A vibration-based Machine Learning type Structural Health Monitoring methodology for populations of composite aerostructures under uncertainty

Keyphrases

• Learning Styles 100%
• Under Uncertainty 100%
• Machine Learning 100%
• Monitoring Method 100%
• Damage Detection 100%
• Structural Health Monitoring 100%
• Aerostructures 100%
• Vibration-based Method 100%
• Damage Characterization 66%
• Coupons 33%
• Principal Coordinate Analysis (PCoA) 33%
• Structural Dynamics 33%
• Similarity-based 33%
• Damage Classification 33%
• Machine Learning Based 33%
• Multiple-input Single-output 33%
• Damage Level 33%
• Parameter Vector 33%
• Experimental Uncertainty 33%
• Strain Sensor 33%
• Sensor Location 33%
• Impact Damage 33%
• Multiple Models 33%
• Data-driven Model 33%
• Damage Location 33%
• Delamination Damage 33%
• Cosine Similarity 33%
• Materials Manufacturing 33%
• Hypersphere 33%
• Strain Signal 33%
• Subspace Representation 33%
• Temperature Uncertainty 33%
• Vibration Acceleration 33%
• Multi-source Information Fusion 33%
• Manufacturing Temperature 33%
• Unsupervised Machine Learning Algorithms 33%
• Transmittance Function 33%
• Manufacturing Uncertainty 33%

Engineering

• Damage Detection 100%
• Structural Health Monitoring 100%
• Learning System 100%
• Model Parameter 33%
• Similarities 33%
• Single Output 33%
• Machine Learning Algorithm 33%
• Principal Components 33%
• Component Analysis 33%
• Input Multiple 33%
• Experimental Uncertainty 33%
• Parameter Vector 33%
• Location Sensor 33%
• Impact Damage 33%
• Structural Dynamics 33%
• Delamination Damage 33%
• Manufacturing Material 33%

Material Science

• Composite Material 100%
• Structural Dynamics 33%
• Delamination 33%