跳到主要內容

臺灣博碩士論文加值系統

(54.161.24.9) 您好!臺灣時間:2022/01/17 11:27
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:田川昇
研究生(外文):Chuan-Sheng Tian
論文名稱:利用基因演算法與類神經網路建立台灣西南海域深部地層滲透率模式之研究
論文名稱(外文):Development of Permeability Models for Southwestern Taiwan Area by both Genetic Algorithm and Artificial Neural Network
指導教授:林再興林再興引用關係
指導教授(外文):Zsay-Shing Lin
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資源工程學系碩博士班
學門:工程學門
學類:材料工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:中文
論文頁數:112
中文關鍵詞:類神經網路地層滲透率井下電測基因演算法
外文關鍵詞:genetic algorithmartificial neural networkwell loggingformation permeability
相關次數:
  • 被引用被引用:9
  • 點閱點閱:943
  • 評分評分:
  • 下載下載:304
  • 收藏至我的研究室書目清單書目收藏:1
摘要

傳統的滲透率模式建立過程中,常面臨模式的選擇以及模式中的參數推求之問題,而採用類神經網路的訓練及學習,可以改進這些問題,所以,本研究目的是利用地球物理井下電測資料及實際測得的岩心滲透率資料,先選擇前人的滲透率模式(傳統模式),利用基因演算法推求模式中的各個參數值而建立模式,同時也利用已知資料訓練類神經網路,建立滲透率模式(類神經網路模式)。

本研究利用台灣南部的三口井(X-9 號井、X-10 號井及 X-11 號井,井深介於 3244 公尺至 3450 公尺間 )之岩心資料,並蒐集及分析這三口井的井測資料:包含自然加瑪 (GR)、感應式電阻電測 (ILD)、球聚式焦點電測 (SFL)及微球聚式焦點電測 (MSF)、井徑 (CAL)、中子 (CNL)、密度 (FDC)、聲波 (BHC)等。本研究所選用滲透率模式為Wylie - Rose 模式、Coates-Dumanoir 模式及孔隙率模式等三種。首先,利用基因演算法分別求得三種滲透率計算模式之參數,其中綜合這三口井在漸新世砂層的資料,分別建立三種模式。又由於漸新世砂層中含NP24B及NP24A地層,因此也分別利用這二地層的資料分別建立Wylie - Rose 模式、Coates-Dumanoir 模式及孔隙率模式,其中以Wylie - Rose 模式為最好。

另外,也利用已知資料訓練類神經網路建立滲透率模式。本研究建立以下三種網路架構:(a)第一種架構的輸入層參數為:深度、井徑電測(CAL)、聲波電測(BHC)、自然加碼(GR)、深感應電阻電測(ILD)、球聚式焦點電測(SFL)及地層密度電測(FDC)等電測資料;輸出層為地層滲透率。(b)第二種架構輸入層的參數為:井徑電測(CAL)、聲波電測(BHC)、自然加碼(GR)、深感應電阻電測(ILD)、球聚式焦點電測(SFL)及地層密度電測(FDC)等電測資料;輸出層為地層滲透率。(c)第三種架構的輸入層參數為:孔隙率、含水飽和度、地層真電阻及地層水電阻;輸出層為地層滲透率。在上述三種網路的訓練結果之中,以第一種類神經網路結果最佳,因為均方誤差(MSE)最小,判定係數(R )最大,建議使用。在基因演算法與類神經網路計算地層滲透率的結果之比較,可看出類神經網路所擬合的資料點較基因演算法更好。

關鍵詞:井下電測;基因演算法; 類神經網路;地層滲透率
ABSTRACT

Permeability information is a very important parameter in the reservoir engineering and underground water study. In the process of deriving the traditional permeability models, the key steps are the selection of model and the determination of constant parameters in the model. These key steps can be easily implemented by developing an artificial neural network. Therefore the purpose of this study is to use geophysics well logging data and core permeability data to derive permeability models (traditional models) in which the parameters in the model are estimated by genetic algorithm. At the same time, we also use the known data to train the artificial neural network for calculating the permeability.

