Conference Tools for 2021 TMS Annual Meeting & Exhibition

Help

About this Abstract
Meeting	2021 TMS Annual Meeting & Exhibition
Symposium	AI/Data informatics: Design of Structural Materials
Presentation Title	Data-driven Approaches for Automated Analysis of Non-metallic Inclusions that Form during Steel Processing
Author(s)	Mohammad Abdulsalam, Nan Gao, Elizabeth Holm, Bryan Webler
On-Site Speaker (Planned)	Bryan Webler
Abstract Scope	Non-metallic inclusions are small oxide, sulfide, or nitride particles that have numerous effects on the processing and properties of steels. Inclusions arise during liquid steel processing and their control is an important objective of steel refining. Improved control strategies have been enabled by improved characterization methods. Automated characterization methods provide multidimensional data on shape, size, and chemical composition for thousands of inclusions on time scales of hours. Measurement and analysis times are, however, still too long for direct process feedback. This talk will review efforts using machine learning and computer vision methods to automate data analysis and increase the speed of data acquisition. We utilize clustering algorithms to identify large agglomerations of inclusions that are particularly detrimental to processing and properties. We have also investigated regression and computer vision methods to extract composition information from images of inclusions to reduce the need for direct composition measurement.
Proceedings Inclusion?	Planned:
Keywords	Iron and Steel, Process Technology, Machine Learning

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Physics-informed Bayesian Experimental Autonomous Researcher for Structural Design

Alloy Design for Additive Manufacturing

Combined Statistical and Energetic Approach to Understand Grain Boundary Embrittlement for Segregation Engineering

Data-driven Approaches for Automated Analysis of Non-metallic Inclusions that Form during Steel Processing

Data Science Approaches for Microstructure-property Connections in Structural Materials

Design of Ti-Al-Cr-V Alloys for Maximum Thermodynamic Stability

Discovery of Optimized ω-phase Free Ti-based Alloys Using CALPHAD and Artificial Intelligence Approach

Evaluating Uncertainty in Clustering of Nanoindentation Mapping Data

Fast and High-throughput Synthesis of Film and Bulk High-entropy Alloys

High-throughput Alloy Design via Additive Manufacturing

High-throughput Calculation to Predict the Eutectic Point in Quaternary System

Incorporating Historical Data & Past Analyses for Improved Tensile Property Prediction of 9% Cr Steel

Machine Learning Approach to Understanding Abnormal Grain Growth

Machine Learning Assisted Exploration of FeCoCrNi Based Nanocrystal-amorphous Dual-phase Alloys

Machine Learning for the Recognition and Synthesis of Polycrystalline Metal Microstructures

Model Reification with Batch Bayesian Optimization

Multi-objective Lattice Optimization Using an Efficient Neural Network Approach

Physics-informed Data-driven Machine Learning Approach for Mesoscale Materials Science

Prediction of the Mechanical Properties of Aluminum Alloy Using Bayesian Learning for Neural Networks

Solving Inverse Problems for Process-structure Linkages Using Asynchronous Parallel Bayesian Optimization

Structural Response Statistics of Deformed Polycrystals Leading to Rare Events

Topology Optimization for Design of Stress-dependent Material Properties

Unsupervised ML to Bridge Molecular Dynamics and Phase field Simulations

Using Machine Learning for Targeted Alloy Design in High Entropy Composition Spaces

Zoning Processing Spaces for Additive Manufacturing: Applications for Inverse Design

Questions about ProgramMaster? Contact programming@programmaster.org