Predicting Machining Errors in Turning Using Hybrid Learning

A recent model-based approach for predicting the compensation required on the next part to be turned on a CNC machine solely on the basis of three independent measurements conducted at selected locations on a limited set of previously machined parts under a similar cutting set-up is reviewed. A new method of achieving the same objective through the use of the learning capability of an adaptive neuro-fuzzy network is developed and tested against experimental data for cylindrical turning. This method requires only one on-machine measurement per sample. It is conducted by a novel contact sensor that probes with the tool and facilitates automation by providing proximity information as the tool approaches the workpiece.