| 基于KRR优化算法的油水系统中CO2溶解度模型 |
| |
| 引用本文： | 龙震宇,王长权,石立红,叶万立,刘洋,李一帆.基于KRR优化算法的油水系统中CO2溶解度模型[J].吉林大学学报(地球科学版),2022,52(1):194-201. |
| |
| 作者姓名： | 龙震宇 王长权 石立红 叶万立 刘洋 李一帆 |
| |
| 作者单位： | 1.长江大学石油工程学院，武汉430100
2.油气钻采工程湖北省重点实验室（长江大学），武汉430100 |
| |
| 摘 要： | 油藏中注入CO2可形成CO2原油地层水三相动态平衡，CO2在油水系统中的溶解度将直接影响CO2驱油效果和封存潜力。为了对CO2在油水系统中的溶解度模型进行研究，以吉林油田某油水系统为例，利用高温高压PVT分析仪开展CO2在不同体积比例油水系统中的溶解度实验，明确了CO2在油水系统中的溶解规律，并基于实验数据，分别利用网格搜索法(GS)和贝叶斯优化算法(BOA)对核岭回归算法(KRR)的参数进行优化，建立了CO2在油水系统中的溶解度预测模型。研究结果表明：CO2在油水系统中的溶解度随CO2注入量的增加而增大，也随油水体积比升高而增大；基于KRR算法的优化模型中，GSKRR模型和BOAKRR模型平均相对误差分别为6.758%和1.998%,说明BOAKRR具有更高的预测精度。利用BOAKRR模型预测并绘制不同温度、不同油水体积比下的CO2在油水系统中的溶解度图版，可为CO2碳捕集、利用与封存（CCUS）技术的应用提供支持。
|
| 关 键 词： | 核岭回归算法(KRR) 贝叶斯优化算法(BOA) 网格搜索法(GS) CO2溶解度 溶解度图版 碳捕集、利用与封存（CCUS）技术 |
| 收稿时间： | 2021-04-29 |
CO2 Solubility Model of Oil-Water System Based on KRR Optimization Algorithm |
| |
| Long Zhenyu,Wang Changquan,Shi Lihong,Ye Wanli,Liu Yang,Li Yifan.CO2 Solubility Model of Oil-Water System Based on KRR Optimization Algorithm[J].Journal of Jilin Unviersity:Earth Science Edition,2022,52(1):194-201. |
| |
| Authors: | Long Zhenyu Wang Changquan Shi Lihong Ye Wanli Liu Yang Li Yifan |
| |
| Institution: | 1． School of Petroleum Engineering College, Yangtze University，Wuhan 430100，China
2． Key Laboratory for Oil Gas Drilling and Production Engineering of Hubei Province（Yangtze University），Wuhan 430100，China
|
| |
| Abstract: | In the process of CO2 injection, a three phase dynamic equilibrium of CO2, crude oil, and formation water is formed. The solubility of CO2 in oil water system will directly affect the displacement effect and storage potential of CO2. In order to study the solubility of CO2 in oil water system, by taking the oil water system of Jilin oilfield as an example, the solubility experiment of CO2 in oil water system with different volume proportion was carried out by using PVT analyzer, and the solubility rule of CO2 in oil water system was clarified. In the experiment, the solubility of CO2 in oil water system increased with the increase of saturation pressure and oil water volume ratio. Based on the experimental data, the parameters of kernel ridge regression(KRR) were optimized by Grid search method (GS) and Bayesian optimization algorithm (BOA), respectively, and the CO2 solubility prediction model of CO2 in oil water system was established. The average relative errors of GS KRR model and BOA KRR model in the optimization model based on KRR algorithm are 6.758% and 1.998% respectively. It shows that by this BOA KRR model , the solubility of CO2 in oil water system can be predicted and plotted with higher precision. By using BOA KRR model, the solubility chart of CO2 in oil water system under different temperature and oil water ratio provides support for the application of CCUS（carbon capture, utilization and storage） technology. |
| |
| Keywords: | kernel ridge regression(KRR) Bayesian optimization algorithm(BOA) grid search(GS) CO2solubility solubility chart carbon capture utilization and storage technology |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《吉林大学学报(地球科学版)》浏览原始摘要信息 |
| 点击此处可从《吉林大学学报(地球科学版)》下载免费的PDF全文 |
