Research on the Improved Detection Algorithm of YOLOv8 Industrial Parts
KONG Zhicheng1**,LIU Xingde2*,XIE Yannan1**,REN Luoying1,YU pengze1
(1.School of Information and Control Engineering,Jilin Institute of Chemical Technology, Jilin City 132022, China:2.School of Mechanical and Electrical Engineering , Jilin Institute of Chemical Technology ,Jilin City 132022, China)
Abstract: With the widespread application of industrial robots, machine vision is also developing rapidly in the industrial field, and compared with traditional manual assembly, the sorting of industrial parts based on deep learning has obvious advantages in terms of efficiency and stability. This paper proposed to improve the YOLOv8 industrial parts detection algorithm, firstly, the attention mechanism model (ResBlock_CBAM) was introduced on the basis of the original model, and the ability of the model to extract key features was improved by combining the residual module (ResBlock) and the attention module (CBAM). Secondly, an efficient Multi-scale Feature Fusion Network (BiFPN) was introduced, which can better integrate features of different scales and improve the detection ability of the model for multi-scale targets. Finally, the Inner-CIoU loss function was improved to improve the generalization ability and convergence performance of the model. The YOLOv8s model was tested on a self-made dataset, and the average accuracy of the test results reached 79.5%, which was 2.1% higher than that of the original model.
孔志成, 刘兴德, 谢延楠, 任洛莹, 余鹏泽. 基于改进YOLOv8工业零件检测算法研究[J]. 吉林化工学院学报, 2025, 42(1): 36-43.
KONG Zhicheng, LIU Xingde, XIE Yannan, REN Luoying, YU pengze. Research on the Improved Detection Algorithm of YOLOv8 Industrial Parts. Journal of Jilin Institute of Chemical Technology, 2025, 42(1): 36-43.
