Defect Detection Using Deep Learning
Electron microscopy is widely used to explore defects in crystal structures, but human tracking of defects can be time-consuming, error-prone, and unreliable, and it is not scalable to large numbers of images or real-time analysis. In this work, we explore the application of machine learning approaches to find the location and geometry of different defect clusters in electron microscopy images of irradiated steels. We show that performance comparable to human analysis can be achieved with relatively small training data sets. We explore multiple deep learning methods that provide various features, e.g., fast processing for video and pixel level categorization to simplify defect dimension determination.
- Evaluation of Human-Bias in Machine Learning Models for Electron Microscopy
- Real-time Microscopy Quantification Using Machine Learning
- Precipitate Stability and Helium Trapping in Advanced Steels
- Accelerated irradiation creep testing coupled with self-adaptive accelerated molecular dynamics simulations for scalability analysis
- Advance Castable Nanostructured Alloys for First-wall/Blanket Applications