Confidence Interval Estimation for Cutting Tool Wear Prediction in Turning Using Bootstrap-Based Artificial Neural Networks.

The degradation of the cutting tool and its optimal replacement is a major problem in machining given the variability in this degradation even under constant cutting conditions. Therefore, monitoring the degradation of cutting tools is an important part of the process in order to replace the tool at the optimal time and thus reduce operating costs. In this paper, a cutting tool degradation monitoring technique is proposed using bootstrap-based artificial neural networks. Different indicators from the turning operation are used as input to the approach: the RMS value of the cutting force and torque, the machining duration, and the total machined length. They are used by the approach to estimate the size of the flank wear (VB). Different neural networks are tested but the best results are achieved with an architecture containing two hidden layers: the first one containing six neurons with a Tanh activation function and the second one containing six neurons with an ReLu activation function. The novelty of the approach makes it possible, by using the bootstrap approach, to determine a confidence interval around the prediction. The results show that the networks are able to accurately track the degradation and detect the end of life of the cutting tools in a timely manner, but also that the confidence interval allows an estimate of the possible variation of the prediction to be made, thus helping in the decision for optimal tool replacement policies.

Sensitivity Analysis of Various Geometries of PCD and Cemented Tungsten Carbide Cutting Tools during the Milling of GFRP Composite.

Although much research has been carried out in the field of the milling of GFRP (Glass Fibre Reinforced Polymer) composites, the complexity of the process is such that it is still not mastered in many industrial cases. The current work is aimed at studying the influence of three different geometries of PCD (PolyCrystalline Diamond) and cemented tungsten carbide cutting tools during the up-milling of GFRP composites at fixed cutting conditions (vc = 502 m/min and vf = 420 mm/min). Delamination, cutting forces and tool wear are compared at the fresh and worn states, and the correlation between the lifespan and the cost of the cutting tool is analysed. The main wearing phase of the tools was performed under the conditions of production in the facilities of a company (Sobelcomp, Loncin, Belgium). The results indicate that the PCD tool with the straight edge, inclined peripheral tooth shape produces the smallest total cutting force and less delamination (shortest and lowest number of delaminated fibres) at both fresh and worn states. Moreover, the grinding ability of PCD makes the cutting tool cost per part lower than for cemented carbide. The PCD tool is therefore the best option to mill GFRP parts.