The monitoring of the turning tool wear process using an artificial neural network. Part 1: The experimental set-up and experimental results

Abstract

The study of machine tool dynamics is performed here as ‘monitoring’, which involves the checking and improving of machine functioning. A computer processes signals collected from certain sensors. These data then lead to the monitoring decision, which is to associate the current state of operation with one of the classes from a set of known classes. For monitoring in turning, the classes (tool conditions) are shown. The paper by Du, Elbestawi, and Wu (1995) represents the main source of inspiration for this paper, the present contribution being the improvement of the classes and of the monitoring indices. It is shown that the strains produced by Fy can be neglected and only the main cutting force is measured by means of the tensometer system. To validate the recordings, couples of recordings having working parameters quite similar in value were selected; nonetheless, these couples belonged to different classes. It is observable that for the recordings whose cutting working conditions are similar, the average value of force Fz increases as the cutting depth and wear increase. The experimental set-up and experimental results are presented.