metadata

title: DP800 DamageClassification
emoji: 🐠
colorFrom: gray
colorTo: yellow
sdk: gradio
sdk_version: 4.22.0
app_file: app.py
pinned: false
license: cc-by-nc-nd-4.0

Damage Classification in Dual Phase Steels

This app is a web-based application for damage classification in dual phase steels using the gradio web development framework.

Input to the app is a (panoramic) image of a dual-phase steel specimen taken in an electron microscope (SEM). In a first step, potential damage sites are identified using a clustering approach: Damage sites typically appear as small holes in the surface of the sample and are, therefore, not easily visible in the image due to the three-dimensional structure of the sample surface when the electron beam hits the sample.

Then, inclusions are identified using a dedicated neural network. Inclusions originate from foreign particles that are embedded into the sample matrix during the manufacturing process and are typically much bigger than other types of damage.

After the inclusions are identified, a second dedicated neural network identifies the following damage classes:

Martensite Cracking
Notch Effect
Interface Decohesion. Further details about the definition of the damage classes can be found in the references below. Additionally, shadows cast by the electron beam during image acquisition are also identified as an imaging artefact.

References

Please cite the following works if you use this app.

Kusche C, Reclik T, Freund M, Al-Samman T, Kerzel U, Korte-Kerzel S (2019) Large-area, high-resolution characterisation and classification of damage mechanisms in dual-phase steel using deep learning. PLoS ONE 14(5): e0216493. link
Setareh Medghalchi, Ehsan Karimi, Sang-Hyeok Lee, Benjamin Berkels, Ulrich Kerzel, Sandra Korte-Kerzel, Three-dimensional characterisation of deformation-induced damage in dual phase steel using deep learning, Materials & Design, Volume 232, 2023, 112108, ISSN 0264-1275, [link] (https://doi.org/10.1016/j.matdes.2023.112108)
original data and code, including the network weights, can be found at Zenodo link

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference