EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Quantitative Microstructure Characterization in Additively Manufactured Nickel Alloy 625 Using Image Segmentation and Deep Learning

Tuğrul Özel, Sijie Ding, Amit Ramasubramanian, Franco Pieri, Doruk Eskicorapci

Machines · 26.03.2026 · 14 (4) · 366

DOI: 10.3390/machines14040366 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machines, online erschienen am 26.03.2026. Verfasst von Tuğrul Özel und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Laser Powder Bed Fusion for metals (PBF-LB/M) is a complex additive manufacturing process in which metal powder is selectively melted layer-by-layer to fabricate 3D parts. Process parameters critically influence the resulting microstructure in nickel alloys, with features such as melt pool marks, grain size and orientation, porosity, and cracks serving as key process signatures. These features are typically analyzed post-process to identify suboptimal conditions. This research aims to develop automated post-process measurement and analysis techniques using image processing, pattern recognition, and statistical learning to correlate process parameters with part quality. Optical microscopy images of build surfaces are analyzed using machine learning algorithms to evaluate porosity, grain size, and relative density in fabricated test coupons. Effect plots are generated to identify trends related to increasing energy density. A novel deep learning approach based on Mask R-CNN is used to detect and segment melt pool regions in optical microscopy images. From the segmented regions, melt pool dimensions—such as width, depth, and area—are extracted using bounding geometry coordinates. Manually labeled images (Type I and Type II) are used to train the model. A comparison between ResNet-50 and ResNet-101 backbones shows that the ResNet-50-based model (Model 2) achieves superior performance, with lower training loss (0.1781 vs. 0.1907) and validation loss (8.6140 vs. 9.4228). Quantitative evaluation using the Jaccard index, precision, and recall metrics shows that the ResNet-101 backbone outperforms ResNet-50, achieving about 4% higher mean Intersection-over-Union, with values of 0.85 for Type I and 0.82 for Type II melt pools, where Type I is detected more accurately due to its more regular morphology and clearer boundaries. By extending Faster R-CNNs with a mask prediction branch, the method allows for precise melt pool measurements, providing valuable insights into process quality and dimensional accuracy, and aiding in the detection of defects in PBF-LB-fabricated parts.

Zitieren

APA

Özel, T., Ding, S., Ramasubramanian, A., Pieri, F., & Eskicorapci, D. (2026). Quantitative Microstructure Characterization in Additively Manufactured Nickel Alloy 625 Using Image Segmentation and Deep Learning. Machines, 14(4), 366. https://doi.org/10.3390/machines14040366

Vancouver

Özel T, Ding S, Ramasubramanian A, Pieri F, Eskicorapci D. Quantitative Microstructure Characterization in Additively Manufactured Nickel Alloy 625 Using Image Segmentation and Deep Learning. Machines. 2026;14(4):366. doi:10.3390/machines14040366

BibTeX
@article{zel2026,
  author = {Özel, Tuğrul and Ding, Sijie and Ramasubramanian, Amit and Pieri, Franco and Eskicorapci, Doruk},
  title = {Quantitative Microstructure Characterization in Additively Manufactured Nickel Alloy 625 Using Image Segmentation and Deep Learning},
  journal = {Machines},
  year = {2026},
  volume = {14},
  number = {4},
  pages = {366},
  doi = {10.3390/machines14040366}
}
Kostenlos starten →