Limited Offer
Save 50% on book bundles
Immediately download your ebook while waiting for your print delivery. No promo code needed.
Artificial Neural Networks in Chemical Engineering processes
From Theory to Applications
- 1st Edition - June 1, 2026
- Language: English
- Paperback ISBN:9 7 8 - 0 - 4 4 3 - 3 2 8 3 2 - 9
- eBook ISBN:9 7 8 - 0 - 4 4 3 - 3 2 8 3 3 - 6
Artificial Neural Networks in Chemical Engineering Processes serves as a comprehensive resource on artificial neural networks within chemical engineering, including understanding… Read more
Purchase options
Institutional subscription on ScienceDirect
Request a sales quoteArtificial Neural Networks in Chemical Engineering Processes serves as a comprehensive resource on artificial neural networks within chemical engineering, including understanding the fundamental principles, learning about relevant algorithms and architectures, and exploring practical case studies. This book covers theoretical principles, relevant algorithms, and practical case studies, this book covers artificial neural network concepts, architectures, and algorithms, with a focus on applications in chemical engineering processes. This book also addressed common challenges by providing practical guidance through successful case studies, offering insights on data pre-processing, model selection, training strategies, and performance evaluation. The book serves as a valuable tool for bridging the gap between neural networks and their practical implementation in chemical engineering. This book will be an invaluable resource for chemical Engineers, particularly researchers and industry professionals working in Machine Learning and Artificial Intelligence. It will also be a very useful guide for Graduate and Postgraduate Students in Chemical Engineering and machine learning. Artificial Neural Networks in Chemical Engineering will also be a valuable resource for anyone working with artificial neural networks in other industries, particularly data scientists and analysts.
• Serves as a comprehensive resource to bridge the gap between theoretical knowledge of neural networks and practical implementation in chemical engineering.
• In-depth explanations of neural network concepts, architectures, and algorithms, with specifics about applications in chemical engineering.
• Outlines various types of artificial neural networks, including feed-forward networks and their applications in chemical engineering processes and systems.
• Practical guidance and case studies showcasing the successful application of neural networks in solving chemical engineering problems.
• Insights into essential aspects such as data pre-processing techniques, model selection, training strategies, and performance evaluation to provide a roadmap for the effective implementation of neural networks in experimental modelling, including code and MATLAB modelling.
• In-depth explanations of neural network concepts, architectures, and algorithms, with specifics about applications in chemical engineering.
• Outlines various types of artificial neural networks, including feed-forward networks and their applications in chemical engineering processes and systems.
• Practical guidance and case studies showcasing the successful application of neural networks in solving chemical engineering problems.
• Insights into essential aspects such as data pre-processing techniques, model selection, training strategies, and performance evaluation to provide a roadmap for the effective implementation of neural networks in experimental modelling, including code and MATLAB modelling.
Chemical Engineers, Researchers in Machine Learning and Artificial Intelligence, Graduate and Postgraduate Students in Chemical Engineering, Industrial Professionals in Chemical Engineering.
Chapter 1: Artificial Neural Networks
1.1. Introduction
1.2. Artificial Neural Networks (ANN)
1.3. Multilayer Perceptron (MLP)
1.4. Radial Basis Function Networks (RBFN)
1.5. Recurrent Neural Networks (RNNs)
1.6. Support Vector Machines/Regression (SVM/SVR)
1.7. Ridge/Lasso/Elastic Net Regression
1.8. Random Forest and Gradient Boosted Trees
1.9. Gradient Boosting Machines (XGBoost, LightGMB)
1.10. Comparative Analysis of Leading Machine Learning Models
1.11. Recent Advances and Future Trends
1.12. Conclusion and Future Prospects
Chapter 2: MATLAB and Python functions of neural networks
2.1. Creating a Neural Network Model using MATLAB
2.1.1. Programming training for MLP, RBF and SVM in MATLAB
2.2. Creating Neural Network Models in Python Import necessary libraries like Keras, PyTorch, scikit-learn for building neural network models.
2.3. Importing the necessary datasets Before creating a neural network model, it is essential to have suitable datasets for training and testing. MATLAB and Python supports importing various data formats, such as Excel spreadsheets, CSV files, or even directly from a database.
