CC BY 4.0Jacob, KevinKevinJacobStraß, BenjaminBenjaminStraßBrosta, NicoNicoBrostaPresti-Senni, JaquelineJaquelinePresti-Senni2026-03-042026-03-042026-02-26https://publica.fraunhofer.de/handle/publica/508869https://doi.org/10.24406/publica-772810.3390/app1605227310.24406/publica-77282-s2.0-105032633656In this paper, a method for determining the filling level of grooves (1 mm (W) × 0.25 mm (H)) in pressed titanium pipe-fitting joints is presented. The joints are inspected in a water bath using a 20 MHz phased array ultrasound, and the acquired raw B-scans are evaluated by a convolutional neural network that performs per-groove regression. Reference filling levels are obtained destructively from micrographs. Compared to X-ray computed tomography and destructive sectioning, the proposed approach overcomes the low material contrast between pipe and fitting, avoids long scan times, and enables a nondestructive, potentially inline-capable quantitative assessment of sub-millimeter grooves. A manual high-frequency ultrasound evaluation with a single probe and conceivable rule-based time-of-flight pipelines with hand-crafted echo picking and thresholds both show only moderate agreement with CT references and require substantial feature engineering for multiple echoes. In contrast, the PAUT-CNN method exploits the full raw B-scan without explicit feature design and achieves a root mean square error of about 7% of the groove filling levels on a held-out test set, corresponding to an absolute error on the order of a few tens of micrometers in groove height. This demonstrates that high-frequency phased array ultrasound combined with data-driven evaluation can quantitatively assess the filling of sub-millimeter grooves in aerospace-relevant press-fit connections.enultrasoundphased arrayconvolutional neural networkpressed pipe fittingsgroove filling levelNDTNDE600 Technik, Medizin, angewandte Wissenschaftenjournal article