Predicting mechanical properties of ultrahigh temperature ceramics using machine learning

Keyphrases

• Analytical Model 12%
• Artificial Neural Network Model 12%
• Best Prediction 12%
• Borides 12%
• Carbides 12%
• Closed-form Analytic Solution 12%
• Design Parameters 12%
• Flexural Fracture 25%
• Flexural Strength 25%
• Fracture Toughness 25%
• High Temperature 12%
• High Temperature Applications 12%
• Incomplete Understanding 12%
• Machine Learning 100%
• Machine Learning Models 37%
• Mechanical Properties 100%
• Mechanical Properties Testing 12%
• Mixture Design 25%
• Mixture Processing 12%
• Nitrides 12%
• Numerical Model 12%
• Parameter Condition 12%
• Performance Prediction 25%
• Processing Parameters 25%
• Random Forest 12%
• Reliability Prediction 12%
• Strength-toughness 25%
• Structural Materials 12%
• Testing Conditions 12%
• Ultra-high Temperature Ceramics 100%
• Young's Modulus 50%

Engineering

• Analytical Model 50%
• Artificial Neural Network Model 25%
• Bending Strength 50%
• Closed Form 25%
• Design Parameter 25%
• Fracture Strength 50%
• High Temperature Applications 25%
• Learning System 100%
• Melting Point 25%
• Nitride 25%
• Numerical Model 25%
• Prediction Performance 50%
• Processing Parameter 50%
• Random Forest 25%
• Structural Materials 25%
• Testing Condition 25%
• Young's Modulus 100%

Material Science

• Boride 25%
• Building Material 25%
• Carbide 25%
• Flexural Strength 50%
• Fracture Toughness 50%
• Nitride Compound 25%
• Young's Modulus 100%