Competitive placement of oil perforation zones in hydraulic flow units from centrality measures

Oliveira, Gustavo P.; Roque, Waldir L.; Araújo, Edson de Andrade; Diniz, A. A. R.; Simões, Tatiana; Santos, M.D.

doi:10.1016/j.petrol.2016.06.008

Cited by 25 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To obtain different clusters that will form HFUs, we group them according to the DRT values of each cell in the reservoir through logical masks (Oliveira et al 2016). For example, Figure 1 illustrates two cluster models.…”

Section: Flow Unit Clusteringmentioning

confidence: 99%

“…For example, Figure 1 illustrates two cluster models. Oliveira et al (2016) have examined the influence of HFU connectivity in the choice of perforation strategies to improve oil recovery. To establish them, metrics were used to classify vertices and identify special roles played by them in relation to other vertices of the volume.…”

Section: Flow Unit Clusteringmentioning

confidence: 99%

“…HFUs are volumes of a reservoir with favoured ability to convey subsurface fluids. This way, flow unit models enable us to select "chunks" of geologic information around wells so that special cells-so-called maximum closeness centrality cells (MaxCs)-known a priori as flow convergence zones are used to construct input arrays with reduced dimension and high quality to describe the production mechanisms necessary to feed the network learning (Oliveira et al 2016(Oliveira et al , 2020.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Cumulative oil production in flow unit-crossing wells estimated by multilayer perceptron networks

Neto

Oliveira

Magalhães

et al. 2021

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

Knowing the ultimate oil production in wells is a crucial point for reservoir planning and management to anticipate value for money. Commercial reservoir simulators are able to predict production curves with high confidence, but repetitive tasks in a few cases may spend a precious time of staff as well as require a large computational effort. Although artificial intelligence (AI) is providing an alternative path to the usual workflow, many commercial simulators lack robust AI algorithms. This work introduces a methodology based on a multilayer perceptron (MLP) neural network to predict the final cumulative oil production of a reservoir at vertical wells that cross hydraulic flow units (HFUs), which are volumes endowed with good flow attributes. Each well location is attached to special spots previously determined from clustering and calculation of maximum closeness centrality points (MaxCs) within a class of HFUs. The database is divided into training, validation, and testing sets organized after processing the UNISIM-I-D synthetic model, representative of the Namorado Field, Campos Basin, Brazil. The key rationale of this paper is to use the feature of MaxCs of being drivers for well placement as knowledge base to learn the production mechanisms of the oilfield. The outcomes are presented from two perspectives: an original MLP and its post-processed version. Both are compared with reservoir simulations carried out in CMG Imex$$^{\copyright }$$ © and achieve reasonable agreement. The performance is measured by root-mean-squared error (RMSE) and mean absolute scaled error (MASE) both in original and post-processed versions. We show that average RMSE and MASE values near 0.07 and 14.00, respectively, are achieved without post-processing. With post-processing, gains of up to 43% are reported for the integral oil volume.

show abstract

Section: Flow Unit Clusteringmentioning

confidence: 99%

Section: Flow Unit Clusteringmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Cumulative oil production in flow unit-crossing wells estimated by multilayer perceptron networks

Neto

Oliveira

Magalhães

et al. 2021

J Petrol Explor Prod Technol

View full text Add to dashboard Cite

show abstract

“…Petrophysical rock typing has a wide variety of applications such as: drilling (e.g., prediction of high mud-loss intervals), production (e.g., potential production zones, locating perforations, diversion system design in acidizing, and prediction of high injectivity zones) (Roque et al, 2017, Oliveira et al, 2016, reservoir studies (net-pay cut-off definition) (Kolodzie, 1980, Saboorian-Jooybari, 2017, representative sample selections for special core analysis (SCAL) tests (Siddiqui et al, 2006, Serag El Din et al, 2014, Mirzaei-Paiaman and Saboorian-Jooybari, 2016, permeability prediction in uncored intervals (Amaefule et al, 1993, Abbaszadeh et al, 1996, Davies and Vessell, 1996, Soto et al, 2001, Taslimi et al, 2008, Askari and Behrouz, 2011, Sokhal et al, 2016, Chen and Yao, 2017, Zhang et al 2018, Wang et al 2018, and defining saturation functions for static and dynamic reservoir models (Mirzaei-Paiaman et al, 2015, Askari andBehrouz, 2011). Generally the literature core-based petrophysical rock typing methods can be classified into three separate categories.…”

