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 Characterization: Structural Descriptors, Data-Intensive Techniques, and Uncertainty Quantification
Presentation Title Predicting Microstructure-sensitive Fatigue-crack Path in 3D Using a Machine Learning Framework
Author(s) Kyle Pierson, Aowabin Rahman, Ashley Spear
On-Site Speaker (Planned) Aowabin Rahman
Abstract Scope Service lives of structural components are often significantly influenced by initiation and evolution of microstructure-sensitive fatigue cracks; however, the dependence of crack propagation on microstructural features can be complex and difficult to model. In this talk, we present a convolutional neural network (CNN)-based framework to approximate the underlying function relating crack path to the relevant microstructural and micromechanical features. The key components of the framework include: (i) a feature-selection scheme to determine a lower-dimensional representation of spatially varying features; (ii) a CNN model to compute the local kink angle of the crack using two different parameterization strategies; and (iii) a dropout technique to compute the model uncertainties associated with the CNN predictions. In general, the CNN model performs comparatively better than other ML algorithms in predicting crack path – even when micromechanical fields are not available as inputs, as the CNN can account for the spatial distribution of microstructural features
Proceedings Inclusion? Planned: Supplemental Proceedings volume

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

100 Years of Scherrer Modifications: Demystifying Diffractogram Width Analyses for Nanocrystalline Materials
3D Morphological Characterization of Porous Cu by Vapor Phase Dealloying Zn-Cu Alloys
A New Crystallographic Defect Quantification Workflow via Advanced-microscopy-based Deep Learning
Advancement of Data Intensive Approaches in Materials Discovery and Design
Adversarial Networks for Microstructure Generation and Modeling Phase Transformation Kinetics
Application of Machine Learning to Microstructure Quantification and Understanding
Artificial Intelligence Approaches to Microstructural Science
Automated Anomaly Detection in Unlabeled Computed Tomography Images
Basis Functions for Quantifying Grain Boundary Texture in Polycrystalline Microstructures
Characterizing GB Atomic Structures at Multiple Scales
Characterizing the Energetics and Structural Configurations of Silicon Carbide Grain Boundaries Using High-throughput Atomistic Techniques
Deep Convolutional Networks for Image Reconstruction from 3D Coherent X-ray Diffraction Imaging Data
Determination of Representative Volume Elements for Small Cracks in Heterogeneous Domains via Convolutional Neural Networks
Feature Engineering of Material Structure for Extracting Process-structure-property Linkages
GB Property Localization: Inference and Uncertainty Quantification of Grain Boundary Structure-property Models
Higher Order Spectral Terms in Grain Boundary Networks
Indexing of Electron Back-Scatter Diffraction Patterns Using a Convolutional Neural Network
Integrated Structural Methods Addressing Aviation Challenges in Composites
Investigating the Atomistic Nature of Grain Boundary Failure
Investigating the Effect of Solute Segregation to Grain Boundaries in Nanocrystalline Alloys Toward Stability and Strengthening
Investigations of Microstructural Effects on Porosity Evolution
Large-scale Defect Contrast Simulations for Scanning and Transmission Electron Microscopy
Large Scale Microstructure Synthesis Using LEGOMAT: Application to Additive Manufacturing
Machine Learning and Electron Backscatter Diffraction
Machine Learning Approach for On-the-fly Crystal System Classification from Powder X-ray Diffraction Pattern
Machine Learning Approaches to Image Segmentation of Large Materials Science Datasets
Machine Learning Reinforced Crystal Plasticity Modeling of Titanium-Aluminum Alloys under Uncertainty
Methods for the Correction of Epistemic Resolution Error through Data Collection Process Simulations
Microstructural Evolution Along Geodesics
Monte Carlo Studies of EBSPs Spectroscopy
Neural Networks for Real-time Processing of Scanning Transmission Electron Microscopy Data
Parametric Models for Crystallographic Texture: Estimation and Uncertainty Quantification
Predicting Compressive Strength of Consolidated Solids from Features Extracted from SEM Images
Predicting Crack Location Using a Radial Distribution Function as a Unique Descriptor of Pore Networks
Predicting Microstructure-sensitive Fatigue-crack Path in 3D Using a Machine Learning Framework
The Grain Boundary Octonion: Metrics, Paths, and Fundamental Zones
Uncertainty Propagation in a Multiscale CALPHAD-reinforced Elastochemical Phase-field Model
Uncertainty Quantification of Far-field HEDM Measurements
Uncertainty Quantification Techniques Applied to Ductile Damage Predictions in the 3rd Sandia Fracture Challenge
Utilizing Convolutional Neural Networks for Prediction of Process and Material Parameters from Microstructural Images
X-Ray Computed Tomography of 3D Crack Lattices in Advanced Ceramics and their Effect on Mechanical Response

Questions about ProgramMaster? Contact programming@programmaster.org