Wang Yu-Hsun, Lai Jing-Yu, Lo Yuan-Chieh, Shih Chih-Hsuan, Lin Pei-Chun
Department of Mechanical Engineering, National Taiwan University, Taipei 10617, Taiwan.
Mechanical and Mechatronics System Research Laboratories, Industrial Technology Research Institute, Hsinchu 31040, Taiwan.
Sensors (Basel). 2022 Jul 11;22(14):5192. doi: 10.3390/s22145192.
Nowadays, the grinding process is mostly automatic, yet post-grinding quality inspection is mostly carried out manually. Although the conventional inspection technique may have cumbersome setup and tuning processes, the data-driven model, with its vision-based dataset, provides an opportunity to automate the inspection process. In this study, a convolutional neural network technique with transfer learning is proposed for three kinds of inspections based on 750-1000 surface raw images of the ground workpieces in each task: classifying the grit number of the abrasive belt that grinds the workpiece, estimating the surface roughness of the ground workpiece, and classifying the degree of wear of the abrasive belts. The results show that a deep convolutional neural network can recognize the texture on the abrasive surface images and that the classification model can achieve an accuracy of 0.9 or higher. In addition, the external coaxial white light was the most suitable light source among the three tested light sources: the external coaxial white light, the high-angle ring light, and the external coaxial red light. Finally, the model that classifies the degree of wear of the abrasive belts can also be utilized as the abrasive belt life estimator.
如今，磨削过程大多是自动化的，但磨削后的质量检测大多是人工进行的。尽管传统检测技术可能具有繁琐的设置和调整过程，但基于视觉数据集的数据驱动模型为检测过程的自动化提供了机会。在本研究中，提出了一种基于迁移学习的卷积神经网络技术，用于基于每个任务中750 - 1000张磨削工件表面原始图像的三种检测：对磨削工件的砂带粒度进行分类、估计磨削工件的表面粗糙度以及对砂带的磨损程度进行分类。结果表明，深度卷积神经网络能够识别砂带表面图像上的纹理，并且分类模型能够达到0.9或更高的准确率。此外，在测试的三种光源（外部同轴白光、高角度环形光和外部同轴红光）中，外部同轴白光最适合作为光源。最后，对砂带磨损程度进行分类的模型也可以用作砂带寿命估计器。
