Evaluation of Physics-Informed Machine Learning Models for Liquid Entrainment During Reflood Transient Using NRC/PSU RBHT Data

Keyphrases

• Reflood Transients 100%
• Machine Learning Models 100%
• Physics-informed Machine Learning 100%
• Liquid Entrainment 100%
• Prediction Accuracy 50%
• State Universities 25%
• Pennsylvania 25%
• Predictive Ability 25%
• Entrainment 25%
• Theoretical Modeling 25%
• Liquid Droplet 25%
• Two-phase Flow 25%
• Large Uncertainty 25%
• Machine Learning Approach 25%
• Transient Simulation 25%
• Mass Transport Processes 25%
• Droplet Entrainment 25%
• Entrainment Model 25%
• Light Water Reactor 25%
• Heat Flux Condition 25%
• Reflood 25%
• Critical Heat Flux 25%
• Thermal-hydraulic Code 25%
• Simulation Fidelity 25%
• Modeling Strategy 25%
• Heat Transport Mechanism 25%
• U.S. Nuclear Regulatory Commission 25%
• Data-driven Machine Learning 25%
• Pure Data 25%
• Accuracy Reliability 25%
• Power Uprate 25%
• Nuclear Reactor Thermal Hydraulics 25%
• Comprehensive Dataset 25%
• Post-critical 25%
• Rod Bundle Heat Transfer 25%

Engineering

• Liquid Entrainment 100%
• Physics-Informed Machine Learning 100%
• Transport Process 25%
• Two-Phase Flow 25%
• Nuclear Reactor 25%
• Accurate Prediction 25%
• Learning Approach 25%
• Thermal Hydraulics 25%
• Predictive Capability 25%
• Empirical Model 25%
• Rod Bundle 25%
• Bundle Heat 25%
• Liquid Droplet 25%
• Light Water Reactors 25%
• Modeling Strategy 25%
• Learning System 25%
• Heat Flux 25%
• Mass Transport 25%
• United States of America 25%

Chemical Engineering

• Learning System 100%
• Heat Flux 20%
• Mass Transport 20%