2.4. Preprocessing the data
2.5. Defining the neural network architecture
2.6. Configuring the training parameters
2.7. Training the neural network
2.8. Evaluating the trained model
2.8.1. R2, MSE, MAE and RMSE
Chapter 3: Modelling of Absorption Processes using ANNs
3.1. Introduction
3.2. Overview of Absorption Processes
3.2.1. Basic Principles of Absorption
3.2.1.1. Definition and Mechanisms
3.2.1.2. Factors Affecting Absorption
3.2.1.2.2. Temperature and Pressure
3.2.1.2.3. pH and Chemical Environment
3.2.3. Applications of Absorption Processes
3.2.3.1. Industrial Applications
3.2.3.2. Energy-Related Applications
3.3. Applications of Artificial Neural Networks in Absorption Processes
3.3.1. Absorption Efficiency
3.3.2. Process Optimization
3.4. Data Collection and Preprocessing
3.4.1. Modelling Absorption Behaviour
3.5. ANN Architectures for Absorption Processes
3.6. Training and Optimization of ANNs
3.7. Performance Evaluation and Validation
3.8. Case Studies and Examples
3.8.1. Analysis of Mass Transfer of Amine-Based CO2 absorption
3.8.2. Investigating the solubility and absorption kinetics of CO2 absorption into an aqueous solution of 1-diethylamino-2-propanol
3.8.3. ANN for the prediction of deviations in the equilibrium model of CO2 capture by absorption using potassium carbonate
3.8.4. Absorption of carbon dioxide in a packed column via ANN for process simulation.
3.9. Conclusion, Challenges and Future Directions
Chapter 4: Modelling of Adsorption Processes using ANNs
4.1. Introduction
4.1.1. Overview of adsorption processes and their importance in various industries.
4.1.2. Introduction to Artificial Neural Networks (ANNs) and their role in modelling and optimization.
4.1.2.1. Wastewater
4.1.2.2. Gas separation
4.2. Fundamentals of Artificial Neural Networks
4.3. Data Collection and Pre-processing
4.4. ANN Modelling for Adsorption Process Optimization
4.5. ANN-Based Prediction of Adsorption Equilibrium
4.5.1. Adsorption Isotherms
4.6. ANN Modelling for Adsorption Kinetics
4.7. ANN-Based Optimization of Adsorbent Design and Operation
4.7.1. Adsorption Capacity
4.7.2. Sensor data analysis
4.8. Case Studies and Examples
4.8.1 Application of ANNs in Adsorption of Organic Pollutants
4.8.1.1. ANNs for Modelling Adsorption of Heavy Metals
4.8.1.2. Optimization of Adsorbent Material Selection using ANNs
4.8.1.3. ANN-Based Modelling and Control of Dynamic Adsorption Systems
4.8.1.4 Challenges and Future Perspectives in ANN Applications for Adsorption Processes
4.8.2. Application of ANNs in CO2 Adsorption
4.8.2.1. Predictive modelling of CO2 adsorption:
4.8.2.2.Optimization of CO2 adsorption processes:
4.9. Conclusion, Challenges and Future Directions
Chapter 5: Modelling of Extraction Processes using ANNs
5.1. Fundamentals of Extraction Process in Chemical Engineering
5.1.1. Definition and Objectives of Extraction
5.1.2. Types and Applications of Extraction Processes
5.1.3. Challenges and Complexities in Extraction Processes
5.2. Role of Artificial Neural Networks in Extraction Process
5.2.1. Understanding the Functioning of ANNs
5.2.2. Advantages of Using ANNs in Extraction Process
5.2.3. Applications of ANNs in Extraction Process Optimization
5.3. Neural Network Models for Extraction Process Optimization
5.3.1. Data Collection and Pre-processing
5.3.2. Architecture and Design of ANN Models for Extraction Process
5.3.3. Training and Validation of ANN Models
5.3.4. Testing and Evaluation of ANN Models
5.4. Case Studies and Examples
5.4.1. Application of ANN Models for Solvent Extraction
5.4.1.1. Solvent extraction of La(III) using [A336][NO3–] and modelling by ANN
5.4.2. ANN-Based Optimization of Liquid-Liquid Extraction
5.4.3. Predictive Modelling of Extraction Process Parameters using ANNs
5.4.4. Application of an ANN model for the supercritical fluid extraction of seed oil
5.5. Conclusion and Future Directions for Research and Development
Chapter 6: Modelling of Distillation Processes using ANNs
6.1. Introduction to Distillation Processes
6.2. Neural Networks and Their Applications
6.3. Utilizing Artificial Neural Networks in Distillation Processes
6.3.1. Modelling Distillation Processes
6.3.2. Predicting Thermodynamic Properties
6.3.3. Optimal Design and Operation
6.4. Case Studies and Industrial Applications
6.4.1.ANN-Based Control System for Distillation Column
6.4.2. A study on the mass transfer in vacuum membrane distillation process for the treatment of radioactive wastewater via ANN
