Synchronous motion of gantry robot using neural network compensator

In this paper, a proportional-integral-derivative neural network (PIDNN) compensator is proposed for the synchronous motion control of a gantry robot. Firstly, the parameters of dual servo systems are identified by experiment and the cascade control strategy, based on traditional PID control, is further applied to reduce the single axis position tracking error. However, the synchronous error between dual servo systems is inevitable due to their inequality in characteristics, the plant uncertainties and environmental disturbance. The PIDNN compensator and an online learning algorithm with two inputs corresponding to synchronous position and velocity errors between dual drive servo systems and generate the compensated force; the compensated force is then fed back to the controller of each axis to compensate the asynchronous motion. The online learning algorithm adjusts the connected weighting of the PIDNN network by using a supervised gradient descent method, such that the defined error function can be minimized. Therefore, the tracking and synchronous motion errors can be simultaneously reduced by the proposed control scheme. Finally, two kinds of position commands with high and low speed are designed for the experiments, and the experimental results show that the proposed PIDNN compensator is feasible to improve the synchronous error of gantry robot.