Multi-objective optimization framework for deepwater riser jetting installation parameters using deep reinforcement learning

Abstract

Optimizing conductor casing jetting installation in offshore oil and gas exploration is essential for underwater wellhead reliability. Traditional models often struggle with the complexities of this process, characterized by jetting drilling and soaking phases. To address this issue, a novel approach using deep reinforcement learning is introduced for comprehensive optimization of jetting parameters, enhancing deep-sea drilling efficiency. The methodology begins with an orthogonal simulated experiment to compile a robust dataset. Following preprocessing, including feature extraction and parameter scaling, a predictive model is developed to correlate installation parameters with jetting and soaking time. A composite action-value Q-learning (CAPQL) based multi-objective reinforcement learning framework is employed, establishing a Markov decision process environment for simultaneous optimization of jetting time and soaking periods. Applying this framework to selected deep-sea wells demonstrates a significant decrease in jetting drilling time (average 46.18%) and soaking time (22.57%), with the predictive model achieving a 99.32% average fit. This approach effectively navigates parameter interdependencies, ensuring optimal outcomes across diverse objectives. These findings present a groundbreaking approach for conductor casing jetting, offering greater precision and efficiency in offshore drilling operations and the potential to redefine industry standards.