Отправлено: 20.05.10 03:05. Заголовок: Predicting formation lithology from log data by using a neural network

Predicting formation lithology from log data by using a neural network
Petroleum Science
China University of Petroleum
ISSN 1672-5107 (Print) 1995-8226
Volume 5, Number 3 / Август 2008 г.
DOI 10.1007/s12182-008-0038-9
pp 242-246

Predicting formation lithology from log data by using a neural network
Kexiong Wang1 and Laibin Zhang2

(1) School of Petroleum Engineering, China University of Petroleum, Beijing, 102249, China
(2) School of Mechanical and Electronic Engineering, China University of Petroleum, Beijing, 102249, China

Received: 5 March 2008 Published online: 7 August 2008

Abstract In order to increase drilling speed in deep complicated formations in Kela-2 gas field, Tarim Basin, Xinjiang, west China, it is important to predict the formation lithology for drilling bit optimization. Based on the conventional back propagation (BP) model, an improved BP model was proposed, with main modifications of back propagation of error, self-adapting algorithm, and activation function, also a prediction program was developed. The improved BP model was successfully applied to predicting the lithology of formations to be drilled in the Kela-2 gas field.
Key words Kela-2 gas field - neural network - improved back-propagation (BP) model - log data - lithology prediction

--------------------------------------------------------------------------------

Kexiong Wang
Email: wkx4328@sina.com



References
Benaouda D, Wadge G, Whitmarsh R B, et al. Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs: An example from the Ocean Drilling Program. Geophysical Journal International. 1999. 136(2): 477–491


Bueno E O J, Perez I C, Escamilla G, et al. Applications of artificial neural networks and dipole sonic anisotropy in low-porosity, naturally fractured, complex lithology formations in the Southern Land Region of Mexico. First International Oil Conference and Exhibition in Mexico held in Cancun, Mexico, 31 August–2 September 2006 (SPE paper 103662)

Falconer I G, Burgess T M and Sheppard M C. Separating bit and lithology effects from drilling mechanics data. SPE/IADC Drilling Conference held in Dallas, Texas, 28 February–2 March 1988 (SPE paper 17191)

Gstalder S and Raynal J. Measurement of some mechanical properties of rocks and their relationship to rock drillability. Journal of Petroleum Technology. 1966. 18(8): 991–996


He M Y. Neural Computing. Xian: Xidian University Press. 1992. 156–178 (in Chinese)

Jiao L C. The Theory of Artificial Neural Networks. Xian: Xidian University Press. 1992. 35–51 (in Chinese)

Mason K L. Tricone bit selection using sonic logs. SPE Drilling Engineering. 1987. 2(2): 135–142 (SPE paper 13256)


Onyia E C. Geology drilling log: A computer database system for drilling simulation. SPE Drilling Engineering. 1987. 2(1): 27–36

Onyia E C. Relationship between formation strength, drilling strength and electric log properties. SPE Annual Technical Conference and Exhibition held in Houston, Texas, 2–5 October 1988 (SPE paper 18166)

Raynal J C, Serge A, Sagot A M, et al. Organization of field tests and evaluation of tricone bit performance using statistical analysis and sonic logs. Journal of Petroleum Technology. 1971. 23(4): 506–512


Rogers S J, Fang J H, Karr C L, and Stanley D A. Determination of lithology from well logs using a neural network. AAPG Bulletin. 1992. 76(5): 731–739

Wiener J M, Rogers J R, and Moll R F. Predicting carbonate permeabilities from wireline logs using a back-propagation neural network. 61st Annu. SEG Int. Mtg. Abstract. 1991

Zhuang Z Q, Wang X F, Wang D S, et al. Neural Networks and Neural Computers. Beijing: Science Press. 1992 (in Chinese)