Optimal artificial neural network design for simultaneous modeling of multicomponent adsorption

Pauletto, Paola S.; Dotto, Guilherme Luiz; Salau, Nina Paula Gonçalves

doi:10.1016/j.molliq.2020.114418

Cited by 40 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…used ANN for multicomponent adsorption. 17 Khodaei et al utilized ANN and response surface methodology (RSM) to predict Cr(VI) removal process by NiO nanoparticles. 1 Also, ANN as a predictive model for metal removal from aqueous solutions has been studied by most researchers for improved generalization and estimation of metal treatment.…”

mentioning

confidence: 99%

Developing an adaptive neuro‐fuzzy inference system based on particle swarm optimization model for forecasting Cr(VI) removal by NiO nanoparticles

Kuyakhi

Boldaji

2021

Env Prog and Sustain Energy

View full text Add to dashboard Cite

The treatment of wastewater from heavy metal ions such as hexavalent chromium Cr(VI) is considered as an important issue in recent years, which is harmful to human health and environment. Since, in engineering, performing the experiments to solve problems is time-consuming and costly. In this study, adaptive neuro-fuzzy inference system (ANFIS) was coupled with particle swarm optimization (PSO) algorithm to develop a predictive model for modeling of Cr(VI) removal percent on NiO nanoparticle. To this end, the trace of four initial parameters containing contact time, Cr(VI) initial concentration, NiO adsorbent dosage, and pH on removing Cr(VI) was investigated. The performance of the developed algorithm was evaluated by statistical parameters such as mean absolute relative deviation mean squared error (MSE)

show abstract

mentioning

confidence: 99%

Developing an adaptive neuro‐fuzzy inference system based on particle swarm optimization model for forecasting Cr(VI) removal by NiO nanoparticles

Kuyakhi

Boldaji

2021

Env Prog and Sustain Energy

View full text Add to dashboard Cite

show abstract

“…Thus, various empirical and theoretical models have been proposed in the literature to evaluate the equilibrium adsorption of heavy metals, namely Langmuir, Freundlich, Toth, and other models. 6 Since the multicomponent adsorption process is highly complex phenomena explained by the competition and interaction nature (synergism, synergism and non-interaction) 7 between adsorbent and multiple adsorbates, as well as operating conditions (pH, time, temperature, and concentration), it is difficult to model using the theoretical models. 8 Various artificial intelligence methods are presented in the literature to overcome the limitations of the theoretical models.…”

Section: Introductionmentioning

confidence: 99%

“…9,10 ANNs are applied successfully to model the non-linear behaviour between dependent and independent variables without knowing any previous details about the physical process in complex systems. 7,[11][12][13][14] However, to the best of our knowledge, very few studies are devoted to the application of LS-SVM or SVM approach to model the competitive adsorption of heavy metals. 15,16 Therefore, the major motivation behind this study was to assess the predictability power of three modelling approaches {ANN, SVM, and LS-SVM} in modelling the nonlinear relationships between the removal capacity from aqueous solution of five ternary heavy metal systems on different adsorbents and the independent parameters.…”

Section: Introductionmentioning

confidence: 99%

Ternary Multicomponent Adsorption Modelling Using ANN, LS-SVR, and SVR Approach – Case Study

Yettou

Laidi

Bey

et al. 2021

Kemija U Industriji

View full text Add to dashboard Cite

The aim of this work was to develop three artificial intelligence-based methods to model the ternary adsorption of heavy metal ions {Pb 2+ , Hg 2+ , Cd 2+ , Cu 2+ , Zn 2+ , Ni 2+ , Cr 4+ } on different adsorbates {activated carbon, chitosan, Danish peat, Heilongjiang peat, carbon sunflower head, and carbon sunflower stem). Results show that support vector regression (SVR) performed slightly better, more accurate, stable, and more rapid than least-square support vector regression (LS-SVR) and artificial neural networks (ANN). The SVR model is highly recommended for estimating the ternary adsorption kinetics of a multicomponent system.

