State of the art modeling of critical transport fluid velocity in directional and horizontal wells by artificial neural network

Drill cutting transport in directional and horizontal well has been studied for many years. It has been a great concern to predict critical transport fluid velocity (CTFV) to avoid cutting bed formation and prevent several drilling problems. In this study an artificial neural network (ANN) model using experimental data from a number of comprehensive tests in cutting transport flow loops has been developed to predict CTFV for directional and horizontal wells. Including the effects of pipe rotation and eccentricity, the ANN model modeled the case with a relative (percent) error of less than 10 % and correlation coefficient value of about 0.96and mean square error (MSE) of 0.007 The statistical error analysis results obtained by the model indicate that ANN model is successful in predicting CTFV. This model is suitable for all inclination angles and for both Bingham and Power law fluids, low value of relative error and consideration of all effective parameters on CTFV are some of the model preferences to conventional models.

کلیدواژه ها:

Critical transport fluid velocity ، Directional wells ، Horizontal wells ، Artificial neural network ، Cutting transport