Conference Tools for MS&T22: Materials Science & Technology

Help

About this Abstract
Meeting	MS&T22: Materials Science & Technology
Symposium	AI for Big Data Problems in Advanced Imaging, Materials Modeling and Automated Synthesis
Presentation Title	Deep Neural Networks for Laser Absorptivity Prediction from Synchrotron X-ray Images
Author(s)	Runbo Jiang, Joseph Aroh, Brian Simonds, Tao Sun, Anthony Rollett
On-Site Speaker (Planned)	Runbo Jiang
Abstract Scope	The quantification of the amount of absorbed light is essential for understanding laser-material interactions and melt pool dynamics in order to minimize defects in additively manufactured metal components. The geometry of a vapor depression, also known as a keyhole, in melt pools formed during laser melting is closely related to laser absorptivity. This relationship has been observed by the state-of-the-art in situ high speed synchrotron x-ray visualization and integrating sphere radiometry. These two techniques create a temporally resolved dataset consisting of keyhole images and the corresponding laser absorptivity. In this work, convolutional neural networks (ResNet50 and ConvNeXt) and vision transformer, are adapted to interpret an unprocessed x-ray image of a keyhole and predict the amount of light absorbed. CAM is used to highlight class-specific regions of images.The high-dimensional features extracted by the CNNs are visualized using PCA to identity the behavior of the relationship between the input keyhole geometry and output laser absorptivity.

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Feasibility Study of Machine Learning-assisted Alloy Design Using Wrought Aluminum Alloys as An Example

AI-enabled Platform for Autonomous Experimentation and Materials Discovery

Are Process-Structure-Property Relationships Useful for Materials Design?

A.I. Driven Sustainable Aluminum Alloy Design

B-1: Autonomous Closed Loop Synthesis of Gold Nanorods via a Modular Chemical-Handling Robotic Platform

B-2: Logistics Box Recognition in Robotic Industrial De-palletizing Procedure with Systematic RGB-D Image Processing Supported by Multiple Deep Learning Method

Data-driven Search for Promising Intercalating Ions and Layered Materials for Metal-ion Batteries

De Novo Inverse Design of Nanoporous Materials by Machine Learning

De Novo Molecular Drug Design Using Deep and Reinforcement Learning

Deep Learning-based Algorithms for X-ray Microtomography Analysis: Unravelling Challenges for 4D Experiments

Deep Learning Approaches for Accelerating Polymer Characterization

Deep Neural Networks for Laser Absorptivity Prediction from Synchrotron X-ray Images

Estimation of Sub-micron Carbide Sizes and Morphologies in Dual-Phase Steels from Light Optical Micrographs Using Generative Adversarial Networks

High-dimensional Neural Network Potential for Liquid Electrolyte Simulations: Applications to Li-ion Battery Materials

Machine Learning Enabled Stacking Fault Energy Prediction in Concentrated Alloys

Machine Learning for Accelerated Defect Dynamics in Materials

Machine Learning Guided Prediction of Rupture Time of 347H Stainless Steel

Multi-Fidelity Machine Learning for Perovskite Discovery

Multi-property Graph Networks for Novel Materials Discovery

Neural Network Prediction of Dynamical Electron Back-Scattered Diffraction Patterns Based on Kinematical Patterns

Phase Identification by Neural Networks Trained from Experimental and Theoretical Structure Data

Physics-informed Machine Learning for Selected Area Electron Diffraction Data Analysis

Rapid Metallic Alloy Development Leveraging Machine Learning

Real-time and Large FOV Ptychography through AI@Edge

Understanding Atomic-scale Mechanisms of Defect Dynamics in Rare Earth Nickelates by Machine Learning and Quantum Simulations

Questions about ProgramMaster? Contact programming@programmaster.org