show abstract

“…Especially in large-scale applications, it is vital to utilize a smart model to forecast the removal efficiency of biosorbents without conducting redundant efforts. In this sense, the ANN approach that is one of the powerful candidates to model both linear and non-linear systems can be successfully applied to modeling the adsorption process, and also optimize the process (Dehghani et al, 2020;Pauletto et al, 2020). It is noteworthy that the performance of the ANN model depends on its structure such as selected backpropagation algorithm, activation function in hidden/output layers, and the number of neurons and hidden layers (Pauletto et al, 2020;Elemen et al, 2012, Fawzy et al, 2018Ghaedi et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

“…It is noteworthy that the performance of the ANN model depends on its structure such as selected backpropagation algorithm, activation function in hidden/output layers, and the number of neurons and hidden layers (Pauletto et al, 2020;Elemen et al, 2012, Fawzy et al, 2018Ghaedi et al, 2014). Thus, it is important to optimize the proposed ANN model (Pauletto et al, 2020). There are several valuable works that get benefits from ANN to predict the adsorption behavior of the various systems.…”

Section: Introductionmentioning

confidence: 99%

Yapay Sinir Ağı Yaklaşımı ile Crystal Violet Katyonik Boyarmaddesinin Biyokütle-temelli Grafen Benzeri Gözenekli Karbon Üzerine Biyosorpsiyonunun Tahmin Edilmesi

Karaman¹

2021

European Journal of Science and Technology

View full text Add to dashboard Cite

Textile industries are considered to be the main actors in water pollution. Estimation of the textile dye sorption capacities of the biosorbents/adsorbents are crucial as design considerations. Herein, the feasibility of utilizing orange-peel-derived graphene-like porous carbons (GCs) as a low-cost biosorbent for removal of Crystal Violet (CV) cationic dye from aqueous solution have been evaluated both by batch biosorption experimental-setup and by using an artificial neural network (ANN) approach. The physicochemical characterization results have indicated that as-synthesized GCs has a specific surface area of 985 m 2 .g -1 , a pore volume of 1.04 cm 3 .g -1 , and a point of zero charge (pHPZC) of 6.50. The biosorption capacity of the biosorbent has been investigated as a function of initial pH, bisorbent dosage, initial dye concentration, and temperature. The optimal biosorption performance values have been achieved at pH of 7.5, the biosorbent dosage of 3.0 g.L -1 , the temperature of 25 ℃, in which 91.6% of initial CV (initial dye concentration of 100 ppm) has been successfully removed. The experimental results have indicated that the biosorption process significantly depends on the temperature whereas ca.15 min of contact time is sufficient for reaching equilibrium. The ANN approach has been utilized to forecast the biosorption performance of GCsThe proposed ANN model has been trained by the Levengberg-Marquardt backpropagation algorithm, by using the activation function of purelin and tansig functions at hidden and output layers, respectively. Different hidden topologies have been evaluated to optimize the ANN model. An optimal ANN model structured with two hidden layers with 5 and 10 neurons in each layer has been developed to forecast the biosorption of CV with high-performance parameters (linear correlation coefficient, R= 0.9995; mean squared error, MSE=0.0004). This work has shown that the experimental data are in harmony with ANN-based data, so it can be speculated that the proposed ANN approach can be utilized for predicting the cationic dye biosorption

show abstract

Optimal artificial neural network design for simultaneous modeling of multicomponent adsorption

Cited by 40 publications

References 38 publications

Developing an adaptive neuro‐fuzzy inference system based on particle swarm optimization model for forecasting Cr(VI) removal by NiO nanoparticles

Developing an adaptive neuro‐fuzzy inference system based on particle swarm optimization model for forecasting Cr(VI) removal by NiO nanoparticles

Ternary Multicomponent Adsorption Modelling Using ANN, LS-SVR, and SVR Approach – Case Study

Yapay Sinir Ağı Yaklaşımı ile Crystal Violet Katyonik Boyarmaddesinin Biyokütle-temelli Grafen Benzeri Gözenekli Karbon Üzerine Biyosorpsiyonunun Tahmin Edilmesi

Contact Info

Product

Resources

About