Modeling Natural Gas Compressibility Factor Using a Hybrid Group Method of Data Handling

Abstract

A Natural gas is increasingly being sought after as a vital source of energy, given that its production is very cheap and does not cause the same environmental harms that other resources, such as coal combustion, do. Understanding and characterizing the behavior of natural gas is essential in hydrocarbon reservoir engineering, natural gas transport, and process. Natural gas compressibility factor, as a critical parameter, defines the compression and expansion characteristics of natural gas under different conditions. In this study, a simple second-order polynomial model based on the group method of data handling (GMDH) is presented to determine the compressibility factor of different natural gases at different conditions, using corresponding state principles. The accuracy of the model evaluated through graphical and statistical analyses. The results show that the model is capable of predicting natural gas compressibility with an average absolute error of only 2.88%, a root means square of 0.03, and a regression coefficient of 0.92. The performance of the developed model compared to widely known, previously published equations of state (EOSs) and correlations, and the precision of the results demonstrates its superiority over all other correlations and EOSs.

Oil Family Typing Using a Hybrid Model of Self-Organizing Map and Artificial Neural Network

“…Mokarizadeh et al 5 implemented ANNs and ML algorithms to determine the solubility of SO2 in ionic liquids. Hemmati-Sarapardeh et al 12 conducted the modeling natural gas compressibility using a kind of ANN. Amooie et al 13 took advantage of ML methods for geological carbon storage studies.…”