In this study, geological well logs from three wells (X-9、X-10 and X-11 , well depths between 3244 m to 3450 m ) in southern Taiwan area are collected and analyzed. The collected well logging data include gamma ray (GR)、resistivity induction log deep (ILD)、resistivity of spherically focused log (SFL)、resistivity of microspherically focused log (MSF)、caliper log (CAL)、compensated neutron log (CNL)、formation density log (FDC) and borehole compensated sonic log (BHC). Three permeability models, such as, Wylie - Rose model、Coates-Dumanoir model and Porosity model, are selected. These three models are derived from using collected data, the well log data and core data, in the interval of Oligocene sand formation. Also, the data in NP24B and NP24A, which are in the the Oligocene sand formation, are used separately to derive the Wylie - Rose model、Coates-Dumanoir model and Porosity model. The Wylie - Rose model is the best of among those models.
Besides, three artificial neural network is also developed from using the data collected. In the first kind of neural network structures, the input parameters are:DEPTH、CAL、BHC、GR、ILD、SFL and FDC;and the output data is formation permeability. In the second kind of neural network, the input parameters are : CAL、BHC、GR、ILD、SFL and FDC;and output data is formation permeability. In the third kind of neural network, the input parameters are:porosity、water saturation、formation resistivity and formation water resistivity;and output data is formation permeability .The result of the first kind of artificial neural network model is the best of the three models ,because of the Mean Square Error being the minimum, and coefficient of determination being the maximum .The permeability calculated from using artificial neural network is better than using genetic algorithm .

Keywords:well logging ; genetic algorithm ; artificial neural network;formation permeability
目錄
頁次
摘要 --------------------------------------------------------------------------- 3
英文摘要 -------------------------------------------------------------------- 5
誌謝 --------------------------------------------------------------------------- 7
目錄 --------------------------------------------------------------------------- 8表目錄 ---------------------------------------------------------------------- 10
圖目錄 ------------------------------------------------------------------------ 12

第一章 緒論----------------------------------------------------------------- 14
§ 1-1前言------------------------------------------------------------------- 14
§1-2研究目的-------------------------------------------------------------- 15

第二章 文獻回顧--------------------------------------------------------- 16
§ 2-1傳統滲透率計算模式---------------------------------------------- 16
§ 2-2基因演算法之應用與原理-------------------------------------- 21
§ 2-3類神經網路之應用與原理-------------------------------------- 28

第三章 資料的蒐集與分析步驟----------------------------------- 36
§ 3-1資料的蒐集------------------------------------------------------- 36
§ 3-2分析步驟與流程圖--------------------------------------------- 40
§ 3-3模式的建立------------------------------------------------------- 43

第四章 分析結果與討論---------------------------------------------- 49
§4-1傳統經驗模式配合基因演算法---------------------------------- 49
§4-1-1 Wylie-Rose 模式------------------------------------------- 49
§4-1-2 Dumanoir-Coates 模式------------------------------------ 53
§4-1-3 Porosity 模式------------------------------------------------- 56
§4-1-4 基因演算法之綜合分析結果----------------------------- 56
§4-2 類神經網路-------------------------------------------------------- 69
§4-2-1類神經網路模式一----------------------------------------- 71
§4-2-2類神經網路模式二----------------------------------------- 76
§4-2-3類神經網路模式三----------------------------------------- 80
§4-3綜合討論------------------------------------------------------------ 84

第五章 結論與建議---------------------------------------------------- 87

參考文獻--------------------------------------------------------------------- 90

附 錄------------------------------------------------------------------- 95
§ 附錄A 岩心資料與井測資料------------------------------------- 95
§ 附錄B 類神經網路之MATLAB程式碼-------------------------- 100
§ 附錄C 井測原理及種類--------------------------------------------- 106
參考文獻

Ali, M., and Chawathe, A., ”Using artificial intelligence to predict permeability from petrographic data” Computers & Ggosciences (September 2000) 915-925

Asquith, G. and Gibson, G., Basic Well Log Analysis for Geologists: Methods in Exploration Series, AAPG, Tulsa, Oklahoma. 1985.

Balan, B., Mohaghegh S. and Ameri, S., State-Of-The-Art in Permeability Determination From Well Log Data: Part1 –A Comparative Study, Model Development, SPE Eastern Regional Conference & Exhibition, 1995

Clark , N.J., Elements of Petroleum
Reservoirs , American Institute of Mining , Metallurgical & Petroleum Engineers , Inc , Dallas , Texas , 1969

Coates, G. and Dumanoir, J.L., “A new approach to improve log-derived permeability, ” Society of Professional Well Log Analysts, 14th Annual Logging Symposium, Trans., paper R. 1973.

Debra A. and Osborne, D.A., “Neural networks provide more accurate reservoir permeability,” Oil & Gas Journal, 1992,pp125-132.

Holland,J.H” Genetic Algorithms and the optimal allocations of trials.SIAM Jornal of Computing,2(2),1971,pp.88-105.

Huang, Z., Shimeld, J., Willianmson, M. and Kastube, J, "Permeability prediction with artificial neural network modeling in the Venture gas field, offshore eastern Canada," GEOPHYSICS(March-April 1996)422-436.

