SDL Materials Design

To this end we adapt deep learning methods and numerical algorithms to our data and evaluate them on materials specific metrics. The final goal is targeting material scientists from both experimental and computational background and providing cross-sectional showcases to bring them together.

Using high resolution panoramic images from Scanning Electron Microscopy (SEM) allows to have a large field of view of the microstructure. We use convolutional neural networks (CNNs) in tasks such as semantic segmentation, object detection and classification to find and locate damages and defects.

Further, we use the segmented images of microstructure as input to generate Finite Element (FE) mesh with interface details and carry out multiphase Finite Element (FE) simulations to evaluate the elastoplastic and fracture behavior of the samples in the framework of computational homogenization.

Current research topics:

• Deep learning models for microstructural analysis of electron microscopy images
• Finite element simulation on deep learning segmented microstructures as input
• Deep learning models for 3D data from atom probe tomography
• Robust structure identification for experimental and simulation data using machine learning

Support activities:

• Providing an interactive web app for material scientists to use our models
• Finding solutions for the community of materials scientists for large scale visualization within the OVITO software

• Ovito GmbH
• DFG Projekt (AL 578/24-1 | EI 453/4-1): “Nano-Mikro Skalenübergang durch Atomistik-Kontinuum-Kopplung mittels Homogenisierung”
• Dr. Sarbajit Banerjee, Davidson Chair in Chemistry, Professor of Materials Science & Engineering, Texas A&M University

2023

• Chemistry–mechanics–geometry coupling in positive electrode materials: a scale-bridging perspective for mitigating degradation in lithium-ion batteries through materials design (David A. Santos, Shahed Rezaei, Delin Zhang, Yuting Luo, Binbin Lin, Ananya R. Balakrishna, Bai-Xiang Xu and Sarbajit Banerjee), Chemical Science.

• Effect of moisture on the delamination properties of fractured PVB-laminated glass: A joint experimental and numerical study (Xing Chen, Binbin Lin, Miriam Schuster, Suwen Chen, Bai-Xiang Xu, Jens Schneider), Composite Structures.

• Determination of the Rate Dependence of Damage Formation in Metallic-Intermetallic Mg–Al–Ca Composites at Elevated Temperature using Panoramic Image Analysis (Setareh Medghalchi, Muhammad Zubair, Ehsan Karimi, Stefanie Sandlöbes-Haut, Ulrich Kerzel, and Sandra Korte-Kerzel), Advanced Engineering Materials.

• Computer vision assisted decomposition analysis of atom probe tomography data (Janis A Sälker, Raheleh Hadian, Jochen M Schneider and Marcus Hans), Journal of Physics D: Applied Physics.

• Three-dimensional characterisation of deformation-induced damage in dual phase steel using deep learning (Setareh Medghalchi, Ehsan Karimi, Sang-Hyeok Lee a, Benjamin Berkels, Ulrich Kerzel, Sandra Korte-Kerzel),
  Materials & Design​.
• A Machine Learning Enabled Image-data-driven End-to-end Mechanical Field Predictor For Dual-Phase Steel (Binbin Lin, Setareh Medghalchi, Sandra Korte-Kerzel, Bai-Xiang Xu), 92nd Annual Meeting of the International Association of Applied Mathematics and Mechanics (GAMM).