scholarly journals Prediction of Equilibrium Phase, Stability and Stress-Strain Properties in Co-Cr-Fe-Ni-Al High Entropy Alloys Using Artificial Neural Networks

Metals ◽  
2020 ◽  
Vol 10 (12) ◽  
pp. 1569
Author(s):  
Nicolae Filipoiu ◽  
George Alexandru Nemnes
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Equilibrium Phase ◽  
Al Alloy ◽  
Mechanical And Thermal Properties ◽  
High Entropy Alloys ◽  
Huge Number ◽  
Stress Strain ◽  
High Entropy ◽  
Artificial Neural

High entropy alloys (HEAs) are still a largely unexplored class of materials with high potential for applications in various fields. Motivated by the huge number of compounds in a given HEA class, we develop machine learning techniques, in particular artificial neural networks, coupled to ab initio calculations, in order to accurately predict some basic HEA properties: equilibrium phase, cohesive energies, density of states at the Fermi level and the stress-strain relation, under conditions of isotropic deformations. Known for its high tensile ductility and fracture toughness, the Co-Cr-Fe-Ni-Al alloy has been considered as a test candidate material, particularly by adjusting the Al content. However, further enhancement of the microstructure, mechanical and thermal properties is possible by modifying also the fractions of the base alloy. Using deep neural networks, we map structural and chemical neighborhood information onto the quantities of interest. This approach offers the possibility for an efficient screening over a huge number of potential candidates, which is essential in the exploration of multi-dimensional compositional spaces.

scholarly journals The Michigan 10-Degree Blue Spectral Survey as a Basis for Future Deep Schmidt Surveys

1995 ◽  
Vol 148 ◽  
pp. 292-295
Author(s):  
N. Houk ◽  
T. von Hippel
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Automatic Classification ◽  
Training Set ◽  
Huge Number ◽  
Distance Methods ◽  
Artificial Neural ◽  
Metric Distance ◽  
Spectral Survey

AbstractThe Henry Draper stars are being systematically classified on the MK System, using the Curtis and Burrell Schmidt telescopes with photographic spectra having a dispersion of 108 Å/mm. Over 156,000 stars south of δ = +5°, have been classified leaving about 69,000 yet to do. The project is expected to be completed around the year 2004. This all-sky network of consistently classified spectra of very good quality should serve as a basis for future deep surveys. Such surveys will almost certainly be automated because of the huge number of stars to be dealt with. Von Hippel et al. at Cambridge plan to scan at least 150,000 of the spectra classified by Houk, using her plates to serve as a ‘training’ set for automatic classification using artificial neural networks. The same data can also be utilized for other methods of automatic classification including the metric-distance methods used by Kurtz and La Sala (Kurtz 1983). Even at lower dispersions, significantly more information can be obtained from Schmidt spectra than by doing Schmidt photometric colour surveys alone, though these are also valuable, especially when used in conjunction with spectra. We urge that large Schmidts not currently having prisms or other dispersive elements consider adding this equipment.

scholarly journals Prediction of Mechanical Properties of Local Concrete in Compression Using Artificial Neural Networks

2020 ◽  
Vol 27 (1) ◽  
pp. 105-121
Author(s):  
Baylasan Mohamad ◽  
Soleman Alamoudi ◽  
Abd alrahman Issa
Keyword(s):  
Mechanical Properties ◽  
Neural Networks ◽  
Compressive Strength ◽  
Artificial Neural Networks ◽  
Actual Behavior ◽  
Stress Strain ◽  
Strain Relationship ◽  
Artificial Neural ◽  
Local Materials ◽  
Ready Mix Concrete

Mechanical properties of concrete are highly dependent on the local materials used in its preparation. experiments on ready mix concrete in our region illustrate the actual behavior of concrete produced by local materials. Six standard cylinders (D=150mm, H=300mm) were casted of most ready mix concrete in central area in Syria (13 of them) covering a wide range of compressive strength . Tests were carried out using a testing machine which gives the applied force values and the corresponding displacement simultaneously until failure. The mean curves representing the (stress-strain) relationship of concrete in compression are drawn, from which the mechanical properties of each mixture were derived, such modulus of elasticity compressive strength ,  and the corresponding strain . Artificial neural networks were trained on experimental test results (using MATLAB). The laws of concrete behaviour were well assimilated by Artificial neural networks, which is possible to be used as an alternative method of available models of stress-strain relationship, by predicting the curve directly for various concrete mixtures prepared using local materials with different mixing ratios, or a complementary method through the adoption of an appropriate mathematical model and then predict its parameters ( ، ، ). ANNs proved their ability to predict mechanical properties of concrete better than linear regression equations, which promises a more accurate and comprehensive prediction.

Sign in / Sign up

Export Citation Format

Share Document