Machine learning-based forward and inverse designs for prediction and optimization of fracture toughness of aluminum alloy

Keyphrases

• Alcoa 20%
• Alloy Composition 20%
• Alloying Elements 20%
• Aluminum Alloy 100%
• Artificial Neural Network 20%
• Better Performance 20%
• Correlation Features 20%
• Deep Machine Learning 20%
• Design System 40%
• Error Criterion 20%
• Error Value 20%
• Extreme Gradient Boosting(XGBoost) 20%
• Forward Design 100%
• Fracture Toughness 100%
• Future Information 20%
• Good Accuracy 20%
• High Fracture Toughness 40%
• Inverse Design 100%
• K-fold Cross-validation 20%
• K-nearest 20%
• Machine Learning Based 100%
• Machine Learning Design 40%
• Machine Learning Framework 20%
• Machine Learning Techniques 20%
• MAPE Value 20%
• Model Feasibility 20%
• Nonlinear Regression 20%
• Pearson Correlation Coefficient 20%
• Pre-screening Tool 20%
• Prediction Accuracy 20%
• R2 Score 20%
• RMSE Value 20%
• Score Value 20%
• Shallow Machine Learning 20%
• Small Data 20%
• Superior Performance 20%
• Support Vector Regression 20%
• System Failure 20%
• System Framework 20%
• XGBoost 20%
• XGBoost Model 20%
• XGBoost Technique 20%

Material Science

• Alloy 14%
• Alloying 28%
• Aluminum Alloy 100%
• Fracture Toughness 100%
• Selecting Material 14%
• Xgboost 57%

Chemical Engineering

• Alloying Element 20%
• Learning System 100%
• Neural Network 20%
• Pearson Correlation Coefficient 20%
• Support Vector Machine 20%
• Xgboost 80%