On the application of artificial neural network for modeling liquid-liquid equilibrium
TL;DR: In this article, a simple add-in, named FeedGen, was developed for reproducing the feed data and expanding the liquid-liquid equilibrium pattern, which was concluded that solvatochromic polarity scales method cannot be used as a wide-range approach for direct modeling liquid- liquid equilibrium systems and is only applicable for limited set of data.
About: This article is published in Journal of Molecular Liquids.The article was published on 2016-08-01. It has received 14 citations till now. The article focuses on the topics: Artificial neural network & Backpropagation.
Citations
More filters
TL;DR: It is concluded that the structure of the NN, including numbers of hidden layer and neurons, can noticeably influence their performance and, compared with mathematical correlations, obtained by curve fitting, ANNs are more accurate.
Abstract: Intelligence methods, including Artificial Neural Networks (ANNs) and Support Vector Machine, are among the popular approaches for modeling the engineering systems with high accuracy. Nanofluid’s thermal conductivity depends on several factors such as the dimensions of nanoparticles, their concentration, synthesis method and temperature. Intelligence methods are appropriate tools to precisely estimate nanofluids’ thermal conductivity. Different methods and structures are used for the modeling of this property. In the present article, the related studies, using intelligence methods in thermal conductivity estimation, are comprehensively reviewed. According to the literature review, the accuracy of the predictive models has an association with their structure, utilized functions, selected input variables and employed algorithm. For instance, compared with mathematical correlations, obtained by curve fitting, ANNs are more accurate. Moreover, it is concluded that the structure of the NN, including numbers of hidden layer and neurons, can noticeably influence their performance. In the reviewed articles, trial and error are performed to distinguish the most favorable structure of ANNs. Due to the dependency of the models on the input variable, considering all the factors affecting the nanofluid’s thermal conductivity results in higher precision of the models.
67 citations
TL;DR: The investigation revealed that the ANN approach is most widely used, while the studies involving the solubility of gases and CO2 represent the most common problems related to ML application in IL studies.
44 citations
TL;DR: In this paper, a novel application of artificial neural networks (ANN) combined with Taguchi orthogonal experimental design methodology (27 runs, 3 levels, 6 factors) was introduced for modeling and optimization of a new alternating pulse current electrocoagulation-flotation (APC-ECF) process for the removal of humic acid (HA) from aqueous media.
27 citations
TL;DR: In this article, a hybrid local composition model was developed for simulating the liquid-liquid equilibria of systems involved in bio-fuels production, based on the hybridization of the NRTL equation and an artificial neural network.
23 citations
TL;DR: Artificial neural networks were investigated as a potentially faster alternative to conventional flash calculation methods and showed speed improvements over TEA of up to 35 times for phase classification, and 15 times for property predictions.
20 citations
References
More filters
TL;DR: In this paper, a new equation based on Scott's two-liquid model and on an assumption of nonrandomness similar to that used by Wilson is derived, which gives an excellent representation of many types of liquid mixtures.
Abstract: A critical discussion is given of the use of local compositions for representation of excess Gibbs energies of liquid mixtures. A new equation is derived, based on Scott's two-liquid model and on an assumption of nonrandomness similar to that used by Wilson. For the same activity coefficients at infinite dilution, the Gibbs energy of mixing is calculated with the new equation as well as the equations of van Laar, Wilson, and Heil; these four equations give similar results for mixtures of moderate nonideality but they differ appreciably for strongly nonideal systems, especially for those with limited miscibility. The new equation contains a nonrandomness parameter α12 which makes it applicable to a large variety of mixtures. By proper selection of α12, the new equation gives an excellent representation of many types of liquid mixtures while other local composition equations appear to be limited to specific types. Consideration is given to prediction of ternary vapor-liquid and ternary liquid-liquid equilibria based on binary data alone.
5,759 citations
12 Dec 2002
TL;DR: In this article, Solvent effects on acid/base equilibria and Tautomeric Equilibria have been investigated in terms of acid-base behavior and specific Solute/Solvent interactions.
