Autonomous Drilling Fluid Management System - Expansion of Fluid Advisory System Across Multiple Fluid Systems

Abstract This research aims to develop a Fluid Advisory System that provides recommendations for the optimal amounts of chemical additives needed to maintain desired fluid properties in various drilling fluid systems. Building on the foundation laid by the Fluid Advisory System for water-based fluids (Ettehadi et al., 2023), this project expands its scope to include both water- and oil-based muds. To achieve this goal, a machine learning (ML) model is created to predict the target fluid properties, with separate models developed for water- and oil-based muds due to their distinct characteristics. These models utilize transfer learning techniques that allow existing models to serve as base models for similar fluid systems thereby enhancing efficiency. An integrated optimization framework determines the ideal quantities of chemical additives, ensuring precise mass calculations and optimal dilution methods. The effectiveness of the Fluid Advisory System is validated through small-scale lab experiments which analyzed samples of water- and oil-based muds previously used offshore, despite the unknown exact compositions of these muds. The testing outcomes demonstrate the system's ability to regulate critical parameters such as mud weight, rheology, API fluid loss, pH, hardness, chloride concentration, oil-water-ratio, concentration of low gravity solids (LGS), excess lime, and electrical stability (ES). In summary, this paper provides a detail account of the development and experimental validation of the Fluid Advisory System, which effectively manages multiple properties of drilling fluids across different fluid systems, offering substantial advantages to fluid engineers and marking a significant advancement in the drilling industry by improving accuracy and efficiency.