EXPERIMENTAL COMPARISON OF SENSORS FOR TOOL-WEAR MONITORING ON MILLING

This paper compares spindle motor current, vibration and acoustic emission sensors for tool-wear monitoring; the methodology and the results are also given. Comparison of the data is not restricted to raw ones, but it is applied to a broad set of derived features by means of previously developed procedures. The analysis of variance is carried out for the best found features. Corresponding models are built to explain the measurements variability, and significative differences are tested. Some quality indexes are specially introduced for the assessment. Finally, sensors are classified according to its sensitivity to the tool wear. From the point of view of the application the observed dependence of measurements on the used tool and on the cutting position, and the discovery of interactions between this last factor and tool wear, are very remarkable facts.