Development of experimental design approach and ANN-based models for determination of Cr(VI) ions uptake rate from aqueous solution onto the solid biodiesel waste residue

Artificial Intelligence Techniques and Response Surface Methodology for the Optimization of Methyl Ester Sulfonate Synthesis from Used Cooking Oil by Sulfonation

Herein, the impacts of sulfonation temperature (100-120 °C), sulfonation time (3-5 h), and NaHSO₃/methyl ester (ME) molar ratio (1:1-1.5:1 mol/mol) on methyl ester sulfonate (MES) yield were studied. For the first time, MES synthesis via the sulfonation process was modeled using the adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN), and response surface methodology (RSM). Moreover, particle swarm optimization (PSO) and RSM methods were used to improve the independent process variables that affect the sulfonation process. The RSM model (coefficient of determination (R²) = 0.9695, mean square error (MSE) = 2.7094, and average absolute deviation (AAD) = 2.9508%) was the least efficient in accurately predicting MES yield, whereas the ANFIS model (R² = 0.9886, MSE = 1.0138, and AAD = 0.9058%) was superior to the ANN model (R² = 0.9750, MSE = 2.6282, and AAD = 1.7184%). The results of process optimization using the developed models revealed that PSO outperformed RSM. The ANFIS model coupled with PSO (ANFIS-PSO) achieved the best combination of sulfonation process factors (96.84 °C temperature, 2.68 h time, and 0.92:1 mol/mol NaHSO₃/ME molar ratio) that resulted in the maximum MES yield of 74.82%. Analysis of MES synthesized under optimum conditions using FTIR, ¹H NMR, and surface tension determination showed that MES could be prepared from used cooking oil.

Efficient adsorption of hexavalent chromium ions onto novel ferrochrome slag/polyaniline nanocomposite: ANN modeling, isotherms, kinetics, and thermodynamic studies

The current research is concerned with the adsorption behavior of chromium (IV) ions in an aqueous solution using a novel ferrochrome slag/polyaniline nanocomposite (FeCr-PANI) adsorbent. The effect of process parameters such as temperature, pH solution, initial Cr (VI) ions concentration, adsorbent dosage, and contact time on the adsorption process is experimentally investigated in this study. Furthermore, we have trained a multilayer artificial neural network (ANN) using the experimental data of various process parameters to successfully predict the adsorption behavior of chromium (IV) ions onto the FeCr-PANI adsorbent. The ANN model was trained using the Lavenberg-Marquardt algorithm and ten neurons in the hidden layer and was able to estimate the % removal efficiency of chromium (IV) under the influence of different process parameters (R² = 0.991). Initial solution pH was observed to have a significant influence on the % removal efficiency. The % removal efficiency was found to be high at 97.10% for the solution with pH 3 but decreased to 64.40% for the solution with pH 11. Cr (VI) % removal efficiency was observed to increase with an increase in solution temperature, adsorbent dosage, and contact time. However, the % removal efficiency was found to decrease from 96.9 to 54.8% with increasing the initial dye concentration from 100 to 400 ppm. Furthermore, the adsorption capacity increased from 9.69 to 21.93 mg/g with an increase in the initial concentration from 100 to 400 ppm, as expected. The Langmuir isotherm model exhibited the best fit with the experimental data (R² = 0.9977). The maximum adsorption capacity was found to be 22.523 mg g^-1 at 298 K. The experimental data fitted well with the pseudo-second-order kinetic model.

Optimizing Fenton-like process, homogeneous at neutral pH for ciprofloxacin degradation: Comparing RSM-CCD and ANN-GA

