Prediction of aerodynamic coefficients for multi-swept delta wings via a hybrid neural network

Keyphrases

• Delta Wing 100%
• Aerodynamic Coefficients 100%
• Hybrid Neural Network 100%
• Angle of Attack 66%
• Aerodynamic Characteristics 66%
• Sideslip Angle 66%
• Training Data 33%
• Additional Inputs 33%
• Mach number 33%
• Machine Learning Techniques 33%
• Flow Condition 33%
• Prediction Skill 33%
• Early Design Phases 33%
• Machine Learning Approach 33%
• Feedforward Neural Network 33%
• Image Classification 33%
• Performance Prediction 33%
• Aspect Ratio 33%
• Cost Savings 33%
• Computational Fluid Dynamics Simulation 33%
• Absolute Value 33%
• Control Surface 33%
• Aerodynamic Analysis 33%
• Wind Tunnel Test 33%
• Reynolds number 33%
• Wind Tunnel Experiment 33%
• Lift Coefficient 33%
• Dynamic Wind 33%
• Control Surface Deflection 33%
• Leading Edge Sweep 33%
• Preliminary Aircraft Design 33%
• Pitching Moment Coefficient 33%
• Wing Configurations 33%
• Combined Image 33%
• Slope Characteristic 33%

Engineering

• Aerodynamic Coefficient 100%
• Delta Wing 100%
• Aerodynamic Characteristic 66%
• Control Surfaces 66%
• Tunnel 66%
• Learning Approach 33%
• Mach Number 33%
• Limitations 33%
• Feedforward 33%
• Image Classification 33%
• Computational Fluid Dynamics 33%
• Prediction Capability 33%
• Flow Condition 33%
• Angle-of-Attack 33%
• Reynolds' Number 33%
• Lift Coefficient 33%
• Aerodynamic Analysis 33%
• Baseline Configuration 33%
• Sideslip Angle 33%
• Network Model 33%
• Design Phase 33%
• Leading Edge 33%
• Machine Learning Technique 33%
• Absolute Value 33%
• Attack Angle 33%
• Pitching Moment Coefficient 33%
• Learning System 33%
• Aspect Ratio 33%