Optimization of dark fermentation for biohydrogen production using a hybrid artificial neural network (ANN) and response surface methodology (RSM) approach

Keyphrases

• Response Surface Methodology 100%
• Biohydrogen Production 100%
• Hybrid Artificial Neural Network 100%
• Dark Fermentation 100%
• Neural Response 100%
• Artificial Neural Network 60%
• Acetic Acid 40%
• Ethanol 40%
• Neural Network Response Surface 40%
• Propionic Acid 40%
• Butyric Acid 40%
• Valeric Acid 40%
• Multiple Objective Optimization 40%
• Statistical Analysis 20%
• Carbon Source 20%
• Training Data 20%
• Operational Parameters 20%
• Hydrogen Production 20%
• Optimal Operating Conditions 20%
• Box-Behnken Design 20%
• Microbes 20%
• Starch 20%
• Biohydrogen 20%
• Novel Hybrids 20%
• Sludge 20%
• Metal Cofactor 20%
• Critical Operations 20%
• Operation Parameters 20%
• Dose Level 20%
• Robust Cost 20%
• Number of Data 20%
• Critical Process Parameters 20%
• Dark Hydrogen Fermentation 20%
• Potato Peel Waste 20%
• Data Matrix 20%
• PH Level 20%
• Starchy Waste 20%
• Hydrogen Production Efficiency 20%
• Hydrogen Generation 20%
• Waste Metal 20%

Engineering

• Artificial Neural Network 100%
• Response Surface Methodology 100%
• Dark Fermentation 100%
• Biohydrogen Production 100%
• Hydrogen Production 40%
• Network Response 40%
• Process Parameter 20%
• Hybrid Approach 20%
• Good Result 20%
• Limited Number 20%
• Significant Change 20%
• Biohydrogen 20%
• Optimal Operating Condition 20%
• Production Performance 20%
• Dose Level 20%
• Objective Optimization 20%

Chemical Engineering

• Neural Network 100%
• Acetic Acid 40%
• Hydrogen Production 40%
• Butyric Acid 40%
• Propionic Acid 40%