Intelligent Defect Identification in Girth Welds of Phased Array Ultrasonic Testing Images Using Median Filtering, Spatial Enrichment, and YOLOv8
Metals · 22.04.2026 · 16 (5) · 458
DOI: 10.3390/met16050458 ↗Kurz gefasst
Fachartikel in der Zeitschrift Metals, online erschienen am 22.04.2026. Verfasst von Mingzhe Bu und 3 weiteren Autor:innen. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: national key R&D plan “theory, algorithm and application of big data analysis for safe operation and maintenance of oil and gas pipeline network”, key R&D plan of Shandong Province, “research on key technologies and equipment development of intelligent welding and testing system for long-distance pipeline”.
Abstract (Originalsprache)
Girth welds are susceptible to defects under high internal pressure and stress. While phased array ultrasonic testing (PAUT) is widely used for non-destructive evaluation, manual inspection remains inefficient and highly dependent on expertise. Furthermore, existing deep learning models often struggle with low accuracy and high complexity. This paper proposes a PAUT defect classification method based on YOLOv8. First, median filtering is employed for denoising, and the results show that noise is effectively reduced while preserving key features, achieving PSNR values of 35.132, 35.938, and 36.138 for slag inclusion, pores, and lack of fusion (LOF), respectively. Subsequently, the spatial enrichment algorithm (SEA) is applied to enhance image details without amplifying noise, yielding a PSNR of 33.71 and an SSIM of 0.96. Finally, the YOLOv8 model is implemented for defect recognition. Experimental results demonstrate that the proposed approach achieves a superior balance between precision and recall with high reliability. This method offers a robust and efficient solution for automated PAUT evaluation in practical engineering applications.
Förderung
- national key R&D plan “theory, algorithm and application of big data analysis for safe operation and maintenance of oil and gas pipeline network”
- key R&D plan of Shandong Province, “research on key technologies and equipment development of intelligent welding and testing system for long-distance pipeline”
Zitieren
APA
Bu, M., Niu, S., Li, X., & Han, B. (2026). Intelligent Defect Identification in Girth Welds of Phased Array Ultrasonic Testing Images Using Median Filtering, Spatial Enrichment, and YOLOv8. Metals, 16(5), 458. https://doi.org/10.3390/met16050458
Vancouver
Bu M, Niu S, Li X, Han B. Intelligent Defect Identification in Girth Welds of Phased Array Ultrasonic Testing Images Using Median Filtering, Spatial Enrichment, and YOLOv8. Metals. 2026;16(5):458. doi:10.3390/met16050458
BibTeX
@article{Bu2026,
author = {Bu, Mingzhe and Niu, Shengyuan and Li, Xueda and Han, Bin},
title = {Intelligent Defect Identification in Girth Welds of Phased Array Ultrasonic Testing Images Using Median Filtering, Spatial Enrichment, and YOLOv8},
journal = {Metals},
year = {2026},
volume = {16},
number = {5},
pages = {458},
doi = {10.3390/met16050458}
}
EUVIMED