本文選題：過程神經(jīng)網(wǎng)絡(luò) + 徑向基��； 參考：《東北石油大學(xué)》2017年碩士論文

【摘要】：經(jīng)過長期的水驅(qū)開發(fā),大量主力油田的開發(fā)區(qū)塊已進(jìn)入高含水期。由于注入溶液對油層的長期沖蝕,導(dǎo)致油水井之間產(chǎn)生優(yōu)勢滲流通道,致使注入溶液沿優(yōu)勢滲流通道無效循環(huán)而造成大量浪費(fèi),降低生產(chǎn)效率。要實(shí)現(xiàn)控水穩(wěn)油、提高油田生產(chǎn)效率,就必須要采取一定的措施對優(yōu)勢滲流通道進(jìn)行封堵,而有效識別優(yōu)勢滲流通道是進(jìn)行措施方案設(shè)計(jì)和優(yōu)化調(diào)整注采關(guān)系的關(guān)鍵前提。本課題通過研究油田開發(fā)過程中的動靜態(tài)數(shù)據(jù)、優(yōu)勢滲流場的形成機(jī)理以及影響因素,在對傳統(tǒng)判斷識別方法分析的基礎(chǔ)上,綜合利用油田地質(zhì)數(shù)據(jù)、開發(fā)數(shù)據(jù)、測試數(shù)據(jù)、儲層開采歷史數(shù)據(jù)等動靜態(tài)資料,提出一種基于徑向基函數(shù)過程神經(jīng)網(wǎng)絡(luò)結(jié)合進(jìn)化算法的油田優(yōu)勢滲流場識別方法和模型,以油田開發(fā)地質(zhì)參數(shù)和生產(chǎn)過程數(shù)據(jù)為輸入,輸出為注采井之間是否存在優(yōu)勢滲流場。利用沃爾什變換將過程輸入數(shù)據(jù)進(jìn)行規(guī)整,同時采用混沌遺傳算法對過程神經(jīng)網(wǎng)絡(luò)模型的性能參數(shù)進(jìn)行優(yōu)化求解,提高模型的自適應(yīng)能力和分類識別的準(zhǔn)確率。本文研究所用數(shù)據(jù)均來源于基于數(shù)模處理的大慶油田某采油廠部分區(qū)塊注水井與生產(chǎn)井的層位月數(shù)據(jù),通過分析滲流通道形成影響因素,篩選確定模型訓(xùn)練所用的指標(biāo)參數(shù)。將從油田開發(fā)實(shí)際歷史資料數(shù)據(jù)中選取的指標(biāo)參數(shù)進(jìn)行預(yù)處理并建立訓(xùn)練樣本集,經(jīng)過訓(xùn)練得到的徑向基過程神經(jīng)網(wǎng)絡(luò)判別模型應(yīng)用到油田優(yōu)勢滲流場判斷識別的實(shí)際問題中,取得了良好的應(yīng)用結(jié)果。本課題在面向油田優(yōu)勢滲流場判斷識別模型及算法研究的基礎(chǔ)上,結(jié)合油田生產(chǎn)開發(fā)數(shù)據(jù)管理情況進(jìn)行軟件原型系統(tǒng)的設(shè)計(jì)開發(fā),并實(shí)際部署應(yīng)用。課題的研究為油田生產(chǎn)開發(fā)提供了一種新的優(yōu)勢滲流場判斷識別方法,可為指導(dǎo)油田開發(fā)控水穩(wěn)油方案的設(shè)計(jì)與封堵措施調(diào)整提供依據(jù)和參考。
[Abstract]:After long-term water-drive development, a large number of major oilfield development blocks have entered a high water cut period. Due to the long-term erosion of the injected solution to the reservoir, there is a dominant seepage channel between oil wells and water wells, which leads to the ineffective circulation of the injected solution along the dominant seepage channel, which results in a large amount of waste and reduces the production efficiency. In order to control water and stabilize oil and improve the production efficiency of oil field, some measures must be taken to seal the dominant seepage channel, and the key premise of the design of measure scheme and the optimization adjustment of injection-production relationship are to identify the dominant seepage channel effectively. By studying the dynamic and static data during oilfield development, the formation mechanism of predominance seepage field and the influencing factors, on the basis of analyzing the traditional judgment and identification method, the paper synthetically uses oilfield geological data, development data and test data. Based on the dynamic and static data of reservoir production history, a method and model of oilfield dominant seepage field identification based on radial basis function (RBF) process neural network and evolutionary algorithm is proposed. The data of oilfield development geological parameters and production process are taken as input. The output is whether there is an advantage seepage field between injection-production wells. The process input data are regularized by Walsh transform and the performance parameters of the process neural network model are optimized by using chaotic genetic algorithm to improve the adaptive ability of the model and the accuracy of classification and recognition. The data used in this paper are all derived from the monthly data of injection wells and production wells in some blocks of Daqing Oilfield based on mathematical model processing. By analyzing the factors affecting the formation of percolation channels, the parameters used for model training are selected and determined. The index parameters selected from the actual historical data of oilfield development are pretreated and the training sample set is established. The trained radial basis process neural network discriminant model is applied to the practical problem of judging and identifying the dominant seepage field in oil field. Good application results have been obtained. Based on the research of recognition model and algorithm of oilfield dominant seepage field, the software prototype system is designed and developed based on the data management of oilfield production and development, and the application of software prototype system is put into practice. The research provides a new method to judge and identify the predominance seepage field for oilfield production and development, and provides the basis and reference for guiding the design of water control and oil stabilization scheme and the adjustment of plugging measures for oilfield development.
【學(xué)位授予單位】：東北石油大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TE312;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李信智;孫玉花;;樁74塊特低滲油藏小井距開發(fā)效果及影響因素分析[J];中國石油大學(xué)勝利學(xué)院學(xué)報(bào);2016年03期

