Intelligent Diagnosis of Rolling Element Bearings Under Various Operating Conditions Using an Enhanced Envelope Technique and Transfer Learning

Keyphrases

• Operating Conditions 100%
• Rolling Element Bearing 100%
• Transfer Learning 100%
• Intelligent Diagnosis 100%
• Envelope Method 100%
• Fault Detection 40%
• Learning-based 40%
• Diverse Datasets 40%
• Convolutional Neural Network 40%
• Resonance Region 40%
• Industrial Data 40%
• Model Accuracy 40%
• Feature Extraction 20%
• Data Envelopment Analysis 20%
• Envelope Signal 20%
• Outer Race Fault 20%
• Inner Race Fault 20%
• Variable Working Conditions 20%
• Noise Reduction 20%
• Detection Accuracy 20%
• Rolling Element Bearing Faults 20%
• Rotating Machinery 20%
• Rotational Speed 20%
• Fault Type 20%
• Preprocessing Techniques 20%
• System Reliability 20%
• Time Domain Signal 20%
• Fault Characteristics 20%
• Laboratory Data 20%
• Optimal System 20%
• Optimal Performance 20%
• Innovations Algorithm 20%
• Bearing Conditions 20%
• Optimal Filtering 20%
• Rolling Element 20%
• Performance Reliability 20%
• Convolutional Neural Network Model 20%
• Identification Algorithm 20%
• Frequency Spectrum Analysis 20%
• Region Identification 20%
• Signal Frequency 20%
• Filter Selection 20%
• Frequency Domain Spectrum 20%

Engineering

• Rolling Element 100%
• Transfer Learning 100%
• Convolutional Neural Network 60%
• Fault Detection 40%
• Industrial Data 40%
• Feature Extraction 20%
• Time Domain 20%
• Frequency Domain 20%
• Rotational Speed 20%
• Input Signal 20%
• Network Model 20%
• Rotating Machinery 20%
• System Reliability 20%
• Domain Signal 20%
• Optimal Performance 20%
• Frequency Spectrum Analysis 20%

Chemical Engineering

• Transfer of Learning 100%
• Transfer Learning 100%
• Neural Network 60%
• Pattern Recognition 20%
• Feature Extraction 20%
• Operating Variables 20%