Research on Weld Seam Bead Recognition Based on Convolution Neural Network
Scientific Programming · 05.10.2022 · 2022 · 1-7
DOI: 10.1155/2022/1626384 ↗Kurz gefasst
Fachartikel in der Zeitschrift Scientific Programming, erschienen am 05.10.2022. Verfasst von Chao Shi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Basic Research Program of China.
Abstract (Originalsprache)
In terms of the problems of five categories of nonweld seam stripes, including inclusion, oil-spot, silk-spot, and water-spot, which interfere with weld seam recognition during robotic welding, a convolutional neural network (CNN) algorithm, combined with a multistage training strategy, is used to construct a digital model for weld seam recognition, on the basis of which the classification accuracy is compared with the standard model of seven categories of representative CNN. The results show that the ResNet model with a multistage training strategy classifies weld seams with an accuracy of 83.8%, which is superior to other standard models. In this study, the physical scenario of weld seam recognition is migrated to a neural network digital model, fulfilling the intelligent recognition of weld seams in complex scenarios based on the CNN digital model.
Förderung
- National Basic Research Program of China
Zitieren
APA
Shi, C., Sun, H., Liu, C., & Tang, Z. (2022). Research on Weld Seam Bead Recognition Based on Convolution Neural Network. Scientific Programming, 2022, 1-7. https://doi.org/10.1155/2022/1626384
Vancouver
Shi C, Sun H, Liu C, Tang Z. Research on Weld Seam Bead Recognition Based on Convolution Neural Network. Scientific Programming. 2022;2022:1-7. doi:10.1155/2022/1626384
BibTeX
@article{Shi2022,
author = {Shi, Chao and Sun, Hongwei and Liu, Chao and Tang, Zhaojia},
title = {Research on Weld Seam Bead Recognition Based on Convolution Neural Network},
journal = {Scientific Programming},
year = {2022},
volume = {2022},
pages = {1--7},
doi = {10.1155/2022/1626384}
}
EUVIMED