Integrated machining error compensation method using OMM data and modified PNN algorithm

This paper presents an integrated machining error compensation method based on polynomial neural network (PNN) approach and inspection database of on-machine-measurement (OMM) system. To improve the accuracy of the OMM system, geometric errors of the CNC machining center and probing errors are compensated. Machining error distributions of a specimen workpiece are measured to obtain error compensation parameters. To efficiently analyze the machining errors, two machining error parameters, Werr and Derr, are defined. Subsequently, these parameters can be modeled using the PNN approach, which is used to determine machining errors for the considered cutting conditions. Consequently, by using an iterative algorithm, tool path can be corrected to effectively reduce machining errors in the end-milling process. Required programs are developed using Ch language, and modified termination method are applied to reduce computation times. Experiments are carried out to validate the approaches proposed in this paper. The proposed integrated machining error compensation method can be effectively implemented in a real machining situation, producing much fewer errors.