Abstract
In order to replace manual visual detection to realize intelligent detection for welding seam defects of automobile wheel hub, an intelligent detection method based on YOLOV4 was proposed. In this paper, the realization scheme of intelligent detection system and an test experiment for detection effect are designed. Firstly, the defect images of automobile hub welds were collected by industrial cameras. Then, data sets were made and the results were obtained through test experiment. After 7000 training iterations, YOLOv4 achieved a model with mean average precision (mAP) of 90.97% on the valid set, with F1 score of 0.94, and with 73.15% on the average Intersection over Union (IoU). The detection time of the single image was less than 18 ms. The detection accuracy of the model on the test set reached 96.42%. The accuracy and speed of this method can meet the requirements of on-line weld detection in automobile hub manufacturers.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
