A New Gas Hydrate Prediction Model for Acidic and Inhibitor-Containing Systems
CHEMISTRY AND TECHNOLOGY OF FUELS AND OILS(2022)
Abstract
dissociation model suitable for the formation of gas hydrate in acidic and alkali-containing systems is established. By introducing inertia weight factor, an improved sinusoidal and cosine algorithm is obtained to optimize BP neural network and build ISCABP gas hydrate prediction model. The ISCABP model and other thermodynamic models were used to predict the hydrate formation conditions of four groups of (CH 4 +CO 2 +H2S) gas mixtures in acidic system, and the hydrate formation conditions of six groups of gas + liquid phase in alkoxide system. The temperature range is 240.15-308.45 K, and the pressure range is 0.05-82.56 mPa. The concentrations of H 2 S and CO 2 in the mixture were 4.95-27.93% (mol) and 6.79-8.4% (mol), respectively. The results show that ISCABP hydrate model has the best predictive value. The model has strong applicability to gas field production, and can provide a theoretical basis for determining the injection amount of inhibitor and formulating the field safe operation strategy.
MoreTranslated text
Key words
natural gas hydrate,ISCABP neural network,inertia weight,flow assurance,reverse learning
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined