Predicting Log Data by Using Artificial Neural Networks to Approximate Petrophysical Parameters of Formation

被引:20
|
作者
Baneshi, M. [1 ]
Behzadijo, M. [2 ]
Schaffie, M. [3 ]
Nezamabadi-Pour, H. [3 ]
机构
[1] Petroiran Dev Co PEDCO, Tehran, Iran
[2] Iranian Cent Oil & Gas Fields Co ICOFC, Shiraz, Iran
[3] Shahid Bahonar Univ Kerman, Energy & Environm Engn Res Ctr EERC, Kerman, Iran
关键词
artificial neural network; predicting petrophysical index; well logging;
D O I
10.1080/10916466.2010.540611
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Petrophysical characteristics of underlying formation have an important role in reservoir management and drilling wells. One of the most common ways to reach this information is well log analysis. These logs represent important parameters of formation by evaluating some characteristics of rocks. Meanwhile, some time well logging does not implement well or some log data are accompanied by so many errors. Therefore, in these cases using cheaper logs or better data can estimate more expensive log or incorrect data. High-skill experts and lithology information are needed for interpretation and evaluation of data. Therefore, designing a model that is able to evaluate the petrophysical index using well log data without laboratory information will be very economical. The authors solve the problem of well log data and interpretation of logs using artificial neural networks. Running various networks has implied that the selection of appropriate network's input is the most important factor in accurate estimates. After selecting the appropriate input data, many networks were run in order to optimize the number of epoch, hidden layers, neurons in each layer and the proper neural network's training function. First, sonic log (DT) is predicted using neural network system. To do this, neutron porosity (NPHI) and density log (RHOB) are used as input variables. In the second network, porosity index (PHIE) is evaluated and predicted considering NPHI, RHOB, and DT. Finally, in third network, saturation index is estimated by using resistivity log and PHIE is predicted by second network.
引用
收藏
页码:1238 / 1248
页数:11
相关论文
共 50 条
  • [1] Predicting important parameters using artificial neural networks
    Ramakumar, K. R.
    HYDROCARBON PROCESSING, 2008, 87 (10): : 81 - 83
  • [2] Predicting oil saturation from velocities using petrophysical models and artificial neural networks
    Boadu, FK
    JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2001, 30 (3-4) : 143 - 154
  • [3] Predicting formation lithology from log data by using a neural network
    Wang Kexiong~(1*) Zhang Laibin~2 1 School of Petroleum Engineering
    Petroleum Science, 2008, (03) : 242 - 246
  • [4] Predicting formation lithology from log data by using a neural network
    Wang Kexiong
    Zhang Laibin
    PETROLEUM SCIENCE, 2008, 5 (03) : 242 - 246
  • [5] Lithology effects on the fractures parameters using image log and petrophysical data
    Soleimani, Bahman
    Amiri, Khayyam
    Samani, Babak
    Shaban, Leila
    RUSSIAN JOURNAL OF EARTH SCIENCES, 2016, 16 (05):
  • [6] Modular artificial neural network for prediction of petrophysical properties from well log data
    Fung, CC
    Wong, KW
    Eren, H
    Charlebois, R
    Crocker, H
    JOINT CONFERENCE - 1996: IEEE INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE & IMEKO TECHNICAL COMMITTEE 7, CONFERENCE PROCEEDINGS, VOLS I AND II: QUALITY MEASUREMENTS: THE INDISPENSABLE BRIDGE BETWEEN THEORY AND REALITY (NO MEASUREMENTS? NO SCIENCE!), 1996, : 1010 - 1014
  • [7] Modular artificial neural network for prediction of petrophysical properties from well log data
    Fung, CC
    Wong, KW
    Eren, H
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 1997, 46 (06) : 1295 - 1299
  • [8] Modular artificial neural network for prediction of petrophysical properties from well log data
    Curtin Univ of Technology, Bentley
    IEEE Trans Instrum Meas, 6 (1295-1299):
  • [9] Predicting total trihalomethane formation in finished water using artificial neural networks
    Lewin, N
    Zhang, Q
    Chu, LL
    Shariff, R
    JOURNAL OF ENVIRONMENTAL ENGINEERING AND SCIENCE, 2004, 3 : S35 - S43
  • [10] USE OF ARTIFICIAL NEURAL NETWORKS IN PREDICTING PARTICLEBOARD QUALITY PARAMETERS
    de Melo, Rafael Rodolfo
    Miguel, Eder Pereira
    REVISTA ARVORE, 2016, 40 (05): : 949 - 958