Prediction of Thermophysical Properties for Binary Mixtures of Common Ionic Liquids with Water or Alcohol at Several Temperatures and Atmospheric Pressure by Means of Artificial Neural Network

The effective CO 2 sequestration in saline aquifers as a climate change-lessening solution is mainly governed by the interfacial tension (IFT) behavior between CO 2 and brine. An innovative and competent decision tree-based approach called stochastic gradient boosting (SGB) tree algorithm was applied to predict the CO 2 -aquifer brine IFT as a function of temperature, pressure, and brine salinities. The produced results were compared with the previously reported outcomes of other machine learning models, namely, radial basis function networks, multilayer perceptron networks, least squares support vector machine, and adaptive neuro fuzzy inference system. Amongst all models, the developed SGB tree algorithm provided superior outputs and turned out to be the most accurate tool.

show abstract

“…Furthermore, the other norms suggested by researchers were also used for further validation. These norms are given as follows:

true k = \frac{\sum y_{normali}^{normalexp} y_{normali}^{normalcal}}{\sum {(y_{normali}^{normalcal})}^{2}}

true k' = \frac{\sum y_{normali}^{normalexp} y_{normali}^{normalcal}}{\sum {(y_{normali}^{normalexp})}^{2}}

true 0.85 \leq k \leq 1.15

true 0.85 \leq k' \leq 1.15

true R_{normalo}^{2} = 1 - \frac{\sum {(y_{normali}^{normalcal} - {ky}_{normali}^{normalcal})}^{2}}{\sum {(y_{normali}^{normalcal} - \bar{y^{normalcal}})}^{2}}

true R'_{normalo}^{2} = 1 - \frac{\sum {(y_{normali}^{normalexp} - k' y_{normali}^{normalexp})}^{2}}{\sum (y_{normali}^{normalexp} -}

…”

Section: Resultsmentioning

confidence: 99%

Estimation of Interfacial Tension for Geological CO₂ Storage

Dehaghani

Soleimani

2019

Chem Eng & Technol

View full text Add to dashboard Cite

show abstract

“…Four parameters A i need to be fitted to experimental data for a polynomial with the order of three. An attempt for predicting mixture viscosities of IL systems has been published by Golzar et al [23]. They used an artificial neural network to predict the viscosity depending on composition and temperature.…”

Section: Introductionmentioning

confidence: 99%

Rheological Behavior of Mixtures of Ionic Liquids with Water

2018

View full text Add to dashboard Cite

The changes in viscosity exhibited upon mixing remain one of the major challenges for substance property prediction. Viscosity often drastically changes after even small changes in concentration of one of the compounds in the mixture. The viscosity behavior of mixtures of ionic liquids with water has been studied. First, a generalized evaluation of the shape of the viscosity‐concentration curves has been done. About one‐tenth of the investigated systems exhibited maxima or inflection points of the curve. The simple logarithmic mixing rule turns out to be applicable as a first approximation for many systems. However, it tends to underestimate mixture viscosity. Following these results, parameters for a group contribution method were fitted and evaluated. This method is based on the Grunberg and Nissan extension of the logarithmic mixing rule.

show abstract

“…It is very important to obtain the optimum number of neurons for the designed network. A small number of neurons cannot achieve the desired prediction accuracy; however, a large number of neurons may cause overfitting or overlearning . In literature, usually 1 to 20 neurons were taken and the MSE was calculated on each neuron .…”

Section: Data Collection and Methodsmentioning

confidence: 99%

“…Artificial neural networks have been applied successfully in many areas during the past few years. [17][18][19] It is in the domain of machine learning and can provide desirable properties where some traditional linear and non-linear regression models lack (such as thermodynamic models to correlate solubility data, and noise-tolerance). Furthermore, ANNs are data driven without being restricted by initial assumptions about functional relationships.…”

Section: Available Data For Ch 4 -Comentioning

confidence: 99%

“…A small number of neurons cannot achieve the desired prediction accuracy; however, a large number of neurons may cause overfitting or overlearning. 18,19 In literature, usually 1 to 20 neurons were taken and the MSE was calculated on each neuron. 17,29 So, the number of neurons that provide the lowest MSE will be selected for the optimal network size.…”

Section: Number Of Neurons In Hidden Layersmentioning

confidence: 99%

See 1 more Smart Citation

Application of artificial neural networks (ANN) for vapor‐liquid‐solid equilibrium prediction for CH₄‐CO₂ binary mixture

et al. 2018

View full text Add to dashboard Cite

The study of the frosting behavior of CO2 in the binary CH4‐CO2 is very important for energy minimization and for the smooth operation of the cryogenic purification process for natural gas due to its extensive cooling requirements. The present study focuses on the solid region of the phase envelope and the development of a predictive model using the artificial neural network (ANN) technique. It validates the model using available experimental data. The model points out the outlying data points. The ANN prediction method developed in this work can be successfully used for the vapor‐solid (V‐S) and vapor‐liquid‐solid (V‐L‐S) equilibrium of a CH4‐CO2 binary mixture for CO2 concentration of 1 to 54.2% and a temperature range of −50°C to −200°C. The use of the model for the liquid‐solid (L‐S) region in its current form is not recommended because the model was not validated due to lack of experimental data in this region. © 2018 Society of Chemical Industry and John Wiley & Sons, Ltd.

show abstract

Prediction of Thermophysical Properties for Binary Mixtures of Common Ionic Liquids with Water or Alcohol at Several Temperatures and Atmospheric Pressure by Means of Artificial Neural Network

Cited by 35 publications

References 93 publications

Estimation of Interfacial Tension for Geological CO₂ Storage

Estimation of Interfacial Tension for Geological CO₂ Storage

Rheological Behavior of Mixtures of Ionic Liquids with Water

Application of artificial neural networks (ANN) for vapor‐liquid‐solid equilibrium prediction for CH₄‐CO₂ binary mixture

Contact Info

Product

Resources

About

Prediction of Thermophysical Properties for Binary Mixtures of Common Ionic Liquids with Water or Alcohol at Several Temperatures and Atmospheric Pressure by Means of Artificial Neural Network

Cited by 35 publications

References 93 publications

Estimation of Interfacial Tension for Geological CO2 Storage

Estimation of Interfacial Tension for Geological CO2 Storage

Rheological Behavior of Mixtures of Ionic Liquids with Water

Application of artificial neural networks (ANN) for vapor‐liquid‐solid equilibrium prediction for CH4‐CO2 binary mixture

Contact Info

Product

Resources

About

Estimation of Interfacial Tension for Geological CO₂ Storage

Estimation of Interfacial Tension for Geological CO₂ Storage

Application of artificial neural networks (ANN) for vapor‐liquid‐solid equilibrium prediction for CH₄‐CO₂ binary mixture