Finite time multilayer neural network command filter backstepping controller design for large scale uncertain nonlinear systems

Abstract

This study presents a novel dynamical multilayer neural network finite time command filter backstepping control scheme. This method realizes the finite time robust tracking control of uncertain nonlinear system. The uncertainty in system varies in large scale around system states. Its boundary is unknown and unavailable before design. The multilayer neural network (MNN) approximater is redesigned into the backstepping controller instead of the common radial basis function (RBF) neural network (NN) and Fuzzy System (FS) to realize the accuracy approximation of the large scale uncertain structure. The introduction of the MNN approximater overcomes the drawback of local identification constraint of RBF NN and Fuzzy System without the structure knowledge and boundary of uncertainty before design. Otherwise, owing to the MNN structure is more complex than common three layer RBF NN, the approximation costs more time to dynamically tune weight parameters online. In order to make up the time consistent between the MNN approximation and the backstepping process, the finite time (FT) command filter (CF) backstepping control strategy balancing the two distinct procedures guarantees the MNN identification of larger scale uncertainty and backstepping control process consistently convergence into a smaller area in uniform finite time interval. Finally, through a practical example, the effectiveness and advantages of are illustrated by comparison between this mechanism and traditional RBF NN method.