Adaptive Neural Network Sliding Mode Control based on Particle Swarm Optimization for Rotary Steering Drilling Stabilized Platform

Abstract

This study focuses on the robust control of stabilized platform of rotary steering drilling system. Firstly, the uncertain and nonlinear mathematical model of stabilized platform is given by considering the outside interference, drilling technology and geometrical parameter perturbation of the borehole on stabilized platform under work condition. Then, an adaptive neural network sliding mode control strategy is introduced,, which uses sliding mode control to guarantee system robustness, makes the uncertain upper bound adjust adaptively with RBF neural network to nonlinear approximate the upper bound of overall uncertainty, reduces chattering by quasi-sliding mode control method. Finally, particle swarm optimization algorithm is applied to search the optimal controller parameters, including adaptive parameter of neural network weight, boundary layer thickness and switching function coefficient. Simulation results demonstrate that the control strategy proposed can make stabilized platform get optimal control performance and robustness.