Haykin, Simon, Neural Networks – A Comprehensive Foundation, Prentice Hall, New Jersey, 1999.

Hornik, K., Stinchcombe, M. and White, H., “Multilayer Feedforward Networks are Universal Approximators,” Neural Networks, vol. 2, 1989.

Jaafar, I.B., Depositional and Diagenetic History of the B-Zone of the Red River Formation (Ordovician) of the Beaver Creek Field, Golden Valley County, North Dakota : M. S. thesis, West Texas State Univ.1980. pp.68

Matlab, Neural Network Toolbox, User's Guide, The Math Work Inc., 1998.

Mohaghegh, S., Arefi, R., Ameri, S., and Rose, D., Design an d Development of an Artificial Nerural Network for Estimation of Formation, SPE Petroleum Computer Conference, 1994

Mohaghegh, S., Arefi, S., Ameri, S and Rose,D., ”Design and Development of an Articial Neural Network for Estimation of Formation Permeability” SPE-28237 , Reservoir Engineering(September 1995)pp.151-154.

Mohaghegh, S., Arefi, R., Ameri, S., Aminiand, K and Nutter, R.,
“Petroleum reservoir characterization with the aid of artificial neural networks” SPE , Reservoir Engineering(September 1996)263-274.

Mohaghegh, S., McVey, D., Aminian, K. and Ameri, S., "Predicting Well- Stimulation Results in a Gas-Storage Field in the Absence go Reservoir Data with Neural Networks," SPE, Reservoir Engineering(November 1996)268-272.

Pirson, S.J.,”S.J.: ”Handbook of Well Log Analysis,” Englewood Cliffs, N.J., Prentice-Hall, Inc.1963.

Schlumberger Log Interpretation Principles / Applications , Schlumberger Educational Services ,Houston,Texas,May 1991 .

Timur, A., ”An Investigation of Permeability, Porosity, and Residual Water Saturation Relationship for Sandstone Reservoirs, ”The Log Analyst, Vol.9, no.4, (July –August 1968) pp.8.

Tixier, M. P., “ Evaluation of Permeability from Electric Logs Resistivity Gradients,“ Oil and Gas Journal. (June 1949) pp.113-122

Wong P. M., Henderson D. J. and Brooks L. J., Permeability Determination Using Neural Networks in the Ravva Fiels, Offshore India, SPE Reservoir Evaluation & Engineering, 1998

Wong, K. W. and Gedeon, T. “A Modular Signal Processing Model for Permeability Prediction in Petroleum Reservoir,” IEEE, 2000

Wong, P. M., Gedeon, T. D., and Taggart, I. J., “An Improved Technique in Porosity Prediction: A Neural Network Approach, ” IEEE Transactions on Geoscience and Remote Sensing, vol.33, NO.4, July 1995.

Wylie, M.R.J. and Rose, W.D., ”Some theoretical considerations related to the quantitative evaluations of the physical characteristics of reservoir rock from electric log data,” Journal Petroleum Technology (1950), v. 189, p.105-118.

Wong P. M., Henderson D. J. and Brooks L. J., Permeability Determination Using Neural Networks in the Ravva Fiels, Offshore India, SPE Reservoir Evaluation & Engineering, 1998

周錦德,石油地質學上冊:地物、地化與地質探勘之整合,台北,1989年,167-222頁。

湯于德 , 以井測資料估算台灣海域深部地層滲透率之研究,碩士論文,台南,1997年6月.

王崇興, 類神經網路評估已開發天然氣礦區蘊藏量之研究, 碩士論文, 台南, 1998年6月

葉怡成, 類神經網路模式應用與實作, 儒林圖書公司, 台北, 1993.

吳忠益, 利用井測資料與基因演算法研究雲林沿海地區深部含水地層特性, 碩士論文, 台南, 2000

蘇木春、張孝德,機器學習:類神經網路、模糊系統以及基因演算法則,全華科技圖書股份有限公司,台北, 9-1 ~ 9-31頁,2000年3月。

游麗娟,基因演算法於幾何形狀最佳化設計之研究,國立中央大學機械工程研究所碩士論文,2000年6月,7-20頁。

林再興 , 陳昶旭,”利用類神經網路及灰色理論預測已生產礦區之油氣生產量級蘊藏量之研究,石油暨石化科技產業科技學術合作八十九年度期末報告, 2001.9

陳昶旭, 林再興 , “利用類神經網路估算地層滲透率之研究”環球學報,2001.10

田川昇、謝秉志、林再興,”利用基因演算法建立滲透率計算模式,” 石油(2001),第36卷,第4期,第1-8頁。(NSC 89-2116-M-006-018)
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top