基于線性回歸與神經(jīng)網(wǎng)絡(luò)的儲(chǔ)層參數(shù)預(yù)測(cè)復(fù)合方法
發(fā)布時(shí)間：2018-12-09 13:10
【摘要】：為提高儲(chǔ)層參數(shù)的預(yù)測(cè)精度,提出一種利用測(cè)井資料,結(jié)合多元線性回歸和神經(jīng)網(wǎng)絡(luò)預(yù)測(cè)儲(chǔ)層參數(shù)的新的復(fù)合方法,具體分兩步:(1)通過(guò)多元線性回歸分析建立回歸值y'的計(jì)算模型,將y'作為儲(chǔ)層參數(shù)的初步預(yù)測(cè)值;(2)通過(guò)RBF神經(jīng)網(wǎng)絡(luò)建立y'的殘差Δd的預(yù)測(cè)模型,將預(yù)測(cè)結(jié)果Δd作為y'的非線性誤差補(bǔ)償,最終建立儲(chǔ)層參數(shù)解釋模型,y=y'+Δd。基于該方法,結(jié)合測(cè)井資料和巖心數(shù)據(jù),建立了鄂爾多斯盆地某致密砂巖氣田M3井區(qū)S_2~2、T_2~2段孔隙度和含水飽和度的測(cè)井解釋模型,結(jié)果顯示,新方法建立的模型預(yù)測(cè)值與S_2~2、T_2~2段實(shí)際巖心孔隙度、含水飽和度值的平均相對(duì)誤差均小于17%,明顯優(yōu)于單獨(dú)根據(jù)多元線性回歸分析或RBF神經(jīng)網(wǎng)絡(luò)建立的解釋模型,預(yù)測(cè)精度更高。
[Abstract]:In order to improve the prediction accuracy of reservoir parameters, a new composite method is proposed to predict reservoir parameters by using logging data, combining multiple linear regression and neural network. It is divided into two steps: (1) the regression value 'calculation model is established by multiple linear regression analysis, and y' is regarded as the preliminary prediction value of reservoir parameters; (2) the prediction model of Y 'residual 螖 d is established by RBF neural network, and the prediction result 螖 d is regarded as the nonlinear error compensation of y'. Finally, the reservoir parameter interpretation model, YY' 螖 d, is established. Based on this method, a logging interpretation model for the porosity and water saturation of SSP _ 2O _ 2T _ 2O _ 2 section in M _ 3 well area of a tight sandstone gas field in Ordos Basin is established by combining well logging data and core data. The results show that, The predicted values of the new model and the actual core porosity and the average relative error of the water saturation values of the two sections are all less than 17, which is obviously superior to the interpretation model established solely on the basis of multiple linear regression analysis or RBF neural network. The prediction accuracy is higher.
【作者單位】： 中國(guó)地質(zhì)大學(xué)(北京)能源學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(41272132) 中國(guó)地質(zhì)調(diào)查局地質(zhì)調(diào)查項(xiàng)目(2-1-2010-18-A,12120115002901-04)資助
【分類號(hào)】：P618.13
[Abstract]:In order to improve the prediction accuracy of reservoir parameters, a new composite method is proposed to predict reservoir parameters by using logging data, combining multiple linear regression and neural network. It is divided into two steps: (1) the regression value 'calculation model is established by multiple linear regression analysis, and y' is regarded as the preliminary prediction value of reservoir parameters; (2) the prediction model of Y 'residual 螖 d is established by RBF neural network, and the prediction result 螖 d is regarded as the nonlinear error compensation of y'. Finally, the reservoir parameter interpretation model, YY' 螖 d, is established. Based on this method, a logging interpretation model for the porosity and water saturation of SSP _ 2O _ 2T _ 2O _ 2 section in M _ 3 well area of a tight sandstone gas field in Ordos Basin is established by combining well logging data and core data. The results show that, The predicted values of the new model and the actual core porosity and the average relative error of the water saturation values of the two sections are all less than 17, which is obviously superior to the interpretation model established solely on the basis of multiple linear regression analysis or RBF neural network. The prediction accuracy is higher.
【作者單位】： 中國(guó)地質(zhì)大學(xué)(北京)能源學(xué)院;
【基金】：國(guó)家自然科學(xué)基金(41272132) 中國(guó)地質(zhì)調(diào)查局地質(zhì)調(diào)查項(xiàng)目(2-1-2010-18-A,12120115002901-04)資助
【分類號(hào)】：P618.13
【相似文獻(xiàn)】
相關(guān)期刊論文 前10條
1 楊斌,肖慈s，
本文編號(hào)：2369410
本文鏈接：http://sikaile.net/kejilunwen/diqiudizhi/2369410.html
最近更新
教材專著