2 姜新祝;許少華;;基于徑向基過程神經(jīng)網(wǎng)絡(luò)的油田措施效果預(yù)測[J];計(jì)算機(jī)與數(shù)字工程;2016年08期

3 王鳴川;石成方;朱維耀;丁樂芳;;優(yōu)勢滲流通道識別與精確描述[J];油氣地質(zhì)與采收率;2016年01期

4 陳存良;王振;牛偉;王漢滿;郭龍飛;;基于最小二乘支持向量機(jī)的大孔道定量計(jì)算方法[J];斷塊油氣田;2015年01期

5 李加祥;陳存良;王振;蔡煒;王滿漢;;基于BP神經(jīng)網(wǎng)絡(luò)的優(yōu)勢通道定量計(jì)算方法[J];河南科學(xué);2014年11期

6 李成政;石陜龍;李成翔;師瓊;;油田開發(fā)中油藏?cái)?shù)值模擬技術(shù)的應(yīng)用及發(fā)展[J];中國石油和化工標(biāo)準(zhǔn)與質(zhì)量;2013年20期

7 馮其紅;史樹彬;王森;馮國智;李先杰;楊光;;利用動態(tài)資料計(jì)算大孔道參數(shù)的方法[J];油氣地質(zhì)與采收率;2011年01期

8 崔慶東;;砂巖油藏大孔道的識別方法[J];油氣井測試;2009年03期

9 孫明;李治平;;注水開發(fā)砂巖油藏優(yōu)勢滲流通道識別與描述[J];斷塊油氣田;2009年03期

10 伍鐵斌;成運(yùn);周桃云;岳舟;;基于混沌遺傳算法的PID參數(shù)優(yōu)化[J];計(jì)算機(jī)仿真;2009年05期

相關(guān)博士學(xué)位論文 前1條

1 盧金娜;基于優(yōu)化算法的徑向基神經(jīng)網(wǎng)絡(luò)模型的改進(jìn)及應(yīng)用[D];中北大學(xué);2015年

相關(guān)碩士學(xué)位論文 前9條

1 張頡健;基于離散過程神經(jīng)網(wǎng)絡(luò)的航空發(fā)動機(jī)性能參數(shù)融合預(yù)測技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2015年

2 巴忠臣;水驅(qū)砂巖油藏優(yōu)勢滲流通道識別研究[D];中國石油大學(xué)(華東);2014年

3 王耀東;基于改進(jìn)粒子群算法的BP神經(jīng)網(wǎng)絡(luò)優(yōu)化及應(yīng)用[D];西安科技大學(xué);2012年

4 關(guān)春雨;油藏?cái)?shù)值模擬與油藏工程方法關(guān)系理論研究[D];東北石油大學(xué);2012年

5 薛升翔;徑向基神經(jīng)網(wǎng)絡(luò)算法優(yōu)化及在嵌入式系統(tǒng)中的應(yīng)用[D];新疆大學(xué);2011年

6 張強(qiáng);基于PNN的動態(tài)系統(tǒng)仿真方法與實(shí)現(xiàn)技術(shù)研究[D];大慶石油學(xué)院;2009年

7 周繼;基于過程神經(jīng)網(wǎng)絡(luò)的動態(tài)系統(tǒng)模式識別方法研究[D];大慶石油學(xué)院;2008年

8 宋德才;喇嘛甸油田大孔道電測特征及其識別方法研究[D];中國海洋大學(xué);2006年

9 李盼池;過程神經(jīng)網(wǎng)絡(luò)模型及學(xué)習(xí)算法研究[D];大慶石油學(xué)院;2004年

，

本文編號：2052143