6.4.3. Utilizing ANN for modelling and simulating the vacuum membrane distillation (VMD) desalination process
6.4.4. Utilizing ANN for the prediction of sulphuric acid solution in the vacuum membrane distillation process
6.4.5. Assisting in the optimization-based design of energy-integrated distillation columns.
6.4.6. Utilizing artificial neural networks for the identification of a packed distillation column for control purposes.
Chapter 7: Modelling of Drying Processes using ANNs
7.1. Types of ANNs commonly used in Drying Processes
7.2. Modelling Drying Processes using ANNs
7.2.1. Data Collection and Preprocessing
7.2.2. Selection of Input and Output Variables
7.2.3. Network Topology and Architecture Design
7.2.4. and Validation of ANN Models
7.2.5. Model Evaluation and Performance Metrics
7.3. Benefits of Using ANNs in Drying Processe
7.3.1. Improved Process Understanding and Prediction
7.3.2. Enhanced Control and Optimization
7.3.3. Reduced Energy Consumption and Environmental Impact
7.3.4. Cost and Time Savings in Experimental Studies
7.4. Case Studies
7.4.1. Application of ANN for Drying Food Products:
7.4.1.1. Utilizing ANN for the modelling of tomato drying process
7.4.1.2. Estimation of moisture ratio for apple drying via ANN
7.4.1.3. Estimation and prediction of temperature and relative humidity in the tobacco drying process using ANNs
7.4.2. Utilizing ANN for Drying of Pharmaceutical Powders
7.4.3. Control of Fluidized Bed Drying Using ANN
7.4.4. Fault Detection in Freeze Drying Process
7.4.5. Utilizing ANN for Biomass Drying
7.5. Applications of Artificial Neural Networks in Drying
7.5.1. Modelling and prediction of drying kinetics
7.5.2. Optimization of drying process parameters
7.5.3. Control strategies for maintaining desired product quality during drying
7.5.4. Monitoring and fault detection in drying systems using ANNs
7.5.5. Integration of ANNs with other advanced techniques in drying processes (e.g., fuzzy logic, genetic algorithms)
7.6. Future Perspectives and Challenges
Chapter 8: Modelling of Leaching processes using ANNs
8.1. Introduction to Leaching
8.1.1. Overview of Leaching Processes
8.1.2. Importance of Optimization in Leaching Operations
8.1.3. Role of Artificial Neural Networks in Leaching Optimization
8.2. Fundamentals of Artificial Neural Networks
8.2.1. Brief Introduction to Artificial Neural Networks (ANNs)
8.2.2. Structure and Functioning of ANNs
8.2.3. Types of ANNs used in Leaching Processes
8.3. Applications of Artificial Neural Networks in Leaching
8.3.1. Predictive Modeling in Leaching
8.3.2. Estimating Metal Recovery Rates
8.3.3. Predicting Concentration Profiles
8.3.4. Forecasting Leaching Efficiency
8.4. Process Optimization using ANNs
8.4.1. Determining Optimal Leaching Parameters
8.4.2. Optimizing Leaching Time and Temperature
8.4.3. Enhancing Selectivity and Recovery
8.5. Quality Control and Fault Detection
8.5.1. Monitoring Leaching Variables
8.5.2. Detecting Anomalies and Outliers
8.5.3. Real-time Process Control
8.6. Data Preparation and ANN Training
8.6.1. Data Collection and Preprocessing
8.6.2. Data Sources and Variables
8.6.3. Data Cleaning and Transformation
8.6.4. Selection of ANN Architectures
8.6.5. Feed-forward Neural Networks
8.6.6. Training and Validation of ANNs
8.6.7. Training Algorithms and Techniques
8.6.8. Cross-validation and Model Evaluation
