永磁球形电机的神经网络自适应控制算法

his paper introduces a 3-DOF spherical motor with three-dimensional orientation measurement ability and its control method. Considering the mechanical structure of the spherical motor, XYZ Euler angle is utilized for the construction of the kinematics model, and the Lagrange's equation is used for the establish of the dynamic model. Since the existing of the dynamic modeling error, friction and external disturbances in the system, the approximation of neural network system model method is applied to the control of the spherical motor. The simulation results show that the proposed method could significantly improve the motion performance compared with the tradition method such as the computed torque control method. The results in this paper could serve as a basis for the future research and experiment.