Rheological Properties Prediction of Flat Rheology Drilling Fluids

Flat rheology drilling fluids are synthetic-based fluids designed to provide better drilling performance with flat rheological properties for deep water and/or cold environments. The detailed mud properties are mainly measured in laboratories and are often measured twice a day in the field. This prevents real-time mud performance optimization and negatively affects the decisions. If the real-time estimation of mud properties, which affects decision-making in time, is absent, the ROP may slow down, and serious drilling problems and severe economic losses may take place. Consequently, it is important to evaluate the mud properties while drilling to capture the dynamics of mudflow. Unlike other mud properties, mud density (MD) and Marsh funnel viscosity (MFV) are frequently measured every 15-20 minutes in the field. The objective of this work is to predict the rheological properties of the flat rheology drilling fluids in real-time using machine learning (ML). A proposed approach is followed to firstly predict the viscometer readings at 300 and 600 RPM (R600 and R300) and then calculate the other mud properties using the existing equations in the literature. For forecasting the viscometer readings, the created model using the decision trees (DT) demonstrated good accuracy. The results revealed a maximum average absolute percentage error (AAPE) below 4.5% and a correlation coefficient (R) of greater than 0.97. The estimated rheological properties showed a good matching with the actual values with low errors.