摘要

Scale deposits impair production reservoirs and foul down hole, surface, and injection equipment. The effects can be rapid and dramatic. One of the most frequent scale-forming compounds in water is calcium carbonate. In a reservoir the production of brine can result in the lowering of the pressure and/or temperature. A pressure drop will decrease the solubility of CaCO3 and thus increase the saturation ratio for CaCO3, whereas a temperature drop will have the opposite effect. The net outcome of a change in pressure and temperature may therefore be a decrease or an increase in the saturation ratio of CaCO3 as specified by the change of temperature relative to the change of pressure. Accordingly, applying robust predictive tools in this research is of high interest in petroleum production systems. The current study plays emphasis on applying the predictive model based on least square support vector machine (LSSVM) to estimate amount of Dissolved Calcium Carbonate Concentration in oil field brines. Genetic algorithm (GA) was used to optimize hyper parameters (gamma and sigma(2)) which are embedded in LSSVM model. Using this method is simple and accurate to determine the amount of Dissolved Calcium Carbonate Concentration in oil field brines with minimum uncertainty.