A5016287426- Microstructure and mechanical properties
- Metallurgy and Material Forming
- Machine Learning in Materials Science
- Microstructure and Mechanical Properties of Steels
- nanoparticles nucleation surface interactions
- Theoretical and Computational Physics
- Aluminum Alloy Microstructure Properties
- Force Microscopy Techniques and Applications
- Solidification and crystal growth phenomena
- Mineral Processing and Grinding
- Industrial Vision Systems and Defect Detection
- High Temperature Alloys and Creep
- Electronic Packaging and Soldering Technologies
- Metal Forming Simulation Techniques
- Hydrogen embrittlement and corrosion behaviors in metals
- Advanced Materials Characterization Techniques
- Aluminum Alloys Composites Properties
- High-pressure geophysics and materials
- Metal Alloys Wear and Properties
- Nuclear Materials and Properties
- Manufacturing Process and Optimization
- Metal and Thin Film Mechanics
- Additive Manufacturing and 3D Printing Technologies
- Electron and X-Ray Spectroscopy Techniques
- Powder Metallurgy Techniques and Materials
Carnegie Mellon University
2015-2024
University of Michigan
1990-2024
Materials Science & Engineering
2019-2024
Ann Arbor Center for Independent Living
2022
National Energy Technology Laboratory
2020
Michigan State University
2003-2019
University of Manchester
2019
Electric Propulsion Laboratory (United States)
2019
McGill University
2019
Pohang University of Science and Technology
2019
Deep learning (DL) is one of the fastest growing topics in materials data science, with rapidly emerging applications spanning atomistic, image-based, spectral, and textual modalities. DL allows analysis unstructured automated identification features. Recent development large databases has fueled application methods atomistic prediction particular. In contrast, advances image spectral have largely leveraged synthetic enabled by high quality forward models as well generative unsupervised...
The fields of machining learning and artificial intelligence are rapidly expanding, impacting nearly every technological aspect society. Many thousands published manuscripts report advances over the last 5 years or less. Yet materials structures engineering practitioners slow to engage with these advancements. Perhaps recent that driving other technical not sufficiently distinguished from long-known informatics methods for materials, thereby masking their likely impact processes, (MPSE)....
The ‘bag of visual features’ image representation was applied to create generic microstructural signatures that can be used automatically find relationships in large and diverse data sets. Using this representation, a support vector machine (SVM) trained classify microstructures into one seven groups with greater than 80% accuracy over 5-fold cross validation. In addition, the bag features implemented as basis for search engine determines best matches query database microstructures. These...
Abstract We apply a deep convolutional neural network segmentation model to enable novel automated microstructure applications for complex microstructures typically evaluated manually and subjectively. explore two tasks in an openly available ultrahigh carbon steel dataset: segmenting cementite particles the spheroidized matrix, larger fields of view featuring grain boundary carbide, particle particle-free denuded zone, Widmanstätten cementite. also demonstrate how combine these data-driven...
Microstructural characterization and analysis is the foundation of microstructural science, connecting materials structure to composition, process history, properties. quantification traditionally involves a human deciding what measure then devising method for doing so. However, recent advances in computer vision (CV) machine learning (ML) offer new approaches extracting information from images. This overview surveys CV methods numerically encoding visual contained image using either...
The thermodynamic equilibrium state of crystalline materials is a single crystal; however, polycrystalline grain growth almost always stops before this reached. Although typically attributed to solute drag, grain-growth stagnation occurs, even in high-purity materials. Recent studies indicate that boundaries undergo thermal roughening associated with an abrupt mobility change, so at typical annealing temperatures, polycrystals will contain both smooth (slow) and rough (fast) boundaries....
Two-dimensional, infinitely degenerate Potts-model simulations were performed on four different lattices at zero and finite temperatures in order to examine the effects of lattice anisotropy temperature domain growth. The discrete Potts model causes deviations from universal growth behavior by weakening vertex angle boundary conditions that form basis von Neumann's law. Smoothing Wulff plot (e.g., extending spin interactions a longer range) or increasing which simulation is can overcome...
Black box algorithms can be useful in science and engineering
Abstract Automated, reliable, and objective microstructure inference from micrographs is essential for a comprehensive understanding of process-microstructure-property relations tailored materials development. However, such inference, with the increasing complexity microstructures, requires advanced segmentation methodologies. While deep learning offers new opportunities, an intuition about required data quality/quantity methodological guideline quantification still missing. This, along...
Metallurgy and material design have thousands of years' history played a critical role in the civilization process humankind. The traditional trial-and-error method has been unprecedentedly challenged modern era when number components phases novel alloys keeps increasing, with high-entropy as representative. New opportunities emerge for alloy artificial intelligence era. Here, successful machine-learning (ML) developed to identify microstructure images eye-challenging morphology martensitic...
Abstract SPPARKS is an open-source parallel simulation code for developing and running various kinds of on-lattice Monte Carlo models at the atomic or meso scales. It can be used to study properties solid-state materials as well model their dynamic evolution during processing. The modular nature allows new diagnostic computations added without modification its core functionality, including algorithms. A variety microstructural (grain growth), diffusion, thin film deposition, additive...
Grain boundaries in polycrystalline materials migrate to reduce the total excess energy. It has recently been found that factors governing migration rates of bicrystals are insufficient explain boundary polycrystals. We first review our current understanding atomistic mechanisms grain based on simulations and high-resolution transmission electron microscopy observations. then at continuum scale observations using high-energy diffraction microscopy. conclude detailed comparisons experimental...