional iterative numerical methods to find a control satisfying those conditions. The burden of computation in this approach is enormous. The suboptimum iterative scheme proposed in this paper does not proceed along those lines. Instead, the neutral system is first converted into a non-linear time-delay system. The non-linear delay term is then treated like an extra perturbing input. A linear non-delay system is optimized at each stage and the resulting sequence of control functions converges rapidly to a suboptimal control for the original problem. One numerical example illustrates the technique.