Intelligent analysis of hot stamping production process based on image recognition
- DOI
- 10.2991/978-94-6463-581-2_63How to use a DOI?
- Keywords
- Intelligent analysis; Image recognition; Hot stamping
- Abstract
Hot stamping is an energy-efficient and low-cost way to produce automotive parts. The hot stamping production line has a high degree of automation and a good digitalization foundation. Due to the lack of a complete information system in most workshops, the digitalized production process data often lacks detailed information on recipes, molds, and parts. In this paper, the infrared temperature field of hot blanks on moulds is obtained using an infrared imaging detection system, and an abnormal blank position detection method based on locating pin finding is proposed, which is experimentally investigated in order to achieve the stability and accuracy. Based on the target detection model to predict the pin position, the correct rate of abnormal position detection of the Faster R-CNN model is analyzed under the conditions of coarse and fine judgments.
- Copyright
- © 2024 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Liang Wang AU - Keyang Shu AU - Yisheng Zhang AU - Bin Zhu AU - Yilin Wang PY - 2024 DA - 2024/12/07 TI - Intelligent analysis of hot stamping production process based on image recognition BT - Proceedings of the 7th International Conference on Advanced High Strength Steel and Press Hardening (ICHSU 2024) PB - Atlantis Press SP - 531 EP - 537 SN - 2590-3217 UR - https://doi.org/10.2991/978-94-6463-581-2_63 DO - 10.2991/978-94-6463-581-2_63 ID - Wang2024 ER -