Department of Smart Health Science and Technology, Kangwon National University, 1 Kangwondaehak-gil, Chuncheon 24341, Republic of Korea.
Electric Power Train R&D Department, Korea Automotive Technology Institute, 303 Pungse-ro, Pungse-myeon, Dongnam-gu, Cheonan 31214, Republic of Korea.
Sensors (Basel). 2023 Jan 20;23(3):1208. doi: 10.3390/s23031208.
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.
提出并验证了一种利用红外（IR）激光视觉和深度学习算法进行铣削刀具磨损估计的新方法。该测量装置采用IR 线激光器以与垂直面成-7.5°、0.0°和+7.5°的角度照射刀具焦点，并在刀具周围以 45°的间隔放置三个相机，以在不同位置收集反射的 IR 光。对于加工材料和方法，通过端铣和向下切削，在 TH308 刀片的作用下，对 100mm×100mm×40mm 的 SDK-11 工件采用干式加工方法。该装置利用由后刀面磨损引起的表面粗糙度旋转刀具反射的漫反射光，并考虑使用偏光滤光片。由于测量的刀具磨损图像的曝光动态范围较低，因此使用曝光融合方法获得高动态范围（HDR）图像。最后，使用多视图卷积神经网络从图像中估计刀具磨损。从估计的刀具磨损结果来看，计算得到的预测误差的平均绝对误差（MAE）为 9.5~35.21μm。该方法通过减少刀具磨损测量的停机时间和提高刀具寿命利用率，提高了加工效率。
