Eventually, a committee machine with SVR and ACE was constructed through the use of hybrid genetic algorithm-pattern search (GA-PS). Subsequently, an alternating conditional expectation (ACE) was used for approximating optimal transformations of input/output data to a higher correlated data and consequently developing a sophisticated model between transformed data. Firstly, structural risk minimization (SRM) principle of support vector regression (SVR) was employed to construct a robust model for estimating FVF from the aforementioned inputs.
This study proposes an accurate, rapid and cost-effective approach for determining FVF from reservoir temperature, dissolved gas oil ratio, and specific gravity of both oil and dissolved gas. Volume change of oil between reservoir condition and standard surface condition is called oil formation volume factor (FVF), which is very time, cost and labor intensive to determine.
