A METHOD OF USING NEURAL NETWORKS AND INVERSE KINEMATICS FOR MACHINE-TOOLS ERROR ESTIMATION AND CORRECTION

A method using artificial neural networks and inverse kinematics for m achine tool error correction is presented. A generalized error model i s derived, by using rigid body kinematics, to describe the error motio n between the cutting tool and workpiece at discrete temperature condi tions. Neural network models are then built to track the time-varying machine tool errors at various thermal conditions. The output Of the n eural network models can. be used to periodically modify, using invers e kinematics technique, the error model's coefficients as the cutting processes proceeded. Thus, the time-varying positioning errors at othe r points within the designated workspace can be estimated. Experimenta l results show that the time-varying machine tool errors can be estima ted and corrected with desired accuracy. The estimated errors resulted from the proposed methodology could be used to adjust the depth of cu t on the finish pass, or correct the probing data for process-intermit tent inspection to improve the accuracy of workpieces.