The Use of Classifiers in Image Analysis of Oil Wells Profiling Process and the Automatic Identification of Events

Different strategies and tools are available at the oil
and gas industry for detecting and analyzing tension and possible
fractures in borehole walls. Most of these techniques are based on
manual observation of the captured borehole images. While this
strategy may be possible and convenient with small images and few
data, it may become difficult and suitable to errors when big
databases of images must be treated. While the patterns may differ
among the image area, depending on many characteristics (drilling
strategy, rock components, rock strength, etc.). In this work we
propose the inclusion of data-mining classification strategies in order
to create a knowledge database of the segmented curves. These
classifiers allow that, after some time using and manually pointing
parts of borehole images that correspond to tension regions and
breakout areas, the system will indicate and suggest automatically
new candidate regions, with higher accuracy. We suggest the use of
different classifiers methods, in order to achieve different knowledge
dataset configurations.

• Jaqueline M. R. Vieira

• Brazil
• classifiers
• data-mining
• Image Segmentation
• oil well visualization
• classifiers.

[1] M. S. Ameen, “Fracture and In-Situ Stress Characterization of
Hydrocarbon Reservoirs”, Geological Society Special Publication 209,
UK, 2003, p. 216.
[2] C. Barton, M. D. Zoback, “Discrimination of Natural Fractures from
Drilling-Induced Wellbore Image Data – Implications for Reservoir
Permeability”, SPE 78599, Reservoir Evaluation & Engineering, 2002.
[3] F. Cavani, R. V. Souza, A. J. Porto, “Segmentação e Classificação de
Imagens de Laranjeiras”, Tese de mestrado USP, São Paulo, 2007.
[4] E. Cruz, D. Carvalho, C. Varella, “Comparação de Classificadores de
Imagens Digitais na Determinação da Cobertura do Solo”, Dissertação
de Mestrado INCRA, Mato Grosso, 2008.
[5] E. Cunha, “Identificação de Litofácies de Poços de Petróleo utilizando
um Método Baseado em Redes Neurais Artificiais. Tese de Mestrado”,
UFCG, Paraíba, 2002.
[6] A. Drummond, “Quimica de Fluídos de Perfuração para Poços de
Petróleo”, UFRJ, 2005.
[7] R. Duda, P. Hart, “Use of the Hough transformation to detect lines and
curves in pictures”, Comm. of ACM 15, 1. 1972, pp. 11-15.
[8] S. M. Luthi, P. Souhaité, “Fractures Apertures from Electrical Borehole
Scans”, Geophysics, Vol. 55, No 7, July 1990.
[9] O. Máximo, D. Fernandes, “Uso de Graus de Confiança das Classes em
Classificadores Bayesianos”, Anais XI SBSR, Belo Horizonte, 2003.
[10] R. A. Nelson, “2004 – AAPG Winter Education Conference Short
Course: Integrated Exploration & Evaluation of Fractured Reservoir”,
Broken N. Consulting, Inc. Simonton, Tx.
[11] K. Oliveira, E. Cunha, H. Gomes, “Implementação de um método
baseado em redes neurais para descoberta de conhecimento em base de
dados de poços de petróleo e gás”, 2o Congresso Brasileiro de P&D em
Petróleo e Gás, 2004.
[12] A. Xavier, C. Guerra, “Detecção de Fraturas de Perfis Geofísicos de
Poço com Morfologia Matemática”, Simpósio Brasileiro de Ciências
Geodésicas e Tecnologia da Geoinformação, Recife, 2010.