Multi-objective genetic algorithm optimization with an artificial neural network for CO2/CH4 adsorption prediction in metal–organic framework

Yulia, Fayza; Chairina, Intan; Zulys, Agustino; Nasruddin, _

doi:10.1016/j.tsep.2021.100967

Cited by 25 publications

(11 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The error histogram is a histogram of the difference (error) between target values and predicted values after training and testing state in MLP. These values show how predicted values differ from target values 62 . Based on the histogram of errors in Figure 4a, the most accumulation of the errors is located on the error at the value of 0.007712.…”

Section: Resultsmentioning

confidence: 90%

Artificial intelligence and response surface methodology to predict CO₂ capture using piperazine‐modified activated alumina

Noroozian

Shahhosseini

Ghaemi

2023

Env Prog and Sustain Energy

View full text Add to dashboard Cite

Carbon dioxide (CO2) is a major greenhouse gas that causes global warming. In this study, piperazine‐modified activated alumina was used for CO2 capture process. The number of 626 experimental data were obtained at different operating conditions to develop the artificial neural networks (ANNs) and response surface methodology (RSM), employed to identify the behavior and performance of the CO2 capture process. Three independent factors, including time (t: 0–1800 s), temperature (T: 20–80°C), and pressure (P: 2.067–10.088 bar), were used as the input variables and CO2 adsorption capacity was used as the response. Among 243 different structures, the multilayer perceptron (MLP) model was optimized with Bayesian regularization backpropagation algorithm and two hidden layers with 17 and 16 neurons. The radial basis function (RBF) model was used with 367 different structures. The optimized structure of the RBF model was obtained with 100 neurons and the spread of 0.5. For optimal networks of MLP and RBF, the best mean square error (MSE) was observed at 1.72e‐04 and 8.28e‐05, and the best coefficient of determination (R2) was obtained 0.998 and 0.999, respectively. Moreover, the response surface methodology (RSM) was used to model the process. The best MSE and R2 values were obtained 0.00454 and 0.9462, respectively. The results showed that ANNs produced more accurate predictions than RSM.

show abstract

Section: Resultsmentioning

confidence: 90%

Artificial intelligence and response surface methodology to predict CO₂ capture using piperazine‐modified activated alumina

Noroozian

Shahhosseini

Ghaemi

2023

Env Prog and Sustain Energy

View full text Add to dashboard Cite

show abstract

“…Since Warren McCulloch and Walter Pitts introduced the concept of artificial neural networks (ANN) in 1943, ANN have evolved rapidly and have been successfully applied in many fields [ 59 ]. Backpropagation-based training-optimization neural networks (BPNN) are the most extensively utilized neural networks in practice and are capable of solving complex nonlinear problems.…”

Section: Methodsmentioning

confidence: 99%

Modification of Multiwalled Carbon Nanotubes and Their Mechanism of Demanganization

Zhou

Mao

et al. 2023

Molecules

View full text Add to dashboard Cite

Multiwalled carbon nanotubes (MWCNTs) were modified by oxidation and acidification with concentrated HNO3 and H2SO4, and the modified multiwalled carbon nanotubes (M-MWCNTs) and raw MWCNTs were characterized by several analytical techniques. Then the demanganization effects of MWCNTs and M-MWCNTs were well investigated and elucidated. The experimental data demonstrated that the adsorption efficiency of Mn(II) could be greatly promoted by M-MWCNTs from about 20% to 75%, and the optimal adsorption time was 6 h and the optimal pH was 6. The results of the kinetic model studies showed that Mn(II) removal by M-MWCNTs followed the pseudo-second-order model. Isothermal studies were conducted and the results demonstrated that the experimental data fitted well with the three models. The reliability of the experimental results was well verified by PSO–BP simulation, and the present conclusion could be used as a condition for further simulation. The research results provide a potential technology for promoting the removal of manganese from wastewater; at the same time, the application of various mathematical models also provides more scientific ideas for the research of the mechanism of adsorption of heavy metals by nanomaterials.

show abstract

“…It leverages on the principle of genetic and natural selection. It is basically a heuristic and searches inclined technique applied to solve a myriad of simple and complex problems by seeking possible optimal solutions [74]. Its operation entails 4 major steps as captured in Figure 4.…”

Section: Genetic Algorithmmentioning

confidence: 99%

“…The iterative cycle is maintained until the desired solution is reached before termination. The algorithm can be implemented in a Matlab environment [74][75][76][77][78].…”

Section: Genetic Algorithmmentioning

confidence: 99%

Evaluation of Heterocyclic Aromatic Compound Dye (Methylene Blue) on Chitosan Adsorbent Sourced from African Snail Shell: Modelling and Optimization Studies

Bello

Olafadehan

2022

J. Appl. Sci. Process Eng.

View full text Add to dashboard Cite

In this article, the modelling and optimization of five operational process parameters involving initial concentration, adsorbent dosage, contact time, temperature and pH of the solution as it affects the treatment of aqueous solution contaminated with methylene blue, a heterocyclic aromatic compound, on chitosan sourced from African Snail Shell were studied using response surface methodology (RSM) and artificial neural network (ANN) techniques coupled with genetic algorithm. The single and interactive effects of the variables were examined by way of analysis of variance (ANOVA). A comparison of the model techniques was done and an evaluation was carried out with some selected error functions. Both modelling and optimization tools performed creditably well. However, the hybrid ANN-GA proved to be a superior modelling and optimization technique with excellent generalization ability which gave an average absolute deviation between the experimental and predicted data of both response variables considered. The insightful relative importance of the process variables based on the renowned Garson and Olden’s algorithm methods coupled with step by step approach initiated in the Matlab environment were equally investigated. The findings from this study revealed in clear terms that pH and initial concentrations were the most influential parameters and the maximum value of 99.28% of methylene blue removed at optimum conditions affirmed that the chitosan adsorbent is viable for the treatment of effluents from the textile industry.

show abstract

Multi-objective genetic algorithm optimization with an artificial neural network for CO2/CH4 adsorption prediction in metal–organic framework

Cited by 25 publications

References 32 publications

Artificial intelligence and response surface methodology to predict CO₂ capture using piperazine‐modified activated alumina

Artificial intelligence and response surface methodology to predict CO₂ capture using piperazine‐modified activated alumina

Modification of Multiwalled Carbon Nanotubes and Their Mechanism of Demanganization

Evaluation of Heterocyclic Aromatic Compound Dye (Methylene Blue) on Chitosan Adsorbent Sourced from African Snail Shell: Modelling and Optimization Studies

Contact Info

Product

Resources

About

Multi-objective genetic algorithm optimization with an artificial neural network for CO2/CH4 adsorption prediction in metal–organic framework

Cited by 25 publications

References 32 publications

Artificial intelligence and response surface methodology to predict CO2 capture using piperazine‐modified activated alumina

Artificial intelligence and response surface methodology to predict CO2 capture using piperazine‐modified activated alumina

Modification of Multiwalled Carbon Nanotubes and Their Mechanism of Demanganization

Evaluation of Heterocyclic Aromatic Compound Dye (Methylene Blue) on Chitosan Adsorbent Sourced from African Snail Shell: Modelling and Optimization Studies

Contact Info

Product

Resources

About

Artificial intelligence and response surface methodology to predict CO₂ capture using piperazine‐modified activated alumina

Artificial intelligence and response surface methodology to predict CO₂ capture using piperazine‐modified activated alumina