Completion Study Aims To Extend Life of Electrical Submersible Pumps

2021 ◽  
Vol 73 (10) ◽  
pp. 54-55
Author(s):  
Chris Carpenter
Keyword(s):  
Horizontal Wells ◽  
Carbonate Reservoir ◽  
Operational Parameters ◽  
Horizontal Section ◽  
Well Completion ◽  
Rock Types ◽  
Rock Typing ◽  
Study Results ◽  
Electrical Submersible Pumps ◽  
Petroleum Development

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper IPTC 20130, “Practical Approach for Solid Production Prediction and Completion Strategy Decisions in Horizontal Wells: A Case Study From a Cretaceous Carbonate Reservoir, North Oman,” by Mohammed Al-Aamri, Sandeep Mahajan, SPE, and Nair Sujith, Petroleum Development Oman, et al., prepared for the 2020 International Petroleum Technology Conference, Dhahran, Saudi Arabia, 13–15 January. The paper has not been peer reviewed. Copyright 2020 International Petroleum Technology Conference. Reproduced by permission. The carbonate reservoir fields in Oman discussed in the complete paper are produced by several horizontal wells from long openhole sections. The wells are completed by barefoot (openhole) completion with electrical submersible pumps (ESPs) located in the wells’ buildup section. The field has experienced significant ESP failures, so a study aimed to provide input for well-completion-strategy design and operational parameters, which could minimize solids production and lower intervention/operating expenditure (OPEX). Based on the study results, recommendations were provided for a drawdown-management strategy, which potentially will benefit from increasing ESP run life and reducing field OPEX. Field Background Problem Statement and Motivation Petrophysical rock typing for the studied reservoir is detailed in the complete paper. The primary understanding of the root cause of these ESP failures was argillaceous rock typing along the horizontal section. The decision was made to recomplete the wells by isolating equipment from such rock typing. As a result, ESP run lives improved, but failures continued. Several wells featured an isolation process from the first day, for example, but run life did not improve. The field team subsequently analyzed a sample of fines taken from the ESP, and their mineralogy was examined. The main finding was that almost 50% of the sample included calcite mineral content with some quartz (Fig. 1). However, the question remained as to which part of the reservoir the sample belonged. All rock types potentially consist of such calcite minerals because of the marine-deposition environment. Hence, investigating and characterizing the possible root causes of the ESP failures, as well as providing effective completion mitigations for upcoming wells, was critical. The key objectives of the study were to understand the mechanisms and causes of the observed solids from a geomechanical standpoint and to provide recommendations to minimize the risk of near-wellbore failure.

Enhanced and Rock Typing-Based Reservoir Characterization of the Palaeocene Harash Carbonate Reservoir-Zelten Field-Sirte Basin-Libya

2021 ◽  
Author(s):  
Mohamed Masoud ◽  
W. Scott Meddaugh ◽  
Masoud Eljaroshi ◽  
Khaled Elghanduri
Keyword(s):  
Rock Type ◽  
Carbonate Reservoir ◽  
Classification Model ◽  
Reservoir Rocks ◽  
The Core ◽  
Core Samples ◽  
Rock Types ◽  
Rock Typing ◽  
Open Hole ◽  
Type Classification

