欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
原油含水率是评价油井产能的一项重要指标，但其易受矿化度、温度、流体状态、流体速度等参数的影响。针对基于电导法的原油含水率检测模型，通过室内外试验，得出了原油含水率的主要影响因素，建立了基于最小二乘法支持向量机的自校准模型。利用Matlab编写了自校准程序，运用10倍交叉验证的方法确定了最小二乘法支持向量机的优化参数，然后把达到预期拟合效果的自校准程序下载到DSP处理器中运行，实现了在一次仪表中对原油含水率测量结果的自校准。试验结果表明，原油含水率的影响因素与原油含水率之间呈非线性关系，自校准算法消除了主要干扰量对原油含水率的影响，实现了测量结果的自标定。和目前油田计量部门使用的蒸馏法相比，基于最小二乘法支持向量机的原油含水率检测模型不仅可以实现实时测量与校准，且原油含水率的相对误差比采用最小二乘法时有所减小。
英文摘要：
Moisture content in crude oil is an important index to evaluate the productivity of oil well, but it is easily affected by salinity ,temperature ,fluid status,fluid velocity and other environmental parameters. In accordance with the moisture content in crude oil detection model based on conductivity method, through indoor and outdoor experiments, the main factors influencing on this index are obtained; and the self calibration model is established based on least square support vector machine. The self calibration program is written by using Matlab, the optimization parameters of least squares support vector machine are determined by 10- fold cross validation, then the self calibration program that reaches predictive fitting effect is downloaded into DSP processor for running; thus the calibration for measurement result of moisture content in crude oil is implemented in primary instrument. The test results indicate that the relationship between moisture content and the influencing factor is nonlinear, the self calibration algorithm eliminates the influence of main disturbance, the self calibration of the measurement result is implemented. Comparing with the distillation method currently used by the metering department of oil field,the detection model based on least squares support vector machine can not only realize real - time measurement and calibration, the relative error of moisture content in crude oil is also improved.
同期刊论文项目
同项目期刊论文
期刊信息
位置：