An Automotive Body-in-White Welding Stud Flexible and Efficient Recognition System

The traditional stud welded inspection method suffers from low efficiency and a lack of precision, which makes it difficult to meet the demand for high efficiency and precision in modern automobile production lines. In this paper, a flexible recognition system incorporating a deep learning model is...

Full description

Saved in:
Bibliographic Details
Main Authors: Hong Huang, Xiangqian Peng, Shiyu Wu, Wenchu Ou, Xiaoping Hu, Lifeng Chen
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10937086/
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The traditional stud welded inspection method suffers from low efficiency and a lack of precision, which makes it difficult to meet the demand for high efficiency and precision in modern automobile production lines. In this paper, a flexible recognition system incorporating a deep learning model is proposed for the inspection of welded studs in the whole car body-in-white of an automobile, including the composition of the recognition system, error analysis, path planning, and the deep learning model used. The proposed system has made significant improvements to both accuracy and detection efficiency. It can detect welded studs in a white car body with high accuracy and efficiency. Its overall detection accuracy of 99.36% demonstrates its potential to automate the production line and reduce production costs.
ISSN:2169-3536