Abstract The Harash Formation was previously known as the Ruaga A and is considered to be one of the most productive reservoirs in the Zelten field in terms of reservoir quality, areal extent, and hydrocarbon quantity. To date, nearly 70 wells were drilled targeting the Harash reservoir. A few wells initially naturally produced but most had to be stimulated which reflected the field drilling and development plan. The Harash reservoir rock typing identification was essential in understanding the reservoir geology implementation of reservoir development drilling program, the construction of representative reservoir models, hydrocarbons volumetric calculations, and historical pressure-production matching in the flow modelling processes. The objectives of this study are to predict the permeability at un-cored wells and unsampled locations, to classify the reservoir rocks into main rock typing, and to build robust reservoir properties models in which static petrophysical properties and fluid properties are assigned for identified rock type and assessed the existed vertical and lateral heterogeneity within the Palaeocene Harash carbonate reservoir. Initially, an objective-based workflow was developed by generating a training dataset from open hole logs and core samples which were conventionally and specially analyzed of six wells. The developed dataset was used to predict permeability at cored wells through a K-mod model that applies Neural Network Analysis (NNA) and Declustring (DC) algorithms to generate representative permeability and electro-facies. Equal statistical weights were given to log responses without analytical supervision taking into account the significant log response variations. The core data was grouped on petrophysical basis to compute pore throat size aiming at deriving and enlarging the interpretation process from the core to log domain using Indexation and Probabilities of Self-Organized Maps (IPSOM) classification model to develop a reliable representation of rock type classification at the well scale. Permeability and rock typing derived from the open-hole logs and core samples analysis are the main K-mod and IPSOM classification model outputs. The results were propagated to more than 70 un-cored wells. Rock typing techniques were also conducted to classify the Harash reservoir rocks in a consistent manner. Depositional rock typing using a stratigraphic modified Lorenz plot and electro-facies suggest three different rock types that are probably linked to three flow zones. The defined rock types are dominated by specifc reservoir parameters. Electro-facies enables subdivision of the formation into petrophysical groups in which properties were assigned to and were characterized by dynamic behavior and the rock-fluid interaction. Capillary pressure and relative permeability data proved the complexity in rock capillarity. Subsequently, Swc is really rock typing dependent. The use of a consistent representative petrophysical rock type classification led to a significant improvement of geological and flow models.

scholarly journals Integrated rock typing and pore facies analyses in a heterogeneous carbonate for saturation height modelling, a case study from Fahliyan Formation, the Persian Gulf

2021 ◽  
Vol 11 (4) ◽  
pp. 1577-1595
Author(s):  
Rasoul Ranjbar-Karami ◽  
Parisa Tavoosi Iraj ◽  
Hamzeh Mehrabi
Keyword(s):  
Capillary Pressure ◽  
Water Saturation ◽  
High Energy ◽  
Carbonate Reservoir ◽  
Reservoir Rock ◽  
Initial Water ◽  
Rock Types ◽  
Rock Typing ◽  
Pore Types ◽  
Fitting Parameters

AbstractKnowledge of initial fluids saturation has great importance in hydrocarbon reservoir analysis and modelling. Distribution of initial water saturation (Swi) in 3D models dictates the original oil in place (STOIIP), which consequently influences reserve estimation and dynamic modelling. Calculation of initial water saturation in heterogeneous carbonate reservoirs always is a challenging task, because these reservoirs have complex depositional and diagenetic history with a complex pore network. This paper aims to model the initial water saturation in a pore facies framework, in a heterogeneous carbonate reservoir. Petrographic studies were accomplished to define depositional facies, diagenetic features and pore types. Accordingly, isolated pores are dominant in the upper parts, while the lower intervals contain more interconnected interparticle pore types. Generally, in the upper and middle parts of the reservoir, diagenetic alterations such as cementation and compaction decreased the primary reservoir potential. However, in the lower interval, which mainly includes high-energy shoal facies, high reservoir quality was formed by primary interparticle pores and secondary dissolution moulds and vugs. Using huge number of primary drainage mercury injection capillary pressure tests, we evaluate the ability of FZI, r35Winland, r35Pittman, FZI* and Lucia’s petrophysical classes in definition of rock types. Results show that recently introduced rock typing method is an efficient way to classify samples into petrophysical rock types with same pore characteristics. Moreover, as in this study MICP data were available from every one meter of reservoir interval, results show that using FZI* method much more representative sample can be selected for SCAL laboratory tests, in case of limitation in number of SCAL tests samples. Integration of petrographic analyses with routine (RCAL) and special (SCAL) core data resulted in recognition of four pore facies in the studied reservoir. Finally, in order to model initial water saturation, capillary pressure data were averaged in each pore facies which was defined by FZI* method and using a nonlinear curve fitting approach, fitting parameters (M and C) were extracted. Finally, relationship between fitting parameters and porosity in core samples was used to model initial water saturation in wells and between wells. As permeability prediction and reservoir rock typing are challenging tasks, findings of this study help to model initial water saturation using log-derived porosity.

