A New Artificial Intelligence Method to Predict Water Flooding Performance in Layered Reservoir

2021 ◽  
Author(s):  
Cunliang Chen ◽  
Xiaodong Han ◽  
Wei Zhang ◽  
Yanhui Zhang ◽  
Fengjun Zhou
Keyword(s):  
Artificial Intelligence ◽  
Numerical Simulation ◽  
Computing Time ◽  
Vertical Direction ◽  
Single Layer ◽  
Oil Production ◽  
Oil Field ◽  
Production Performance ◽  
New Method ◽  
Water Flooding

Abstract The ultimate goal of oilfield development is to maximize the investment benefits. The reservoir performance prediction is directly related to oilfield investment and management. The traditional strategy based on numerical simulation has been widely used with the disadvantages of long run time and much information needed. It is necessary to form a fast and convenient method for the oil production prediction, especially for layered reservoir. A new method is proposed to predict the development indexes of multi-layer reservoirs based on the injection-production data. The new method maintains the objectivity of the data and demonstrates the superiority of the intelligent algorithm. The layered reservoir is regarded as a series of single layer reservoirs on the vertical direction. Considering the starting pressure gradient of non-Newtonian fluid flow and the variation of water content in the oil production index, the injection-production response model for single-layer reservoirs is established. Based on that, a composite model for the multi-layer reservoir is established. For model solution, particle swarm optimization is applied for optimization of the new model. A heterogeneous multi-layer model was established for validation of the new method. The results obtained from the new proposed model are in consistent with the numerical simulation results. It saves a lot of computing time with the incorporation of the artificial intelligence methods. It showed that this technique is valid and effective to predict oil performance in layered reservoir. These examples showed that the application of big data and artificial intelligence method is of great significance, which not only shortens the working time, but also obtains relatively higher accuracy. Based on the objective data of the oil field and the artificial intelligence algorithm, the prediction of oil field development data can be realized. This technique has been used in nearly 100 wells of Bohai oilfields. The results showed in this paper reveals that it is possible to estimate the production performance of the water flooding reservoirs.

Unlocking By-Passed Oil with Autonomous Inflow Control Devices Through an Integrated Approach

2021 ◽  
Author(s):  
Pawan Agrawal ◽  
Sharifa Yousif ◽  
Ahmed Shokry ◽  
Talha Saqib ◽  
Osama Keshtta ◽  
...  
Keyword(s):  
Continuous Production ◽  
Oil Production ◽  
Gas Production ◽  
Oil Field ◽  
Production Performance ◽  
Fluid Distribution ◽  
Flow Profile ◽  
Horizontal Drain ◽  
Control Devices

Abstract In a giant offshore UAE carbonate oil field, challenges related to advanced maturity, presence of a huge gas-cap and reservoir heterogeneities have impacted production performance. More than 30% of oil producers are closed due to gas front advance and this percentage is increasing with time. The viability of future developments is highly impacted by lower completion design and ways to limit gas breakthrough. Autonomous inflow-control devices (AICD's) are seen as a viable lower completion method to mitigate gas production while allowing oil production, but their effect on pressure drawdown must be carefully accounted for, in a context of particularly high export pressure. A first AICD completion was tested in 2020, after a careful selection amongst high-GOR wells and a diagnosis of underlying gas production mechanisms. The selected pilot is an open-hole horizontal drain closed due to high GOR. Its production profile was investigated through a baseline production log. Several AICD designs were simulated using a nodal analysis model to account for the export pressure. Reservoir simulation was used to evaluate the long-term performance of short-listed scenarios. The integrated process involved all disciplines, from geology, reservoir engineering, petrophysics, to petroleum and completion engineering. In the finally selected design, only the high-permeability heel part of the horizontal drain was covered by AICDs, whereas the rest was completed with pre-perforated liner intervals, separated with swell packers. It was considered that a balance between gas isolation and pressure draw-down reduction had to be found to ensure production viability for such pilot evaluation. Subsequent to the re-completion, the well could be produced at low GOR, and a second production log confirmed the effectiveness of AICDs in isolating free gas production, while enhancing healthy oil production from the deeper part of the drain. Continuous production monitoring, and other flow profile surveys, will complete the evaluation of AICD effectiveness and its adaptability to evolving pressure and fluid distribution within the reservoir. Several lessons will be learnt from this first AICD pilot, particularly related to the criticality of fully integrated subsurface understanding, evaluation, and completion design studies. The use of AICD technology appears promising for retrofit solutions in high-GOR inactive strings, prolonging well life and increasing reserves. Regarding newly drilled wells, dedicated efforts are underway to associate this technology with enhanced reservoir evaluation methods, allowing to directly design the lower completion based on diagnosed reservoir heterogeneities. Reduced export pressure and artificial lift will feature in future field development phases, and offer the flexibility to extend the use of AICD's. The current technology evaluation phases are however crucial in the definition of such technology deployments and the confirmation of their long-term viability.

