Soft Computing Techniques in Solid Waste and Wastewater Management

Section 1 Soft computing applications in wastewater management

1 Wastewater—Sources, Toxicity, and Their Consequences to Human Health
Rama Rao Karri, Gobinath Ravindran and Mohammad Hadi Dehghani

1 Introduction

2 Review of sources

3 Review of pollutants, toxicity, and their consequences to human health
     3.1 Heavy metals
     3.2 Dyes and pigments
     3.3 Pesticides
     3.4 Radioactive materials
     3.5 Arsenic
     3.6 Negative impacts of ammonium

4 Conclusions and future perspectives
References

2 Wastewater Treatment Processes—Techniques, Technologies, Challenges Faced, and Alternative Solutions
Bahram Rezai and Ebrahim Allahkarami

1 Introduction

2 Wastewater treatment processes

3 Primary treatment
     3.1 Screening
     3.2 Comminution
     3.3 Grit removal
     3.4 Sedimentation
     3.5 Coagulation and flocculation
     3.6 Flotation

4 Secondary treatment
     4.1 Suspended growth processes
     4.2 Fixed growth processes

5 Tertiary or advanced treatment
     5.1 Ion exchange
     5.2 Chemical oxidation
     5.3 Activated carbon adsorption
     5.4 Solids removal

6 The challenges faced and future perspectives

7 Summary
References

3 Review of Soft Computing Techniques for Modeling, Design, and Prediction of Wastewater Removal Performance
Priya Banerjee, Rama Rao Karri, Aniruddha Mukhopadhyay and Papita Das

1 Introduction

2 Evolution of soft computing techniques

3 Different methods of soft computing
     3.1 Genetic algorithm (GA)
     3.2 Response surface methodology (RSM)
     3.3 Artificial neural networks (ANNs)
     3.4 Taguchi method
     3.5 Fuzzy logic (FL)
     3.6 Particle swarm optimization (PSO)
     3.7 Support vector machines (SVMs)
     3.8 Support vector regression (SVR)

4 Different algorithms for achieving process optimization

5 Significant parameters optimized for enhancing adsorbent efficiency
     5.1 Effect of solution pH
     5.2 Effect of temperature
     5.3 Effect of initial adsorbate concentration
     5.4 Effect of adsorbent dosage

6 Application of soft computing methodologies for process modeling and optimization

7 Analysis of the efficiency of different soft computing techniques

8 Future application of soft computing techniques for wastewater treatment plants

9 Conclusion
References

4 Application of Neural Networks in Wastewater Degradation Process for the Prediction of Removal Efficiency of Pollutants
Bahram Rezai and Ebrahim Allahkarami

1 Introduction

2 Artificial neural network
     2.1 Model evaluation criteria

3 Application of ANN in modeling wastewater treatment processes
     3.1 Prediction of removal efficiency of heavy metals
     3.2 Prediction of removal efficiency of dyes and pigments
     3.3 Prediction of removal efficiency of pesticides and other organic pollutants

4 Hybrid ANN techniques
     4.1 Combination of ANN with genetic algorithm (GA-ANN)
     4.2 Combination of ANN with particle swarm optimization (PSO-ANN)
     4.3 Combination of ANN with other optimization techniques

5 Summary
References

5 Application of Artificial Neural Networks on Water and Wastewater Prediction: A Review
Ha Manh Bui, Hiep Nghia Bui, Tuan Minh Le and Rama Rao Karri

1 Introduction

2 Artificial neural network (ANN) theory
     2.1 What is an ANN?
     2.2 Network designing in wastewater process
     2.3 Application of ANN on municipal water and wastewater treatment modeling

3 Conclusions
References

6 Application of Bayesian Networks Modeling in Wastewater Management
Abbas Roozbahani

1 Introduction

2 Bayesian network
     2.1 Basics and background
     2.2 Structural and parameter learning
     2.3 BN softwares

3 Applications of BNs in wastewater management
     3.1 Case study 1: Failure prediction of sewer pipes in wastewater networks
     3.2 Case study 2: Prediction analysis of wastewater treatment plants
     3.3 Case study 3: Cost-effective sewer asset management
     3.4 Case study 4: Diagnosis system design for wastewater treatment process
     3.5 Case study 5: Risk analysis of wastewater reuse

