期刊名称：Walailak Journal of Science and Technology (WJST)
印刷版ISSN：2228-835X
出版年度：2014
卷号：12
期号：2
页码：125-140
语种：English
出版社：Institute of Research and Development, Walailak University.
摘要：With the development of the natural gas industry in the 20th century, the production, processing and distribution of natural gas under high-pressure conditions has become necessary. Under these conditions, it was found that the production and transmission pipelines were becoming blocked with what looked like to be ice. Hammerschmidt determined that hydrates were the cause of plugged natural gas pipelines. Gas hydrates and difficulties related to their formation in production and transmission pipelines and equipment, are the major concerns of the gas industry. The main objective of this study was to present a novel approach to access more accurate hydrate formation rate predicting models based on a combination of flow loop experimental data with learning power of adaptive neural-fuzzy inference systems and more than 900 data points of the , , , and i- hydrate formation rate. Using this data set different predictive models were developed. It was found that such models can be used as powerful tools, with total errors less than 6 % for the developed models, in predicting hydrate formation rate in these cases. doi: 10.14456/WJST.2015.10
关键词：Adaptive Neural-Fuzzy Inference System, gas hydrate formation, kinetic inhibitor, rate model
