Joint parameters identification of robot based on traveling wave approach and neural network

A new approach to identify joint parameters of the flexible joint robot under movement was proposed.Combining the traveling wave approach of structures and the rotated transform matrix of joint,wave equations of mechanism were established.Considering the conditions of the general force balance and displacement boundary of each joint,vibration torques of system in moving states were obtained.Furthermore,vibration equations were gained according to the vibration torques and vibration angles.Regarding as the weight of neural network,joint dynamic stiffness and damping in the vibration equations were identified by using the neural network.Parameters identification experiments of a 3-DOF manipulator were done and the experimental results show that the approach is feasible and effective.