The ability of artificial neural network in prediction of the acid gases solubility in different ionic liquids

Sedghamiz, Mohammad Amin; Rasoolzadeh, Ali; Rahimpour, Mohammad Reza

doi:10.1016/j.jcou.2014.12.003

Cited by 68 publications

(26 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… Abbreviation T c (K) P c (bar) ω References [EMIM][EtSO 4 ] 1061.1 40.4 0.3368 65 [EMIM][PF 6 ] 663.5 19.5 0.6708 65 [EMIM][Tf 2 N] 1244.9 32.6 0.1818 65 [EMIM][eFAP] 830. 7 100.3 1.5099 66 [HMIM][Tf 2 N] 876.2 22.2 1.3270 65 [HMIM][PF 6 ] 754.3 15.5 0.8352 65 [BMIM][BF 4 ] 632.3 20.4 0.8489 65 [BMIM][PF 6 ] 708.9 17.3 0.7553 65 [BMIM][Tf 2 N] 1265 27.6 0.2656 65 [OMIM][PF 6 ] 800.1 14.0 …”

Section: Experimental Data Acquisition and Preliminary Analysismentioning

confidence: 99%

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

Abdi

Hadipoor

Esmaeili-Faraj

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Absorption has always been an attractive process for removing hydrogen sulfide (H2S). Posing unique properties and promising removal capacity, ionic liquids (ILs) are potential media for H2S capture. Engineering design of such absorption process needs accurate measurements or reliable estimation of the H2S solubility in ILs. Since experimental measurements are time-consuming and expensive, this study utilizes machine learning methods to monitor H2S solubility in fifteen various ILs accurately. Six robust machine learning methods, including adaptive neuro-fuzzy inference system, least-squares support vector machine (LS-SVM), radial basis function, cascade, multilayer perceptron, and generalized regression neural networks, are implemented/compared. A vast experimental databank comprising 792 datasets was utilized. Temperature, pressure, acentric factor, critical pressure, and critical temperature of investigated ILs are the affecting parameters of our models. Sensitivity and statistical error analysis were utilized to assess the performance and accuracy of the proposed models. The calculated solubility data and the derived models were validated using seven statistical criteria. The obtained results showed that the LS-SVM accurately predicts H2S solubility in ILs and possesses R2, RMSE, MSE, RRSE, RAE, MAE, and AARD of 0.99798, 0.01079, 0.00012, 6.35%, 4.35%, 0.0060, and 4.03, respectively. It was found that the H2S solubility adversely relates to the temperature and directly depends on the pressure. Furthermore, the combination of OMIM+ and Tf2N-, i.e., [OMIM][Tf2N] ionic liquid, is the best choice for H2S capture among the investigated absorbents. The H2S solubility in this ionic liquid can reach more than 0.8 in terms of mole fraction.

show abstract

Section: Experimental Data Acquisition and Preliminary Analysismentioning

confidence: 99%

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

Abdi

Hadipoor

Esmaeili-Faraj

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…In order to develop dependable models, it is necessary to collect properties of CO 2 in different ILs from the literature. In this study, the 544 samples were collected and depicted partly in Table 2 [20,[35][36][37][38][39][40]. All the solubility of CO 2 in ionic liquids in this paper was obtained in the equilibrium phase.…”

Section: Data Collecting and Groupingmentioning

confidence: 99%

Prediction of CO2 Solubility in Ionic Liquids Based on Multi-Model Fusion Method

et al. 2019

View full text Add to dashboard Cite

Reducing the emissions of greenhouse gas is a worldwide problem that needs to be solved urgently for sustainable development in the future. The solubility of CO2 in ionic liquids is one of the important basic data for capturing CO2. Considering the disadvantages of experimental measurements, e.g., time-consuming and expensive, the complex parameters of mechanism modeling and the poor stability of single data-driven modeling, a multi-model fusion modeling method is proposed in order to predict the solubility of CO2 in ionic liquids. The multiple sub-models are built by the training set. The sub-models with better performance are selected through the validation set. Then, linear fusion models are established by minimizing the sum of squares of the error and information entropy method respectively. Finally, the performance of the fusion model is verified by the test set. The results showed that the prediction effect of the linear fusion models is better than that of the other three optimal sub-models. The prediction effect of the linear fusion model based on information entropy method is better than that of the least square error method. Through the research work, an effective and feasible modeling method is provided for accurately predicting the solubility of CO2 in ionic liquids. It can provide important basic conditions for evaluating and screening higher selective ionic liquids.

