多传感器融合技术在原油含水率测量中的应用
首发时间:2006-08-02
摘要:本文通过多传感器技术对原油含水率测量影响的多个参量进行测定,提出基于多元非线性回归和神经网络的融合方法建立原油含水率预测模型,并采用分段建模的方法进行改进。评价结果表明:神经网络模型预测效果优于多元非线性回归模型,原油含水率分段预测模型效果优于统一模型。尤其是改进的神经网络分段预测模型具有网络结构简化、收敛速度快,泛化能力强的特点,取得很好的拟合精度和预测效果。
For information in English, please click here
Application of Multi-sensor Fusion Technology in Measuring of Water content ratio in Crude Oil
Abstract:Using multi-sensor technology, some parameters affecting the measurement of water content ratio of crude oil are measured, and prediction models of water content ratio of crude oil based on the methods of multivariate nonlinear regression and artificial neutral networks are presented, and then being improved by subsection modeling. The assessed results show that the prediction effect of artificial neutral networks model is better than that of multivariate nonlinear regression model, as well as the forecast effect of subsection model for water content ratio of crude oil is better than that of united model. In particular the improving neural network subsection prediction model can take advantage of simple network structure, fast convergence rate and strong generalization capability, and get a good modeling effect.
Keywords: Crude oil Water content ratio Multivariate nonlinear regression Neutral networks Prediction model
基金:
论文图表:
引用
No.7781780341154501****
同行评议
共计0人参与
勘误表
多传感器融合技术在原油含水率测量中的应用
评论
全部评论0/1000