Prediction of water removal rate in a natural gas dehydration system using radial basis function neural network

Abstract

2016) Prediction of water removal rate in a natural gas dehydration system using radial basis function neural network, Petroleum Science and Technology, 34:10, 951-960To link to this article: http://dx. ABSTRACTNatural gas commonly contains water as a contaminant that can condense to water or form gas hydrates, which causes a range of problems during gas production, transportation, and processing. Therefore, the removal of gas moisture is of great importance. A common and popular method for removing water contamination from natural gas is using solid dehydrators. Calcium chloride is a nonregenerative desiccant to dehydrate natural gas. With continual water adsorption, CaCl 2 changes to consecutively higher states of hydration, finally producing a CaCl 2 brine solution. This method does not require heating or moving parts. In addition, it does not react with H 2 S or CO 2 . These features make this method a popular one for drying natural gas. Nevertheless, precise and simple methods are needed to predict the water content of natural gas dried by calcium chloride dehydrator units. In this study, an intelligent method, called the radial basis function neural network, was incorporated to predict the gas moisture dehydrated by calcium chloride in dehydration units. Modeling was performed under different conditions of a fresh recharge and before recharging. The overall correlation factor of 0.9999 for both the fresh charge and before charging conditions showed that the outputs of the proposed models were in agreement with the experimental data. In addition, the developed models were compared with the previously proposed intelligent models and classic correlations. The comparison showed that the developed model is superior to the previously proposed models and correlations regarding the accuracy of prediction.

Developing an Automated Gas Sampling Chamber for Measuring Variations in CO2 Exchange in a Maize Ecosystem at Night

“…CaCl 2 is mainly used as a desiccant to achieve dehydration of natural gas [19]. While re-adsorbing water, it reaches a high-level hydration state, forming the corresponding CaCl 2 salt solution.…”

“…While re-adsorbing water, it reaches a high-level hydration state, forming the corresponding CaCl 2 salt solution. This process does not require the movement of parts or heating, and does not react with CO 2 to a certain extent [19]. Thus, CaCl 2 is widely used in the drying of natural gas and was used to control the air humidity in this study.…”

Accurate model based on artificial intelligence for prediction of carbon dioxide solubility in aqueous tetra‐n‐butylammonium bromide solutions

“…Hence, developing accurate and predictive models for solubility prediction of CO 2 in TBAB and other compounds is of great importance. The excellent performance of intelligent methods has been proved in solving different problems of chemical engineering . This study presents application of intelligent approaches named genetic algorithm–radial basis function (GA‐RBF), hybrid adaptive neuro‐fuzzy inference systems (Hybrid‐ANFIS), and gene expression programming (GEP) models for prediction of solubility of CO 2 in TBAB using experimental data from literature.…”

“…The excellent performance of intelligent methods has been proved in solving different problems of chemical engineering. [30][31][32][33][34] This study presents application of intelligent approaches named genetic algorithm-radial basis function (GA-RBF), hybrid adaptive neuro-fuzzy inference systems (Hybrid-ANFIS), and gene expression programming (GEP) models for prediction of solubility of CO 2 in TBAB using experimental data from literature. The effectiveness and reliability of models were checked through various graphical and statistical analyses.…”

Prediction of H2S Solubility in Liquid Electrolytes by Multilayer Perceptron and Radial Basis Function Neural Networks

“…Beside these methods, there are intelligence techniques such as least square support vector machines (LSSVMs) 13–15, fuzzy logic (FL) 14, 16, genetic algorithms (GAs) 14, 16, and artificial neural networks (ANNs) 17–24, which have found wide application in many scopes of science and engineering, as a result of their capacity in analysis and modeling ambiguous and complex subjects, which were difficult and complicated to solve in the past. Eslamimanesh et al 25 applied the ANN method to predict the supercritical CO 2 solubility in 24 mostly used ILs.…”