Achieving Improved Drilling Performance with Hole Cleaning Technology in Horizontal Shale Gas Wells in Sichuan Basin of China

2021 ◽  
Author(s):  
Guodong Ji ◽  
Haige Wang ◽  
Hongchun Huang ◽  
Meng Cui ◽  
Feixue Yulong ◽  
...  
Keyword(s):  
Shale Gas ◽  
Sichuan Basin ◽  
Horizontal Wells ◽  
Drill String ◽  
Operating Parameters ◽  
Optimal Operating ◽  
Horizontal Section ◽  
Drill Cuttings ◽  
Well Completion ◽  
Cuttings Bed

Abstract The horizontal section length of shale gas horizontal wells in Sichuan Basin in the south-west of China generally exceeds 2000m. Cuttings are apt to accumulate and form cuttings beds along such long and curve horizontal sections due to low cuttings carrying capacity, which often results in excessive torque and drag or even stuck pipes during drilling process. According to the statistics dada inthe period of Jan. - Oct. 2019, more than 25 stuck pipe incidents and 15 rotary steering tools loss in borehole were reported due to inefficient cuttings transportation in the long horizontal wells in Sichuan Basin. This paper studies the cuttings transportation and cuttings bed formation in horizontal wells. A prediction model for the distribution of cuttings bed was established. A monitoring and analysis software for the cuttings bed and cuttings cleaner with V-shaped spiral blades that is used to agitate the cuttings bed wasdeveloped. The software calculates the distribution and thickness of the cuttings bed according to the well trajectory, wellbore structure, drilling fluid characteristics, etc., and provides the optimal operating parameters for the removal of the cuttings bed by the rotating and reciprocating drill string. Then, the drill cuttings remover in the drill string moves to the predicted position of the drill cuttings, scrapes the drill cuttings and creates a swirling flow during the pipe rotation. The combined application of software and makeup remover can effectively solve the issue of borehole cleaning in long horizontal wells. One of the field applications was carried out in the well Ning 209H12, a shale gas horizontal well in Sichuan Basin. The well experienced excessive torque and drag issue during the tripping of drill string of long horizontal section. Thesoftware ran based on oil well data, and it determines the placement and thickness of cuttings beds in the well and calculates the optimal operating parameters for a flow rate of about 32L/s and a speed of 100rpm to remove them. By rotatingand reciprocating the drill string with recommended operating parameters along the cuttings bed interval, the removers helped cleaning the cuttings bed efficiently and significant amount of cuttings was observed at vibration screen. After cleaning the cuttings bed interval, the trip smoothly ran to the bottom without any excessive torque and drag, and then continues to drill in cooperation with the removers to the total depth. During the well completion, there was no problem with the operation of electrical logging and production casing. This cuttings removal technology has been used in other shale gas formations and tight gas formations where horizontal wells are widely used.

scholarly journals Carbonate reservoir rock typing algorithm based on integrated approach (IRT)

2021 ◽  
Vol 6 (4) ◽  
pp. 62-70
Author(s):  
Mariia A. Kuntsevich ◽  
Sergey V. Kuznetsov ◽  
Igor V. Perevozkin
Keyword(s):  
Water Saturation ◽  
Integrated Approach ◽  
Learning Technologies ◽  
Carbonate Reservoir ◽  
Reservoir Rock ◽  
Static Properties ◽  
Reservoir Properties ◽  
Optimal Method ◽  
Rock Types ◽  
Rock Typing

