Vol 5, No 3 (2023)

Background: Absolute permeability plays an important role in studying the fluids flow in porous media during the development of oil and gas reservoirs, the injection of CO₂ into reservoirs for storage, the monitoring of pollutants migration in underground aquifers, and the modeling of catalytic systems. Therefore, an accurate and fast evaluation of its values is an important task.

Aim: The purpose of this article is to study the applicability of machine learning methods for predicting the absolute permeability of carbonate samples, as well as ways to improve the prediction of permeability.

Materials and methods: The input data is 408 small volumes extracted from four cylindrical carbonate samples composed almost entirely of calcite. Input data includes total and connected porosity, specific surface area, radii of all and only connected pores, coordination number, throat radius and length, tortuosity, and absolute permeability. Permeability prediction is carried out using regression machine learning methods such as random forest, extremely random trees and extended gradient boosting. Parameters (data) of small volumes were determined using pore-scale modeling of water flow in their pore space applying a specialized Avizo software.

Results: Data of small volumes extracted from fractured and non-fractured samples were analyzed, and the results showed that there are good relationships between many parameters of small volumes. For example, the connected and total porosity have a second-order polynomial relationship with a high correlation coefficient. Using the above-mentioned regression machine learning methods, absolute permeability values were predicted when input data divided into training and testing data in a ratio of 80/20 and 70/30.

Conclusion: Using the logarithm of permeability instead of permeability itself and considering fractured and non-fractured samples separately, can increase the accuracy of absolute permeability prediction using the above-mentioned machine learning methods up to 90%. The extremely random trees method is the most accurate among the three machine learning methods considered for our task.

Background: The drilling of new wells is one of the most effective geological and technical activities. In mature fields characterized by high production of reserves and high water availability, the selection of design points for drilling is a difficult task. Forecasting the parameters of new wells is possible by using geological and hydrodynamic models or analytical methods. In this paper, the authors propose the use of machine learning algorithms to predict the initial parameters of new wells based on an extensive set of geological and field data.

Aim: The article describes the process of developing machine learning algorithms and demonstrates the performance indicators of a complex model. As part of this work, testing of machine learning algorithms was performed to predict the start-up water cut of potential candidates.

Materials and methods: Within the framework of this work, various machine learning methods were applied on geological and technical field data.

Results: The developed complex model showed acceptable convergence results based on classification and regression metrics, which indicates its applicability for predicting the start-up water cut of project wells.

Conclusion: This method of predicting indicators is an alternative tool for predicting the start-up water cut of new wells, which makes it possible to clarify and supplement the forecast parameters calculated using a geological and hydrodynamic model or empirical dependencies of the initial water cut of new wells on geological parameters.

Background: The injection of the thermal agent as "steam" reduces the viscosity of the oil and the mobility ratio, which increases the displacement and coverage factor, and ultimately significantly increases the oil recovery factor. This statement was the basis for determining the effect of steam enthalpy on the oil recovery factor, as well as for reliably determining the flow rate of flared gas, as a result of which the existing gas pipeline will be reconstructed, the required amount of fresh water will be calculated, and the distribution of steam pumping in the entire Karazhanbas field.

Aim: The purpose of the article is to consider the influence of the quality of steam produced at the steam generator units of the Karazhanbas field on the oil recovery factor. The main parameter that determines the quality of steam is dryness, which was calculated using the actual values of the boiler (pressure, temperature, gas flow), flue gas tests on a special device, as well as laboratory tests to determine the heat value of the combusted gas.

Materials and methods: This work used materials from GHM (geological and hydrodynamic modeling), results of studies of boiler flue gases and heat balance.

Results: The calculation showed a low quality of the produced steam, which negatively affects the recovery factor.

Conclusion: Evaluation to determine the optimal value of saturated steam parameters (steam dryness, temperature in terms of development efficiency) showed that the higher the temperature and dryness of steam at the wellhead and bottom hole of the injection well, the higher the oil recovery factor at the Karazhanbas field.

Background: In this paper, the potential of applying hydraulic fracturing with the installation of a gravel pack in the Cretaceous horizons of the M field is investigated. The relevance of the work is due to the fact that today the selection of optimal technologies to increase the rate of oil production from the Cretaceous deposits an open platform for proposals and discussions. The low oil recovery coefficient is due to the existing restrictions on the oil production process: high oil viscosity, the presence of gas and water-oil zones, abundant sand production in a poorly cemented reservoir.

Aim: The purpose of the work is to study the potential application of Frac-Pack technology in the wells of the M field.

Materials and methods: In order to assess the potential of using Frac-Pack in a special FracPro software, a model of geomechanical and filtration properties of the formation was developed and a simulation of the design with various injection parameters was performed. Based on the results of laboratory studies of the content of mechanical impurities in liquids sampled at the M field, the diameter of the proppant and the flow section of the filter were determined.

Results: As a result of the study, hydraulic fracturing was simulated for a well from a sample of potential candidates, the oil flow rate was calculated after the application of the proposed technology, materials for the implementation of Frac-Pack technology were selected based on laboratory studies.

Conclusion: The study showed that the proposed pre-development strategy is the most optimal for shallow wells of the M field, as it is aimed not only at solving the problem of combating the removal of mechanical impurities, but also increasing oil production.

Background: The appearance of intercasing pressure in many cases is associated with inadequate quality of primary cementing. Despite the fact that many studies are aimed at preventing problems of primary cementing, at improving the quality of well completion, it should be noted that the problem of intercasing pressure at existing gas and gas condensate wells is increasing.

Aim: The purpose of this work is to study and eliminate wells with intercasing pressure at the Amangeldy gas condensate field.

Materials and methods: This paper presents the procedure for preparing the well and carrying out the elimination of intercasing pressure, as well as the chemical components of cementing slurry.

Results: The conducted studies and measures on wells No.121; No.105; No.103 and No.101 showed a positive result and the effectiveness of the composition of cementing slurry.

Conclusion: The presented technology for the elimination of intercasing pressure and the composition of the cementing slurry can be widely used in many fields of Kazakhstan.

Background: The concept of reliability of gas distribution systems implies the possibility of reliable transportation of the required amount of gas to the consumer in compliance with the specified parameters in normal operation for a certain period of time.

Aim: The peculiarity of gas distribution networks is that they are long-term planning systems, with the growth of cities and the connection of consumers, the radius of their impact increases, expands, rebuilds, worn-out nodes and elements are replaced with new ones. The main goal at this stage of operation is the absence of significant reconstruction measures to improve the reliability of the system.

Materials and methods: Work has been carried out to analyze the probability of triggering, the failure rate and the probability of failures of gas supply systems for single indicators.

Results: To ensure the reliability and durability of gas boilers during replacement, the following 8 different measures were proposed.

Conclusion: The article proposes a closed circuit, the introduction of network redundancy in the system by ringing or duplicating elements and considers the social nature of gas distribution systems.