![一种基于聚类算法的原油含水数据分析方法](/CN/2019/1/126/images/201910631281.jpg)
基本信息:
- 专利标题: 一种基于聚类算法的原油含水数据分析方法
- 专利标题(英):Crude oil water content data analysis method based on clustering algorithm
- 申请号:CN201910631281.3 申请日:2019-07-12
- 公开(公告)号:CN110796155A 公开(公告)日:2020-02-14
- 发明人: 任桂山 , 李红艳 , 葛党科 , 徐国安 , 米立飞 , 孙凯 , 王存博 , 徐津民
- 申请人: 大港油田集团有限责任公司
- 申请人地址: 天津市滨海新区大港三号院
- 专利权人: 大港油田集团有限责任公司
- 当前专利权人: 大港油田集团有限责任公司,中国石油天然气集团有限公司
- 当前专利权人地址: 天津市滨海新区大港三号院
- 代理机构: 天津市三利专利商标代理有限公司
- 代理人: 张义
- 主分类号: G06K9/62
- IPC分类号: G06K9/62 ; G06Q10/06
The invention discloses a crude oil water content data analysis method based on a clustering algorithm. According to a known differential pressure-electric value rule of fluid produced by an oil well,differential pressure-electric value feature points of different oil wells are used as clustering data points, the clustering algorithm is selected to divide the data points into three types including a liquid phase, a gas phase and a mixed phase. The differential pressure-electric value rule of liquid phase fluid is that the differential pressure is high and the electric value is low, the differential pressure-electric value rule of gas phase fluid is that the differential pressure is low and the electric value is high, and mixed phase fluid is in the middle. According to the method, the data point distribution rule of the oil well output fluid under the three fluid characteristics of the liquid phase, the gas phase and the mixed phase is established and analyzed through the clustering algorithm, and the problem that a good clustering result cannot be obtained through traditional data analysis is effectively solved.
IPC结构图谱:
G | 物理 |
--G06 | 计算;推算;计数 |
----G06K | 数据识别;数据表示;记录载体;记录载体的处理 |
------G06K9/00 | 用于阅读或识别印刷或书写字符或者用于识别图形,例如,指纹的方法或装置 |
--------G06K9/62 | .应用电子设备进行识别的方法或装置 |