| About this Abstract |
| Meeting |
MS&T24: Materials Science & Technology
|
| Symposium
|
Light Metal Technology
|
| Presentation Title |
Deep Learning Assisted Characterization of Microstructure in Cast Mg Alloy: Fine Feature Detection in 3D Using X-ray Microscopy |
| Author(s) |
Kaushik Yanamandra, Noushin Moharrami, Feng Lin Ng |
| On-Site Speaker (Planned) |
Kaushik Yanamandra |
| Abstract Scope |
Magnesium (Mg) alloys are pivotal in automotive and aerospace industries due to their lightweight and high-strength characteristics. Traditional methods of material analysis are often labor-intensive and subject to human error, leading to inconsistencies in characterization. The advent of deep learning (DL) has revolutionized the field of material science. This study underscores the significance of using DL algorithms in X-ray microscopy (XRM) for enhancing the accuracy and efficiency of feature detection within Mg alloys. A unique combination of a high-resolution objective lens and deep-learning-powered reconstruction was employed to achieve sub-micron resolution in dense, large Mg alloy samples. Advancements in scintillator technology and Deep learning assisted reconstruction techniques, such as DeepRecon and upscaling through DeepScout, have made it possible to achieve non-destructive, high-resolution 3D visualization of dense internal structures. The application of DL in XRM is a transformative approach that promises to elevate the standards of precision and reliability in material characterization. |