文章检索
首页» 过刊浏览» 2021» Vol.6» Issue(3) 505-515     DOI : 10.3969/j.issn.2096-1693.2021.03.041
最新目录| | 过刊浏览| 高级检索
基于两层分解算法和改进 SVM 的油田采出水处理效果预测研究
徐磊,侯磊,朱振宇,徐震,雷婷,李雨,李强,陈秀芹,王九玲 ,陈星燃
1 中国石油大学(北京)机械与储运工程学院,北京 102249 2 中国石油大学(北京)石油工程教育部重点实验室,北京 102249 3 中国石化胜利油田有限公司桩西采油厂,东营 257237 4 北京交通大学( 威海校区) 土建学院,威海 264200
Prediction of oilfield produced water treatment based on a two-layer decomposition technique and modified SVM
XU Lei, HOU Lei, ZHU Zhenyu, XU Zhen, LEI Ting1,2, LI Yu1,2, LI Qiang, CHEN Xiuqin, WANG Jiuling, CHEN Xingran
1 College of Mechanical and Transportation Engineering, China University of Petroleum-Beijing, Beijing 102249, China 2 MOE Key Laboratory of Petroleum Engineering, China University of Petroleum-Beijing, Beijing 102249, China 3 Zhuangxi Oil Production Company of Sinopec Shengli Oilfield, Dongying 257237, China 4 School of Civil Engineering, Beijing Jiaotong University(Weihai), Weihai 264200, China

全文:   HTML (1 KB) 
文章导读  
摘要  准确的水质预测是评估油田联合站采出水处理效果的重要依据,为水质预警提供科学依据。传统方法存 在主观性强和耗时性长等缺点,现有部分研究借助于机器学习方法,但对数据噪声和数据非线性考虑不足。本 研究提出一种基于两层分解算法与改进支持向量机相结合的预测方法。通过两层分解算法消除冗余噪声,提取 初始数据主要特征。利用分层抽样对原始数据集进行划分,避免传统随机抽样引起的样本偏差。采用改进粒子 群算法优选支持向量机参数,提高全局收敛能力。针对桩西采油厂联合站 4 个案例,依据相对误差、平均绝对 百分比误差和决定系数 3 个评价指标对提出的预测方法展开准确性评价,基于 4 个案例 3 个指标值的平均值分 别为-0.38%、5.23%和 0.82%。相比于现有主流机器学习方法,提出的预测方法具有较高的预测精度。
服务
把本文推荐给朋友
加入我的书架
加入引用管理器
关键词 : 油田联合站;水质预测;机器学习;两层分解算法;改进支持向量机
Abstract
The accurate prediction of the produced water quality is an important basis for evaluation of the treatment effect of    
the produced water at the oilfield joint station, which can provide a scientific basis for early warning of water quality. In the tradi  
tional method, we can see that the prediction of the oilfield produced water quality is mainly based on the experience of experts,  
however, there is no doubt that this method has a strong personal subjectivity so it is difficult to reach an accurate prediction    
of the quality of the produced water. There is also a part of existing studies to measure whether the produced water quality is    
up to the relevant standard. However, this method has the disadvantage of taking a long time so that it is not conducive for the    
efficient development of on-site work. Now there is a part of the existing research with the help of machine learning algorithms,    
but the situation of data noise and data non-linearity is not fully considered in these methods. In response to the above problems,    
a novel method for water quality prediction is put forward in this paper, which is based on the combination of the two-layer    
decomposition method and the modified support vector machine (SVM) algorithm. Through the two-layer decomposition method    
put forward above, the redundant noise in the prediction process can be eliminated effectively, and at the same time the major    
features of the original data can be extracted. The method of stratified sampling is used to divide the original dataset so as to    
avoid the sample deviation caused by the method of traditional random sampling. A modified particle swarm algorithm is applied    
to optimize the parameters of the SVM so that the global convergence ability can be improved by this algorithm. On the basis of    
the four cases of the Zhuangxi oil production plant joint station, the prediction accuracy of this method is evaluated in the light of    
three evaluation indexes: the relative error, the average absolute percentage error and the determination coefficient. On the basis    
of the average values of these 4 cases on the three indicators are -0.38   %   , 5.23   %   and 0.82   %   , respectively. Compared with the    
existing mainstream machine learning algorithms, we can see that the method in this paper has higher prediction accuracy.  


Key words: oilfield joint station; water quality prediction; machine learning; two-layer decomposition; modified support vector machine
收稿日期: 2021-09-29     
PACS:    
基金资助:
通讯作者: houleicup@126.com
引用本文:   
徐磊, 侯磊, 朱振宇, 徐震, 雷婷, 李雨, 李强, 陈秀芹, 王九玲, 陈星燃. 基于两层分解算法和改进SVM的油田采出水处理效果预测 研究. 石油科学通报, 2021, 03: 505-515 XU Lei, HOU Lei, ZHU Zhenyu, XU Zhen, LEI Ting, LI Yu, LI Qiang, CHEN Xiuqin, WANG Jiuling, CHEN Xingran. Prediction of oilfield produced water treatment based on a two-layer decomposition technique and modified SVM. Petroleum Science Bulletin, 2021, 03: 505-515.
链接本文:  
版权所有 2016 《石油科学通报》杂志社