基于遗传优化小波神经网络逆模型的油水测量

考虑基于传统的介电常数法动态测量原油含水率时存在多变量交叉敏感性, 检测精度无法满足石油生产实时优化控制的需要, 研究了利用多传感技术对存在交叉耦合的多敏感参量进行测量, 提出了一种基于多维数据驱动的遗传优化小波神经网络逆模型及其辨识方法。该模型克服了传统神经网络初始参数随机选取的盲目性, 具有全局优化和复杂非线性自学习性能, 摒弃了多影响因素之间的交叉敏感性。仿真和实验结果表明了该模型的有效性, 其模型预测值与实验标定值之间的相关系数为0.999 6, 优于BP-NN模型。该方法具有较强的泛化能力和鲁棒性, 有效抑制了温度、矿化度等多参量交叉敏感性及传感器自身非线性对测量精度的影响, 改善了多传感器系统的非线性动态特性和检测精度。

Abstract

As the traditional measuring method based on dielectric coefficients shows cross-sensitivity for multi-parameters in the measurement of oil/water two-phase flows, it can not meet the requirements of real-time optimization control for petroleum production. Therefore, this paper investigates a method to measure multi-parameters with cross-sensitivity by using multi-sensing technology.It presents an inverse model of wavelet neural network with genetic optimization and also researches its identification method. The model overcomes the blindness of initialization weight-value choice in traditional neural networks, provides the abilities of global optimization and nonlinear self-learning, and eliminates the cross-sensitivity of multi-factors. The simulation and experimental results demonstrate the validity and effectiveness of the proposed model and show that the correlation coefficient between the predicted values and calibration values is 0.999 6, which is better than that of BP-NN model. The method has strong generalized capability and robust convergence rate, and can effectively eliminate the influence of the cross-sensitivity of multi-factors and the nonlinearity of sensor self on the measuring precision, and improve the dynamic characteristics and measurement accuracy of sensor systems.

参考文献

[1] HEWITT G F. Measurement for Two-Phase Flow Parameters ［M］. London: Academic Press, 1978.

[2] 张冬至, 夏伯锴, 宋永强. 原油含水率测量多因素影响的数值模拟与实验研究［J］.计算机与应用化学, 2008, 25(8): 947-950.

ZHANG D ZH, XIA B K, SONG Y Q. Numerical simulation and experimental research of multi-factor influence on the measurement of water content in crude oil ［J］.Computers and Applied Chemistry, 2008, 25(8): 947-950. (in Chinese)

[3] ZHANG Y, LIU J H, ZHANG Y H, et al.. Cross sensitivity reduction of gas sensors using genetic algorithm neural network［J］. Optical Engineering, 2002, 41(3): 615-625.

[4] 金靖, 张忠钢, 王峥, 等. 基于RBF神经网络的数字闭环光纤陀螺温度误差补偿［J］. 光学精密工程, 2008, 16(2): 235-240.

JIN J, ZHANG ZH G, WANG ZH, et al.. Temperature error compensation for digital closed-loop fiber optic gyroscope based on RBF neural network［J］.Opt. Precision Eng., 2008, 16(2): 235-240. (in Chinese)

[5] 洪喜, 续志军, 杨宁. 基于径向基函数网络的光电编码器误差补偿法［J］.光学精密工程, 2008, 16(4): 598-604.

HONG X, XU ZH J, YANG N. Error compensation of optical encoder based on RBF network ［J］. Opt. Precision Eng., 2008, 16(4): 598-604. (in Chinese)

[6] 高贯斌, 王文, 林铿, 等. 圆光栅角度传感器的误差补偿及参数辨识［J］.光学精密工程, 2010, 18(8): 1766-1772.

GAO G B, WANG W, LIN K, et al.. Error compensation and parameter identification of circular grating angle sensors ［J］. Opt. Precision Eng., 2010, 18(8): 1766-1772. (in Chinese)

[7] 汤晓君, 刘君华. 交叉敏感情况下多传感器系统的动态特性研究［J］. 中国科学E辑, 2005, 35(1): 85-105.

TANG X J, LIU J H. Research on dynamic characteristics for multi-sensor system with cross sensitivity ［J］. Science in China (Series E) , 2005, 35(1): 85-105. (in Chinese)

[8] TUNCER E, SERDYUK Y V, GUBANSKI S M. Dielectric mixtures: electrical properties and modeling ［J］. IEEE Transactions on Dielectrics and Electrical Insulation, 2002, 9(5): 809-828.

[9] MOHAMED A M O, ELAMAL M, ZEKRI A Y. Effect of salinity and temperature on water cut determination in oil reservoirs ［J］. Journal of Petroleum Science and Engineering, 2003, 40(3-4): 177-188.

[10] AL-OTAIBI M B, ELKAMEL A, NASSEHI V, et al.. A computational intelligence based approach for the analysis and optimization of a crude oil desalting and dehydration process［J］. Energy & Fuels, 2005, 19(6): 2526-2534.

[11] 任磊, 王天婧, 陈祥光. 基于小波变换的油水混合物时域介电谱分析［J］. 兵工学报, 2008, 29(1): 47-51.

REN L, WANG T J, CHEN X G. Analysis of oil-water mixture using time domain dielectric spectroscopy based on wavelet transform ［J］. Acta Armamentarii, 2008, 29(1): 47-51. (in Chinese)

[12] 戴先中, 殷铭, 王勤. 传感器动态补偿的神经网络逆系统方法［J］. 仪器仪表学报, 2004, 25(5): 593-596.

DAI X ZH, YIN M, WANG Q. A novel dynamic compensating method based on ANN inverse system［J］. Chinese Journal of Scientific Instrument, 2004, 25(5): 593-596. (in Chinese)

[13] 于丽丽, 刘永红, 蔡宝平, 等. 基于小波神经网络的双电极同步伺服放电加工工艺效果预测［J］. 中国石油大学学报(自然科学版), 2008, 32(4): 87-90.

YU L L, LIU Y H, CAI B P, et al.. Prediction for electrical discharge machining process with synchronous servo double electrodes based on wavelet neural network ［J］. Journal of China University of Petroleum (Natural Science Edition), 2008, 32(4): 87-90. (in Chinese)

[14] 俞阿龙, 黄惟一. 力觉临场感系统中操作环境动力学的小波神经网络模型［J］. 仪器仪表学报, 2006, 27(1): 14-18.

U A L, HUANG W Y. Research on the dynamic model of operating environment in force telepresence system［J］. Chinese Journal of Scientific Instrument, 2006, 27(1): 14-18. (in Chinese)

[15] 高美静, 赵勇, 谈爱玲. 基于遗传小波神经网络的多传感器信息融合技术的研究［J］. 仪器仪表学报, 2007, 28(11): 2103-2104.

GAO M J, ZHAO Y, TAN A L. Study on genetic wavelet neural network based multi-sensor information fusion technique［J］. Chinese Journal of Scientific Instrument, 2007, 28(11): 2103-2104. (in Chinese)

张冬至, 胡国清. 基于遗传优化小波神经网络逆模型的油水测量[J]. 光学精密工程, 2011, 19(7): 1588. ZHANG Dong-zhi, HU Guo-qing. Measurement of oil-water flow based on inverse model of wavelet neural network with genetic optimization[J]. Optics and Precision Engineering, 2011, 19(7): 1588.

基于遗传优化小波神经网络逆模型的油水测量

关于本站 Cookie 的使用提示

全站搜索

基于遗传优化小波神经网络逆模型的油水测量

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索