Determination of Drilling Mud Density Change with Pressure and Temperature Made Simple and Accurate by ANN

An artificial neural network (ANN) model was developed to provide accurate predictions of mud density as a function of mud type, pressure, and temperature. Available experimental measurements of water-base and oil-base drilling fluid at 0-1400 psi and ≤ 400°F were used to develop and test the ANN model. The drilling fluid was composed of 298 cc of No. 2 diesel oil, 52 cc of 30% calcium chloride brine, 5 g of organophilic bentonite, 5 g of emulsifier, and 2 g of alcium hydroxide. The model provided predictions with exceptional accuracy. Trend analysis proved that the model recognizes and obeys the physical behavior of mud density with changing pressure and temperature. The developed model could be used by mud and drilling engineers in planning and executing drilling operations where the behavior of the fluid density with changing temperature and pressure is of utmost importance.