Unlocking optimal performance and flow level control of three-phase separator based on reinforcement learning: A case study in Basra refinery

Abstract

This research explores the application of a new reinforcement learning (RL-based) controller for a three-phase separator connected to a gas turbine. The control of flow levels within the separator directly impacts fluid flow turbulence, especially when the equipment is linked to waste heat gas from the turbine to improve gas quality. The study introduces the novel RL-based controller and validates its effectiveness in real-world conditions using three-phase separators in Basra, Iraq, and through a review of relevant literature. The controller can adapt to inlet conditions such as pressure, temperature, mass flow rate, and incoming heat from the gas turbine. Waste heat recovery from the gas can enhance gas purity but also increase turbulence in water and oil. Maintaining a calm flow while ensuring high-speed flow over the baffle in the middle of the separator is crucial for optimal performance. The study considers two geometrical configurations of the vessel for redesigning the separator at the Basra refinery. The controller was implemented using the groovyBC utility within the OpenFOAM software. This model was then utilized to simulate real-world scenarios at the Basra refinery, displaying faster convergence, more rapid response, and more accurate tracking of the target fluid level. This study marks the initial effort to apply the deep deterministic policy gradient (DDPG) controller in computational fluid dynamic (CFD) work. The findings demonstrated a significant enhancement in separation efficiency by more than 36%, as well as smoother streamlines through the control and maintenance of pressure and velocity over the baffle.