The goal of carbonate rock typing is a realistic distribution of well data in a 3D model and the distribution of the corresponding rock types, on which the volume of hydrocarbon reserves and the dynamic characteristics of the flow will depend. Common rock typing approaches for carbonate rocks are based on texture, pore classification, electrofacies, or flow unit localization (FZI) and are often misleading because they based on sedimentation processes or mathematical justification. As a result, the identified rock types may poorly reflect the real distribution of reservoir rock characteristics. Materials and methods. The approach described in the work allows to eliminate such effects by identifying integrated rock types that control the static properties and dynamic behavior of the reservoir, while optimally linking with geological characteristics (diagenetic transformations, sedimentation features, as well as their union effect) and petrophysical characteristics (reservoir properties, relationship between the porosity and permeability, water saturation, radius of pore channels and others). The integrated algorithm consists of 8 steps, allowing the output to obtain rock-types in the maximum possible way connecting together all the characteristics of the rock, available initial information. The first test in the Middle East field confirmed the applicability of this technique. Results. The result of the work was the creation of a software product (certificate of state registration of the computer program “Lucia”, registration number 2021612075 dated 02/11/2021), which allows automating the process of identifying rock types in order to quickly select the most optimal method, as well as the possibility of their integration. As part of the product, machine learning technologies were introduced to predict rock types based on well logs in intervals not covered by coring studies, as well as in wells in which there is no coring.

scholarly journals Study on discriminant method of rock type for porous carbonate reservoirs based on Bayesian theory

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xinxin Fang ◽  
Hong Feng
Keyword(s):  
Middle East ◽  
Rock Type ◽  
Carbonate Reservoir ◽  
Oil Field ◽  
Carbonate Reservoirs ◽  
Pressure Curve ◽  
Permeability Model ◽  
Permeability Characteristics ◽  
Rock Types ◽  
Study Results

AbstractRock typing is an extremely critical step in the estimation of carbonate reservoir quality and reserves in the Middle East. In order to recognize the rock types of carbonate reservoirs in the Mishrif Formation better, classify the reservoirs accurately, and establish the permeability model in line with the study area precisely, it is necessary to study the recognition method conforming to the actual situation of the study area. The practice shows that the current recognition methods based on capillary pressure curve, flow unit and NMR logging data can effectively distinguish rock types, but a large number of accurate experimental data are required, which can only be applied in a few cored well, however, cannot be applied in the whole oil field. In this study, based on core, thin section, logging data, the sedimentary characteristics of carbonate reservoir, logging response of four rock types as well as porosity and permeability characteristics of Mishrif Formation in W are comprehensively studied. Based on Bayesian stepwise discriminant theory in multivariate statistics, the Bayesian discrimination model based on conventional logging data is established. The examining results showed that, compared with the description of logging and coring, the accuracy of Bayesian discriminant model and cross confirmation rate have achieved more than 80% for the original sample. Reliability verification showed that the matching degree of the rock type recognized in the non-cored well with the core and mud logging was as high as 90%, which matched the depositional environment of the entire region. The study results confirm the validity and generalizability of the Bayesian method to identify and predict rock types, which can be applied to the entire Middle East region to solve the problem of the lack of core data to accurately evaluate the quality of non-cored wells and accurately predict production, meeting the needs of actual reservoir evaluation and production development in the Middle East.

The history of UGS Strachocina investment as an example of success achieved by cooperation between a western company and Polish oil and gas companies

Nafta-Gaz ◽  
2021 ◽  
Vol 77 (11) ◽  
pp. 760-764
Author(s):  
Bogdan Filar ◽  
◽  
Mariusz Miziołek ◽  
Mieczysław Kawecki ◽  
Marek Piaskowy ◽  
...  
Keyword(s):  
Oil And Gas ◽  
Drilling Fluid ◽  
Horizontal Wells ◽  
Gas Storage ◽  
Natural Fracture ◽  
Horizontal Section ◽  
Well Completion ◽  
Working Volume ◽  
Drilling Technology ◽  
Fluid Losses

