Machining error compensation using neural network and on-machine-measurement database

This paper presents a methodology of machined surface error compensation by using ANN(Artificial Neural Network) model trained by inspection database of OMM(On-Machine-Measurement) system First, we make compensation for the geometric errors of the machining center by using a closed-loop configuration for the improvement of machining and inspection accuracy. The probing errors are also taken into account. Then, we manufacture a specimen workpiece and then inspect machined surface error distribution. In order to efficiently analyze the surface errors, we define two characteristic surface error parameters W-err and D-err. Subsequently, it is possible to model these parameters by using ANN model. This ANN model allows us to determine the surface errors in the domain of considered cutting conditions. Based on this ANN model, we try to correct the tool path in order to effectively reduce the errors by using an iterative algorithm. An iterative algorithm allows us to integrate changes of the cutting conditions according to the corrected tool path. Experimentation is carried out in order to validate the approaches proposed in this paper.