4 Conclusion and recommendations
References

7 Pareto Multiobjective Bioinspired Optimization of Neuro-Fuzzy Technique for Predicting Sediment Transport in Sewer Pipe
Isa Ebtehaj, Hossein Bonakdari, Hamed Azimi, Bahram Gharabghi, Seyed Hamed Ashraf Talesh, Ali Jamali and Rama Rao Karri

1 Introduction
     1.1 Overview of open-channel sediment transport
     1.2 Related works
     1.3 Research objective

2 Method
     2.1 Modeling using ANFIS
     2.2 ANFIS design using evolutionary algorithms

3 Methodology
     3.1 Dimensional analysis of sediment transport
     3.2 Modeling sediment transport in pipe channels using ANFIS-EA/SVD
     3.3 Goodness of fit of model performance

4 Results and discussion
     4.1 Finding the optimum model
     4.2 Uncertainty analysis
     4.3 Discrepancy value investigation

5 Conclusions
References

8 Soft Computing Optimization Algorithms and Their Application in Parameter Estimation of a Rigorous Adsorption Kinetics Model
Kannan Aravamudan

1 Introduction

2 Simple adsorption kinetic models

3 Homogeneous surface diffusion model (HSDM)

4 Conventional algorithms
     4.1 Levenberg algorithm
     4.2 Marquardt algorithm
     4.3 Nelder–Mead algorithm

5 Introduction to soft-computing
     5.1 Ant system algorithm
     5.2 Genetic algorithms
     5.3 Simulated annealing algorithm
     5.4 Particle swarm optimization
     5.5 Firefly algorithm
     5.6 Social spider algorithm

6 Elephant herd optimization
     6.1 Initialization of elephants
     6.2 Movements of calf
     6.3 Movements of mother elephant
     6.4 Movements of the matriarch
     6.5 Termination of search
     6.6 Overview of the current elephant herd optimization algorithm
     6.7 Implementation of EHO for estimation of HSDM parameters
     6.8 Validation of Ds estimation
     6.9 Validation of kc estimation
     6.10 Estimation of kc and Ds parameters using different algorithms

7 Summary and conclusions
References

9 Sustainable Management of Wastewater Treatment Plants Using Artificial Intelligence Techniques
Mahmoud Nasr, Karam Mohamed, Michael Attia and Mona G. Ibrahim

1 Introduction

2 Survey on recent studies

3 Modeling techniques in the context of wastewater treatment

4 Wastewater treatment processes

5 Artificial neural networks (ANNs)

6 Fuzzy logic (FL)

7 Adaptive neuro-fuzzy inference system (ANFIS)

8 Recommendations

9 Conclusions
References

10 Modeling Wastewater Treatment Process: A Genetic Programming Approach
C Sivapragasam, Naresh K Sharma and S Vanitha

1 Introduction

2 Soft computing methods
     2.1 Artificial neural network (ANN)
     2.2 Genetic programming
     2.3 Comparative note on ANN and GP

3 Case studies
     3.1 Constructed wetlands
     3.2 Bioreactor performance modeling

4 Conclusion
References

Section 2 Soft computing applications in solid waste management

11 Solid Waste—Sources, Toxicity, and Their Consequences to Human Health
Mohammad Hadi Dehghani, Ghasem Ali Omrani and Rama Rao Karri

1 Introduction
     1.1 Definition and classification of municipal solid waste production sources
     1.2 Classification of solid waste components

2 Health effects due to unsanitary disposal of municipal waste

3 Environmental effects due to unsanitary disposal of municipal wastes
     3.1 Water pollution
     3.2 Soil pollution
     3.3 Air pollution