In 2006 Oil and Gas Institute, Underground Gas Storage Department was given the task of designing the UGS Strachocina working volume, production and injection rates enlargement. Gas storage Strachocina is located in the south eastern part of Poland, near Sanok. The UGS Department ran some analysis before that date, which gave us the answer that the old vertical well technology would not be enough to achieve investment success. We knew that we needed to use horizontal well technology in which we had no experience at all. At that time there were only a few horizontal wells drilled in Poland. We decided to start cooperation with the company Baker Hughes, and asked them to help us to design the drilling technology and well completions. We knew that we needed to drill 8 horizontal wells in difficult reservoir conditions. Based on Baker Hughes’ recommendations, the EXALO Polish drilling company’s experience and the Institute’s knowledge of storage reservoir geology, the trajectories of 8 new wells were designed. Working with Baker Hughes, we designed the well completion based on expandable filters, the second time this type of completion technology had been used in the world at that time. During drilling, we were prepared for drilling fluid losses because of the extensive Strachocina reservoir’s natural fracture system. The investment was in doubt during the drilling of the first two horizontal wells because of huge drilling fluid losses and the inability of drilling the horizontal section length as designed. We lost 4000 cubic metres of drilling fluid in a one single well. During the drilling of the 2nd well, we asked Baker Hughes to help us to improve the drilling technology. Our partners from Baker Hughes prepared the solution in 3 weeks, and so we were able to use this new technology on the 3rd well drilled. It turned out that we could drill a longer horizontal section with less drilling fluid loss. The paper will show the idea of the project, the team building process, the project problems solved by the team, decisions made during the UGS Strachocina investment and the results. It will show how combining “western” technology and experience with “eastern” knowledge created a success story for all partners.

Geomechanical Controls on Frac-Hits

2022 ◽  
Author(s):  
Dharmendra Kumar ◽  
Ahmad Ghassemi
Keyword(s):  
Pore Pressure ◽  
Fracture Propagation ◽  
Horizontal Wells ◽  
Operational Parameters ◽  
Modeling And Analysis ◽  
Matrix Deformation ◽  
In Situ Conditions ◽  
Fracture Fluid ◽  
Poroelastic Model ◽  
Element Method

Abstract The communication among the horizontal wells or "frac-hits" issue have been reported in several field observations. These observations show that the "infill" well fractures could have a tendency to propagate towards the "parent" well depending on reservoir in-situ conditions and operational parameters. Drilling the horizontal wells in a "staggered" layout with both horizontal and vertical offset could be a mitigation strategy to prevent the "frac-hits" issue. In this study, we present a detailed geomechanical modeling and analysis of the proposed solution. For numerical modeling, we used our state-of-the-art fully coupled poroelastic model "GeoFrac-3D" which is based on the boundary element method for the rock matrix deformation/fracture propagation and the finite element method for the fracture fluid flow. The "GeoFrac-3D" simulator fully couples pore pressure to stresses and allows for dynamic modeling of production/injection and fracture propagation. The simulation results demonstrate that production from a "parent’ well causes a non-uniform reduction of the reservoir pore pressure around the production fractures, resulting in an anisotropic decrease of the reservoir total stresses, which could affect fracture propagation from the "infill" wells. We examine the optimal orientation and position of the "infill" well based on the numerical analysis to reduce the "frac-hits" issue in the horizontal well refracturing. The posibility of "frac-hits" can be reduced by optimizing the direction and locations of the "infill" wells, as well as re-pressurizing the "parent" well. The results suggest that arranging the horizontal wells in a "staggered" or "wine rack" arrangement decreases direct well interference and could increase the drainage volume.