8.7. Case Studies and Examples
8.7.1. Application of ANN in Gold Leaching Processes
8.7.1.1. Modeling Cyanide Leaching of Gold Ores
8.7.1.2. Optimization of Leaching Parameters
8.7.2. Predictive Modeling for Copper Leaching
8.7.2.1 Estimating Copper Extraction Rates
8.7.2.2. Enhancing Heap Leach Performance
8.7.3 ANN Applications in Uranium Leaching
8.7.3.1 Predicting Uranium Recovery from Ores
8.7.4. Optimizing Acid Consumption in Leaching
8.8. Advantages, Limitations, and Future Perspectives
8.8.1. Advantages of ANNs in Leaching Processes
8.8.2. Challenges and Limitations of ANN Applications
8.8.3. Future Directions and Emerging Trends in ANN-based Leaching Optimization
Chapter 9: Modelling of Thermodynamic Properties using ANNs
9.1. Introduction
9.2. Advantages of ANNs in Thermodynamics
9.3. Applications of ANNs in Thermodynamic Properties
9.3.1. Phase Equilibrium Predictions:
9.3.2. Property Prediction:
9.3.3. Enthalpies and Entropies
9.3.3.1. Predicting Enthalpy of Combustion
9.3.3.2. Predict Standard Enthalpy of Formation of Hydrocarbons
9.3.4. CO2 Solubility
9.3.5. Process Optimization
9.4. Data-Driven Approach
9.5. Thermodynamic study of absorption systems via ANN
9.5.1. Prediction of heat capacity of amine solutions via ANN
9.6. Case studies of CO2 Solubility
9.6.1. Prediction of CO2 solubility in water via ANN
9.6.2. Modeling of CO2 Solubility in mixture of Piperazine (PZ) and Diethanolamine (DEA) Solution via ANN
9.6.3. Prediction of CO2 solubility in methanol solution via ANN
9.6.4. Prediction of CO2 Solubility in Polymers
9.6.5. CO2 Equilibrium Solubility in Three Tertiary Amines via Machine Learning
Chapter 10: Modelling of Vapour Liquid Equilibria systems using ANNs ]
10.1. Introduction to Vapour-Liquid Equilibrium (VLE)
10.1.1 Overview of Vapour-Liquid Equilibrium
10.1.2 Importance of VLE in Chemical Engineering Processes
10.1.3 Challenges in Predicting VLE Behaviour
10.2. Fundamentals of Artificial Neural Networks (ANNs)
10.2.1 Overview of Artificial Neural Networks
10.2.2 Architecture and Components of ANN
10.2.3 Training and Learning Algorithms for ANNs
10.3. Applications of Artificial Neural Networks in VLE Prediction
10.3.1 Use of ANNs for Phase Behaviour Prediction
10.3.2 Development of ANN Models for Binary Systems
10.3.3 Extension of ANN Models to Multicomponent Systems
10.3.4 Incorporating Thermodynamic Models with ANNs
10.4. Data Acquisition and Pre-processing for ANN Modelling
10.4.1 Selection of Training and Testing Datasets
10.4.2 Data Cleaning and Outlier Detection
10.4.3 Feature Selection and Extraction Techniques
10.5. ANN Model Development and Training
10.5.1 Designing the Architecture of an ANN
10.5.2 Initialization and Optimization of ANN Parameters
10.5.3 Training and Validation of the ANN Model
10.5.4 Performance Evaluation of the ANN Model
10.7. Case Studies
10.7.1. Binary VLE Prediction using ANN in Ethanol-Water System
10.7.2. Multicomponent VLE Prediction using ANN in Hydrocarbon Mixture
10.7.2.1. VLLE Predictions in N-Octane/Water Blends via ANN
10.7.2.2. Modelling of ternary acetic acid–n-propyl alcohol–water system via ANN
10.7.3. Azeotropic Systems Description
10.7.3.1. Boiling points of ternary azeotropic mixtures
10.7.3.2. Predicting of viscosity, density, and refractive index of ternary systems containing 1-octyl-3-methyl-imidazolium bis (trifluoromethylsulfonyl) imide via ANN
