Modelling of lead adsorption from industrial sludge leachate on red mud by using RSM and ANN

Geyikçi, Feza; Kılıç, Erdal; Çoruh, Semra; Elevli, Sermin

doi:10.1016/j.cej.2011.12.019

Cited by 188 publications

(64 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, the ANN model is more flexible and predictable which allows the addition of a new set of experiment to build a new dependable model. This is because the RSM model has the limitation where it assumes only quadratic non-linear correlation whilst the ANN model overcomes this limitation since this model can inherently capture almost any complex and non-linear process (Bingol et al, 2012;Geyikci et al, 2012). (Ghosh et al, 2015) (C) (Bingol et al, 2012).…”

Section: Comparison Of Rsm and Annmentioning

confidence: 99%

Predicting the capability of carboxylated cellulose nanowhiskers for the remediation of copper from water using response surface methodology (RSM) and artificial neural network (ANN) models

Hamid

Jenidi

Thielemans

et al. 2016

Industrial Crops and Products

View full text Add to dashboard Cite

This study observed the influence of temperature, initial Cu(II) ion concentration, and sorbent dosage on the Cu(II) removal from the water matrix using surface-oxidized cellulose nanowhiskers (CNWs) bearing carboxylate functionalities. In addition, this study focused on the actual conditions in a wastewater treatment plant. Conductometric titration of CNWs suspensions showed a surface charge of 54 and 410 mmol/kg for the unmodified and modified CNWs, respectively, which indicated that the modified CNWs provide a relatively high surface area per unit mass than the unmodified CNWs. In addition, the stability of the modified CNWs was tested under different conditions and proved that the functional groups were permanent and not degraded. Response surface methodology (RSM) and artificial neural network (ANN) models were employed in order to optimize the system and to create a predictive model to evaluate the Cu(II) removal performance of the modified CNWs. The performance of the ANN and RSM models were statistically evaluated in terms of the coefficient of determination (R 2 ), 2 absolute average deviation (AAD), and the root mean squared error (RMSE) on predicted experiment outcomes. Moreover, to confirm the model suitability, unseen experiments were conducted for 14 new trials not belonging to the training data set and located both inside and outside of the training set boundaries. Result showed that the ANN model (R 2 =0.9925, AAD = 1.15%, RMSE = 1.66) outperformed the RSM model (R 2 =0.9541, AAD = 7.07%, RMSE = 3.99) in terms of the R 2 , AAD, and RMSE when predicting the Cu (II) removal and is thus more reliable. The Langmuir and Freundlich isotherm models were applied to the equilibrium data and the results revealed that Langmuir isotherm (R 2 = 0.9998) had better correlation than the Freundlich isotherm (R 2 = 0.9461). Experimental data were also tested in terms of kinetics studies using pseudo-first order and pseudo-second order kinetic models. The results showed that the pseudo-second-order model accurately described the kinetics of adsorption.

show abstract

Section: Comparison Of Rsm and Annmentioning

confidence: 99%

Predicting the capability of carboxylated cellulose nanowhiskers for the remediation of copper from water using response surface methodology (RSM) and artificial neural network (ANN) models

Hamid

Jenidi

Thielemans

et al. 2016

Industrial Crops and Products

View full text Add to dashboard Cite

show abstract

“…ANN resembles the functioning of the human brain, demonstrating the ability to learn, recall and standardizes from training patterns or data [19] through interconnected computing elements [20]- [23]. ANN adapts to experimental test results, empirical data or theoretical results [24], tolerates approximate or imprecise data, gets continuously trained (or retrained), solves complex problems and provides accurate predictive solutions [19], [22]- [23], [25]- [27].…”

Section: Steelmentioning

confidence: 99%

Modeling and Prediction of Flexural Strength of Hybrid Mesh and Fiber Reinforced Cement-Based Composites Using Artificial Neural Network (Ann)

