Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
Optimization of the “mature” fields development in machine learning algorithms is one of the urgent problems nowadays. The task is set to extend the effective operation of wells, optimize production management at the late stage of field development. Based on the task set, the article provides an overview of possible solutions in waterflooding management problems. Production management technology is considered as an alternative to intensification of operation, which is associated with an increase in the produciton rate and involves finding solutions aimed at reducing the water cut of well production. The practical implementation of the “Neural technologies for production improvement” includes the following steps: evaluation, selection, predictive analytics. The result is a digital technological regime of wells that corresponds to the set goal and the solution of the optimization problem in artificial intelligence algorithms using the software and hardware complex “Atlas – Waterflood Management”. “Neural technologies for production improvement” have been successfully tested at the pilot project site of the productive formation of the Vatyeganskoe field. The article provides a thorough and detailed analysis of the work performed, describes the algorithms and calculation results of the proxy model using the example of the pilot area, as well as the integration of the “Atlas – Waterflood Management” and the organization of the workflow with the field professionals of the Territorial Production Enterprise Povkhneftegaz.
Optimization of the “mature” fields development in machine learning algorithms is one of the urgent problems nowadays. The task is set to extend the effective operation of wells, optimize production management at the late stage of field development. Based on the task set, the article provides an overview of possible solutions in waterflooding management problems. Production management technology is considered as an alternative to intensification of operation, which is associated with an increase in the produciton rate and involves finding solutions aimed at reducing the water cut of well production. The practical implementation of the “Neural technologies for production improvement” includes the following steps: evaluation, selection, predictive analytics. The result is a digital technological regime of wells that corresponds to the set goal and the solution of the optimization problem in artificial intelligence algorithms using the software and hardware complex “Atlas – Waterflood Management”. “Neural technologies for production improvement” have been successfully tested at the pilot project site of the productive formation of the Vatyeganskoe field. The article provides a thorough and detailed analysis of the work performed, describes the algorithms and calculation results of the proxy model using the example of the pilot area, as well as the integration of the “Atlas – Waterflood Management” and the organization of the workflow with the field professionals of the Territorial Production Enterprise Povkhneftegaz.
One of the important tasks of analyzing oil field development is predicting well performance. For this purpose, displacement characteristics are often used, which represent the dependence of some indicators on others. To determine the parameters of these dependencies, regression analysis of historical data is used. Dependences of the choice of watering production wells with water pumped into injection wells, water or the law of the exhausted aquifer. A feature of displacement characteristics is generally considered to be that they can only be used when fluid flows in the formation are established. This is due to the fact that with the classical approach, displacement of characteristics is not observed in the explicit form of well interference. Therefore, the search for displacement characteristics, with the help of which we can talk about the mutual influence of wells, is an important factor. This is the subject of this work. Water cut and water-oil ratio (WOR) are related by a well-known formula. The paper proposes regression models for WOR. They obtained the result taking into account the classical logic of the WOR from accumulated oil production. Water cut is calculated from water saturation. The proposed regression models of water saturation are based on the analysis of equations of theories of two-phase filtration in difference form. 11 watering models were studied, two including classical ones and 9 new ones. Dependencies for reservoir and bottomhole pressures were also developed. The proposed models are intended to analyze the operation of wells during the development of an oil reservoir in an elastic-water-pressure mode. The models were tested on a real field and their effectiveness was analyzed. Some new models perform well in a selection of tests. In particular, all the proposed models give better results than the classical model: the logarithm of the water-oil ratio from the accumulation of oil production.
The main types of CRM models (Capacitance Resistive Model) are considered. The advantage of CRM models over other types of models is the exclusion from consideration of reservoir pressure, information about which is usually unsystematic, scattered, and often unreliable. Particular attention in the work is paid to ML-CRM models that describe flow in layered formations. According to the literature, three models are described that are closest to the proposed one in this paper.The author’s model of interaction between wells during waterflooding of an oil reservoir with double permeability (layered heterogeneous reservoir) is proposed within the framework of the CRM modeling concept. Differences of the proposed model from models of other authors: 1) the model takes into account possible flows between layers due to vertical filtration across the bedding; 2) the model takes into account the two-phase nature of filtration during waterflooding, thanks to the use of a differential equation for the conservation of water volume in reservoir conditions, this approach is the most accurate and physically justified; 3) differential equations of the model are solved using numerical methods; 4) a system consisting of two layers with different filtration and capacitance properties is considered.The proposed model was tested on model and actual data. In the model example, when comparing various development indicators calculated using the CRM model and using a hydrodynamic simulator, the coefficient of determination is at least 0.9. This is a good result and indicates a high level of coincidence of the curves. In the actual example, when comparing those calculated using the CRM model and actual development indicators, the coefficient of determination is at least 0.7. This is also a good result for the actual data and indicates a high level of agreement between the calculated and actual curves.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.