Antibiotics are considered among the most non-biodegradable environmental contaminants due to their genetic resistance. Considering the importance of antibiotics removal, this study was aimed at multi-objective modeling and optimization of the Fenton-like process, homogeneous at initial circumneutral pH. Two main issues, including maximizing Ciprofloxacin (CIP) removal and minimizing sludge to iron ratio (SIR), were modeled by comparing central composite design (CCD) based on Response Surface Methodology (RSM) and hybrid Artificial Neural Network-Genetic Algorithm (ANN-GA). Results of simultaneous optimization using ethylene diamine tetraacetic acid (EDTA) revealed that at pH ≅ 7, optimal conditions for initial CIP concentration, Fe²⁺ concentration, [H₂O₂]/[Fe²⁺] molar ratio, initial EDTA concentration, and reaction time were 14.9 mg/L, 9.2 mM, 3.2, 0.6 mM, and 25 min, respectively. Under these optimal conditions, CIP removal and SIR were predicted at 85.2% and 2.24 (gr/M). In the next step, multilayer perceptron (MLP) and radial basis function (RBF) artificial neural networks (ANN) were developed to model CIP and SIR. It was concluded that ANN, especially multilayer perceptron (MLP-ANN) has a decent performance in predicting response values. Additionally, multi-objective optimization of the process was performed using Genetic Algorithm (GA) and Non-dominated Sorting Genetic Algorithm-II (NSGA-II) to maximize CIP removal efficiencies while minimizing SIR. NSGA-II optimization algorithm showed a reliable performance in the interaction between conflicting goals and yielded a better result than the GA algorithm. Finally, TOPSIS method with equal weights of the criteria was applied to choose the best alternative on the Pareto optimal solutions of the NSGA-II. Comparing the optimal values obtained by the multi-objective response surface optimization models (RSM-CCD) with the NSGA-II algorithm showed that the optimal variables in both models were close and, according to the absolute relative error criterion, possessed almost the same performance in the prediction of variables.

Prediction of airborne pollen concentrations by artificial neural network and their relationship with meteorological parameters and air pollutants

After the early rainfall in the autumn of 2013, respiratory syndromes spread in the Khuzestan province of Iran with the most severity in Ahvaz. There have been recurring outbreaks in recent years. Considering that pollen-derived airborne allergens are regarded as key aeroallergens and the main cause of allergic rhinitis and asthma, this work aimed to forecast total pollen concentration in Ahvaz through an artificial neural network (ANN), followed by evaluating the pollen spatial distribution across the city and the association between pollen concentrations and environmental parameters. The utilized ANN in this work included an input layer with 13 parameters, a hidden layer of five neurons, and an output layer. Data were classified into training, validation, and testing sets. The ANN was implemented with 70% and 80% of data for training. The value of the correlation coefficient for the data validation of these two networks was 0.89 and 0.92, respectively. The results also indicated that despite the difference in the mean concentration of the pollens in various areas of Ahvaz, this difference was not statistically significant (P > 0.05). Furthermore, there was a negative correlation between the concentration of total pollen and relative humidity, precipitation, and air pressure. However, it had a positive correlation with temperature. Consequently, considering the logistical challenges of monitoring bioaerosols in the air, the ANN approach could predict total pollen concentrations. Therefore, in addition to measurements, the ANN technique can be a good tool to enable authorities to mitigate the impact of airborne pollen on people.

Performance evaluation of whey flux in dead-end and cross-flow modes via convolutional neural networks

Effluent originating from cheese production puts pressure onto environment due to its high organic load. Therefore, the main objective of this work was to compare the influence of different process variables (transmembrane pressure (TMP), Reynolds number and feed pH) on whey protein recovery from synthetic and industrial cheese whey using polyethersulfone (PES 30 kDa) membrane in dead-end and cross-flow modes. Analysis on the fouling mechanistic model indicates that cake layer formation is dominant as compared to other pore blocking phenomena evaluated. Among the input variables, pH of whey protein solution has the biggest influence towards membrane flux and protein rejection performances. At pH 4, electrostatic attraction experienced by whey protein molecules prompted a decline in flux. Cross-flow filtration system exhibited a whey rejection value of 0.97 with an average flux of 69.40 L/m²h and at an experimental condition of 250 kPa and 8 for TMP and pH, respectively. The dynamic behavior of whey effluent flux was modeled using machine learning (ML) tool convolutional neural networks (CNN) and recursive one-step prediction scheme was utilized. Linear and non-linear correlation indicated that CNN model (R² - 0.99) correlated well with the dynamic flux experimental data. PES 30 kDa membrane displayed a total protein rejection coefficient of 0.96 with 55% of water recovery for the industrial cheese whey effluent. Overall, these filtration studies revealed that this dynamic whey flux data studies using the CNN modeling also has a wider scope as it can be applied in sensor tuning to monitor flux online by means of enhancing whey recovery efficiency.

Application of neural network in metal adsorption using biomaterials (BMs): a review

ANN models for predicting wastewater treatment efficacy of biomaterial adsorbents.