4 Industrial and hazardous waste

5 Radioactive wastes

6 Electronic wastes

7 Health-care wastes

8 Environmental impacts of incinerators

9 Conclusion
References

12 Solid Waste Treatment: Technological Advancements and Challenges
Vinay Pratap, Sakina Bombaywala, Ashootosh Mandpe and Saif Ullah Khan

1 Introduction
     1.1 An integrated solid waste management framework
     1.2 Issues in solid waste management
     1.3 Indian scenario of municipal solid waste treatment

2 Solid waste treatment technologies
     2.1 Mechanical and biological method

3 Models in solid waste management
     3.1 Role of life cycle assessment in solid waste treatment

4 Circular economy in waste management

5 Legal framework for solid waste management

6 Conclusion and future perspectives
References

13 Solid Waste Treatment Processes and Remedial Solution in the Developing Countries
O.O. Ayeleru and P.A. Olubambi

1 Introduction

2 Area of the study

3 Municipal solid waste generation and management globally
     3.1 Municipal solid waste generation and management in Africa
     3.2 Waste classification
     3.3 Current municipal solid waste handling techniques in the developing countries
     3.4 Current methods for managing solid waste globally
     3.5 Remedial measure to avert the effect of municipal solid waste

4 Conclusion
References

14 Soft Computing Applications in Municipal Solid Waste Forecast: A Short Review
O.O. Ayeleru, L.I. Fajimi, B.O. Oboirien and P.A. Olubambi

1 Introduction

2 Soft computing techniques in solid waste management
     2.1 Linear regression approach
     2.2 Time series approach
     2.3 Neural network approach
     2.4 Supported vector machine (SVM) approach
     2.5 Adaptive neuro-fuzzy inference system (ANFIS) approach
     2.6 Decision tree approach
     2.7 Gradient boosted regression tree (GBRT) approach
     2.8 k-Nearest neighbor (k-NN) approach

3 Evaluation metrics

4 Results

5 Conclusion
References

15 Dynamic Multi-objective Optimization of Integrated Waste Management Using Genetic Algorithms
Mohamed Abdallah, Zakiya Rahmat-Ullah and Abdulrahman Metawa

1 Introduction

2 Optimization framework
     2.1 Management strategies
     2.2 Modeling parameters
     2.3 Single-objective optimization
     2.4 Multi-objective optimization
     2.5 Genetic algorithm

3 Case study: inputs, results, and discussion
     3.1 Input parameters
     3.2 Single-objective optimization
     3.3 Multi-objective optimization

4 Conclusions
References

16 Prediction of Effluent Chemical Oxygen Demand and Suspended Solids From a Domestic Wastewater Treatment Plant Using SVM and ANN
Sakaa Bachir, Boudibi Samir, Chaffai Hicham and Hani Azzedine

1 Introduction

2 Literature reviews of artificial intelligence related to wastewater treatment

3 Materials and methods
     3.1 Study area and data description
     3.2 Support vector machine (SVM)
     3.3 Performance evaluation

4 Results and discussion

5 Conclusion
References

17 Artificial Intelligence Models for Forecasting of Municipal Solid Waste Generation
Rahul Mishra, Ekta Singh, Aman Kumar and Sunil Kumar

1 Introduction

2 Artificial intelligence models
     2.1 Artificial neural network (ANN)
     2.2 Adaptive neuro-fuzzy interference systems (ANFIS)
     2.3 Genetic algorithm (GA)
     2.4 Gray model (1, 1)
     2.5 Support vector machine (SVM)
     2.6 Linear regression (LR) analysis
     2.7 k-Nearest neighbors (kNN)
     2.8 Discrete wavelet theory (DWT)
     2.9 Hybrid models

3 Application areas
     3.1 Solid waste characteristics prediction
     3.2 Bin level detection
     3.3 Vehicle routing
     3.4 Waste management planning

4 Conclusion
References

18 A Design Framework for an Integrated End-of-Life Vehicle Waste Management System in Malaysia
Norazli Othman, Atikah Razali, Shreeshivadasan Chelliapan, Roslina Mohammad and Hesam Kamyab

