A novel intelligent strategy for improving measurement precision of FOG

This paper discusses neural network-based strategy for reducing the existin g errors of fiber-optic gyroscope (FOG), A series-single-layer neural netwo rk, which is composed of two single-layer networks in series, is presented for eliminating random noises. This network has simpler architecture, faste r learning speed, and better performance compared to conventional backpropa gation (BP) networks. Accordingly, after considering the characteristics of the power law noise in FOG, an advanced learning algorithm is proposed by using the increments of errors in energy function. Furthermore, a radial ba sis function (RBF) neural network-based method is also posed to evaluate an d compensate the temperature drift of FOG. The orthogonal least squares (OL S) algorithm is applied due to its simplicity, high accuracy, and fast lear ning speed. The simulation results show that the series-single-layer networ k (SSLN) with the advanced learning algorithm provides a fast and effective way for eliminating different random noises including stable and unstable noises existing in FOG, and the RBF network-based method offers a powerful and successful procedure for evaluating and compensating the temperature dr ift.