Abstract: INTRODUCTION SOLUTE-SOLVENT INTERACTIONS Solutions Intermolecular Forces Solvation Preferential Solvation Micellar Solvation (Solubilization) Ionization and Dissociation CLASSIFICATION OF SOLVENTS Classification of Solvents According to Chemical Constitution Classification of Solvents Using Physical Constants Classification of Solvents in Terms of Acid-Base Behaviour Classification of Solvents in Terms of Specific Solute/Solvent Interactions Classification of Solvents Using Multivariate Statistical Methods SOLVENT EFFECTS ON THE POSITION OF HOMOGENEOUS CHEMICAL EQUILIBRIA General Remarks Solvent Effects on Acid/Base Equilibria Solvent Effects on Tautomeric Equilibria Solvent Effects on other Equilibria SOLVENT EFFECTS ON THE RATES OF HOMOGENEOUS CHEMICAL REACTIONS General Remarks Gas-Phase Reactivities Qualitative Theory of Solvent Effects on Reaction Rates Quantitative Theories of Solvent Effects on Reaction Rates Specific Solvation Effects on Reaction Rates SOLVENT EFFECTS ON THE ABSORPTION SPECTRA OF ORGANIC COMPOUNDS General Remarks Solvent Effects on UV/Vis Spectra Solvent Effects on Infrared Spectra Solvent Effects on Electron Spin Resonance Spectra Solvent Effects on Nuclear Magnetic Resonance Spectra EMPIRICAL PARAMETERS OF SOLVENT POLARITY Linear Gibbs Energy Relationships Empirical Parameters of Solvent Polarity from Equilibrium Measurements Empirical Parameters of Solvent Polarity from Kinetic Measurements Empirical Parameters of Solvent Polarity from Spectroscopic Measurements Empirical Parameters of Solvent Polarity from Other Measurements Interrelation and Application of Solvent Polarity Parameters Multiparameter Approaches SOLVENTS AND GREEN CHEMISTRY Green Chemistry Reduction of Solvent Use Green Solvent Selection Non-Traditional Solvents Outlook APPENDIX: PROPERTIES, PURIFICATION, AND USE OF ORGANIC SOLVENTS Physical Properties Purification of Organic Solvents Spectroscopic Solvents Solvents as Reaction Media Solvents for Recrystallization Solvents for Extraction and Partitioning (Distribution) Solvents for Adsorption Chromatography Solvents for Acid/Base Titrations in Non-Aqueous Media Solvents for Electrochemistry Toxicity of Organic Solvents
5,515 citations
TL;DR: The UNIQUAC equation as discussed by the authors is a semi-theoretical equation for the excess Gibbs energy of a liquid mixture, which is generalized through introduction of the local area fraction as the primary concentration variable.
Abstract: To obtain a semi-theoretical equation for the excess Gibbs energy of a liquid mixture, Guggenheim's quasi-chemical analysis is generalized through introduction of the local area fraction as the primary concentration variable. The resulting universal quasi-chemical (UNIQUAC) equation uses only two adjustable parameters per binary. Extension to multicomponent systems requires no ternary (or higher) parameters.
The UNIQUAC equation gives good representation of both vapor-liquid and liquid-liquid equilibria for binary and multicomponent mixtures containing a variety of nonelectrolyte components such as hydrocarbons, ketones, esters, amines, alcohols, nitriles, etc., and water. When well-defined simplifying assumptions are introduced into the generalized quasi-chemical treatment, the UNIQUAC equation reduces to any one of several well-known equations for the excess Gibbs energy, including the Wilson, Margules, van Laar, and NRTL equations.
The effects of molecular size and shape are introduced through structural parameters obtained from pure-component data and through use of Staverman's combinatorial entropy as a boundary condition for athermal mixtures. The UNIQUAC equation, therefore, is applicable also to polymer solutions.
4,130 citations
TL;DR: In this article, a group-contribution method is presented for the prediction of activity coefficients in nonelectrolyte liquid mixtures, which combines the solution-of-functional-groups concept with a model for activity coefficients based on an extension of the quasi chemical theory of liquid mixture (UNIQUAC).
Abstract: A group-contribution method is presented for the prediction of activity coefficients in nonelectrolyte liquid mixtures. The method combines the solution-of-functional-groups concept with a model for activity coefficients based on an extension of the quasi chemical theory of liquid mixtures (UNIQUAC). The resulting UNIFAC model (UNIQUAC Functional-group Activity Coefficients) contains two adjustable parameters per pair of functional groups.
By using group-interaction parameters obtained from data reduction, activity coefficients in a large number of binary and multicomponent mixtures may be predicted, often with good accuracy. This is demonstrated for mixtures containing water, hydrocarbons, alcohols, chlorides, nitriles, ketones, amines, and other organic fluids in the temperature range 275° to 400°K.
2,787 citations
Book•
01 Jan 1997
TL;DR: An Introduction to Nueral Networks will be warmly welcomed by a wide readership seeking an authoritative treatment of this key subject without an intimidating level of mathematics in the presentation.
Abstract: From the Publisher:
An Introduction to Nueral Networks will be warmly welcomed by a wide readership seeking an authoritative treatment of this key subject without an intimidating level of mathematics in the presentation.
2,135 citations