Pre - lter Design for High Speed ContouringMachinesBill

Machines Bill C.H. Chang, Roy C. Ko and Saman K. Halgamuge Mechatronics Research Group Dept. of Mechanical and Manufacturing Engineering The University of Melbourne, Australia bcch,royko,[email protected] Abstract High-speed and high-precision tracking control is required for future contouring machine tools. It was known that by preltering the command trajectory in an appropriate way, the contouring error can be e ectively reduced. This paper presents the result of a hybrid approach applied to prelter design, which incorporates a MLP neural network to enhance the performance of recently proposed Adaptive Calibrating Controller. Due to the presence of non-linearities such as friction and signal quantization, the proposed method further reduces contouring error by taking advantages of the non-linear and learning nature of the Neural Network. Simulation results on the dynamic model of a commercial laser pro ling machine is demonstrated.