فهرست نشریات علمی دسترسی آزاد ایران

Drilling fluids are essential for efficient drilling operations, with gelation performance playing a crucial role in maintaining wellbore stability, transporting cuttings, and preventing losses. This review examines the transformative potential of artificial intelligence (AI) and numerical simulation in enhancing the optimization of drilling fluid gel performance and formulation design. Four AI techniques—expert systems, artificial neural networks (ANNs), support vector machines (SVMs), and genetic algorithms—are evaluated, with ANNs dominating 52% of studies due to their ability to model nonlinear relationships. Numerical simulation methods, including computational fluid dynamics (CFD), molecular dynamics (MD), and Monte Carlo simulations, are analyzed for their capacity to simulate fluid behavior under complex conditions. Key challenges include limited access to field data and oversimplified model assumptions, which hinder predictive accuracy. Circulation loss, a primary concern in over 17% of research, underscores the need for robust predictive models. The review proposes three future directions: enhancing interpretable AI through feature engineering, establishing open-access oil and gas databases, and advancing microscopic numerical simulations to reduce data dependency. By integrating AI with numerical methods, researchers can better address high-dimensional, nonlinear problems in drilling fluid design. This synergy promises cost-effective, precise formulation optimization, paving the way for intelligent drilling technologies. The findings underscore the need for hybrid approaches and data accessibility to address current limitations and drive innovation in the drilling fluid industry, ultimately enhancing operational efficiency and environmental sustainability.