Prediction and Optimization of WAG Flooding by Using LSTM Neural Network Model in Middle East Carbonate Reservoir

2021 ◽  
Author(s):  
Ruijie Huang ◽  
Chenji Wei ◽  
Baozhu Li ◽  
Jian Yang ◽  
Suwei Wu ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Numerical Simulation ◽  
Short Term Memory ◽  
Oil Production ◽  
Simulation Method ◽  
Analysis Data ◽  
Carbonate Reservoir ◽  
Parameters Optimization ◽  
Model Based

Abstract Production prediction continues to play an increasingly significant role in reservoir development adjustment and optimization, especially in water-alternating-gas (WAG) flooding. As artificial intelligence continues to develop, data-driven machine learning method can establish a robust model based on massive data to clarify development risks and challenges, predict development dynamic characteristics in advance. This study gathers over 15 years actual data from targeted carbonate reservoir and establishes a robust Long Short-Term Memory (LSTM) neural network prediction model based on correlation analysis, data cleaning, feature variables selection, hyper-parameters optimization and model evaluation to forecast oil production, gas-oil ratio (GOR), and water cut (WC) of WAG flooding. In comparison to traditional reservoir numerical simulation (RNS), LSTM neural networks have a huge advantage in terms of computational efficiency and prediction accuracy. The calculation time of LSTM method is 864% less than reservoir numerical simulation method, while prediction error of LSTM method is 261% less than RNS method. We classify producers into three types based on the prediction results and propose optimization measures aimed at the risks and challenges they faced. Field implementation indicates promising outcome with better reservoir support, lower GOR, lower WC, and stabler oil production. This study provides a novel direction for application of artificial intelligence in WAG flooding development and optimization.

scholarly journals A New Method of Plugging the Fracture to Enhance Oil Production for Fractured Oil Reservoir using Gel Particles and the HPAM/Cr3+ System

Polymers ◽  
2019 ◽  
Vol 11 (3) ◽  
pp. 446 ◽  
Author(s):  
Lei Zhang ◽  
Nasir Khan ◽  
Chunsheng Pu
Keyword(s):  
Oil Recovery ◽  
Oil Production ◽  
Oil Reservoirs ◽  
New Method ◽  
Water Flooding ◽  
Whole Process ◽  
Gel Particles ◽  
The Matrix ◽  
Water Cut ◽  
Enhance Oil Recovery

Due to the strong heterogeneity between the fracture and the matrix in fractured oil reservoirs, injected water is mainly moved forward along the fracture, which results in poor water flooding. Therefore, it is necessary to reduce the water cut and increase oil production by using the conformance control technology. So far, gel particles and partially hydrolyzed polyacrylamide (HPAM)/Cr3+ gel are the most common applications due to their better suitability and low price. However, either of the two alone can only reduce the conductivity of the fracture to a certain extent, which leads to a poor effect. Therefore, to efficiently plug the fracture to enhance oil recovery, a combination of gel particles and the HPAM/Cr3+ system is used by laboratory tests according to their respective advantages. The first step is that the gel particles can compactly and uniformly cover the entire fracture and then the fracture channel is transformed into the gel particles media. This process can enhance the oil recovery to 18.5%. The second step is that a suitable HPAM/Cr3+ system based on the permeability of the gel particles media is injected in the fractured core. Thus, the fracture can be completely plugged and the oil in the matrix of the fractured core can be displaced by water flooding. This process can enhance oil recovery to 10.5%. During the whole process, the oil recovery is increased to 29% by this method. The results show that this principle can provide a new method for the sustainable and efficient development of fractured oil reservoirs.