10.8. ANNs in vapor-liquid equilibrium (VLE) in aqueous solutions of electrolytes
10.8.1. Traditional Approaches to VLE Prediction
10.8.2. Artificial Neural Networks (ANNs)
10.8.2.1. ANNs to predicted VLE for ternary system of NH3-CO2-H2O
10.8.2.2. Vapor–liquid equilibrium data analysis for mixed solvent–electrolyte systems
10.8.2.3. Vapor-Liquid-Liquid Equilibrium (VLLE) Predictions in N-Octane/Water Blends
10.8.2.4. VLE calculation of ternary system: Water, ethanol and 1-butyl-3-methylimidazolium acetate.
10.8.2.5. Prediction of activity coefficient ratio of electrolytes in systems containing amino acids or peptide + water + one electrolyte (NaCl, KCl, NaBr, KBr)
10.9. Conclusion
Chapter 11. Modelling of chemical reactors and reactions using ANNs
11.1 Applications of ANNs in Catalysis
11.1.1 Prediction of catalytic activity
11.1.2 Optimization of catalysis
11.2 Applications of ANNs in Reaction Descriptors and Potential Energy Surface (PES) Prediction
11.2.1 Prediction of reaction descriptors
11.2.2 Prediction of PES for specific reactions and catalysts
11.3 Challenges and Future Prospects
11.3.1 Limits of ANN applications in chemical reactions
11.3.2 Future developments and research directions
11.4 Case Studies and Examples
11.4.1 Practical applications of ANNs in chemical reactions
11.4.2 Successful studies and examples
11.5 Conclusion
Chapter 12. Modelling of pharmaceutical processing using ANNs
12.1 Current pharmaceutical practice in manufacturing solid-dosage oral formulations
12.1.1 Quality-by-Design (QbD) paradigm in pharmaceutical industry
12.1.2 Continuous manufacturing versus batch processing
12.1.3 Unit operations in pharmaceutical manufacturing
12.2 Applications of ANNs in pharmaceutical processing
12.2.1 Prediction of granule size in wet granulation process
12.2.2 Prediction of critical quality attributes in dry granulation
12.2.3 Prediction of residence time distribution in wet granulation
12.2.4 Estimation of solvation energy of pharmaceutical compounds in solvents
12.3 Challenges and Future Prospects
12.3.1 Limits of ANN modeling in pharmaceutical processing
12.3.2 Future developments and research directions
12.4 Conclusion
1.1. Introduction
1.2. Artificial Neural Networks (ANN)
1.3. Multilayer Perceptron (MLP)
1.4. Radial Basis Function Networks (RBFN)
1.5. Recurrent Neural Networks (RNNs)
1.6. Support Vector Machines/Regression (SVM/SVR)
1.7. Ridge/Lasso/Elastic Net Regression
1.8. Random Forest and Gradient Boosted Trees
1.9. Gradient Boosting Machines (XGBoost, LightGMB)
1.10. Comparative Analysis of Leading Machine Learning Models
1.11. Recent Advances and Future Trends
1.12. Conclusion and Future Prospects
Chapter 2: MATLAB and Python functions of neural networks
2.1. Creating a Neural Network Model using MATLAB
2.1.1. Programming training for MLP, RBF and SVM in MATLAB
2.2. Creating Neural Network Models in Python Import necessary libraries like Keras, PyTorch, scikit-learn for building neural network models.
2.3. Importing the necessary datasets Before creating a neural network model, it is essential to have suitable datasets for training and testing. MATLAB and Python supports importing various data formats, such as Excel spreadsheets, CSV files, or even directly from a database.
2.4. Preprocessing the data
2.5. Defining the neural network architecture
2.6. Configuring the training parameters
2.7. Training the neural network
2.8. Evaluating the trained model
2.8.1. R2, MSE, MAE and RMSE
Chapter 3: Modelling of Absorption Processes using ANNs
3.1. Introduction
3.2. Overview of Absorption Processes
3.2.1. Basic Principles of Absorption
3.2.1.1. Definition and Mechanisms
3.2.1.2. Factors Affecting Absorption
3.2.1.2.2. Temperature and Pressure
3.2.1.2.3. pH and Chemical Environment
3.2.3. Applications of Absorption Processes
3.2.3.1. Industrial Applications
3.2.3.2. Energy-Related Applications
3.3. Applications of Artificial Neural Networks in Absorption Processes
3.3.1. Absorption Efficiency
3.3.2. Process Optimization
3.4. Data Collection and Preprocessing
3.4.1. Modelling Absorption Behaviour
3.5. ANN Architectures for Absorption Processes
3.6. Training and Optimization of ANNs
3.7. Performance Evaluation and Validation
3.8. Case Studies and Examples
3.8.1. Analysis of Mass Transfer of Amine-Based CO2 absorption
3.8.2. Investigating the solubility and absorption kinetics of CO2 absorption into an aqueous solution of 1-diethylamino-2-propanol
3.8.3. ANN for the prediction of deviations in the equilibrium model of CO2 capture by absorption using potassium carbonate