1 Introduction

2 Materials and methods
     2.1 Scope of study
     2.2 Study site
     2.3 Data collection

3 Results and analysis
     3.1 Reliability test and descriptive analysis
     3.2 ELV-generated factor
     3.3 ELV disposal factor
     3.4 Mapping ELV flows at residential, commercial, and industrial premises
     3.5 Proposed design framework for integrated ELV waste management

4 Conclusion
References

19 Effect of Normalization Protocol on Pulping Process Selection Using TOPSIS Multicriteria Decision-Making Method—A Case Study of Palm Oil Empty Fruit Bunches
Kumar Anupam, Pankaj Kumar Goley and Anil Yadav

1 Introduction

2 Research methodology
     2.1 Data collection
     2.2 Calculation of weights by entropy method
     2.3 Executing procedure of TOPSIS
     2.4 Assessment of normalization protocols

3 Results and discussion
     3.1 Weights of POEFB organosolv pulping criteria
     3.2 Evaluation of POEFB organosolv pulping processes using TOPSIS
     3.3 Selection of suitable normalization protocol

4 Conclusion
References

20 Long-Term Solid Waste Quantity Prediction Using AI-Based Models, Considering Climate Change Impact—A Case Study
Aida H. Baghanam, Vahid Nourani and Koorosh Shakoori

1 Introduction

2 Materials and methods
     2.1 Study area
     2.2 Used data
     2.3 Proposed methodology
     2.4 Artificial neural network
     2.5 Least square support vector machines
     2.6 Wavelet transform
     2.7 Model evaluation criteria

3 Results and discussion
     3.1 Time series analysis and preprocessing results
     3.2 Calibration of AI-based models
     3.3 ANN-based simulation model for future

4 Conclusion
References

Section 3 Application of soft computing techniques for process modeling, optimisation and control of waste water and solid waste

21 Process Optimization and Modeling of Hydraulic Fracturing Process Wastewater Treatment Using Aerobic Mixed Microbial Reactor via Response Surface Methodology
Thirugnanasambandham Karchiyappan and Rama Rao Karri

1 Introduction

2 Materials and methods
     2.1 Characteristics of wastewater obtained from hydraulic fracturing process
     2.2 Inoculum and acclimatization
     2.3 Experimental design
     2.4 Different design of experiments (DOE) approaches
     2.5 RSM-BBD framework
     2.6 Analytical method
     2.7 Kinetic studies

3 Results and discussion
     3.1 Microbial characterization
     3.2 Evaluation of process variables on the COD degradation
     3.3 Statistical analysis of response surface model
     3.4 Interactive effect of process variables on the COD degradation
     3.5 Optimization of process variables to enhance the COD degradation
     3.6 Kinetic modeling of COD degradation using mixed culture

4 Review of relevant studies

5 Conclusion
References

22 Modeling Undefined Complexities of Wastewater Treatment Processes With Artificial Neural Network
M. Mansoor Ahammed and Mahesh Gadekar

1 Introduction

2 Artificial neural network fundamentals
     2.1 Structure of artificial neural network
     2.2 Evaluation of ANN model performance
     2.3 Backpropagation algorithms
     2.4 Sensitivity analysis

3 Application of ANN in modeling wastewater treatment processes
     3.1 Application in heavy metal and dye removal
     3.2 Application in anaerobic treatment processes
     3.3 Use of hybrid methods in modeling
     3.4 Use of RSM-ANN in modeling wastewater treatment processes

4 Concluding remarks
References

23 Optimization of Process Conditions in Wastewater Degradation Process
Saeed Shojaei and Siroos Shojaei

1 Introduction

2 Challenges for water purification across the world

3 Wastewater treatment methods
     3.1 Wastewater treatment types

4 Optimization of process conditions
     4.1 Experimental design objectives
     4.2 Experimental factors
     4.3 Selection of responses
     4.4 Interactions
     4.5 Response functions
     4.6 Factorial designs
     4.7 Design of experiments through Taguchi method
     4.8 Taguchi philosophy deals with the following points
     4.9 Designing experiments by Design–Expert software
     4.10 Multigoal optimization in experiment
     4.11 Comparison of adsorbents for various dyes removal (case study)