Expansion of Data Analytics for Optimizing Steamflood In Mukhaizna Heavy Oil Field

2021 ◽  
Author(s):  
Mohammed Al Asimi ◽  
Nasar Al Qasabi ◽  
Duc Le ◽  
Yuchen Zhang ◽  
Di Zhu ◽  
...  
Keyword(s):  
Heavy Oil ◽  
Data Analytics ◽  
Oil Production ◽  
Steam Injection ◽  
Lessons Learned ◽  
Oil Field ◽  
Production Performance ◽  
Optimization Process ◽  
Successful Implementation ◽  
Full Field

Abstract After successful implementation of data analytics for steamflood optimization at the Mukhaizna heavy oil field in Oman late 2018, Occidental expanded the project to two additional areas with a total of 626 wells in 2019, followed by full field coverage of more than 3,200 wells in 2020. In 2019, two separate low-fidelity proxy models were built to model the two pilot areas. The models were updated with more features to account for additional reservoir phenomena and a larger scope. On the proxy engine side, speed and robustness were improved, resulting in reduced CPU processing time and lower cost. Because of advancements in software programing and the pilots’ encouraging production performance, full-field coverage was accelerated so the model could support the efforts in optimizing steam injection during the 2020 OPEC+ production cut, not only to comply with allotted quotas, but also to allocate the resources optimally, especially the costly steam. Good improvements have been observed in overall steamflood performance, the models’ capabilities, and the optimization workflow. The steam/oil ratio has been reduced through the increase in oil production in both expanded study areas while keeping the total steam injection volume constant. Overall field steam utilization was improved both during the 2020 OPEC+ production cuts and during the production ramp-up stage afterward. With the continuous improvement in supporting tools and scripts, most of the steam optimization process steps were automated, from preparing, checking, and formatting input data to analyzing, validating, and visualizing the model outputs. Another result of these improvements was the development of a user-friendly web application to manage the model workflow efficiently. This web app greatly improved the process of case submittals, including data preparation and QC, running models (history matching and forecasting), as well as visualization of the entire workflow. In terms of optimization workflow, these improvements resulted in less time spent by the field optimization engineer in updating, refreshing, and generating new model recommendations. It also helped reduce the time spent by the reservoir management team (RMT) to test and validate the new ideas before field implementation. This paper will describe the improvements in the proxy model and the overall optimization process, show the observed oil production increases, and discuss the challenges faced and the lessons learned.

Optimising Oil Field Net Present Value with Produced Water Salinities and Tracers

2021 ◽  
Author(s):  
Babalola Daramola
Keyword(s):  
Reservoir Simulation ◽  
Produced Water ◽  
Water Injection ◽  
Oil Production ◽  
Oil Field ◽  
Water Flooding ◽  
Water Salinity ◽  
History Match ◽  
Infill Drilling ◽  
Salinity Data

Abstract This paper presents case studies of how produced water salinity data was used to transform the performance of two oil producing fields in Nigeria. Produced water salinity data was used to improve Field B’s reservoir simulation history match, generate infill drilling targets, and reinstate Field C’s oil production. A reservoir simulation study was unable to history match the water cut in 3 production wells in Field B. Water salinity data enabled the asset team to estimate the arrival time of injected sea water at each production well in oil field B. This improved the reservoir simulation history match, increased model confidence, and validated the simulation model for the placement of infill drilling targets. The asset team also gained additional insight on the existing water flood performance, transformed the water flooding strategy, and added 9.6 MMSTB oil reserves. The asset team at Field C was unable to recover oil production from a well after it died suddenly. The team evaluated water salinity data, which suggested scale build up in the well, and completed a bottom-hole camera survey to prove the diagnosis. This justified a scale clean-out workover, and added 5000 barrels per day of oil production. A case study of how injection tracer data was used to characterise a water injection short circuit in Field D is also presented. Methods of using produced water salinity and injection tracer data to manage base production and add significant value to petroleum fields are presented. Produced water salinity and injection tracer data also simplify water injection connectivity evaluations, and can be used to justify test pipeline and test separator installation for data acquisition.

