Super-twisting Sliding Mode Control Based on RBF Neural Network

The problems of model uncertainty and complex interference exist in the near space vehicle. The control system needs to anti-interference and adapt to the changes of system parameters while ensuring the rapidity. Therefore, a super-twisting sliding mode control method based on RBF neural network is proposed. RBF neural network can estimate the uncertainties in the system model, design the adaptive law of single parameter through the minimum parameter learning method, which ensures the demand of real-time control. The super-twisting sliding mode control with strong robustness can effectively suppress disturbance and estimation error of the neural network, and can weaken the chattering phenomenon. Lyapunov stability theory proves the stability of the closed-loop system. The effectiveness of the proposed control scheme is verified by digital simulation.