Intelligent control of servo system based on a novel neural network

This paper firstly proposes a novel neural network based on Newton´s forward interpolation - NFI-AMS, which is capable of implementing error-free approximations to multivariable polynomial functions of arbitrary order. The advantages it offers over conventional CMAC neural network are: high precision of learning, much smaller memory requirement without the data-collision problem, much less computational effort for training and faster convergence rates than that attainable with multi-layer BP neural networks. Secondly, a servo system intelligent control scheme based on NFI-AMS is designed, where NFI-AMS is employed to learn the inverse dynamic model of the servo system. A set of numerical simulations has been conducted, and simulation results have shown that the novel neural network based control strategy is feasible and efficient. The novel neural network has great potential in the application areas of real-time intelligent control for complex system.