{"title":"Unlocking optimal performance and flow level control of three-phase separator based on reinforcement learning: A case study in Basra refinery","authors":"","doi":"10.1016/j.tsep.2024.102885","DOIUrl":null,"url":null,"abstract":"<div><p>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.</p></div>","PeriodicalId":23062,"journal":{"name":"Thermal Science and Engineering Progress","volume":null,"pages":null},"PeriodicalIF":5.1000,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Thermal Science and Engineering Progress","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2451904924005031","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0
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.
期刊介绍:
Thermal Science and Engineering Progress (TSEP) publishes original, high-quality research articles that span activities ranging from fundamental scientific research and discussion of the more controversial thermodynamic theories, to developments in thermal engineering that are in many instances examples of the way scientists and engineers are addressing the challenges facing a growing population – smart cities and global warming – maximising thermodynamic efficiencies and minimising all heat losses. It is intended that these will be of current relevance and interest to industry, academia and other practitioners. It is evident that many specialised journals in thermal and, to some extent, in fluid disciplines tend to focus on topics that can be classified as fundamental in nature, or are ‘applied’ and near-market. Thermal Science and Engineering Progress will bridge the gap between these two areas, allowing authors to make an easy choice, should they or a journal editor feel that their papers are ‘out of scope’ when considering other journals. The range of topics covered by Thermal Science and Engineering Progress addresses the rapid rate of development being made in thermal transfer processes as they affect traditional fields, and important growth in the topical research areas of aerospace, thermal biological and medical systems, electronics and nano-technologies, renewable energy systems, food production (including agriculture), and the need to minimise man-made thermal impacts on climate change. Review articles on appropriate topics for TSEP are encouraged, although until TSEP is fully established, these will be limited in number. Before submitting such articles, please contact one of the Editors, or a member of the Editorial Advisory Board with an outline of your proposal and your expertise in the area of your review.