Real time prediction of the rheological parameters of NaCl water-based drilling fluid using artificial neural networks

The rheological properties of the drilling fluid play a vital role in controlling the drilling operation. Rheological properties such as plastic viscosity, yield point, and flow behavior index are very important in calculating the rig hydraulics, surge and swab pressure, equivalent circulation density, and hole cleaning efficiency. Laboratory measurements of drilling fluid properties are a tiresome task and required specific equipment (mud balance, Fan VG viscometer). The common procedure on the well site is to perform a rheological test twice a day, while mud density, Marsh funnel viscosity, and solid percent are measured frequently every 15 to 20 minutes. Previous studies did not include the solid content of the drilling fluid in predicting the rheological properties of the drilling fluid. The objective of this research is to develop new empirical correlations that can be used to predict the rheological properties (Plastic viscosity, apparent viscosity, yield point, flow behavior index, and consistency index of the drilling fluid) of NaCl water-based drilling fluid on real time based on the frequent measurements of mud density, Marsh funnel viscosity, and solid percent. Artificial neural network technique was used to develop the empirical correlations based on 3000 actual field measurements of mud rheological properties. The obtained results showed that the five developed correlations using ANN technique can be used to predict the rheological properties of NaCl water based drilling fluid with a high accuracy; the average absolute error was less than 6.5% and the correlation coefficient was higher than 90%. The developed technique is inexpensive with no additional required equipment. It will help the drilling engineers to calculate the equivalent circulation density, surge and swab pressures, and hole cleaning which are strong functions of the rheological parameters in a real time.