3.8.4. Absorption of carbon dioxide in a packed column via ANN for process simulation.
3.9. Conclusion, Challenges and Future Directions
Chapter 4: Modelling of Adsorption Processes using ANNs
4.1. Introduction
4.1.1. Overview of adsorption processes and their importance in various industries.
4.1.2. Introduction to Artificial Neural Networks (ANNs) and their role in modelling and optimization.
4.1.2.1. Wastewater
4.1.2.2. Gas separation
4.2. Fundamentals of Artificial Neural Networks
4.3. Data Collection and Pre-processing
4.4. ANN Modelling for Adsorption Process Optimization
4.5. ANN-Based Prediction of Adsorption Equilibrium
4.5.1. Adsorption Isotherms
4.6. ANN Modelling for Adsorption Kinetics
4.7. ANN-Based Optimization of Adsorbent Design and Operation
4.7.1. Adsorption Capacity
4.7.2. Sensor data analysis
4.8. Case Studies and Examples
4.8.1 Application of ANNs in Adsorption of Organic Pollutants
4.8.1.1. ANNs for Modelling Adsorption of Heavy Metals
4.8.1.2. Optimization of Adsorbent Material Selection using ANNs
4.8.1.3. ANN-Based Modelling and Control of Dynamic Adsorption Systems
4.8.1.4 Challenges and Future Perspectives in ANN Applications for Adsorption Processes
4.8.2. Application of ANNs in CO2 Adsorption
4.8.2.1. Predictive modelling of CO2 adsorption:
4.8.2.2.Optimization of CO2 adsorption processes:
4.9. Conclusion, Challenges and Future Directions
Chapter 5: Modelling of Extraction Processes using ANNs
5.1. Fundamentals of Extraction Process in Chemical Engineering
5.1.1. Definition and Objectives of Extraction
5.1.2. Types and Applications of Extraction Processes
5.1.3. Challenges and Complexities in Extraction Processes
5.2. Role of Artificial Neural Networks in Extraction Process
5.2.1. Understanding the Functioning of ANNs
5.2.2. Advantages of Using ANNs in Extraction Process
5.2.3. Applications of ANNs in Extraction Process Optimization
5.3. Neural Network Models for Extraction Process Optimization
5.3.1. Data Collection and Pre-processing
5.3.2. Architecture and Design of ANN Models for Extraction Process
5.3.3. Training and Validation of ANN Models
5.3.4. Testing and Evaluation of ANN Models
5.4. Case Studies and Examples
5.4.1. Application of ANN Models for Solvent Extraction
5.4.1.1. Solvent extraction of La(III) using [A336][NO3–] and modelling by ANN
5.4.2. ANN-Based Optimization of Liquid-Liquid Extraction
5.4.3. Predictive Modelling of Extraction Process Parameters using ANNs
5.4.4. Application of an ANN model for the supercritical fluid extraction of seed oil
5.5. Conclusion and Future Directions for Research and Development
Chapter 6: Modelling of Distillation Processes using ANNs
6.1. Introduction to Distillation Processes
6.2. Neural Networks and Their Applications
6.3. Utilizing Artificial Neural Networks in Distillation Processes
6.3.1. Modelling Distillation Processes
6.3.2. Predicting Thermodynamic Properties
6.3.3. Optimal Design and Operation
6.4. Case Studies and Industrial Applications
6.4.1.ANN-Based Control System for Distillation Column
6.4.2. A study on the mass transfer in vacuum membrane distillation process for the treatment of radioactive wastewater via ANN