Design and Execution of the First Large-Scale Polymer Injection Pilot in Sirikit Oil Field

2021 ◽  
Author(s):  
Weeraya Wuttipittayamongkol ◽  
Pannapon Trinavarat ◽  
Warisa Nuntaprayoon ◽  
Monrawee Pancharoen ◽  
Rapheephan Laochamroonvorapongse
Keyword(s):  
Large Scale ◽  
Oil Field ◽  
Production Performance ◽  
Water Flooding ◽  
Small Scale ◽  
Mechanical Degradation ◽  
Close Monitoring ◽  
Polymer Injection ◽  
Fluid Saturation ◽  
Water Cut

Abstract Becoming more mature with field-wide water flooding implementation for more than 30 years, Sirikit Oil Field (S1) is going forward to the next rejuvenating step of enhanced oil recovery (EOR). Generally, the field contains light oil (40° API) in highly stratified sand-shale sequences with low net-to-gross ratios. High reservoir temperature, low permeability, and high water cut observed from production make it even more challenging for polymer injection projects. Nonetheless, the success from a small-scale field trial has shown a promising future of EOR application in the field and brought an execution of the first large-scale polymer injection pilot. Polymer screening laboratory tests, a reservoir simulation study, data acquisition program and techniques, injectivity tests, polymer injection unit design, and risk assessment were parts of the pilot preparation, in which the key learnings from the previous pilot have been incorporated. The gathering and determination of baseline parameters including production performance, injection profiles, reservoir fluid saturation profiles, etc., were registered for ultimate evaluation. Then, the continuous polymer injection has been started since October 2019 in two separated fault blocks where 12 injectors and 20 producers are located in different injection patterns. During several months of polymer injection, both foreseen and unforeseen changes have enlivened the pilot management. Although the injectivity test with polymer solution prior to the pilot demonstrated no injection difficulty, several wells have shown injectivity deterioration with time. Mechanical degradation is induced in these wells by the installation of flow restriction devices to lessen solution viscosity and, hence, prolong polymer injectivity. Well integrity issues and artificial lift breakdown negatively affect field production and close-in wells make it harder for voidage replacement control. Immediate troubleshooting and close monitoring have been placed and eventually leads to the recognition of encouraging results. Polymer helps improve vertical injection profiles as seen from injection logging. Saturation logging presents a sign of oil saturation decrease around the wellbore area. Reduction of water cut and rise of oil production have pleasantly come after a few months from the start. Intensive surveillance program will be continued over the course of pilot injection. The critical success of the EOR pilot execution depends on the detailed planning, prudent surveillance and comprehensive evaluation. Sirikit oil field is moving to a turning point and the pilot outcome would lead the way to a further milestone, so as to avoid premature end of the field's production.

Research on Residual Oil Distribution Regular of Steam Flooding after Polymer Flooding

2013 ◽  
Vol 734-737 ◽  
pp. 1440-1444 ◽  
Author(s):  
Shang Ming Shi ◽  
Hua Bin Wei ◽  
Bo Li ◽  
Hong Lou ◽  
Dong Kai Huo
Keyword(s):  
Numerical Simulation ◽  
High Water ◽  
Polymer Flooding ◽  
Test Area ◽  
Oil Field ◽  
Water Flooding ◽  
Field Development ◽  
Steam Flooding ◽  
Remaining Oil ◽  
Distribution Laws

The study on distribution laws of remaining oil in high water cut stage is the difficulty of oil field development in the mid-to late period. Aiming at the long development time of Western Bei 2 area of Saertu oilfield in Daqing Oilfield and its complicated well history conditions undergone water flooding, polymer flooding and steam flooding, the 3D geological static model has been established in this test area based on the study on its structure characteristics and sedimentary features. By applying the method of fine reservoir numerical simulation, the paper completes the numerical simulation of remaining oil in the test area and summarizes types of remaining oil as well as their distribution laws in the test area, which provides a reliable basis for the further deployment and adjustment measures in the oilfield.

