Physics-informed machine learning assisted uncertainty quantification for the corrosion of dissimilar material joints

Keyphrases

• Uncertainty Quantification 100%
• Corrosion 100%
• Galvanic Corrosion 100%
• Physics-informed Machine Learning 100%
• Dissimilar Material Joint 100%
• Electrolyte 66%
• High Performance 33%
• Environmental Factors 33%
• Finite Element 33%
• Physics-based 33%
• Mass Production 33%
• Ferroaluminum 33%
• Geometric Factor 33%
• Shorter Cycle Times 33%
• Reliability Analysis 33%
• Crevice 33%
• Material Needs 33%
• Al-Fe 33%
• Service Life 33%
• Equilibrium Potential 33%
• Electrolyte Conductivity 33%
• Material Loss 33%
• Machine Learning Based 33%
• Corrosion Model 33%
• Al Anode 33%
• Welded Joint 33%
• Surrogate Model 33%
• Corrosion Behavior 33%
• Corrosion Environment 33%
• Service Safety 33%
• Corrosion Performance 33%
• Self-piercing Riveting 33%
• Resistance Spot Welding 33%
• Corrosion Analysis 33%
• Safety Usage 33%
• Corrosion Control 33%

Engineering

• Joints (Structural Components) 100%
• Uncertainty Quantification 100%
• Finite Element Method 14%
• Reliability Analysis 14%
• Service Life 14%
• Adaptability 14%
• Mass Production 14%
• Welds 14%
• Material Loss 14%
• Corrosion Model 14%
• Surrogate Model 14%
• Riveting 14%
• Corrosion Behavior 14%
• Equilibrium Potential 14%
• Resistance Spot 14%
• Spot Welding 14%
• Corrosion Control 14%

Material Science

• Corrosion 100%
• Galvanic Corrosion 42%
• Anode 28%
• Finite Element Method 14%
• Cathode 14%
• Spot Welding 14%