6.4.3. Utilizing ANN for modelling and simulating the vacuum membrane distillation (VMD) desalination process
6.4.4. Utilizing ANN for the prediction of sulphuric acid solution in the vacuum membrane distillation process
6.4.5. Assisting in the optimization-based design of energy-integrated distillation columns.
6.4.6. Utilizing artificial neural networks for the identification of a packed distillation column for control purposes.
Chapter 7: Modelling of Drying Processes using ANNs
7.1. Types of ANNs commonly used in Drying Processes
7.2. Modelling Drying Processes using ANNs
7.2.1. Data Collection and Preprocessing
7.2.2. Selection of Input and Output Variables
7.2.3. Network Topology and Architecture Design
7.2.4. and Validation of ANN Models
7.2.5. Model Evaluation and Performance Metrics
7.3. Benefits of Using ANNs in Drying Processe
7.3.1. Improved Process Understanding and Prediction
7.3.2. Enhanced Control and Optimization
7.3.3. Reduced Energy Consumption and Environmental Impact
7.3.4. Cost and Time Savings in Experimental Studies
7.4. Case Studies
7.4.1. Application of ANN for Drying Food Products:
7.4.1.1. Utilizing ANN for the modelling of tomato drying process
7.4.1.2. Estimation of moisture ratio for apple drying via ANN
7.4.1.3. Estimation and prediction of temperature and relative humidity in the tobacco drying process using ANNs
7.4.2. Utilizing ANN for Drying of Pharmaceutical Powders
7.4.3. Control of Fluidized Bed Drying Using ANN
7.4.4. Fault Detection in Freeze Drying Process
7.4.5. Utilizing ANN for Biomass Drying
7.5. Applications of Artificial Neural Networks in Drying
7.5.1. Modelling and prediction of drying kinetics
7.5.2. Optimization of drying process parameters
7.5.3. Control strategies for maintaining desired product quality during drying
7.5.4. Monitoring and fault detection in drying systems using ANNs
7.5.5. Integration of ANNs with other advanced techniques in drying processes (e.g., fuzzy logic, genetic algorithms)
7.6. Future Perspectives and Challenges
Chapter 8: Modelling of Leaching processes using ANNs
8.1. Introduction to Leaching
8.1.1. Overview of Leaching Processes
8.1.2. Importance of Optimization in Leaching Operations
8.1.3. Role of Artificial Neural Networks in Leaching Optimization
8.2. Fundamentals of Artificial Neural Networks
8.2.1. Brief Introduction to Artificial Neural Networks (ANNs)
8.2.2. Structure and Functioning of ANNs
8.2.3. Types of ANNs used in Leaching Processes
8.3. Applications of Artificial Neural Networks in Leaching
8.3.1. Predictive Modeling in Leaching
8.3.2. Estimating Metal Recovery Rates
8.3.3. Predicting Concentration Profiles
8.3.4. Forecasting Leaching Efficiency
8.4. Process Optimization using ANNs
8.4.1. Determining Optimal Leaching Parameters
8.4.2. Optimizing Leaching Time and Temperature
8.4.3. Enhancing Selectivity and Recovery
8.5. Quality Control and Fault Detection
8.5.1. Monitoring Leaching Variables
8.5.2. Detecting Anomalies and Outliers
8.5.3. Real-time Process Control
8.6. Data Preparation and ANN Training
8.6.1. Data Collection and Preprocessing
8.6.2. Data Sources and Variables
8.6.3. Data Cleaning and Transformation
8.6.4. Selection of ANN Architectures
8.6.5. Feed-forward Neural Networks
8.6.6. Training and Validation of ANNs
8.6.7. Training Algorithms and Techniques
8.6.8. Cross-validation and Model Evaluation
8.7. Case Studies and Examples
8.7.1. Application of ANN in Gold Leaching Processes
8.7.1.1. Modeling Cyanide Leaching of Gold Ores
8.7.1.2. Optimization of Leaching Parameters
8.7.2. Predictive Modeling for Copper Leaching
8.7.2.1 Estimating Copper Extraction Rates
8.7.2.2. Enhancing Heap Leach Performance
8.7.3 ANN Applications in Uranium Leaching
8.7.3.1 Predicting Uranium Recovery from Ores
8.7.4. Optimizing Acid Consumption in Leaching
8.8. Advantages, Limitations, and Future Perspectives
8.8.1. Advantages of ANNs in Leaching Processes
8.8.2. Challenges and Limitations of ANN Applications
8.8.3. Future Directions and Emerging Trends in ANN-based Leaching Optimization
Chapter 9: Modelling of Thermodynamic Properties using ANNs
9.1. Introduction
9.2. Advantages of ANNs in Thermodynamics
9.3. Applications of ANNs in Thermodynamic Properties
9.3.1. Phase Equilibrium Predictions:
9.3.2. Property Prediction:
9.3.3. Enthalpies and Entropies
9.3.3.1. Predicting Enthalpy of Combustion
9.3.3.2. Predict Standard Enthalpy of Formation of Hydrocarbons
9.3.4. CO2 Solubility
9.3.5. Process Optimization
9.4. Data-Driven Approach
9.5. Thermodynamic study of absorption systems via ANN