Managing limited subsurface data in a mature oil field case study: extending the production lifetime of a 50-year-old oil field in Indonesia: Rantau oil field Waterflood Pilot Project

2013 ◽  
Vol 53 (2) ◽  
pp. 489
Author(s):  
Reza Ardianto
Keyword(s):  
Oil Recovery ◽  
Oil And Gas ◽  
Oil Production ◽  
Pilot Project ◽  
Oil Field ◽  
Oil Fields ◽  
Water Flooding ◽  
Peak Oil ◽  
Screening Criteria ◽  
The Government

Business management of oil and gas in Pertamina State Oil enterprises was handed to one of its subsidiaries: Pertamina EP (PEP). With a vast working area of 140,000 km2, it consists of 214 fields where 80% is an old field (mature field or brown field). Most of these oil fields were discovered during Dutch colonialism. One of these fields was Rantau oil field, discovered in 1928; it is considered one of potential structure at the time. Peak oil production was achieved at 31,711 barrels of oil per day (BOPD) (wc 17.2%) in 1969, and it is still producing 2,500 BOPD from primary stage.To get better recovery from the Rantau oil field, it is necessary to identify the potential of secondary recovery water-flooding. Some screening criteria had been completed to select an appropriate method that could be applied in the Rantau field. PEP is preparing an Enhanced Oil Recovery (EOR) program to be applied in some oil fields with subsurface and surface potential consideration. The implementation was initiated by the EOR Department at PEP. The issue of the national oil production increasing program from the government has to be realised by the EOR Department at Pertamina EP. Following the national oil increasing program, management of PEP urged to increase oil production in a rapid and realistic way. As a result, the program of secondary and tertiary recovery pilot project should be conducted simultaneously by the EOR Department on some of the fields that have passed their peak. On the other hand, PEP has only limited geology, geophysics, reservoir, and production (GGRP) data, and most of the oil fields have been producing since 1930s. The conditions that have to be dealt with are as follows: production from the existing field is declining, data is collected and interpreted during a long period, huge amounts of production data, and reservoir model and simulation do not exist and are not frequently updated. Based on this, the planning of EOR struggled due to length of time needed versus the need for quick development. It has become much more of a challenge for the team consisting of integrated geophysics, geology, reservoir, production, process facility, project management and economic evaluation. This extended abstract presents the term of managing limited GGRP data that contributes to the successful pilot waterflood project in the Rantau field. It also explains the uses of limited subsurface GGRP data to overcome the uncertainty for planning of the waterflood pilot project in the Rantau field, as a part of planning using limited data.

Process Design of Cyclic Water Flooding by Real-Time Monitoring

2018 ◽  
Vol 140 (11) ◽  
Author(s):  
Kobra Pourabdollah
Keyword(s):  
Real Time ◽  
Production Rate ◽  
Process Design ◽  
Water Injection ◽  
Oil Production ◽  
Oil Field ◽  
Water Flooding ◽  
Injection System ◽  
Real Time Monitoring ◽  
Naturally Fractured

The gradual decline in the oil production rate of water flooded reservoirs leads to decrease in the profit of water flooding system. Although cyclic water injection (CWI) was introduced to reduce the descending trend of oil production in water flooded reservoirs, it must be optimized based upon the process parameters. The objective of this study is to develop all process design criteria based upon the real-time monitoring of CWI process in a naturally fractured reservoir having five producing wells and five injector wells completed in an Arab carbonated formation containing light crude oil (API = 42 deg). For this aim, a small pilot oil field was selected with water injection facilities and naturally producing oil wells and all data were collected from the field tests. During a five years' field test, the primary observations at the onset of shutdown periods of the water injection system revealed a repeatable significant enhancement in oil production rate by a factor of plus 5% leading us to assess the application of CWI. This paper represents the significant parameters of pressure and productivity affected during CWI in naturally fractured carbonate reservoirs based upon a dual porosity generalized compositional model. The results hopefully introduce other oil producer companies to the potential of using CWI to increase oil production in conventional water injection systems. The results also outline situations where such applications would be desirable.

Sign in / Sign up

Export Citation Format

Share Document