Experimental Investigation on the Milling Performance of a 50 μm D-Shaped Micromilling Cutter with Different Materials

In micromilling, the performance and diameter of the milling cutter directly determine the service life of the milling cutter and the surface quality of the microgroove. Therefore, it is vital for high-precision milling to explore the milling performance of different materials and expand the application scope of micromilling cutter sizes. In this study, the milling performance of three kinds of material cutters—carbide, diamond coating and polycrystalline diamond (PCD)—was evaluated. A series of micromilling tests were carried out to determine the effects of cutter material type on cutter wear, surface quality and burr formation, particularly when a 50 µm micromilling cutter was used in the milling process. A D-shaped milling cutter with a diameter of 50 µm was manufactured on a self-developed high-precision modular machine tool by wire electrode electric discharge grinding (WEDG) technology. From theoretical and experimental perspectives, it is easy to master microgroove quality milled by different material cutters. The results show that the microgrooves processed with PCD cutters have fewer burrs, lower surface roughness values, and a smoother groove bottom morphology.

Bagging-gradient boosting decision tree based milling cutter wear status prediction modelling

Aiming to monitor wear condition of milling cutters in time and provide tool change decisions to ensure manufacturing safety and product quality, a tool wear monitoring model based on Bagging-Gradient Boosting Decision Tree (Bagging-GBDT) is proposed. In order to avoid incomplete tool state information contained in a single domain feature parameter, a multi-domain combination method is used to extract candidate characteristic parameter sets from time domain, frequency domain, and time–frequency domain. Then top 21 significant features are screened by eXtreme Gradient Boosting selection method. Synthetic Minority Oversampling Technique technology is integrated during feature selection to overly sample feature vectors, so that wear condition categories can be well balanced. Bagging idea is then introduced for parallel calculation of the gradient boosting decision tree and to improve its generalization ability. A Bagging-GBDT milling cutter wear condition prediction model is constructed and verified by public ball-end milling data set. Experiments show that random features and training samples selection can effectively improve prediction performance and generalization ability of prediction model. Our Bagging-GBDT model gains F1 score of 0.99350, which is 0.2% and 13.2% higher than the random forest algorithm and basic GBDT model, respectively.

Bit Design Methodology to Mitigate High-Frequency Torsional Oscillation

This paper reviews field data where high-frequency torsional oscillation (HFTO) was seen on previous bit runs and hypothesizes on features or design metrics that may have directly influenced this vibration. This paper investigates four metrics of bit design: Cutter wear, shear length:shear area ratio, choice of secondary cutter material, and effective backrake. Hypotheses are established linking these metrics to HFTO, and then data from field runs is shown to correlate the hypotheses. At this point, a bit was designed and manufactured to put the HFTO avoidance hypotheses into practice. Prior to laboratory testing, a theoretical model is used to identify resonant torsional frequencies. A series of laboratory experiments followed to test the hypotheses and demonstrated that there is correlation between all factors, but in one case is counter to the hypothesis. This information is of use when selecting or designing bits in environments where HFTO is known to occur. The findings may also assist in explaining performance that's below expectations where HFTO is not able to be explicitly measured.