Forecasting PM2.5 concentration using artificial neural network and its health effects in Ahvaz, Iran

The main objective of the present study was to predict the associated health endpoint of PM_2.5 using an artificial neural network (ANN). The neural network used in this work contains a hidden layer with 27 neurons, an input layer with 8 parameters, and an output layer. First, the artificial neural network was implemented with 80% of data for training then with 90% of data for training. The value of R for the data validation of these two networks was 0.80 and 0.83 respectively. The World Health Organization AirQ ⁺ software was utilized for assessing Health effects of PM_2.5 levels. The mean PM_2.5 over the 9-year study period was 63.27(μg/m³), about six times higher than the WHO guideline. However, the PM_2.5 concentration in the last year decreased by about 25% compared to the first year, which is statistically significant (P-value = 0.0048). This reduced pollutant concentration led to a decrease in the number of deaths from 1785 in 2008 to 1059 in 2016. Moreover, a positive correlation was found between PM_2.5 concentration and temperature and wind speed. Considering the importance of predicting PM_2.5 concentration for accurate and timely decisions as well as the accuracy of the artificial neural network used in this study, the artificial neural network can be utilized as an effective instrument to reduce health and economic effects.

Modelling and process optimization for biodiesel production from Nannochloropsis salina using artificial neural network

In the present investigation, calcium oxide solid nanocatalyst derived from the egg shell and Nannochloropsis salina were used for the production of biodiesel. The morphological characteristics and functional groups of synthesized nanocatalyst was characterized by SEM and FTIR analysis. Process variables optimization for biodiesel production was studied using RSM and ANN. The R² values for RSM and ANN was found to be 0.8751 and 0.957 which showed that the model was significantly fit with the experimental data. The maximum FAME conversion for the synthesized nanocatalyst CaO was found to be 86.1% under optimum process conditions (nanocatalyst amount: 3% (w/v); oil to methanol ratio 1:6 (v/v); reaction temperature: 60 °C; reaction time 55 min). Concentration of FAME present in biodiesel was identified by GC-MS analysis.

Rotatable central composite design versus artificial neural network for modeling biosorption of Cr6+ by the immobilized Pseudomonas alcaliphila NEWG-2

Heavy metals, including chromium, are associated with developed industrialization and technological processes, causing imbalanced ecosystems and severe health concerns. The current study is of supreme priority because there is no previous work that dealt with the modeling of the optimization of the biosorption process by the immobilized cells. The significant parameters (immobilized bacterial cells, contact time, and initial Cr6+ concentrations), affecting Cr6+ biosorption by immobilized Pseudomonas alcaliphila, was verified, using the Plackett-Burman matrix. For modeling the maximization of Cr6+ biosorption, a comparative approach was created between rotatable central composite design (RCCD) and artificial neural network (ANN) to choose the most fitted model that accurately predicts Cr6+ removal percent by immobilized cells. Experimental data of RCCD was employed to train a feed-forward multilayered perceptron ANN algorithm. The predictive competence of the ANN model was more precise than RCCD when forecasting the best appropriate wastewater treatment. After the biosorption, a new shiny large particle on the bead surface was noticed by the scanning electron microscopy, and an additional peak of Cr6+ was appeared by the energy dispersive X-ray analysis, confirming the role of the immobilized bacteria in the biosorption of Cr6+ ions.

Machine learning approach for elucidating and predicting the role of synthesis parameters on the shape and size of TiO2 nanoparticles

In the present work a series of design rules are developed in order to tune the morphology of TiO₂ nanoparticles through hydrothermal process. Through a careful experimental design, the influence of relevant process parameters on the synthesis outcome are studied, reaching to the develop predictive models by using Machine Learning methods. The models, after the validation and training, are able to predict with high accuracy the synthesis outcome in terms of nanoparticle size, polydispersity and aspect ratio. Furthermore, they are implemented by reverse engineering approach to do the inverse process, i.e. obtain the optimal synthesis parameters given a specific product characteristic. For the first time, it is presented a synthesis method that allows continuous and precise control of NPs morphology with the possibility to tune the aspect ratio over a large range from 1.4 (perfect truncated bipyramids) to 6 (elongated nanoparticles) and the length from 20 to 140 nm.

