Three-stage hybrid fault diagnosis for rolling bearings with compressively sampled data and subspace learning techniques

Keyphrases

• Bearing Fault 50%
• Bearing Fault Diagnosis 50%
• Compressive Measurement 50%
• Compressive Sampling 100%
• Computation Time 50%
• Concatenated 100%
• Data Learning 100%
• Feature Learning 50%
• High Classification Accuracy 50%
• Hybrid Fault Diagnosis 100%
• Hybrid Method 50%
• Learning Algorithm 50%
• Learning Techniques 100%
• One-class Support Vector Machine (OCSVM) 50%
• Processing Time 50%
• Reduced Computation 50%
• Rolling Bearing 100%
• Sampled Signals 100%
• Storage Requirement 100%
• Subspace Learning 100%
• Time Requirement 50%
• Vibration Data 50%

Engineering

• Bearing Fault Diagnosis 50%
• Classification Accuracy 50%
• Compressive Sampling 100%
• Computation Time 50%
• Fault Diagnosis 100%
• Hybrid Method 50%
• Learning Algorithm 50%
• Learning Technique 100%
• Processing Time 50%
• Rolling Bearings 100%
• Sampled Data 100%
• Sampled Signal 100%
• Storage Requirement 100%
• Support Vector Machine 50%

Chemical Engineering

• Support Vector Machine 100%