A Nonlinear Neural Network-assisted Variable Structure Controller for Flexible Space Structure

摘要

The development of a neural network-based scheme for adaptively implementing a variable structure controller to drive a flexible space structure is described in this paper. An efficient integration of the operational strong features of a trained neural network and a variable structure controller is made in the development of the overall control scheme. The nonlinear part and the imprecision part caused by mode truncation are taken as unknown model. The recurrent neural networks are adopted for identifying the uncertainty of the system based on nominal model on real time. As a result, it avoids the intensively chattering on sliding surface caused by conservative design for uncertainty. Finally, the simulations provide a good result.