A Comparative Study on Machine Learning Algorithms for Smart Manufacturing: Tool Wear Prediction Using Random Forests

Keyphrases

• Machine Learning Algorithms 100%
• Random Forest 100%
• Manufacturing Tool 100%
• Least Squares Support Vector Regression (LSSVR) 80%
• Back-propagation Artificial Neural Network (BP-ANN) 60%
• Feed-forward Back-propagation 60%
• Artificial Intelligence 40%
• Manufacturing Systems 40%
• Data-driven Methods 40%
• Prognostic Methods 40%
• Mathematical Model 20%
• Artificial Neural Network 20%
• Machine Learning Techniques 20%
• Physical Understanding 20%
• Rapid Advancement 20%
• Single Hidden Layer 20%
• Forest-based 20%
• Predictive Models 20%
• Prediction Accuracy 20%
• System Behavior 20%
• Regression Forest 20%
• Engineering Fields 20%
• Complex Manufacturing Process 20%
• System of Interest 20%
• Prognostics Management 20%
• Maintenance Management 20%
• Remaining Useful Life 20%
• Classical Model 20%
• Mechanical Failure 20%
• Network Support 20%
• Complex Manufacturing Systems 20%
• Machinery Maintenance 20%

Engineering

• Machine Learning Algorithm 100%
• Manufacturing Tool 100%
• Random Forest 100%
• Smart Manufacturing 100%
• Gas Fuel Manufacture 80%
• Support Vector Machine 80%
• Feedforward 60%
• Artificial Neural Network 60%
• Artificial Intelligence 40%
• Engineering 20%
• Collected Data 20%
• Closed Form 20%
• Experimental Result 20%
• Manufacturing Process 20%
• Accurate Prediction 20%
• System Behavior 20%
• Machine Learning Technique 20%
• Hidden Layer 20%
• Mechanical Failure 20%
• Mathematical Model 20%
• Network Support 20%

Chemical Engineering

• Learning System 100%
• Neural Network 100%
• Support Vector Machine 100%
• Artificial Intelligence 50%