Improving Machining Precision in Turning Process Using Artificial Neural Networks

Machining inaccuracies are caused by imprecision of the machine itself and interaction between tool and workpiece. This paper proposes a unified approach to attack this problem. A neural network is used to learn the inverse mapping between the commanded and machined (actual) part dimensions generated by a CNC turning process. After training, the neural network is able to generate corrective CNC codes for the desired part dimensions. We compared the errors in part dimensions due to compensated and uncompensated codes, showing the feasibility of using neural nets for improving machining accuracy. Our approach is simple but effective.