Modeling of process intensification of biodiesel production from Aegle Marmelos Correa seed oil using microreactor assisted with ultrasonic mixing

Conventionally, the batch type reactors were used for the production of biodiesel. However, in recent years, the usage of microreactors has started emerging as a significant substitute for biodiesel production due to its higher conversion rate at a short duration. These microreactors have a significantly high surface to volume ratio and high heat-mass transfer rate. The disadvantage of this type of reactors is its low mixing rate of the reagents. This can be overcome with the assistance of ultrasonic mixing. The main objective of this paper is to study the interlaced effect of a continuous flow microreactor and ultrasonic mixing on trans-esterification of Aegle Marmelos Correa seed oil using sodium methoxide catalyst. Results of microreactors with 0.3 mm and 0.8 mm diameter were compared. The effects of process parameters namely, flow rate (2-10 mL/min), reaction temperature (45-65 °C), catalyst amount (0.5-2.5 wt%), oil to methanol molar ratio (1:6-1:18) and ultrasonic mixing time (30-150 s) were studied using response surface methodology (RSM). The biodiesel yield of 98% and 91.8% were obtained for 0.3 mm and 0.8 mm microreactors, respectively. The maximum biodiesel yield observed in 0.3 mm reactor under following optimum conditions: 6.8 mL/min flow rate, 48 °C reaction temperature, 1.3 wt% catalyst, 1:9 oil to methanol molar ratio and 83 s ultrasonic mixing time. The predictive and generalization abilities of RSM and artificial neural network (ANN) models were evaluated and compared. The study showed that ANN and RSM models could predict the yield with an R² value of 0.9955 and 0.9900 respectively. However, the ANN model predicted the yield with the least mean square error value of 0.00001294, which is much lower than RSM.

Application of electro-Fenton process for treatment of composting plant leachate: kinetics, operational parameters and modeling

BACKGROUND

Composting plant leachate is considered as one of the highly polluted wastewaters which is necessary to be treated by simple, economic, fast and environmentally compatible methods. In this study, treatment of fresh composting plant leachate by electro-Fenton (EF) process was investigated.

METHODS

The effect of various input variables like pH (2-7), DC currents (1.5-3 A), H₂O₂ concentrations (theoretical ratio H₂O₂/COD: 0.1-0.6), TDS changes (4-6%), feeding mode, and BOD/COD ratio at the optimal point were studied. The settling characteristics of the waste sludge produced by the treatment (sludge volumes after 30-min sedimentation: V₃₀) were also determined. Artificial neural network (ANN) approach was used for modeling the experimental data.

RESULTS

Based on the results, the best removal rate of COD was obtained at pH: 3, 3 A constant DC current value, 0.6 theoretical ratio H₂O₂/COD and the feeding mode at four step injection. BOD/COD ratio at the optimal point was 0.535 and the maximum COD removal was achieved at TDS = 4%. In the optimal conditions, 85% of COD was removed and BOD/COD ratio was increased from 0.270 to 0.535. The data follow the second-order kinetic (R² > 0.9) and neural network modeling also provided the accurate prediction for testing data.

CONCLUSION

Results showed that EF process can be used efficiently for treatment of composting plant leachate using the proper operating conditions.

Biosorptive removal of Zn(II) ions by Pongamia oil cake (Pongamia pinnata) in batch and fixed-bed column studies using response surface methodology and artificial neural network

Design of experiment and artificial neural networks (ANN) have been effectively employed to predict the rate of uptake of Zn(II) ions onto defatted pongamia oil cake. Four independent variables such as, pH (2.0-7.0), initial concentration of Zn(II) ions (50-500 mg/L), temperature (30ºC-50 °C), and dosage of biosorbent (1.0-5.0 g/L) were used for the batch mode while the three independent variables viz. flowrate, initial concentration of Zn(II) ions and bed height were employed for the continuous mode. Second-order polynomial equations were then derived to predict the Zn(II) ion uptake rate. The optimum conditions for batch studies was found to be pH: 4.45, metal ion concentration: 462.48 mg/L, dosage: 2.88 g/L, temperature: 303 K and on the other hand the column studies flow rate: 5.59 mL/min, metal ion concentration: 499.3 mg/L and bed height: 14.82 cm. Under these optimal condition, the adsorption capacity was 80.66 mg/g and 66.29 mg/g for batch and column studies, respectively. The same data was fed to train a feed-forward multilayered perceptron, using MATLAB to develop the ANN based model. The predictive capabilities of the two methodologies were compared, by means of the absolute average deviation (AAD) (4.57%), model predictive error (MPE) (4.15%), root mean square error (RMSE) (3.19), standard error of prediction (SEP) (4.23) and correlation coefficient (R) (0.99) for ANN and for RSM AAD (16.27%), MPE (21,25%), RMSE (13.15%), SEP and R (0.96) by validation data. The findings suggested that compared to the prediction ability of RSM model, the properly trained ANN model has better prediction ability. In batch studies, equilibrium data was used to determine the isotherm constants and first and second order rate constants. In column, bed depth service time (BDST) and Thomas model was used to fit the obtained column data.

