Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Crystal nucleation in metallic alloys using x-ray radiography and machine learning.

ABSTRACT: The crystallization of solidifying Al-Cu alloys over a wide range of conditions was studied in situ by synchrotron x-ray radiography, and the data were analyzed using a computer vision algorithm trained using machine learning. The effect of cooling rate and solute concentration on nucleation undercooling, crystal formation rate, and crystal growth rate was measured automatically for thousands of separate crystals, which was impossible to achieve manually. Nucleation undercooling distributions confirmed the efficiency of extrinsic grain refiners and gave support to the widely assumed free growth model of heterogeneous nucleation. We show that crystallization occurred in temporal and spatial bursts associated with a solute-suppressed nucleation zone.

SUBMITTER: Liotti E

PROVIDER: S-EPMC5898834 | biostudies-other | 2018 Apr

REPOSITORIES: biostudies-other

ACCESS DATA

Json Xml

Publications

Crystal nucleation in metallic alloys using x-ray radiography and machine learning.

Liotti Enzo E Arteta Carlos C Zisserman Andrew A Lui Andrew A Lempitsky Victor V Grant Patrick S PS

Science advances 20180413 4

The crystallization of solidifying Al-Cu alloys over a wide range of conditions was studied in situ by synchrotron x-ray radiography, and the data were analyzed using a computer vision algorithm trained using machine learning. The effect of cooling rate and solute concentration on nucleation undercooling, crystal formation rate, and crystal growth rate was measured automatically for thousands of separate crystals, which was impossible to achieve manually. Nucleation undercooling distributions co ...[more]

PMID: 29662954

Similar Datasets

Small dataset for hot cracking susceptibility of Al alloys and Ni alloys using dynamic X-ray radiography (DXR) technique.

Project description:Hot cracking as the major concern in the manufacturing process of metal alloys is detrimental to part performance and can lead to catastrophic failure. However, current research in this field is restricted to the scarcity of the relevant hot cracking susceptibility data. Here, using the DXR technique provided at 32-ID-B beamline of Advanced Photon Source (APS) at Argonne National Laboratory, we characterized the hot cracking formation in Laser Powder Bed Fusion (L-PBF) process for ten commercial alloys (Al7075, Al6061, Al2024, Al5052, Haynes 230, Haynes 160, Haynes X, Haynes 120, Haynes 214, and Haynes 718). The extracted DXR images captured the post-solidification hot cracking distribution and allow the quantification of the hot cracking susceptibility of those alloys. We further exploited this in our recent effort on hot cracking susceptibility prediction [1] and established a hot cracking susceptibility dataset posted on Mendeley Data for the purpose of facilitating the relevant research in this field.

| S-EPMC10036496 | biostudies-literature

Enhancing Protein Crystal Nucleation Using In Situ Templating on Bioconjugate-Functionalized Nanoparticles and Machine Learning.

Project description:Although protein crystallization offers a promising alternative to chromatography for lower-cost protein purification, slow nucleation kinetics and high protein concentration requirements are major barriers for using crystallization as a viable strategy in downstream protein purification. Here, we demonstrate that nanoparticles functionalized with bioconjugates can result in an in situ template for inducing rapid crystallization of proteins at low protein concentration conditions. We use a microbatch crystallization setup to show that the range of successful crystallization conditions is expanded by the presence of functionalized nanoparticles. Furthermore, we use a custom machine learning-enabled emulsion crystallization setup to rigorously quantify nucleation parameters. We show that bioconjugate-functionalized nanoparticles can result in up to a 7-fold decrease in the induction time and a 3-fold increase in the nucleation rate of model proteins compared to those in control environments. We thus provide foundational insight that could enable crystallization to be used in protein manufacturing by reducing both the protein concentration and the time required to nucleate protein crystals.

| S-EPMC10020963 | biostudies-literature

Design of high bulk moduli high entropy alloys using machine learning.

Project description:In this work, the authors have demonstrated the use of machine learning (ML) models in the prediction of bulk modulus for High Entropy Alloys (HEA). For the first time, ML has been used for optimizing the composition of HEA to achieve enhanced bulk modulus values. A total of 12 ML algorithms were trained to classify the elemental composition as HEA or non-HEA. Among these models, Gradient Boosting Classifier (GBC) was found to be the most accurate, with a test accuracy of 78%. Further, six regression models were trained to predict the bulk modulus of HEAs, and the best results were obtained by LASSO Regression model with an R-square value of 0.98 and an adjusted R-Square value of 0.97 for the test data set. This work effectively bridges the gap in the discovery and property analysis of HEAs. By accelerating material discovery via providing alternate means for designing virtual alloy compositions having favourable bulk modulus for respective applications, this work opens new avenues of applications of HEAs.

| S-EPMC10665368 | biostudies-literature

Unsupervised topological learning approach of crystal nucleation.

Project description:Nucleation phenomena commonly observed in our every day life are of fundamental, technological and societal importance in many areas, but some of their most intimate mechanisms remain however to be unravelled. Crystal nucleation, the early stages where the liquid-to-solid transition occurs upon undercooling, initiates at the atomic level on nanometre length and sub-picoseconds time scales and involves complex multidimensional mechanisms with local symmetry breaking that can hardly be observed experimentally in the very details. To reveal their structural features in simulations without a priori, an unsupervised learning approach founded on topological descriptors loaned from persistent homology concepts is proposed. Applied here to monatomic metals, it shows that both translational and orientational ordering always come into play simultaneously as a result of the strong bonding when homogeneous nucleation starts in regions with low five-fold symmetry. It also reveals the specificity of the nucleation pathways depending on the element considered, with features beyond the hypothesis of Classical Nucleation Theory.

| S-EPMC8873400 | biostudies-literature

Prediction of Breast Cancer Estrogen Receptor Status using Machine Learning

Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.

