RESUMEN
A novel method for tool wear estimation in milling using infrared (IR) laser vision and a deep-learning algorithm is proposed and demonstrated. The measurement device employs an IR line laser to irradiate the tool focal point at angles of -7.5°, 0.0°, and +7.5° to the vertical plane, and three cameras are placed at 45° intervals around the tool to collect the reflected IR light at different locations. For the processing materials and methods, a dry processing method was applied to a 100 mm × 100 mm × 40 mm SDK-11 workpiece through end milling and downward cutting using a TH308 insert. This device uses the diffused light reflected off the surface of a rotating tool roughened by flank wear, and a polarization filter is considered. As the measured tool wear images exhibit a low dynamic range of exposure, high dynamic range (HDR) images are obtained using an exposure fusion method. Finally, tool wear is estimated from the images using a multi-view convolutional neural network. As shown in the results of the estimated tool wear, a mean absolute error (MAE) of prediction error calculated was to be 9.5~35.21 µm. The proposed method can improve machining efficiency by reducing the downtime for tool wear measurement and by increasing tool life utilization.
RESUMEN
Powder bed fusion of metals using a laser beam system (PBF-LB/M) of highly complex and filigree parts made of tool steels is becoming more important for many industrial applications and scientific investigations. To achieve high density and sufficient chemical homogeneity, pre-alloyed gas-atomized spherical powder feedstock is used. For high-performance materials such as tool steels, the number of commercially available starting powders is limited due to the susceptibility to crack formation in carbon-bearing steels. Furthermore, scientific alloy development in combination with gas-atomization is a cost-intensive process which requires high experimental effort. To overcome these drawbacks, this investigation describes the adaption of a hot work tool steel for crack-free PBF-LB/M-fabrication without any preheating as well as an alternative alloying strategy which implies the individual admixing of low-cost aspherical elemental powders and ferroalloy particles with gas-atomized pure iron powder. It is shown that the PBF-LB/M-fabrication of this powder mixture is technically feasible, even though the partly irregular-shaped powder particles reduce the flowability and the laser reflectance compared to a gas-atomized reference powder. Moreover, some high-melting alloying ingredients of the admixed powder remain unmolten within the microstructure. To analyze the laser energy input in detail, the second part of the investigation focuses on the characterization of the individual laser light reflectance of the admixed alloy, the gas-atomized reference powder and the individual alloying elements and ferroalloys.