Search

Suction plays an important role in the disordered manufacturing scenarios because of its single-point contact and reliability. The prediction of suction region is the primary problem needs to be solved in these applications. However, the traditional non-deep learning methods is insufficient for its poor generalization performance, and the deep learning method is inconvenient as it requires manually labeled datasets for training. Therefore, a suction region prediction method from knowledge to learning is proposed to overcome these challenges, which adopts a suction reliability matrix based on the depth image to label the disordered manufacturing datasets without manual labeling, where the effects of suction cup model, part centroid and depth are all considered. The disordered manufacturing dataset annotated is used to train the suction region prediction model based on fully convolutional neural network, which can be customized according to the model of suction cup and parts. Experiments and analysis show that the proposed method has the advantages of short detection time, high robustness and strong generalization ability. [ABSTRACT FROM AUTHOR]

• A vision-based fusion method is proposed for measurement of workpiece dimensions. • FCN deep leaning model is used to detect interference regions of workpiece images. • Interference regions are processed by the directional texture repair method. • A method based on HED deep leaning model for rough edge detection is proposed. • The measuring accuracy of the proposed method can reach 0.02 mm. Image preprocessing and edge detection are the two most critical steps when applying machine vision to measure workpiece dimension in industrial field. The surface of the workpiece is usually covered with interference regions, which makes edge detection difficult. Aiming at the problem, the Full Convolutional Network (FCN) model is used to detect interference regions of workpiece images, and then interference regions are processed by the directional texture repair method. To avoid the influence of workpiece surface texture after rough machining, a method based on Holistically-nested Edge Detection (HED) model for rough edge detection of workpiece images is proposed. The edge is obtained by HED, and then it is post-processed based on the non-maximum value suppression and double threshold segmentation methods in the Canny operator to obtain a refined edge image. In order to further improve the accuracy of the dimension measurement, sub-pixel level edge detection accuracy is achieved by cubic spline interpolation. Finally, the method is validated by a shaft workpiece. The measuring accuracy of the outer diameter of the workpiece can reach 0.02 mm, which can effectively meet the requirements of fast semi-finishing inspection. This research provides a common workpiece dimension measurement method in industrial field and methodological guidance for the application of deep learning in industrial inspection. [ABSTRACT FROM AUTHOR]

• The vision-based fusion method is proposed for defect detection and evaluation of milling cutter spiral cutting edge. • Deep learning model is used to extract the target region in order to guarantee the robustness to illumination. • Traditional image processing method is used to detect defects and evaluate precision in order to ensure the accuracy. Cutting tool is one of the most important parts of machine tool which greatly influences the machining quality. Defect detection of cutting tool spiral cutting edge is usually done by quality control workers after manufactured, which costs time and the quality cannot be guaranteed. In order to detect defects on the spiral cutting edge automatically and reliably within limited cycle time, this paper proposes a vision-based fusion method. This method first uses improved Yolov3-tiny to extract the target cutting edge region, and then traditional image processing method is used to detect and evaluate defects. Compared with only using deep learning, the detection accuracy and evaluation precision of defects are improved. Compared with traditional image processing method, the robustness of illumination is improved. In the case study, the detection result shows that the proposed method can effectively detect and evaluate small defects on the spiral cutting edges illumination insensitively with high detection accuracy. [ABSTRACT FROM AUTHOR]