Target detection of electronic components on PCB (Printed circuit board) based on vision is the core technology for 3C (Computer, Communication and Consumer Electronics) manufacturing companies to achieve quality control and intelligent assembly of robots. However, the number of electronic components on PCB is large, and the shape is different. At present, the accuracy of the algorithm for detecting all electronic components is not high. This paper proposes an improved algorithm based on YOLO (you only look once) V3 (Version 3), which uses a real PCB picture and a virtual PCB picture with synthesized data as a joint training dataset, which greatly increases the recognizability of training electronic components and provides the greatest possibility for data enhancement. After analyzing the feature distribution of the five dimensionality-reduced output layers of Darknet-53 and the size distribution of the detection target, it is proposed to adjust the original three YOLO output layers to four YOLO output layers and generate 12 anchor boxes for electronic component detection. The experimental results show that the mean average precision (mAP) of the improved YOLO V3 algorithm can achieve 93.07%.
Due to the poor mechanical properties of traditional simulation models of the organic light-emitting device (OLED) bending area, this article puts forward a finite element model of 3D bending simulation of the OLED bending area. During the model construction, it is necessary to determine the viscoelastic and hyperelastic mechanical properties, respectively. In order to accurately obtain the stress changes of material deformation during the hyperelasticity determination, a uniaxial tensile test and a shear test were used to obtain data and thus to characterize the hyperelastic properties. In order to measure the viscoelasticity, a stress relaxation test was used to draw the stress relaxation curve, so as to characterize the viscoelastic properties. Then, the plane or axisymmetric stress–strain analysis was achieved, and the material parameters of the 3D model of the OLED bending area were obtained. Finally, the 3D model was applied to the 3D bending of the OLED bending area. Combined with the axisymmetric finite element analysis method, the 3D bending simulation finite element model of the OLED bending area was constructed by dividing the finite element mesh. Experimental results show that the mechanical properties of the proposed model are better than those of traditional OLED bending simulation models. Meanwhile, the proposed model has stronger application advantages.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.