scispace - formally typeset
Search or ask a question
Institution

Sonatrach

CompanyAlgiers, Algeria
About: Sonatrach is a company organization based out in Algiers, Algeria. It is known for research contribution in the topics: Hydraulic fracturing & Structural basin. The organization has 460 authors who have published 494 publications receiving 6339 citations. The organization is also known as: Sonatrach SPA.


Papers
More filters
Journal ArticleDOI
TL;DR: A new integrated intelligent computing paradigm to form a constitutive model applicable to rock fractures is presented, which integrates the radial basis function neural network (RBFNN) with grey wolf optimization (GWO) and the statistical results revealed the superiority of RBFNN-GWO over RBFNA in terms of prediction accuracy.
Abstract: Making a relation between strains and stresses is an important subject in the rock engineering field. Shear behaviors of rock fractures have been extensively investigated by different researchers. Literature mostly consists of constitutive models in the form of empirical functions that represent experimental data using mathematical regression techniques. As an alternative, this study aims to present a new integrated intelligent computing paradigm to form a constitutive model applicable to rock fractures. To this end, an RBFNN-GWO model is presented, which integrates the radial basis function neural network (RBFNN) with grey wolf optimization (GWO). In the proposed model, the hyperparameters and weights of RBFNN were tuned using the GWO algorithm. The efficiency of the designed RBFNN-GWO was examined comparing it with the RBFNN-GA model (a combination of RBFNN and the Genetic Algorithm). The proposed models were trained based on the results of a systematic set of 84 direct shear tests gathered from the literature. The finding of the current study demonstrated the efficiency of both the RBFNN-GA and RBFNN-GWO models in predicting the dilation angle, peak shear displacement, and stress as the rock fracture properties. Among the two models proposed in this study, the statistical results revealed the superiority of RBFNN-GWO over RBFNN-GA in terms of prediction accuracy.

9 citations

Journal ArticleDOI
TL;DR: In this paper, the authors present details of the different plays of the Taoudenni Basin from the Chenachène region in Algeria, showing that the best reservoirs are associated with fractured intervals in the Douik Group and the Dar Echeikh Group.
Abstract: Abstract The Taoudenni Basin, North Africa's largest sedimentary basin, is located in western Mauritania, northern Mali and southwestern Algeria. Of the four petroleum wildcat wells drilled to date, the Abolag-1 well, Mauritania, yielded gas shows in Infracambrian (Neoproterozoic) stromatolitic carbonates. We present details of the different plays of the basin from the Chenachène region in Algeria. The Infracambrian is generally composed of three sedimentary packages: a basal sandstone (a unit of the Douik Group), overlain by carbonates (the Hank Group), sandstones and shales (the Dar Echeikh Group). The play is sourced by Infracambrian organic-rich black shales. In neighbouring Mauritania these were penetrated by water wells and shallow boreholes, containing in places >20% TOC. In the Hank Group the best reservoirs are associated with fractured intervals. The Dar Echeikh Group includes several potential reservoir units with porosities of up to 26%. Potential petroleum trap types in the Algerian part of the Taoudenni Basin are associated with folds, the basal Palaeozoic unconformity, and Infracambrian and Triassic–Jurassic half-graben.

9 citations


Authors
Network Information
Related Institutions (5)
China University of Petroleum
39.1K papers, 483.7K citations

73% related

Chevron Corporation
14.5K papers, 271.7K citations

71% related

ExxonMobil
23.7K papers, 535.7K citations

70% related

Mobil
10.6K papers, 237.4K citations

70% related

Royal Dutch Shell
23.6K papers, 551.6K citations

69% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
20231
20227
202150
202045
201923
201822