An Adaptive Parallel Feature Learning and Hybrid Feature Fusion-Based Deep Learning Approach for Machining Condition Monitoring

Keyphrases

• Learned Features 100%
• Deep Learning Methods 100%
• Feature Learning 100%
• Machining Condition Monitoring 100%
• Hybrid Feature Fusion 100%
• Importance Weighting 66%
• Adaptive Features 66%
• Industrial Internet of Things (IIoT) 66%
• Parallel Feature Extraction 66%
• Space Domain 66%
• Handcrafted Features 66%
• Rapid Development 33%
• Model Performance 33%
• System Status 33%
• Data-driven Methods 33%
• Information Communication Technology 33%
• Feature Representation 33%
• Sensing Technology 33%
• Highest Weight 33%
• Multiple Domains 33%
• Single Domain 33%
• Sparse Autoencoder 33%
• Attention Module 33%
• Internet of Things Environment 33%
• Automatic Feature Learning 33%
• Abstract Features 33%
• Condition Monitoring Data 33%
• Real-life Case Studies 33%
• Data-driven Paradigm 33%

Computer Science

• Deep Learning Method 100%
• Representation Learning 100%
• Feature Fusion 100%
• Learning Approach 100%
• Condition Monitoring 100%
• Industrial Internet of Things 50%
• Domain Knowledge 50%
• Feature Extraction 50%
• Performance Model 25%
• System Condition 25%
• Multiple Domain 25%
• Learned Feature 25%
• Rapid Development 25%
• Case Study 25%
• Monitoring Data 25%
• Information and Communication Technology 25%
• Sparse Autoencoder 25%

Engineering

• Learning Approach 100%
• Condition Monitoring 100%
• Deep Learning Method 100%
• Feature Extraction 50%
• Industrial Internet 50%
• Domain Knowledge 50%
• Internet-Of-Things 50%
• Real Life 25%
• Limitations 25%
• Information and Communication Technologies 25%
• Monitoring Data 25%
• Autoencoder 25%