Neural network based tracking control of a flexible macro-micro manipulator system

Motion prediction and supervisory control of the macro–micro parallel manipulator system

This paper deals with the motion prediction and control of the macro–micro parallel manipulator system for a 500-m-aperture spherical radio telescope (FAST). Firstly, based on principles of parallel mechanism, a decoupled tracking and prediction algorithm to predict the position and orientation of the movable macro parallel manipulator is presented in this paper. Then, taken as the upper layer supervisory controller in the joint space of the micro parallel manipulator, the adaptive interaction PID controller utilizing the adaptive interaction algorithm to adjust the parameters of a canonical PID controller is discussed. In addition, the digital servo filters with feedforward are employed in the linear actuators as the lower layer controllers. Experimental results of a one-tenth scale FAST field model validate the effectiveness of the supervisory controller and the motion prediction algorithm.

MPID Control Tuning for a Flexible Manipulator Using a Neural Network

This paper studies the use of neural networks as a tuning tool for the gain in Modified Proportional-Integral-Derivative (MPID) control used to control a flexible manipulator. The vibration control gain in the MPID controller has been determined in an empirical way so far. It is a considerable time consuming process because the vibration control performance depends not only on the vibration control gain but also on the other parameters such as the payload, references and PD joint servo gains. Hence, the vibration control gain must be tuned considering the other parameters. In order to find optimal vibration control gain for the MPID controller, a neural network based approach is proposed in this paper. The proposed neural network finds an optimum vibration control gain that minimizes a criteria function. The criteria function is selected to represent the effect of the vibration of the end effector in addition to the speed of response. The scaled conjugate gradient algorithm is used as a learning algorithm for the neural network. Tuned gain response results are compared to results for other types of gains. The effectiveness of using the neural network appears in the reduction of the computational time and the ability to tune the gain with different loading condition.