Sakthivel¹

2016

geomate

View full text Add to dashboard Cite

ABSTRACT:In this paper, Artificial Neural Network (ANN) has been used to predict the equivalent flexural strength of hybrid mesh and fiber reinforced cement-based composites (HMFRCBC). Three ANN models (Models 1, 2 and 3) were developed for predicting the flexural strength of cement-based composites. Model 1 used 48 data of the previously published data of the present authors and Model 2 used 48 data (out of the 75 ANN validated data) from previous studies related to mesh reinforced cement-based composites. Model 3 with 98 data (combined data sets of Model 1 and Model 2) employed seven input parameters, namely the width and depth of slab, cylinder compressive strength, mesh ultimate strength, mesh volume fraction, fiber volume fraction, fiber ultimate strength, and an output, the ultimate flexural strength of mesh and fiber reinforced cement based composites. Hidden layer was fixed based on 5 trial runs for Models 1 and 2, and 10 trial runs for Model 3. All the three models (Models 1, 2 and 3) were trained with 80% of the data, and tested with balance 20% of the data. For Models 1, 2 and 3, the Lowest Individual Error (LIE) of 11.18%, 6.95% and 11.56% (respectively) is achieved in Trial Run No.1.4 (with I-H-O, Input-Hidden Neurons-Output of 5-6-1), Trial Run No.2.2 (5-4-1) and Trial Run No.3.7 (7-10-1) respectively. Also, the lowest absolute average deviation (AAD%) of 4.81%, 3.51% and 4.58% (respectively); lowest Root Mean Square Error (RMSE) of 0.86, 0.76 and 0.99 (respectively); and highest R 2 of 0.933, 0.988 and 0.975 (respectively) are seen for these trials 1.4, 2.2, 3.7 in Models 1, 2 and 3 respectively. All the three ANN models were found to be in good agreement with actual results, and these three ANN models can serve as simple but reliable predictive tools in determination of flexural strength of HMFRCBC.

show abstract

“…Therefore, in this study, spent tea leaves were modified with alkali and used as biosorbent for the removal of Cu(II) from aqueous solutions. Nowadays, response surface methodology (RSM) and artificial neural network (ANN) methods are jointly applied by researchers worldwide to predict the adsorption/biosorption behavior in solid-liquid systems (Geyikci et al 2012;Bingol et al 2012). The concurrent application of both techniques allows researchers to compare the results of different modeling approaches and to better understand their process under investigation (Geyikci et al 2012).…”

Section: Introductionmentioning

confidence: 99%

“…Nowadays, response surface methodology (RSM) and artificial neural network (ANN) methods are jointly applied by researchers worldwide to predict the adsorption/biosorption behavior in solid-liquid systems (Geyikci et al 2012;Bingol et al 2012). The concurrent application of both techniques allows researchers to compare the results of different modeling approaches and to better understand their process under investigation (Geyikci et al 2012). Thus, in the present study, a two-level three-factor (2 3 ) full factorial central composite design (CCD) in RSM and ANN-based models were developed to predict the relationship between the experimental variables (pH, biosorbent dose and contact time) on the biosorption efficiency (response variable).…”

Section: Introductionmentioning

confidence: 99%

Modeling of biosorption of Cu(II) by alkali-modified spent tea leaves using response surface methodology (RSM) and artificial neural network (ANN)

2014

View full text Add to dashboard Cite

In the present work, spent tea leaves were modified with Ca(OH) 2 and used as a new, non-conventional and low-cost biosorbent for the removal of Cu(II) from aqueous solution. Response surface methodology (RSM) and artificial neural network (ANN) were used to develop predictive models for simulation and optimization of the biosorption process. The influence of process parameters (pH, biosorbent dose and reaction time) on the biosorption efficiency was investigated through a twolevel three-factor (2 3 ) full factorial central composite design with the help of Design Expert. The same design was also used to obtain a training set for ANN. Finally, both modeling methodologies were statistically compared by the root mean square error and absolute average deviation based on the validation data set. Results suggest that RSM has better prediction performance as compared to ANN. The biosorption followed Langmuir adsorption isotherm and it followed pseudo-second-order kinetic. The optimum removal efficiency of the adsorbent was found as 96.12 %.

show abstract

Modelling of lead adsorption from industrial sludge leachate on red mud by using RSM and ANN

Cited by 188 publications

References 37 publications

Predicting the capability of carboxylated cellulose nanowhiskers for the remediation of copper from water using response surface methodology (RSM) and artificial neural network (ANN) models

Predicting the capability of carboxylated cellulose nanowhiskers for the remediation of copper from water using response surface methodology (RSM) and artificial neural network (ANN) models

Modeling and Prediction of Flexural Strength of Hybrid Mesh and Fiber Reinforced Cement-Based Composites Using Artificial Neural Network (Ann)

Modeling of biosorption of Cu(II) by alkali-modified spent tea leaves using response surface methodology (RSM) and artificial neural network (ANN)

Contact Info

Product

Resources

About