Investigation of Horizontal Wells with Multi-Stage Hydraulic Fracturing Technological Efficiency in the Development of Low-Permeability Oil Reservoirs

2021 ◽  
Author(s):  
Aleksander Valerievich Miroshnichenko ◽  
Valery Alekseevich Korotovskikh ◽  
Timur Ravilevich Musabirov ◽  
Aleksei Eduardovich Fedorov ◽  
Khakim Khalilovich Suleimanov
Keyword(s):  
Hydraulic Fracturing ◽  
Performance Indicators ◽  
Oil And Gas ◽  
Horizontal Wells ◽  
Productivity Index ◽  
Specific Mass ◽  
Horizontal Section ◽  
Technological Complexity ◽  
Multi Stage ◽  
Effective Development

Abstract The deterioration of the reservoir properties of potential oil and gas bearing areas on mature and green fields, as well as the increase in the volume of hard-to-recover reserves on low-permeable reservoirs set us new challenges in searching and using effective development technologies to maintain and even increase the oil production levels. Based on successful international experience, Russian oil and gas companies use horizontal wells (HW) with multi-stage hydraulic fracturing (MSHF) for the cost-effective development of low-permeable reservoirs. Thus, since the first pilot works of drilling technologies and completion of HW with MSHF in 2011, at the beginning of 2020, over 1,200 HW with MSHF were drilled and came on stream at the fields of LLC RN-Yuganskneftegaz, about half of which are at the exploitation play AS10-12 of the northern license territory (NLT) of the Priobskoye field. In searching the best technologies and engineering solutions, the company tested different lengths of horizontal section of HW, the number of hydraulic fracturing (HF) stages and distances between hydraulic fracturing ports, as well as different specific mass of the proppant per frac port. Recently, there has been a tendency in design solutions to increase the length of the HWs and the number of hydraulic fractures with a decreasing distance between the frac ports and a decreasing specific mass of the proppant per frac port. This work studies the actual and theoretical efficiency of HW with MSHF of various designs (different lengths of horizontal section of HW and the number of HF stages) and to assess the viability of increasing the technological complexity, as well as to analyze the actual impact of loading the proppant mass per port on performing HW with MSHF. The study is based on the results of the analysis of the factual experience accumulated over the entire history of the development of the exploitation play AS10-12 of the NLT of the Priobskoye field of the Rosneft Company. In studying the viability of increasing the technological complexity, especially, increasing the length of horizontal section of HW, increasing the number of HF stages, and reducing the distance between the frac ports: we discovered the typical methodological errors made in analyzing the efficiency of wells of various designs; we developed the methodology for analysis of the actual multiplicity of indicators of wells of various designs, in particular, HW with MSHF relative to deviated wells (DW) with HF; we carried out the statistical analysis of the actual values of the multiplicity of performance indicators and completion parameters of HW with MSHF of various designs relative to the surrounding DW with HF of the exploitation play AS10-12 of the NLT of the Priobskoye field; we performed the theoretical calculation of the multiplicity of the productivity coefficient for the HW with MSHF of various designs relative to DW with HF for the standard development system of the exploitation play AS10-12 of the NLT of the Priobskoye field; we compared the actual and theoretical results. The paper also presents the results of studying the actual effect of changes of proppant's mass per port on performance indicators of HW with MSHF of the same design and with an increase in the number of fractures of the hydraulic fracturing without changing the length of horizontal section of HW. As for performance indicators, being the basis for estimating the efficiency of HW with MSHF of various designs, we used the productivity index per meter of the effective reservoir thickness and the cumulative fluid production per meter of the effective reservoir thickness per a certain period of operation. And as the completion parameters, we used the length of the horizontal section of HW, the number of HF stages, the distance between the frac ports, and the specific mass of the proppant per meter of the effective reservoir thickness per frac port. The results of this work are the determining vector of development for future design decisions in improving the efficiency of HW with MSHF.