2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress

Machine learning for detecting moyamoya disease in plain skull radiography using a convolutional neural network.

Project description:BackgroundRecently, innovative attempts have been made to identify moyamoya disease (MMD) by focusing on the morphological differences in the head of MMD patients. Following the recent revolution in the development of deep learning (DL) algorithms, we designed this study to determine whether DL can distinguish MMD in plain skull radiograph images.MethodsThree hundred forty-five skull images were collected as an MMD-labeled dataset from patients aged 18 to 50 years with definite MMD. As a control-labeled data set, 408 skull images of trauma patients were selected by age and sex matching. Skull images were partitioned into training and test datasets at a 7:3 ratio using permutation. A total of six convolution layers were designed and trained. The accuracy and area under the receiver operating characteristic (AUROC) curve were evaluated as classifier performance. To identify areas of attention, gradient-weighted class activation mapping was applied. External validation was performed with a new dataset from another hospital.FindingsFor the institutional test set, the classifier predicted the true label with 84·1% accuracy. Sensitivity and specificity were both 0·84. AUROC was 0·91. MMD was predicted by attention to the lower face in most cases. Overall accuracy for external validation data set was 75·9%.InterpretationDL can distinguish MMD cases within specific ages from controls in plain skull radiograph images with considerable accuracy and AUROC. The viscerocranium may play a role in MMD-related skull features. FUND: This work was supported by grant no. 18-2018-029 from the Seoul National University Bundang Hospital Research Fund.

| S-EPMC6413674 | biostudies-literature

Phase nucleation through confined spinodal fluctuations at crystal defects evidenced in Fe-Mn alloys.

Project description:Analysis and design of materials and fluids requires understanding of the fundamental relationships between structure, composition, and properties. Dislocations and grain boundaries influence microstructure evolution through the enhancement of diffusion and by facilitating heterogeneous nucleation, where atoms must overcome a potential barrier to enable the early stage of formation of a phase. Adsorption and spinodal decomposition are known precursor states to nucleation and phase transition; however, nucleation remains the less well-understood step in the complete thermodynamic sequence that shapes a microstructure. Here, we report near-atomic-scale observations of a phase transition mechanism that consists in solute adsorption to crystalline defects followed by linear and planar spinodal fluctuations in an Fe-Mn model alloy. These fluctuations provide a pathway for austenite nucleation due to the higher driving force for phase transition in the solute-rich regions. Our observations are supported by thermodynamic calculations, which predict the possibility of spinodal decomposition due to magnetic ordering.

| S-EPMC5859155 | biostudies-literature

Fatigue database of complex metallic alloys.

Project description:The past few decades have witnessed rapid progresses in the research and development of complex metallic alloys such as metallic glasses and multi-principal element alloys, which offer new solutions to tackle engineering problems of materials such as the strength-toughness conflict and deployment in harsh environments and/or for long-term service. A fatigue database (FatigueData-CMA2022) is compiled from the literature by the end of 2022. Data for both metallic glasses and multi-principal element alloys are included and analyzed for their statistics and patterns. Automatic extraction and manual examination are combined in the workflow to improve the efficiency of processing, the quality of published data, and the reusability. The database contains 272 fatigue datasets of S-N (the stress-life relation), ε-N (the strain-life relation), and da/dN-ΔK (the relation between the fatigue crack growth rate and the stress intensity factor range) data, together with the information of materials, processing and testing conditions, and mechanical properties. The database and scripts are released in open repositories, which are designed in formats that can be continuously expanded and updated.

| S-EPMC10338547 | biostudies-literature

Evolutionary design of machine-learning-predicted bulk metallic glasses.

Project description:The size of composition space means even coarse grid-based searches for interesting alloys are infeasible unless heavily constrained, which requires prior knowledge and reduces the possibility of making novel discoveries. Genetic algorithms provide a practical alternative to brute-force searching, by rapidly homing in on fruitful regions and discarding others. Here, we apply the genetic operators of competition, recombination, and mutation to a population of trial alloy compositions, with the goal of evolving towards candidates with excellent glass-forming ability, as predicted by an ensemble neural-network model. Optimization focuses on the maximum casting diameter of a fully glassy rod, D max, the width of the supercooled region, ΔT x, and the price-per-kilogramme, to identify commercially viable novel glass-formers. The genetic algorithm is also applied with specific constraints, to identify novel aluminium-based and copper-zirconium-based glass-forming alloys, and to optimize existing zirconium-based alloys.

| S-EPMC9923804 | biostudies-literature

Machine Learning Nucleation Collective Variables with Graph Neural Networks.

Project description:The efficient calculation of nucleation collective variables (CVs) is one of the main limitations to the application of enhanced sampling methods to the investigation of nucleation processes in realistic environments. Here we discuss the development of a graph-based model for the approximation of nucleation CVs that enables orders-of-magnitude gains in computational efficiency in the on-the-fly evaluation of nucleation CVs. By performing simulations on a nucleating colloidal system mimicking a multistep nucleation process from solution, we assess the model's efficiency in both postprocessing and on-the-fly biasing of nucleation trajectories with pulling, umbrella sampling, and metadynamics simulations. Moreover, we probe and discuss the transferability of graph-based models of nucleation CVs across systems using the model of a CV based on sixth-order Steinhardt parameters trained on a colloidal system to drive the nucleation of crystalline copper from its melt. Our approach is general and potentially transferable to more complex systems as well as to different CVs.

| S-EPMC10902841 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data