Artificial neural network (ANN) approach for modeling Zn(II) adsorption in batch process

Yıldız, Sayiter

doi:10.1007/s11814-017-0157-3

Cited by 30 publications

(12 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, adsorption process was found to be in compliance with pseudo-second order kinetic model. Similar kinetic behaviours were also reported in previous studies [33,34,50].…”

Section: Pseudo-second Order Modelsupporting

confidence: 91%

“…Metal removal can be characterized with the reduced volume of specific regions and total pores after Ni(II) adsorption. Surface and cross section images of the adsorbents were taken by using AFM to determine morphological properties such as surface porosity, roughness and texture [33]. Surface characterization involves micro-porosity, roughness and macro-pores size distribution measurements using atomic force microscopy before and after adsorption (Fig.…”

Section: Characterization Of Adsorbentmentioning

confidence: 99%

See 1 more Smart Citation

Heavy Metal Adsorption by Dewatered Iron-Containing Waste Sludge

Yıldız

Sevinç

2018

Ecological Chemistry and Engineering S

Self Cite

View full text Add to dashboard Cite

Drinking water treatment plants produce significant amounts of waste sludge. In this study, removal of Nickel ion by use of wastewater sludge was aimed. The adsorption capability of waste sludge was optimized with varying physical parameters such as pH, adsorbent dosage, adsorbate concentration, contact time, shaking speed and temperature. Initial concentration was set as 25 mg/dm3, absorbent dose was set as 0.3 g/cm3, and temperature was set as 25 °C. Compliance of balance data with Langmuir, Freundlich, Temkin and D-R isotherm models was investigated. The highest R2 values were obtained with Freundlich isotherm (R2 = 0.92-0.95). Adsorption kinetics was analysed using pseudo-first order, pseudo-second order, Weber and Morris intraparticle diffusion and Elovich kinetic models, and the system was found to be in a better compliance with pseudo-second order kinetic model. Iron sludge was used as sorbent, and accordingly total iron ion measurements were carried out to determine its possible effects on water. Additionally, SEM, EDX, FTIR spectroscopy, XRD spectrum and atomic force microscope (AFM) measurements were conducted to determine the interaction between the sorbent and metal ions, in addition to characterization of the sorbent. As indicated by research results, drinking water treatment sludge proved to be a potential adsorbent for removal of nickel(II) ions from the solution.

show abstract

“…Consequently, adsorption process was found to be in compliance with pseudo-second order kinetic model. Similar kinetic behaviours were also reported in previous studies [33,34,50].…”

Section: Pseudo-second Order Modelsupporting

confidence: 91%

Section: Characterization Of Adsorbentmentioning

confidence: 99%

Heavy Metal Adsorption by Dewatered Iron-Containing Waste Sludge

Yıldız

Sevinç

2018

Ecological Chemistry and Engineering S

Self Cite

View full text Add to dashboard Cite

show abstract

“…Currently, the application of artificial intelligence and the machine learning system play an important role in computational and mathematical modeling . The high regressions validity and precise simulations obtained by applying these neural network algorithms have encouraged the implementation of such techniques . Artificial neural network modeling is the concept of simulated human brain neurons, by back propagation to the start point to achieve minimal errors and deviations.…”

Section: Introductionmentioning

confidence: 99%

“…43 The high regressions validity and precise simulations obtained by applying these neural network algorithms have encouraged the implementation of such techniques. [44][45][46][47] Artificial neural network modeling is the concept of simulated human brain neurons, by back propagation to the start point to achieve minimal errors and deviations. However, various learning algorithms and tools are available, with differences in precision, data sets capability, and assessment period.…”

Section: Introductionmentioning

confidence: 99%

High‐temperature CO₂ removal from CH₄ using silica membrane: experimental and neural network modeling

et al. 2019

View full text Add to dashboard Cite

Inorganic membranes can operate under harsh conditions. However, successful synthesis of inorganic membranes is still challenging, and its performance depends on many factors. This work reports the effect of dip‐coating duration, inlet pressure, and inlet flow rate on the flux, permeability, and selectivity of silica membranes. A silica membrane was prepared by the deposition of silica sol onto porous alumina support. The permeability test was conducted at 100 °C using a single gas of CO2 and CH4. The highest flux was observed at the maximum inlet pressure and inlet flow rate for the membrane prepared at the minimum dip‐coating duration. The neural network modeling of the membrane predicted permeabilities showed a considerably high validity regression (R ≈ 0.99) of the predicted data linked to the experimental sets. The separation factor (α) was the highest at the maximum dip‐coating duration. The synthesized silica membrane has potential for CO2/CH4 separation under harsh operating conditions. © 2019 Society of Chemical Industry and John Wiley & Sons, Ltd.

show abstract

“…Moreover, the ANN is able to describe the interactive effect between variables, as well as the relationship of each variable with outputs to give the target result. In addition, it is capable of solving complex and highly nonlinear relationships between several variables [10,11,12,13].…”

Section: Introductionmentioning

confidence: 99%

Modeling of Ammonium and COD Adsorption in Aqueous Solutions Using an Artificial Neural Network

Khalil¹,

Smolyanichenko²,

Vilson³

et al. 2019

Proceedings of the International Symposium "Engineering and Earth Sciences: Applied and Fundamental Research" Dedicated to the

View full text Add to dashboard Cite

This paper illustrates the application of the artificial neural network for adsorption of ammonium NH4 + and COD from fish farm by rice straw as low cost carbonaceous. The effects of input parameters (contact time, pH, initial concentration of NH4 + and COD, adsorbent dosages, and temperature) are studied to optimize the conditions for maximum removal of NH4 + and COD. The artificial neural network with a single hidden layer with ten nodes trained with Levenberg-Marquardt algorithm predicted the removal efficiency of NH4 + and COD from aqueous solution accurately.

show abstract

Artificial neural network (ANN) approach for modeling Zn(II) adsorption in batch process

Cited by 30 publications

References 68 publications

Heavy Metal Adsorption by Dewatered Iron-Containing Waste Sludge

Heavy Metal Adsorption by Dewatered Iron-Containing Waste Sludge

High‐temperature CO₂ removal from CH₄ using silica membrane: experimental and neural network modeling

Modeling of Ammonium and COD Adsorption in Aqueous Solutions Using an Artificial Neural Network

Contact Info

Product

Resources

About

Artificial neural network (ANN) approach for modeling Zn(II) adsorption in batch process

Cited by 30 publications

References 68 publications

Heavy Metal Adsorption by Dewatered Iron-Containing Waste Sludge

Heavy Metal Adsorption by Dewatered Iron-Containing Waste Sludge

High‐temperature CO2 removal from CH4 using silica membrane: experimental and neural network modeling

Modeling of Ammonium and COD Adsorption in Aqueous Solutions Using an Artificial Neural Network

Contact Info

Product

Resources

About

High‐temperature CO₂ removal from CH₄ using silica membrane: experimental and neural network modeling