Long-Period Dynamic Characteristics of Embedded Track Using Machine Learning

Keyphrases

• Machine Learning 100%
• Dynamic Characteristics 100%
• Embedded Track 100%
• Vibration Response 40%
• Service Life 40%
• Characteristic Changes 20%
• Performance Requirements 10%
• Polymer Materials 10%
• Noise Reduction 10%
• Dynamic Response 10%
• Dynamic Response Analysis 10%
• Fatigue Test 10%
• Performance Change 10%
• Subway 10%
• Clustering Algorithm 10%
• Tram 10%
• Continuous Support 10%
• Sinusoidal Excitation 10%
• Tracking Performance 10%
• Vibration Performance 10%
• Service Process 10%
• System Embedded 10%
• Noise Performance 10%
• Decay Process 10%
• Response Test 10%
• Vibration Noise 10%
• Performance Status 10%
• Whole Life Cycle 10%
• Change Law 10%
• Deep Learning Network 10%
• Label-only 10%
• High-speed Railway 10%
• Maintenance Cycle 10%
• Cycle Fatigue 10%
• Self-supervised Deep Learning 10%
• Continuous Vibration 10%
• Fastener System 10%
• Noise Laws 10%

Engineering

• Learning System 100%
• Service Life 100%
• Lifecycle 50%
• Dynamic Response 50%
• Noise Performance 25%
• Polymer Material 25%
• Railway 25%
• Test Result 25%
• Mechanical Fatigue Test 25%
• Subways 25%
• Sinusoidal Excitation 25%
• Service Process 25%
• Clustering Algorithm 25%
• Performance Requirement 25%
• Cycle Fatigue 25%
• Deep Learning Method 25%