Optimization of multiplex quantitative polymerase chain reaction based on response surface methodology and an artificial neural network-genetic algorithm approach

Multiplex quantitative polymerase chain reaction (qPCR) has found an increasing range of applications. The construction of a reliable and dynamic mathematical model for multiplex qPCR that analyzes the effects of interactions between variables is therefore especially important. This work aimed to analyze the effects of interactions between variables through response surface method (RSM) for uni- and multiplex qPCR, and further optimize the parameters by constructing two mathematical models via RSM and back-propagation neural network-genetic algorithm (BPNN-GA) respectively. The statistical analysis showed that Mg2+ was the most important factor for both uni- and multiplex qPCR. Dynamic models of uni- and multiplex qPCR could be constructed using both RSM and BPNN-GA methods. But RSM was better than BPNN-GA on prediction performance in terms of the mean absolute error (MAE), the mean square error (MSE) and the Coefficient of Determination (R2). Ultimately, optimal parameters of uni- and multiplex qPCR were determined by RSM.

Coupling process study of lipid production and mercury bioremediation by biomimetic mineralized microalgae

Considering the high concentration of mercury in industrial wastewater, such as coal-fired power plants and gold mining wastewater, this research study investigated the coupling process of lipid production and mercury bioremediation using microalgae cells. Chlorella vulgaris modified by biomimetic mineralization. The cultivation was divided in two stages: a natural cultivation for 7days and 5days of Hg²⁺ addition (10-100μg/L) for cultivation at different pH values (4-7) after inoculation. Next, the harvested cells were eluted, and lipid was extracted. The fluorescein diacetate (FDA) dye tests demonstrated that the mineralized layer enhanced the biological activity of microalgae cells in Hg²⁺ contaminated media. Hg distribution tests showed that the Hg removal capacity of modified cells was increased from 62.85% to 94.74%, and 88.72% of eluted Hg²⁺ concentration was observed in modified cells compared to 48.42% of raw cells, implying that more mercury was transferred from lipid and residuals into elutable forms.

Reduction and prediction of N2O emission from an Anoxic/Oxic wastewater treatment plant upon DO control and model simulation

In order to make a better understanding of the characteristics of N₂O emission in A/O wastewater treatment plant, full-scale and pilot-scale experiments were carried out and a back propagation artificial neural network model based on the experimental data was constructed to make a precise prediction of N₂O emission. Results showed that, N₂O flux from different units followed a descending order: aerated grit tank>oxic zone≫anoxic zone>final clarifier>primary clarifier, but 99.4% of the total emission of N₂O (1.60% of N-load) was monitored from the oxic zone due to its big surface area. A proper DO control could reduce N₂O emission down to 0.21% of N-load in A/O process, and a two-hidden-layers back propagation model with an optimized structure of 4:3:9:1 could achieve a good simulation of N₂O emission, which provided a new method for the prediction of N₂O emission during wastewater treatment.

Study on optimization of process parameters for enhancing the multi-hydrolytic enzyme activity in garbage enzyme produced from preconsumer organic waste

The garbage enzymes produced from preconsumer organic waste containing multi hydrolytic enzyme activity which helps to solubilize the waste activated sludge. The continuous production of garbage enzyme and its scaling up process need a globe optimized condition. In present study the effect of fruit peel composition and sonication time on enzyme activity were investigated. Garbage enzyme produced from 6g pineapple peels: 4g citrus peels pre-treated with ultrasound for 20min shows higher hydrolytic enzymes activity. Simultaneously statistical optimization tools were used to model garbage enzyme production with higher activity of amylase, lipase and protease. The maximum activity of amylase, lipase and protease were predicted to be 56.409, 44.039, 74.990U/ml respectively at optimal conditions (pH (6), temperature (37°C), agitation (218 RPM) and fermentation duration (3days)). These optimized conditions can be successfully used for large scale production of garbage enzyme with higher hydrolytic enzyme activity.

