Dynamic Fractional Order Sliding Mode Control Method of Micro Gyroscope Using Double Feedback Fuzzy Neural Network
Juntao Fei, Fang Chen
Abstract
In this paper, a dynamic fractional order sliding mode control method based on a double feedback fuzzy neural network controller is proposed to deal with the unknown parameters and upper bound of uncertainty. Firstly, the switching function of the dynamic fractional order sliding mode control is designed, which not only fixes switching function of the ordinary sliding mode control, but also increases the fractional order, so that the switching function has a higher degree of freedom. In addition, the expert experience of fuzzy logic and the self-learning ability of neural network are used to improve the control accuracy and estimate the upper bound of uncertainty. Meanwhile, by using Lyapunov stability theory, the adaptive laws of unknown parameters in the system are derived to realize online adjustment, which increases the robustness of the system. Finally, the simulation results show that the proposed control method is more effective than the ordinary adaptive sliding mode control method in terms of convergence speed, parameter fitting effect, output signal tracking speed and tracking error.