Predicting hydrate stability zones of petroleum fluids using sound velocity data of salt aqueous solutions

Predicting hydrate stability zones of petroleum fluids from the aqueous phase properties can have a practical application as measuring these properties is normally easier than hydrate phase equilibrium measurement and can reduce experimental costs and efforts. In this work, the possibility of estimating hydrate stability zone from sound velocity data of salt aqueous solutions is investigated using a feed-forward artificial neural network method with a modified Levenberg–Marquardt algorithm. The method considers the changes of sound velocity in salt (NaCl, KCl, NaBr, KBr, BaCl2, MgCl2, Na2SO4, HCOONa) aqueous solution with respect to sound velocity in pure water and therefore there is no need to have a quantitative analysis of the aqueous solution. Independent data (not used in training and developing of the method) are used to examine the reliability of this tool. The predictions of this method are in acceptable agreement with independent experimental data, demonstrating the reliability of this tool for estimating the hydrate stability zone in the presence of salt aqueous solutions.