Fatigue damage detection of aerospace-grade aluminum alloys using feature-based and feature-less deep neural networks

Keyphrases

• Aluminum Alloy 100%
• Feature-based 100%
• Aerospace 100%
• Deep Neural Network 100%
• Fatigue Damage Assessment 100%
• Black Box 66%
• Ultrasonic Data 66%
• Deep Learning Architectures 66%
• Time Series Data 33%
• Reliable Operation 33%
• Autocorrelation 33%
• Numerical Modeling 33%
• Signal Processing Techniques 33%
• Damage Detection 33%
• A-Si 33%
• Most Common Cause 33%
• Fatigue Failure 33%
• Fatigue Damage 33%
• Continuous Monitoring 33%
• Human Supervision 33%
• Fatigue Testing 33%
• Similar Problem 33%
• Failure Cause 33%
• Network Use 33%
• Deep Learning 33%
• Fatigue Crack Detection 33%
• Testing Apparatus 33%
• Deep Network 33%

Engineering

• Fatigue Damage 100%
• Damage Detection 100%
• Deep Neural Network 100%
• Ultrasonics 50%
• Black Box 33%
• Neural Network Architecture 33%
• Reliable Operation 16%
• Processing Method 16%
• Frequency Domain 16%
• Fatigue Crack 16%
• Numerical Modeling 16%
• Data Series 16%
• Crack Detection 16%
• Fatigue Failure 16%
• Simplifies 16%
• Continuous Monitoring 16%
• Fatigue Testing 16%
• Using Sensor 16%
• Field Operation 16%
• Deep Learning Method 16%

Material Science

• Fatigue Damage 100%
• Aluminum Alloy 100%
• Aluminum 33%
• Crack Detection 33%
• Fatigue Crack 33%