Intelligent MPD Set-Point Control for Narrow Windows: A Reinforcement Learning Framework for Automated Choke Control in Deepwater HPHT Wells

Deep water high-pressure, high-temperature (HPHT) drilling in managed pressure drilling (MPD) offers great challenges because of very thin changes between pore pressure and fracture gradient, frequently below equivalent mud weight of 0.3 ppg. Traditional rule-based MPD tuning algorithms fail to hold optimal setpoints in real-time resulting in influx/loss events and inefficient rate of penetration (ROP). This paper introduces a new reinforcement learning (RL) model of intelligent MPD set-point control, which is more specifically backpressure and equivalent circulating density (ECD) optimization in narrow-margin deepwater wells that characteristic of the Gulf of Guinea area, such as Ghana and Nigeria. A Deep Deterministic Policy Gradient (DDPG) model was optimized using past MPD operational data in West African deepwater campaigns which included a multi-objective reward function balancing between influx risk, loss risk, and ROP optimization. The paradigm shows that the pressure control accuracy (23% improvement over rule-based approaches) and mean absolute pressure deviation (42 psi to 32 psi) are lower in comparison to rule-based approaches. Moreover, the model had an average increase of 15 percent in the average ROP and was able to keep wellbore stable despite the thin drilling window. The intelligent control system detected and reacted to simulated kick situations 18 seconds earlier than the traditional automated MPD systems, which is a giant development in real-time well control capacity. The above results imply that the operational benefits of RLbased MPD control are enormous in strenuous deepwater HPHT drilling operations, and could be applicable to the whole range of the Gulf of Guinea deepwater drilling ventures.