Modelling the Effects of Temperature and Pressure on Equivalent Circulating Density (ECD) During Drilling Operations Using Artificial Neural Networks

Incorrect evaluation of equivalent circulating density (ECD) while drilling oil and gas wells may result in problems such as lost circulation, kicks, differential pipe sticking etc especially narrow margins. Due to the incompressible nature liquids, increase wellbore pressure will only have appreciable effect on fluid rheology at higher pressures, whereas a small temperature cause decrease rheology. One thousand eleven (1,011) field data obtained from high pressure; (HPHT) were used develop artificial neural networks (ANNs) for this study. Training train network validation guarantee that generalizes training stage. Test evaluate prediction capability developed model. Four error metrics, namely R-square (R2), mean square (MSE), root (RMSE) average absolute percentage (AAPE) assess performance networks. Forecasts testing indicate optimized ECD model produced accuracy; R2 0.9993, MSE 0.000265, RMSE 0.01628 AAPE 0.337. The performed better than existing models terms accuracy calculated errors. help improving during pre-drill design phase, which is quite critical margin wells.