Universal intelligent models for liquid density of CO2 + hydrocarbon mixtures

Moradkhani, M.A.; Hosseini, Seyyed Hossein; Ranjbar, K.

doi:10.1016/j.fuel.2022.126642

Cited by 18 publications

(3 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 1), was chosen for this study as it offered the best fit between the experimental and predicted values among a variety of activation functions. Such a result was observed in our earlier works for different systems 82,83,[85][86][87][88] , where σ denotes the gaussian function's standard deviation, and d is the Euclidean distance between the input data and the center of network. Ultimately, the weighted sum of activation functions is presented by the output layer,…”

Section: Methodssupporting

confidence: 77%

“…In this study, three well-known intelligent schemes, namely, MLP, GPR and RBF were used to design predictive models for H 2 S solubility for various single and multicomponent solvents. According to our previous studies [82][83][84][85] , these approaches have high capabilities for accurate modeling of engineering systems with nonlinear and complicated behaviors.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent modeling of hydrogen sulfide solubility in various types of single and multicomponent solvents

Moradkhani

Hosseini

Ranjbar

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

This study aims to study the solubility of acid gas, i.e., hydrogen sulfide (H2S) in different solvents. Three intelligent approaches, including Multilayer Perceptron (MLP), Gaussian Process Regression (GPR) and Radial Basis Function (RBF) were used to construct reliable models based on an extensive databank comprising 5148 measured samples from 54 published sources. The analyzed data cover 95 single and multicomponent solvents such as amines, ionic liquids, electrolytes, organics, etc., in broad pressure and temperature ranges. The proposed models require just three simple input variables, i.e., pressure, temperature and the equivalent molecular weight of solvent to determine the solubility. A competitive examination of the novel models implied that the GPR-based one gives the most appropriate estimations with excellent AARE, R2 and RRMSE values of 4.73%, 99.75% and 4.83%, respectively for the tested data. The mentioned intelligent model also performed well in describing the physical behaviors of H2S solubility at various operating conditions. Furthermore, analyzing the William's plot for the GPR-based model affirmed the high reliability of the analyzed databank, as the outlying data points comprise just 2.04% of entire data. In contrast to the literature models, the newly presented approaches proved to be applicable for different types of single and multicomponent H2S absorbers with AAREs less than 7%. Eventually, a sensitivity analysis based on the GPR model reflected the fact that the solvent equivalent molecular weight is the most influential factor in controlling H2S solubility.

show abstract

Section: Methodssupporting

confidence: 77%

Section: Methodsmentioning

confidence: 99%

Intelligent modeling of hydrogen sulfide solubility in various types of single and multicomponent solvents

Moradkhani

Hosseini

Ranjbar

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Resolving the drawbacks of MLP networks, such as their empirical structure and under or overfitting possibility is the motivation behind the development of RBF networks. The high potency for interpolation, prompt convergence, simple structure and sublime reliability are the main advantages of these networks 56 . The structure of this network is similar to that of a single-layer MLP network, which includes a number of neurons equal to the number of data points used for training.…”

Section: Rbfmentioning

confidence: 99%

Two-phase Flow Condensation Inside Smooth Channels of Various Sizes: Universal Smart Models to Estimate the Frictional Pressure Drop

Moradkhani,

Hosseini,

Song

et al. 2024

Preprint

View full text Add to dashboard Cite

Reliable and comprehensive predictive tools for the frictional pressure drop (FPD) are of particular importance for systems involving two-phase flow condensation. However, the available models are only applicable to specific operating conditions and channel sizes. Thus, this study aims at developing universal models to estimate the FPD during condensation inside smooth mini/micro and conventional (macro) channels. An extensive databank, comprising 8037 experimental samples and 23 working fluids from 50 reliable sources, was prepared to achieve this target. A comprehensive investigation on the literature models reflected the fact that all of them are associated with high deviations, and their average absolute relative errors (AAREs) exceed 26%. Hence, after identifying the most effective input variables through the Spearman's correlation analysis, three soft-computing paradigms, i.e., multilayer perceptron (MLP), gaussian process regression (GPR) and radial basis function (RBF) were employed to establish intelligent and dimensionless models for the FPD based on the Chisholm's theory. Among them, the most accurate results were presented by the GPR approach with AARE and \({R}^{2}\) values of 4.10%, 99.23% respectively, in the testing step. The truthfulness and applicability of the models were explored through an array of statistical and visual analyses, and the results affirmed the obvious superiority of the newly proposed approaches over the literature correlations. Furthermore, the novel predictive tools excellently described the physical variations of the condensation FPD versus the operating parameters. Ultimately, the order of importance of factors in controlling the condensation FPD was clarified by a sensitivity analysis.

show abstract

Minimum spouting velocity of fine particles in fountain confined conical spouted beds using machine learning and least square fitting approaches

Moradkhani,

Miroliaei,

Ghasemi

et al. 2024

Can J Chem Eng

View full text Add to dashboard Cite

The present study concerns the development of new models to estimate the minimum spouting velocity (Ums) in various configurations of fountain‐confined conical spouted beds (FC‐CSBs) with fine particles. Existing literature correlations were found to be inaccurate for FC‐CSBs. Therefore, smart modelling techniques were employed to design more accurate predictive tools. The radial basis function (RBF) approach provided the best predictions for systems without draft tubes as well as those with open‐sided draft tubes. Additionally, the Gaussian process regression (GPR) approach yielded the best predictions for systems with nonporous draft tubes. The mean absolute percentage error (MAPE) values for the testing phase were 5.80%, 5.67%, and 5.59%, respectively. These models consider how bed shape and particle properties affect Ums. The sensitivity analysis was conducted to determine the factors with more importance in controlling Ums. Finally, simpler correlations were derived for Ums prediction in different FC‐CSB configurations, with accuracy around 12% error.

show abstract

Universal intelligent models for liquid density of CO2 + hydrocarbon mixtures

Cited by 18 publications

References 101 publications

Intelligent modeling of hydrogen sulfide solubility in various types of single and multicomponent solvents

Intelligent modeling of hydrogen sulfide solubility in various types of single and multicomponent solvents

Two-phase Flow Condensation Inside Smooth Channels of Various Sizes: Universal Smart Models to Estimate the Frictional Pressure Drop

Minimum spouting velocity of fine particles in fountain confined conical spouted beds using machine learning and least square fitting approaches

Contact Info

Product

Resources

About