README.html
Niyem M. Bawana, Pascal Pomarède, Dicky Januarizky Silitonga, Hugo CHERID, Fodil Meraghni, Nico F. Declercq, David S. Citrin, Alexandre Locquet · Recherche Data Gouv France · 2026
Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.
Recherche Data Gouv France · OpenAlex · dataset · 2026
Abstract
General Description This dataset presents a collection of images obtained by X-ray tomography of composite materials of the Glass Fiber Reinforced Polymer (GFRP) type with 4 woven layers. The samples were then impacted at different energy levels to train a machine learning model to detect damage zones within the composite. The images are saved in .png format and each represents a slice of a sample viewed from the side (horizontal B-scan - sliceY / vertical B-scan sliceZ).
These images are grouped into two categories: damaged: samples showing damage after impact (delamination, matrix cracks, fiber breakage) undamaged: slices showing no damage The data is divided into three subsets: train: data used to train the model val: data used to validate performance after training test: independent data used to evaluate the model’s robustness An associated scientific publication will be added later (reference [1]). More details about the composite material, the impact process, and data acquisition are available in README.html.
Open the resolved locator · 10.57745/oolrya
Metadata licence: OpenAlex metadata (CC0)