EUVIMEDEUVIMED entdecken
Crossref

Intelligent Recognition and 3-D Reconstruction of Surface Defects in Automotive Forgings

Qi Gao, Mengwu Wu, Lin Hua, Xunpeng Qin

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 5010313-5010313

DOI: 10.1109/tim.2026.3697097 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Qi Gao und 3 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Gefördert von: Key Research and Development Program of Hubei Province, China, Open Fund of Hubei Longzhong Laboratory, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the realm of surface defect detection for automotive forgings, the identification of surface cracks holds paramount importance, as it is crucial for ensuring both the surface integrity and internal quality of the components. Once defects are detected, the affected areas of automotive forgings must undergo grinding and polishing, a process that relies on accurately determining the 3-D spatial location of these defects. Consequently, the 3-D reconstruction of surface defects on forgings emerges as an indispensable step. However, the intricate morphology of surface cracks in forged components presents a significant challenge for automated detection. To address this issue, this study proposes an innovative cascade framework comprising segmentation–detection–segmentation. The first segmentation module primarily segments the forged component, the detection module aims to localize areas of surface defects in the forging, while the second segmentation module precisely extracts pixel-level features within the crack region. Building upon the accurate segmentation results, the system subsequently performs stereo matching and 3-D reconstruction processes, ultimately yielding precise 3-D coordinates of the crack defects. The experimental results demonstrate that the U-Net model achieved a mean intersection-over-union (mIoU) score of 99.03 %, providing strong quantitative evidence of its effectiveness in generating precise and reliable segmentation results for the forging components. The YOLO11 object detection model achieved a mAP@0.5:0.95 of 85.9 %, outperforming YOLOv5s (82.0 %) and YOLOv8s (83.1 %). The model achieves an impressive accuracy of 99.3 %, with a mAP@0.5:0.95 reaching 85.9 %. Furthermore, the U2-Net segmentation model achieved a Dice coefficient of 95.31 %, the highest among the three evaluated segmentation models, attaining a Dice similarity coefficient of 95.31 %. Quantitative evaluation of the reconstructed cracks reveals high precision, with relative deviations of less than 4 % from ground truth for both length and width measurements.

Förderung

  • Key Research and Development Program of Hubei Province, China
  • Open Fund of Hubei Longzhong Laboratory, China

Zitieren

APA

Gao, Q., Wu, M., Hua, L., & Qin, X. (2026). Intelligent Recognition and 3-D Reconstruction of Surface Defects in Automotive Forgings. IEEE Transactions on Instrumentation and Measurement, 75, 5010313-5010313. https://doi.org/10.1109/tim.2026.3697097

Vancouver

Gao Q, Wu M, Hua L, Qin X. Intelligent Recognition and 3-D Reconstruction of Surface Defects in Automotive Forgings. IEEE Transactions on Instrumentation and Measurement. 2026;75:5010313-5010313. doi:10.1109/tim.2026.3697097

BibTeX
@article{Gao2026,
  author = {Gao, Qi and Wu, Mengwu and Hua, Lin and Qin, Xunpeng},
  title = {Intelligent Recognition and 3-D Reconstruction of Surface Defects in Automotive Forgings},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {5010313--5010313},
  doi = {10.1109/tim.2026.3697097}
}
Kostenlos starten →