5 Conclusion and future perspective
References

24 System Control and Optimization in Wastewater Treatment: A Particle Swarm Optimization (PSO) Approach
Xudong Ye, Bing Chen, Rune Storesund and Baiyu Zhang

1 Introduction

2 Concepts of particle swarm optimization and literature reviews
     2.1 Concepts of particle swarm optimization
     2.2 Literature reviews of particle swarm optimization on wastewater treatment studies

3 Methodologies on multiagent hybrid particle swarm optimization (MAHPSO)

4 Application of MAHPSO for WWTN planning
     4.1 Description of the case study
     4.2 WWTN model description

5 Results and discussion
     5.1 Optimal plan of WWTN
     5.2 Comparison with GA and HPSO

6 Conclusion
References

25 Fuzzy Logic Control of Active Sludge–Based Wastewater Treatment Plants
Abdul Gaffar Sheik, S. Murali Mohan and A. Seshagiri Rao

1 Introduction

2 WWTP layout and methodology
     2.1 Description of process and WWTP structure
     2.2 Model attributes
     2.3 Temperature effect: model-based approach

3 Evaluation criterion
     3.1 Assessment of plant criteria
     3.2 Evaluation of plant performance
     3.3 Illustration of process control
     3.4 Fuzzy control design for WWTPs

4 Simulations and results

5 Conclusions
References

26 Development of Smart AnAmmOx System and Its Agile Operation and Decision Support for Pilot-Scale WWTP
Alam Nawaz, Amarpreet Singh Arora, Choa Mun Yun, Jung June Lee and Moonyong Lee

1 Introduction

2 Pilot-scale AnAmmOx SBR system
     2.1 AnAmmOx SBR process flow at pilot scale
     2.2 AnAmmOx SBR system

3 Mathematical modeling and computational analysis
     3.1 Mathematical model development and system simulation
     3.2 Decision support for optimal operation

4 Smart AnAmmOx SBR architecture
     4.1 Detailed module functionality

5 Conclusions and future prospects
References

27 Prediction of Ammonium Removal by Biochar Produced From Agricultural Wastes Using Artificial Neural Networks: Prospects and Bottlenecks
Ngoc-Thuy Vu and Khac-Uan Do

1 Introduction

2 ANN developed to predict ammonium removal
     2.1 ANN model
     2.2 ANN basic structure
     2.3 Development of ANN model
     2.4 Characteristics of ANN model for ammonium prediction

3 Evaluation of ANN for ammonium prediction
     3.1 Data used for ANN modeling
     3.2 Estimation of mean square error
     3.3 Optimization of ANN model
     3.4 ANN training algorithm
     3.5 ANN used to predict ammonium removal under different affecting factors

4 Perspective of ANN for the prediction of ammonium by biochar

5 Conclusions and recommendations
References

28 Multiscenario Approach for Capturing Uncertainties in Energy-Integrated Autothermal Thermophilic Aerobic Digestion Systems
Elisaveta Kirilova, Rayka Vladova, and Natasha Vaklieva-Bancheva

1 Introduction

2 Two-stage stochastic optimization
     2.1 General conception
     2.2 BASIC GA—optimization method

3 Analysis of the possibilities for heat integration of the flows in a conventional ATAD system
     3.1 Industrial data
     3.2 Analysis of the opportunities for energy integration

4 Determination of heat integration framework

5 Mathematical models describing the heat integration

6 Including the heat integration superstructure within a two-stage stochastic optimization problem
     6.1 Analysis of the energy integration efficiency at the boundaries of stochastic space
     6.2 Approximation of the stochastic space
     6.3 Defining the first- and the second-stage variables
     6.4 Stochastic model, constraints and objective function

7 Optimization results and discussion

8 Verification of the approach

9 Conclusions
References

Index