Physics-guided, data-refined modeling of granular material-filled particle dampers by deep transfer learning

Keyphrases

• Granular Materials 100%
• Deep Neural Network 100%
• Deep Transfer Learning 100%
• Particle Damper 100%
• Refined Modeling 100%
• Physics-guided 100%
• Filling Ratio 50%
• Multi-fidelity 50%
• Excitation Frequency 37%
• Excitation Amplitude 37%
• Particle Filling 37%
• Cavity Height 37%
• Modeling Approach 25%
• Damper 25%
• Broad Frequency Band 25%
• Particle Size 12%
• Highly Nonlinear 12%
• Learning-based 12%
• Dynamic Characteristics 12%
• Amplitude Parameter 12%
• Constitutive Equation 12%
• Nonlinear Dynamics 12%
• Number of Features 12%
• Modeling Capability 12%
• Cavity Configuration 12%
• Output Parameters 12%
• Transfer Learning Model 12%
• Transfer Learning 12%
• Particle Material 12%
• Nonlinear Problems 12%
• Energy Loss Factor 12%
• Dynamic Deep Neural Network 12%
• Noise Mitigation 12%
• Learning philosophy 12%
• Multi-fidelity Modeling 12%
• Vibration Noise 12%

Engineering

• Transfer Learning 100%
• Filled Particle 100%
• Deep Neural Network 100%
• Network Model 44%
• Excitation Frequency 33%
• Optimal Design 11%
• Energy Dissipation 11%
• Input Parameter 11%
• Non-Linear Dynamic 11%
• Constitutive Equation 11%
• Output Parameter 11%
• Loss Factor 11%
• Nonlinear Problem 11%
• Material Particle 11%

Material Science

• Granular Material 100%