OtterMars's starred repositories
Ensemble-Method-for-Predicting-the-Mechanical-Properties-of-Strain-Hardening-Cementitious-Composites
A project that aims to build a model for predicting the behavior of Strain hardening cementitious composites also known as Engineered Cementitious Composites
Mech-Prop-using-ML
Extraction of Mechanical Properties (includes Proportional limit, Yield Point, Ultimate tensile strength, Fracture point) of complex Alloy like Al6061 at various temperatures using Machine Learning.
master_thesis
This repository contains data, analyses and software to model mechanical properties of austempered ductile iron (ADI) and use heuristic optimization to search through discrete space of solutions (chemical composition, heat treatment parameters) for solution that fulfills conditions of norms for ADI and has a balance between cost and quality of production.
prediction-of-mechanical-properties-of-steels-
prediction of mechanical properties of steels with ML
MechPropModels
Applying machine learning models to mechanical properties
Abalone-Age-Prediction
Predicting Algae's age using different attributes and Machine Learning Algorithms for Regression Analysis.
MachineLurgy
Prediction of Mechanical Properties of Low-Alloy Steels
Regression_to_Predict_Alloy_Hardness
This work was done in collaboration with Uttam Bhandari.
Predicting-Concrete-Strength-for-high-performance
Domain: Material manufacturing | Feature Engineering, Regression, Decision trees | Predicting the Strength of high performance concrete
Comp4560
A combination of lightweight, high specific strength, and good castability make magnesium alloys a promising engineering material for the automotive and aerospace industries. Vehicle weight reduction is one of the major means available to improve automotive fuel efficiency. High-strength steels, Aluminium (Al), and polymers are already being used to reduce weight significantly, but substantial additional reductions could be achieved by greater use of low-density magnesium (Mg) and its alloys. This project herein, therefore, relies on the use of machine learning, to assist in the development of A.I. to predict alloy compositions that are potentially useful for future metallic alloys. This study shows how a machine learning approach is able to offer acceptable precision predictions with respect to the main mechanical properties of metals.
Casting-Quality-Inspection
Metal Casting Quality Inspection with CNN, built using TensorFlow in Python
MXene-machine-learning
Classification of MXenes into metals and non-metals based on physical properties
AlloyModel
Prediction of Metal Alloy Stability
high_cycle_fatigue_tool
A Python tool with GUI (Graphical User Interface) for processing CSV files obtained from fatigue experiments up to the high-cycle fatigue ranges. Additionally, tests with monotonic loading can be processed.
DimeNet-Periodic
Predict materials properties using structural and compositional information with DimeNet++
Multi-objective_optimization
Find Pareto front using PHYSBO. This example targets 3 glass properties at the same time with visuals like a responsive surface.
concrete-strength-prediction
Concrete is the single most widely used man-made material in the world. Construction workers rely on experiments to determine the strength of concrete. The app presents an attempt to predict the strength based on the information of raw materials by machine learning methods.
Material_Informatics
Basic components to perform material informatics: modeling (GPR, KRR, XGB, NN, RF, linear, and ensemble learning of them), backward prediction, multi target screening, etc.
Prediction-of-strain-rate-dependencies-in-materials
B.Tech Final Year Project
Concrete-Compressive-Strength-Prediction
It predicts the Concrete Compressive Strength depending upon raw material
ecloud
Materials representation plays a key role in machine learning based prediction of materials properties and new materials discovery. Currently both graph and 3D voxel representation methods are based on the heterogeneous elements of the crystal structures. Here, we propose to use electronic charge density (ECD) as a generic unified 3D descriptor for materials property prediction with the advantage of possessing close relation with the physical and chemical properties of materials. We developed an ECD based 3D convolutional neural networks (CNNs) for predicting elastic properties of materials, in which CNNs can learn effective hierarchical features with multiple convolving and pooling operations. Extensive benchmark experiments over 2,170 Fm-3m face-centered-cubic (FCC) materials show that our ECD based CNNs can achieve good performance for elasticity prediction. Especially, our CNN models based on the fusion of elemental Magpie features and ECD descriptors achieved the best 5-fold cross-validation performance. More importantly, we showed that our ECD based CNN models can achieve significantly better extrapolation performance when evaluated over non-redundant datasets where there are few neighbor training samples around test samples. As additional validation, we evaluated the predictive performance of our models on 329 materials of space group Fm-3m by comparing to DFT calculated values, which shows better prediction power of our model for bulk modulus than shear modulus. Due to the unified representation power of ECD, it is expected that our ECD based CNN approach can also be applied to predict other physical and chemical properties of crystalline materials.