2019/12/31 by Narjes Nabipour, Nabipour, Narjes, Amir Mosavi +7
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #68Q05 #FOS: Computer and information sciences #Fault Detection and Control Systems #Machine Learning (cs.LG) #Machine Learning and ELM #Spectroscopy Techniques in Biomedical and Chemical Research
paper · pdf · doi:10.48550/arxiv.2009.03983
openalex publication_date 2019/12/31 · openalex created_date 2022/07/23 · openalex updated_date 2026/07/28
Calculating hydrocarbon components solubility of natural gases is known as\none of the important issues for operational works in petroleum and chemical\nengineering. In this work, a novel solubility estimation tool has been proposed\nfor hydrocarbon gases including methane, ethane, propane, and butane in aqueous\nelectrolyte solutions based on extreme learning machine (ELM) algorithm.\nComparing the ELM outputs with a comprehensive real databank which has 1175\nsolubility points concluded to R-squared values of 0.985 and 0.987 for training\nand testing phases respectively. Furthermore, the visual comparison of\nestimated and actual hydrocarbon solubility led to confirm the ability of the\nproposed solubility model. Additionally, sensitivity analysis has been employed\non the input variables of the model to identify their impacts on hydrocarbon\nsolubility. Such a comprehensive and reliable study can help engineers and\nscientists to successfully determine the important thermodynamic properties\nwhich are key factors in optimizing and designing different industrial units\nsuch as refineries and petrochemical plants.\n