9.5.1. Prediction of heat capacity of amine solutions via ANN
9.6. Case studies of CO2 Solubility
9.6.1. Prediction of CO2 solubility in water via ANN
9.6.2. Modeling of CO2 Solubility in mixture of Piperazine (PZ) and Diethanolamine (DEA) Solution via ANN
9.6.3. Prediction of CO2 solubility in methanol solution via ANN
9.6.4. Prediction of CO2 Solubility in Polymers
9.6.5. CO2 Equilibrium Solubility in Three Tertiary Amines via Machine Learning
Chapter 10: Modelling of Vapour Liquid Equilibria systems using ANNs ]
10.1. Introduction to Vapour-Liquid Equilibrium (VLE)
10.1.1 Overview of Vapour-Liquid Equilibrium
10.1.2 Importance of VLE in Chemical Engineering Processes
10.1.3 Challenges in Predicting VLE Behaviour
10.2. Fundamentals of Artificial Neural Networks (ANNs)
10.2.1 Overview of Artificial Neural Networks
10.2.2 Architecture and Components of ANN
10.2.3 Training and Learning Algorithms for ANNs
10.3. Applications of Artificial Neural Networks in VLE Prediction
10.3.1 Use of ANNs for Phase Behaviour Prediction
10.3.2 Development of ANN Models for Binary Systems
10.3.3 Extension of ANN Models to Multicomponent Systems
10.3.4 Incorporating Thermodynamic Models with ANNs
10.4. Data Acquisition and Pre-processing for ANN Modelling
10.4.1 Selection of Training and Testing Datasets
10.4.2 Data Cleaning and Outlier Detection
10.4.3 Feature Selection and Extraction Techniques
10.5. ANN Model Development and Training
10.5.1 Designing the Architecture of an ANN
10.5.2 Initialization and Optimization of ANN Parameters
10.5.3 Training and Validation of the ANN Model
10.5.4 Performance Evaluation of the ANN Model
10.7. Case Studies
10.7.1. Binary VLE Prediction using ANN in Ethanol-Water System
10.7.2. Multicomponent VLE Prediction using ANN in Hydrocarbon Mixture
10.7.2.1. VLLE Predictions in N-Octane/Water Blends via ANN
10.7.2.2. Modelling of ternary acetic acid–n-propyl alcohol–water system via ANN
10.7.3. Azeotropic Systems Description
10.7.3.1. Boiling points of ternary azeotropic mixtures
10.7.3.2. Predicting of viscosity, density, and refractive index of ternary systems containing 1-octyl-3-methyl-imidazolium bis (trifluoromethylsulfonyl) imide via ANN
10.8. ANNs in vapor-liquid equilibrium (VLE) in aqueous solutions of electrolytes
10.8.1. Traditional Approaches to VLE Prediction
10.8.2. Artificial Neural Networks (ANNs)
10.8.2.1. ANNs to predicted VLE for ternary system of NH3-CO2-H2O
10.8.2.2. Vapor–liquid equilibrium data analysis for mixed solvent–electrolyte systems
10.8.2.3. Vapor-Liquid-Liquid Equilibrium (VLLE) Predictions in N-Octane/Water Blends
10.8.2.4. VLE calculation of ternary system: Water, ethanol and 1-butyl-3-methylimidazolium acetate.
10.8.2.5. Prediction of activity coefficient ratio of electrolytes in systems containing amino acids or peptide + water + one electrolyte (NaCl, KCl, NaBr, KBr)
10.9. Conclusion
Chapter 11. Modelling of chemical reactors and reactions using ANNs
11.1 Applications of ANNs in Catalysis
11.1.1 Prediction of catalytic activity
11.1.2 Optimization of catalysis
11.2 Applications of ANNs in Reaction Descriptors and Potential Energy Surface (PES) Prediction
11.2.1 Prediction of reaction descriptors
11.2.2 Prediction of PES for specific reactions and catalysts
11.3 Challenges and Future Prospects
11.3.1 Limits of ANN applications in chemical reactions
11.3.2 Future developments and research directions
11.4 Case Studies and Examples
11.4.1 Practical applications of ANNs in chemical reactions
11.4.2 Successful studies and examples
11.5 Conclusion
Chapter 12. Modelling of pharmaceutical processing using ANNs
12.1 Current pharmaceutical practice in manufacturing solid-dosage oral formulations
12.1.1 Quality-by-Design (QbD) paradigm in pharmaceutical industry
12.1.2 Continuous manufacturing versus batch processing
12.1.3 Unit operations in pharmaceutical manufacturing
12.2 Applications of ANNs in pharmaceutical processing
12.2.1 Prediction of granule size in wet granulation process
12.2.2 Prediction of critical quality attributes in dry granulation
12.2.3 Prediction of residence time distribution in wet granulation
12.2.4 Estimation of solvation energy of pharmaceutical compounds in solvents
12.3 Challenges and Future Prospects
12.3.1 Limits of ANN modeling in pharmaceutical processing
12.3.2 Future developments and research directions
12.4 Conclusion
- No. of pages: 500
- Language: English
- Edition: 1
- Published: June 1, 2026
- Imprint: Elsevier
- Paperback ISBN: 9780443328329
- eBook ISBN: 9780443328336