show abstract

“…Several researchers used 70% of the total datasets for training and 15% for validation and 15% for testing the ANN model. Therefore in this study, experimental data of CO 2 solubility are randomly divided into three distinct groups: 70% of data sets for training, 15% for validation, and 15% to test the ANN model.…”

Section: Vle Modelingmentioning

confidence: 99%

Experimental measurements and modelling of CO₂ solubility in aqueous mixtures of benzylamine and N‐(2‐aminoethyl) ethanolamine

Mukherjee

Bandyopadhyay

Samanta

2018

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

In this work, carbon dioxide solubility in N-(2-aminoethyl) ethanolamine (AEEA) activated aqueous benzylamine (BZA) solutions are studied using a stirred-cell reactor in the temperature and pressure range of 313.15-333.15 K and 0.2-219 kPa, respectively. AEEA is a linear diamine with a primary and secondary amine groups, and BZA is a primary cyclic amine. The concentration of the aqueous blends used are (20mass% BZA + 10mass% AEEA), (24mass% BZA + 6mass% AEEA), and (28mass% BZA + 2mass% AEEA).Density and viscosity of unloaded aqueous amine blends are also measured in experimental temperature and concentration ranges and correlated using Joubian-Acree mathematical model. Model-predicted density and viscosity data are in good agreement with experimental results showing 0.05% and 3.41% AAD, respectively. To correlate experimental vapor-liquid-equilibrium data, Kent-Eisenberg (KE), artificial neural network (ANN), and soft models are used. Equilibrium constants of monocarbamate formation reaction of BZA and AEEA are regressed as a function of temperature and CO 2 loading to fit the experimental data with KE model expression. KE model is also utilized to estimate the pH of CO 2 loaded aqueous amine solutions. ANN model is found to predict CO 2 solubility with better accuracy (1.56% AAD) in comparison of KE model (8.27% AAD) and soft model (15.5%). The CO 2 absorption capacity of (20mass% BZA + 10mass% AEEA) solvent (~0.8 mol CO 2 /mol amine) is higher than that of monoethanolamine (~0.5 mol CO 2 /mol amine).Heats of absorption values of (BZA + AEEA) solvents (~25 kJ/mol CO 2 ) predicted from Gibbs-Helmholtz relationship are found to be lower than that of MEA (~87 kJ/mol CO 2 ) and PZ (~66 kJ/mol CO 2 ).

show abstract

The ability of artificial neural network in prediction of the acid gases solubility in different ionic liquids

Cited by 68 publications

References 68 publications

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

Prediction of CO2 Solubility in Ionic Liquids Based on Multi-Model Fusion Method

Experimental measurements and modelling of CO₂ solubility in aqueous mixtures of benzylamine and N‐(2‐aminoethyl) ethanolamine

Contact Info

Product

Resources

About

The ability of artificial neural network in prediction of the acid gases solubility in different ionic liquids

Cited by 68 publications

References 68 publications

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

Prediction of CO2 Solubility in Ionic Liquids Based on Multi-Model Fusion Method

Experimental measurements and modelling of CO2 solubility in aqueous mixtures of benzylamine and N‐(2‐aminoethyl) ethanolamine

Contact Info

Product

Resources

About

Experimental measurements and modelling of CO₂ solubility in aqueous mixtures of benzylamine and N‐(2‐aminoethyl) ethanolamine