ProgramMaster Logo
Conference Tools for 2020 TMS Annual Meeting & Exhibition
Login
Register as a New User
Help
Submit An Abstract
Propose A Symposium
Presenter/Author Tools
Organizer/Editor Tools
About this Abstract
Meeting 2020 TMS Annual Meeting & Exhibition
Symposium ICME Gap Analysis in Materials Informatics: Databases, Machine Learning, and Data-Driven Design
Presentation Title Relating Microstructure Features to Response Using Convolutional Neural Networks
Author(s) Sean P. Donegan, Navneet Kumar, Michael Groeber
On-Site Speaker (Planned) Sean P. Donegan
Abstract Scope Fast acting methods for quantifying the relationship between microstructure and properties are an enabling capability for ICME-driven materials design. Given a property of interest, a number of microstructural factors may contribute to the magnitude of its response. For example, hot spots in the local stress state of a polycrystal may arise from elastic anisotropy, local morphology, and crystallographic orientations relative to the load state. It is therefore advantageous to investigate frameworks that predict properties directly from an input microstructure, learning the necessary features based on training data. We describe such a method using convolutional neural networks (CNNs), parameterizing the input microstructure as an image. The CNN is trained by creating synthetic microstructures in DREAM.3D whose elastic response is modeled using a technique based on fast Fourier transforms. We discuss the importance of capturing key information, such as crystallographic anisotropy, in the microstructural image description, and its impact on model accuracy.
Proceedings Inclusion? Planned: Supplemental Proceedings volume

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Bayesian Framework for Materials Knowledge Systems
Artificial Intelligence for Material and Process Design
Automated Data Curation for Electron Microscopy Using the Materials Data Facility
Combining Machine Learning and ICME for Alloy Development
Computational Classification, Generation and Time-evolution Prediction of Alloy Microstructures with Deep Learning
Deep Materials Informatics: Illustrative Applications of Deep Learning in Materials Science
Discovering and Navigating Gaps and Connections in Data for Materials Design
Gaps and Barriers to the Successful Integration and Adoption of Practical Materials Informatics Tools and Workflows
Gaps, Limitations, and Pitfalls of Materials Informatics
Improved Performance of Automatic Characterization of Steel Microstructure by Machine Learning Architecture
L-18 (Invited): Multi-fidelity Surrogate Assisted Framework for Prediction and Control of Meltpool Geometry in Additive Manufacturing Processes
L-19: Data-driven Hard-magnetic Materials Selection for AC Applications by Multiple Attribute Decision Making
L-20: Data Driven Prediction of Crystallographic Attributes of Small Molecules Using Various Molecular Fingerprints
L-21 (Digital): Deep Learning Image Analysis for Lattice Material Qualification
L-22: Effect of Microtextured Regions on the Deformation Behavior of Titanium Alloys Submitted to Monotonic and Cyclic Loadings Investigated using FFT-EVP Simulations
L-25: Multi-class Inclusion Identification via Machine Learning of Multilevel Image Features
L-26: Prediction of Temperature after Cooling in Coils Using Machine Learning and Finite Element Method
L-27: Uncertainty Quantification in Metallic Additive Manufacturing Through Physics-informed Data-driven Modeling with Experimental Validation
Machine Learning-directed Navigation of Synthetic Design Space: A Statistical Learning Approach to Controlling the Synthesis of Perovskite Halide Nanoplatelets in the Quantum-confined Regime
Machine Learning for Materials Science: Open, Online Tools in NanoHUB
Machine Learning to Predict Oxidation Behavior of High-temperature Alloys
Magicmat (MAterials Genome and Integrated Computational MAterials Toolkit) and Its Application for Thermoelectric Materials Design
Polymer Informatics: Current Status & Critical Next Steps
Predicting Electronic Density of States of Nanoparticles by Principal Component Analysis and Crystal Graph Convolutional Neural Network
Prediction of Steel Micro-structure by Deep Learning Using Database of Thermo-dynamics and Phase Field Model
Reduction of Uncertainty in a First-principles-based CALPHAD-type Phase Diagram via Sequential Learning of Phase Equilibrium Data
Relating Microstructure Features to Response Using Convolutional Neural Networks
Steel Development and Optimization Using Response Surface Models
The MGI and ICME
Training Data-driven Machine Learning Models Using Physics Simulations: Predicting Local Thermal Histories in Additive Manufactured Components
Uncertainty Quantification and Propagation in ICME Enabled by ESPEI
View on Data Ecosystem of Materials
Questions about ProgramMaster? Contact programming@programmaster.org