Adaptive Neural Backstepping PID Global Sliding Mode Fuzzy Control of MEMS Gyroscope

An adaptive global sliding mode fuzzy control using radial basis function (RBF) neural network (NN) based on backstepping technique is presented for a micro electromechanical systems (MEMS) gyroscope. The proportion integral differential (PID) sliding surface has the capacity of restraining the steady-state error. Meanwhile, we take advantage of the global sliding mode manifold to overcome shortcomings of the conventional sliding mode controller, obtaining the fast response and overall robustness. Furthermore, faced with the unknown dynamic characteristic of the MEMS system, an RBF neural approximator is employed to estimate it. Besides, a fuzzy controller is put forward to suppress the chattering phenomenon caused by the sliding mode controller. The globally asymptotic stability of the closed loop system is guaranteed by the selected adaptive laws and Lyapunov theory. The simulation results demonstrate satisfactory effects of the proposed advanced controller. The comparison studies verify the better properties of the suggested control approach.