Skip to Main content Skip to Navigation

Prédiction des Paramètres Physiques des Couches Pétrolifères par Analyse des Réseaux de Neurones et Analyse Faciologique.

Abstract : Characterization of the shaly sand reservoirs by well log data is a practical way of reservoir descriptions in the oil fields. During the last few years several studies were conducted in the field of petroleum engineering by applying artificial intelligence. This work represents a petrophysical-based method that uses well loggings and core plug data to predict well log data recorded at depth in shaly sand reservoir of the Triassic Formation in Hassi R’Mel field (Algerian Sahara). In the study of oil reservoirs, the prediction of absolute permeability is a fundamental key in reservoir descriptions which has a direct impact on, amongst others, effective completion designs, successful water injection programs and more efficient reservoir management. The Triassic Formations of the Hassi R’Mel field are composed of sandstones and shaly sand with dolomite. Logs from the 10 wells are the starting point for the reservoir characterization. This work presents a hybrid neuro-fuzzy model based on the use of well log data in porosity and permeability estimation. A fuzzy logic approach is used to calibrate the calculated permeability and core permeability and neural network was developed in this model based on data available in the field. Fuzzy analysis is based on fuzzy logic and is used to get the best related well logs with core porosity and permeability data. Neural network is used as a nonlinear regression method to develop transformation between the selected well logs and core measurements. Porosity and permeability are predicted in these wells using the linear regression and multilayer perceptron models are constructed. Their reliabilities are compared using regression coefficients for predictions in uncored sections. This method of intelligent technique is used as a powerful tool for reservoir properties estimation from well logs in oil and natural gas development projects.
Document type :
Complete list of metadata
Contributor : Isabelle Dubigeon Connect in order to contact the contributor
Submitted on : Tuesday, May 12, 2015 - 10:54:59 AM
Last modification on : Friday, September 16, 2022 - 10:36:49 AM
Long-term archiving on: : Wednesday, April 19, 2017 - 8:28:48 PM


  • HAL Id : tel-01150323, version 1


Rafik Baouche. Prédiction des Paramètres Physiques des Couches Pétrolifères par Analyse des Réseaux de Neurones et Analyse Faciologique.. Sciences de la Terre. université M'hamed Bougara. Boumerdès, 2015. Français. ⟨tel-01150323⟩



Record views


Files downloads