High Order Sliding Mode Control of Manipulator Based on Neural Network
Aiming at the chattering problems of unknown model parameters and external interference in the design of multi-joint manipulator control system,a high-order sliding mode control based on neural network was pro-posed.Based on the fast terminal sliding mode surface,saturation function was used to solve the singular problem,and radial basis neural network(RBFNN)was used to approximate the system parameters.An error estimator is added to compensate for estimation errors and external interference.At the same time,an adaptive finite time con-trol law with appropriate updating law is designed.The experimental results show that the control method is more feasible and advantageous in trajectory tracking of robot arm.
robot manipulatorradial basis function neural networkhigh order sliding modeterminal sliding mode control
万方数据
维普
