Calorific value prediction of coal and its optimization by machine learning based on limited samples in a wide range

Keyphrases

• Artificial Neural Network 100%
• Calorific Value 100%
• Random Forest 100%
• Machine Learning Based 100%
• Limited Samples 100%
• Carbon Content 100%
• Calorific Value Tracking 100%
• Mean Absolute Error 50%
• Performance Prediction 50%
• Hydrogen Content 50%
• Number of Data 50%
• R2 Value 50%
• Nonlinear Model 50%
• Satisfactory Performance 50%
• Random Forest Method 50%
• Artificial Neural Network Method 50%
• Volatile Matter 50%
• Heating Value 50%
• Decision Tree 50%
• Ash Content 50%
• Sulfur Content 50%
• Self-consistent Model 50%
• Multiple Linear Regression Method 50%
• Experimental Determination 50%
• Fixed Carbon 50%
• Value Estimation 50%
• Carbon-sulfur 50%
• Limited Amount of Data 50%
• Hyperparameter Tuning 50%
• Volatile Carbon 50%
• Univariate Equations 50%
• Precision Instrument 50%
• Sample Properties 50%
• Neural Network Method 50%
• Six Parameters 50%

Engineering

• Calorific Value 100%
• Artificial Neural Network 75%
• Random Forest 75%
• Mean Absolute Error 25%
• Simplifies 25%
• Nonlinear Model 25%
• Limited Amount 25%
• Ash Content 25%
• Prediction Performance 25%
• Sulphur Content 25%
• Experimental Determination 25%
• Fixed Carbon 25%

Chemical Engineering

• Neural Network 100%
• Learning System 100%