Section: Introductionmentioning

confidence: 99%

A new approach in petrophysical rock typing

Mirzaei‐Paiaman

Ostadhassan

Rezaee

et al. 2018

Journal of Petroleum Science and Engineering

108

View full text Add to dashboard Cite

Petrophysical rock typing in reservoir characterization is an important input for successful drilling, production, injection, reservoir studies and simulation. In this study petrophysical rock typing is divided into two major categories: 1) a petrophysical static rock type (PSRT): a collection of rocks having the same primary drainage capillary pressure curves or unique water saturation for a given height above the free water level, 2) a petrophysical dynamic rock type (PDRT): a set of rocks with a similar fluid flow behavior. It was shown that static and dynamic rock types do not necessarily overlap or share petrophysical properties, regardless of wettability. In addition, a new index is developed to define PDRTs via the Kozeny-Carman equation and Darcy's law. We also proposed a different index for delineation of PSRTs by combining the Young-Laplace capillary pressure expression and the Kozeny-Carman equation. These new indices were compared with the existing theoretical and empirical indices. Results showed that our indices are representatives of previously developed models which were also tested with mercury injection capillary pressure, water-oil primary drainage capillary pressure, and water-oil relative permeability data on core plugs from a highly heterogeneous carbonate reservoir in an Iranian oil field. This study enabled us to modify the conventional J-function to enhance its capability of normalizing capillary pressure data universally.

show abstract

“…Soluções para este problema têm sido investigadas mediante técnicas derivadas de conceitos da teoria dos grafos e de redes sociais, tais como conectividade, métricas de centralidade e fluxo, como propõem Oliveira et al [1] e Roque et al [2].…”

Section: Introductionunclassified

Grafos Conexos e Centralidade de Intermediação: Uma Aplicação à Modelagem de Poços Multilaterais em Reservatórios Petrolíferos

Oliveira

Roque²,

Santos³

et al. 2018

Revista CI

View full text Add to dashboard Cite

Resumo: Este artigo apresenta uma aplicação da centralidade de intermediação da teoria dos grafos como parâmetro para o posicionamento de poços multilaterais em reservatórios de petróleo.Palavras-chave: grafo; centralidade de intermediação; conectividade; poços multilaterais; caracterização de reservatórios. IntroduçãoA atividade exploratória realizada pela indústria de petróleo e gás tem por meta prospectar reservas de recursos em porções das subsuperfícies terrestre (onshore) e marítima (offshore). Juntamente com o gás natural, o chamado "ouro negro" representa mais de 50% da matriz energética global. No Brasil, em particular, o petróleo assumiu uma posição ainda mais proeminente a partir da descoberta das gigantescas reservas offshore do pré-sal. Por esta razão, o desenvolvimento de tecnologias voltadas à engenharia de poços para águas ultraprofundas tem sido um eixo norteador para a pesquisa aplicada à modelagem de reservatórios.Reservas de petróleo são comprovadas através de estudos geológicos de grande porte e extensos ensaios laboratoriais, ambos complementados por simulações numéricas. No que tange à última, é praxe na indústria recorrer a modelos computacionais a fim de se prever comportamentos reais de produção com um custo incomparavelmente menor, já que estratégias otimizadas podem ser formuladas sem que haja necessidade de testes em campo.Encontrar os melhores locais onde os poços de produção devem ser posicionados é, sem dúvidas, um dos grandes desafios da modelagem e caracterização de reservatórios como área de estudo preliminar à implantação de projetos de desenvolvimento de campo. Soluções para este problema têm sido investigadas mediante técnicas derivadas de conceitos da teoria dos grafos e de redes sociais, tais como conectividade, métricas de centralidade e fluxo, como propõem Oliveira et al. Devido à natureza heterogênea das formações rochosas, diversas configurações de poços precisam ser usadas para o atingimento de regiões de difícil acesso. Neste aspecto, à exceção dos poços verticais, tradicionalmente empregados no decurso da história da indústria petrolífera, surgem os conceitos de poço direcional, poço horizontal e, mais amplamente, poço multilateral, resultantes do notável avanço tecnológico galgado pela engenharia de poços nas atividades de perfuração, completação e produção.Poços direcionais são aqueles perfurados em ângulo diferente de noventa graus em relação à superfície e direcionados exatamente à zona produtiva (pay zone). Já os poços horizontais são aqueles que possuem seções paralelas às camadas estratigráficas da subsuperfície. Algumas razões que promovem a opção por poços horizontais em detrimento dos verticais são: (i) maximização da área de contato do poço com a região produtiva; (ii) atraso do fenômeno do "cone de água" (coning), devido à manutenção de uma baixa pressão de drawdown no reservatório e (iii) aumento de eficiência em processos de injeção para recuperação avançada de óleo.Por outro lado, poços multilaterais, praticados em reservatórios de baixa permeabilidad...

show abstract

Competitive placement of oil perforation zones in hydraulic flow units from centrality measures

Cited by 25 publications

References 12 publications

Cumulative oil production in flow unit-crossing wells estimated by multilayer perceptron networks

Cumulative oil production in flow unit-crossing wells estimated by multilayer perceptron networks

A new approach in petrophysical rock typing

Grafos Conexos e Centralidade de Intermediação: Uma Aplicação à Modelagem de Poços Multilaterais em Reservatórios Petrolíferos

Contact Info

Product

Resources

About