Agile Machining Error Compensation Method in Flat-End Milling Process Based on Ploynomial Neural Network Application

초록

This paper presents an agile machining error compensation method based on a PNN(Polynomial Neural Network) approach and inspection database of OMM(On-Machine-Measurement) system. To improve the accuracy of the OMM system, the compensation for the geometric errors of the machining center and the probing errors are taken into account. The machining error distributions are measured from a specimen workpiece. To efficiently analyze acquired the machining errors, we define two characterized machining error parameters Werr and Derr. Subsequently, it is possible to model these parameters by using a PNN approach, which allows determining the machining errors for considered cutting conditions. Consequently, the tool path can be corrected in order to effectively reduce the errors by using an iterative algorithm. Experimentation is carried out in order to validate the approaches proposed in this paper.