Fluoride adsorption by doped and un-doped magnetic ferrites CuCe(x)Fe(2-x)O4: Preparation, characterization, optimization and modeling for effectual remediation technologies

A series of doped and un-doped magnetic adsorbents CuCexFe2-xO4 (x=0.0-0.5) for fluoride were prepared with the micro-emulsion method. Fluoride adsorption was optimized for solution pH, temperature, contact time, and initial concentration and was monitored via normal phase ion chromatography (IC). The effect of concomitant anions was also explored to perform and simulate competitive fluoride adsorption in real water samples. Optimal adsorption was discovered by a simple quadratic model based on central composite design (CCD) and the response surface method (RSM). The adsorption, electrochemical and magnetic properties were compared between doped and un-doped ferrites. Doped ferrites (x=0.1-0.5) were found to be superior to un-doped ferrites (x=0) regarding the active sites, functional groups and fluoride adsorption. The characterization, optimization and application results of the doped ferrites indicated enhanced fluoride adsorption and easy separation with a simple magnet.

Ultrasound assisted biodiesel production from sesame (Sesamum indicum L.) oil using barium hydroxide as a heterogeneous catalyst: Comparative assessment of prediction abilities between response surface methodology (RSM) and artificial neural network (ANN)

The present study estimates the prediction capability of response surface methodology (RSM) and artificial neural network (ANN) models for biodiesel synthesis from sesame (Sesamum indicum L.) oil under ultrasonication (20 kHz and 1.2 kW) using barium hydroxide as a basic heterogeneous catalyst. RSM based on a five level, four factor central composite design, was employed to obtain the best possible combination of catalyst concentration, methanol to oil molar ratio, temperature and reaction time for maximum FAME content. Experimental data were evaluated by applying RSM integrating with desirability function approach. The importance of each independent variable on the response was investigated by using sensitivity analysis. The optimum conditions were found to be catalyst concentration (1.79 wt%), methanol to oil molar ratio (6.69:1), temperature (31.92°C), and reaction time (40.30 min). For these conditions, experimental FAME content of 98.6% was obtained, which was in reasonable agreement with predicted one. The sensitivity analysis confirmed that catalyst concentration was the main factors affecting the FAME content with the relative importance of 36.93%. The lower values of correlation coefficient (R(2)=0.781), root mean square error (RMSE=4.81), standard error of prediction (SEP=6.03) and relative percent deviation (RPD=4.92) for ANN compared to those R(2) (0.596), RMSE (6.79), SEP (8.54) and RPD (6.48) for RSM proved better prediction capability of ANN in predicting the FAME content.

Competitive biosorption of Cr(vi) and Zn(ii) ions in single- and binary-metal systems onto a biodiesel waste residue using batch and fixed-bed column studies

A feasible biosorption process for the removal of Cr(vi) and Zn(ii) ions from single and binary solutions onto a defatted pongamia oil cake (DPOC) was investigated.

Response surface optimization and artificial neural network modeling of biodiesel production from crude mahua (Madhuca indica) oil under supercritical ethanol conditions using CO2 as co-solvent

The present study describes the renewable, environment-friendly approach for the production of biodiesel from low cost, high acid value mahua oil under supercritical ethanol conditions using carbon dioxide (CO₂) as a co-solvent.

Optimizing municipal wastewater treatment plants using an improved multi-objective optimization method

An improved multi-objective optimization (MOO) model was established and used for simultaneously optimizing the treatment cost and multiple effluent quality indexes (including effluent COD, NH4(+)-N, NO3(-)-N) of a municipal wastewater treatment plant (WWTP). Compared with previous models that were mainly based on the use of fixed decision factors and did not taken into account the treatment cost, this model introduces a relationship model based on back propagation algorithm to determine the set of decision factors according to the expected optimization targets. Thus, a more flexible and precise optimization of the treatment process was allowed. Moreover, a MOO of conflicting objectives (i.e., treatment cost and effluent quality) was achieved. Applying this method, an optimal balance between operating cost and effluent quality of a WWTP can be found. This model may offer a useful tool for optimized design and control of practical WWTPs.