Digital Rock Typing DRT Algorithm Formulation with Optimal Supervised Semantic Segmentation

2022 ◽  
Author(s):  
Omar Alfarisi ◽  
Djamel Ouzzane ◽  
Mohamed Sassi ◽  
TieJun Zhang
Keyword(s):  
Carbonate Rock ◽  
Chemical Properties ◽  
Rock Physics ◽  
Semantic Segmentation ◽  
Rock Properties ◽  
Digital Rock Physics ◽  
Digital Rock ◽  
Rock Types ◽  
Fluid Saturation ◽  
Rock Typing

<p><a></a>Each grid block in a 3D geological model requires a rock type that represents all physical and chemical properties of that block. The properties that classify rock types are lithology, permeability, and capillary pressure. Scientists and engineers determined these properties using conventional laboratory measurements, which embedded destructive methods to the sample or altered some of its properties (i.e., wettability, permeability, and porosity) because the measurements process includes sample crushing, fluid flow, or fluid saturation. Lately, Digital Rock Physics (DRT) has emerged to quantify these properties from micro-Computerized Tomography (uCT) and Magnetic Resonance Imaging (MRI) images. However, the literature did not attempt rock typing in a wholly digital context. We propose performing Digital Rock Typing (DRT) by: (1) integrating the latest DRP advances in a novel process that honors digital rock properties determination, while; (2) digitalizing the latest rock typing approaches in carbonate, and (3) introducing a novel carbonate rock typing process that utilizes computer vision capabilities to provide more insight about the heterogeneous carbonate rock texture.<br></p>

A Machine Learning Methodology for Rock-Typing Using Relative Permeability Curves

2021 ◽  
Author(s):  
Carlos Esteban Alfonso ◽  
Frédérique Fournier ◽  
Victor Alcobia
Keyword(s):  
Machine Learning ◽  
Capillary Pressure ◽  
Relative Permeability ◽  
Fractional Flow ◽  
Flow Curves ◽  
Rock Types ◽  
Rock Typing ◽  
Relative Permeability Curves ◽  
Permeability Data

Abstract The determination of the petrophysical rock-types often lacks the inclusion of measured multiphase flow properties as the relative permeability curves. This is either the consequence of a limited number of SCAL relative permeability experiments, or due to the difficulty of linking the relative permeability characteristics to standard rock-types stemming from porosity, permeability and capillary pressure. However, as soon as the number of relative permeability curves is significant, they can be processed under the machine learning methodology stated by this paper. The process leads to an automatic definition of relative permeability based rock-types, from a precise and objective characterization of the curve shapes, which would not be achieved with a manual process. It improves the characterization of petrophysical rock-types, prior to their use in static and dynamic modeling. The machine learning approach analyzes the shapes of curves for their automatic classification. It develops a pattern recognition process combining the use of principal component analysis with a non-supervised clustering scheme. Before this, the set of relative permeability curves are pre-processed (normalization with the integration of irreducible water and residual oil saturations for the SCAL relative permeability samples from an imbibition experiment) and integrated under fractional flow curves. Fractional flow curves proved to be an effective way to unify the relative permeability of the two fluid phases, in a unique curve that characterizes the specific poral efficiency displacement of this rock sample. The methodology has been tested in a real data set from a carbonate reservoir having a significant number of relative permeability curves available for the study, in addition to capillary pressure, porosity and permeability data. The results evidenced the successful grouping of the relative permeability samples, according to their fractional flow curves, which allowed the classification of the rocks from poor to best displacement efficiency. This demonstrates the feasibility of the machine learning process for defining automatically rock-types from relative permeability data. The fractional flow rock-types were compared to rock-types obtained from capillary pressure analysis. The results indicated a lack of correspondence between the two series of rock-types, which testifies the additional information brought by the relative permeability data in a rock-typing study. Our results also expose the importance of having good quality SCAL experiments, with an accurate characterization of the saturation end-points, which are used for the normalization of the curves, and a consistent sampling for both capillary pressure and relative permeability measurements.

Sign in / Sign up

Export Citation Format

Share Document