Improving Water-Based Drilling Mud Performance Using Biopolymer Gum: Integrating Experimental and Machine Learning Techniques

Abstract

Drilling through shale formations can be expensive and time-consuming due to the instability of the wellbore. Further, there is a need to develop inhibitors that are environmentally friendly. Our study discovered a cost-effective solution to this problem using Gum Arabic (ArG). We evaluated the inhibition potential of an ArG clay swelling inhibitor and fluid loss controller in water-based mud (WBM) by conducting a linear swelling test, capillary suction timer test, and zeta potential, fluid loss, and rheology tests. Our results displayed a significant reduction in linear swelling of bentonite clay (Na-Ben) by up to 36.1% at a concentration of 1.0 wt. % ArG. The capillary suction timer (CST) showed that capillary suction time also increased with the increase in the concentration of ArG, which indicates the fluid-loss-controlling potential of ArG. Adding ArG to the drilling mud prominently decreased fluid loss by up to 50%. Further, ArG reduced the shear stresses of the base mud, showing its inhibition and friction-reducing effect. These findings suggest that ArG is a strong candidate for an alternate green swelling inhibitor and fluid loss controller in WBM. Introducing this new green additive could significantly reduce non-productive time and costs associated with wellbore instability while drilling. Further, a dynamic linear swelling model, based on machine learning (ML), was created to forecast the linear swelling capacity of clay samples treated with ArG. The ML model proposed demonstrates exceptional accuracy (R2 score = 0.998 on testing) in predicting the swelling properties of ArG in drilling mud.

Keywords

• water-based mud
• swelling inhibition
• fluid loss
• Gum Arabic
• green additive
• machine learning