Articles

Automation

Development of approaches to automated correlation from well log data using machine learning

Latypov I.D., Markov A.V., Evgrafov N.A., Shagimardanova L.R.

DOI: 10.24412/2076-6785-2024-4-47-51

Abstract
This paper discusses the principles and methods of in-situ section correlation and examples of its application to enhance the quality of petrophysical interpretation. One issue with automatic in-situ correlation is its dependence on the order in which wells are considered. To eliminate this problem, one option is to define the bypass paths of wells based on their proximity according to a Euclidean norm using log curve data. The paper presents an approach to automatic well log correlation using principal cluster analysis, component analysis and dynamic time warping.

Materials and methods
The paper discusses methods for intra-situ correlation of well sections.
Automatic section correlation is based on the use of cluster analysis algorithms, principal component analysis and dynamic transformation of the time scale. Principal component methods and cluster1 analysis are used to organize data from different wells according to geophysical responses, which allows for more efficient cross-section correlation using the dynamic time transformation (DTW) algorithm.

Keywords
well log correlation, k-means method, dynamic time warping, principal component method

Application of automated decryption methods in recognition of anthropogenic impact zones on oil and gas fields

Eleshkevich A.D., Eremenko M.S., Saibel E.G., Khristolubov I.A., Chernov A.G.

DOI: 10.24412/2076-6785-2023-7-127-131

Abstract
This article discusses the experience of creating and implementing methods of automated decoding using machine learning algorithms to solve the problem of identifying areas of anthropogenic impact in oil and gas fields. The options for using various remote sensing data are described to identify such areas, using examples of forest clearings, along with their advantages and disadvantages. An original approach based on neural networks for decoding aerospace imagery is proposed, and its prospects for use are considered.

Materials and methods
Numerical modeling method using Earth remote sensing data.


Keywords
pattern recognition, remote sensing data, anthropogenic zones, computer vision, machine learning, forest cuttings, environmental monitoring, neural networks

Thermometry process automation as a part of the geotechnical control system implementation in Tomsk Scientific Research Institute of Oil and Gas

Badichev K.S., Mazovets S.A., Kilin E.A., Napryushkin A.A., Gilev N.G.

DOI: 10.24412/2076-6785-2023-7-122-126

Abstract
The article presents the results obtained by Tomsk Scientific Research Institute of Oil and Gas in creating a software module for the Information resource “Geotechnical control” (IR GC), its capabilities and areas of application are described. This software component allows minimizing additional manual operations and risks of human error when receiving data from thermometric equipment. The use of IRGC, which includes this software component, contributes to enhancing environmental safety and reducing labor costs for conducting geotechnical monitoring in oil and gas industry.

Materials and methods
In the course of this work, an analysis of data transmission methods from thermistor strings was carried out and a software module for consolidating data collected from thermometric equipment was developed.

Keywords
geotechnical monitoring, automation, ground temperature, thermometric equipment, temperature monitoring

Development of a methodology for predicting reservoir properties of oil using machine learning methods

Freiman O.A., Eremin N.A.

DOI: 10.24412/2076-6785-2022-7-118-120

Abstract
Reservoir properties of oil are necessary to justify the effective regulation of field development. Measurement accuracy in field development depends on reservoir data (eg material balance calculations, reserves estimation, predictive data analysis). Incorrect measurement of reservoir properties can lead to serious errors in the calculation results. In the literature, the influence of reservoir data uncertainty on test results was considered, for example, in material balance equations and estimates of hydrocarbon reserves and the release of more volatile fluids. In recent decades, various models have been developed to assess the reservoir properties of formation fluids, such as empirical, compositional and based on neural networks. In this study, a machine learning method will be used to predict the performance indicators of an oil field and calculate reservoir fluid properties.

Materials and methods
Reservoir fluid properties were taken from a open database for the Volve field, North Sea, Norwegian sector. Machine learning methods formed the basis for determining reservoir properties of fluids and calculating technological development indicators.

Keywords
reservoir properties, oil and gas, machine learning, artificial intelligence

On extending the service life of process automation systems, process control systems GOFO-2/Ya mal

Kutygin I.A., Eremin N.A., Basnieva I.K.

DOI: 10.24412/2076-6785-2023-7-113-117

Abstract
The development and improvement of automated process control systems at gas transportation enterprises based on platform software products is relevant task. The process control system GOFO-2 is one of the world’s largest automated control systems for technological processes of gas transportation. The software and hardware complex are open and flexible tool for solving the problem of extending the service life of the automated process control system GOFO-2, which will reduce investments and minimize risks. The development of the gas transportation system, implementation of new technologies and refinement of the equipment contribute to the improvement of automated process control systems.

Materials and methods
The main tendency for modernization the automated control system for the technological process of gas transport GOFO-2/Yamal were developed during this work, in terms of: shock-free transition to a new set of technical facilities for integrating information and cybernetic processes and creating a unified information space.
The shockless transition model is based on the method of integrating an object-oriented hierarchical SCADA database existing at the data center into a modern system.
To organize the overhaul work, methods of optimal planning for the removal of equipment for repair were used based on special multifactor optimization algorithms that take into account predictive analysis of the condition of equipment, work schedule, availability of crews and materials, as well as forecast of equipment load based on machine learning algorithms.

Keywords
service life, process automation systems, process control systems, dispatch control, gas transportation

Automatic adaptation of models for in-field gas network as part of intelligent control system

Arkhipov Yu.A., Loznyuk O.A., Strekalov A.V.

DOI: 10.24412/2076-6785-2023-8-101-106

The article considers a new method of automatic adaptation of a deterministic physical and mathematical model of the gas well production collection network within the field. A number of algorithms are shown that allow fully automatic adaptation of models of wells, pipeline fittings and the pipeline network as a whole with high accuracy and minimizing the likelihood of a decrease in predictive capability.

Materials and methods
In the article, the modeling tool is deterministic physical and mathematical models. Optimization problems for model adaptation are solved using numerical methods of nonlinear programming and simulation neural networks.

Keywords
transport, gas, network, pipeline, well, production,
modeling, adaptation

Prediction of temperature distribution along the oil wells during steam cycling

Stepanov V.A., Yasnitsky L.N.

DOI: 10.24412/2076-6785-2023-3-69-73

Abstract
One of the main sources of obtaining information about the degree of heating of the oil reservoir and the effectiveness of steam cyclic treatment of wells is geophysical research, which consists in measuring the temperature in the wellbore using a descent geophysical instrument.
This is a rather laborious and not always successful process. As an alternative, this article attempts to develop an engineering software product capable of predicting the temperature distribution in a well and thus partially or completely replace the downhole survey. The neural network underlying the engineering product was trained on data from the wells of the Usinskoye field. The article notes that forecasting the temperature distribution in wells can allow engineers to find and implement the most rational modes of steam cycling treatment.

Materials and methods
When designing, generating, testing neural networks and neural network modeling, software tools, developments and experience of the scientific school of the Perm State National Research University were used. To train neural networks, a dataset was used, created on the basis of steam cycling data from 50 wells in the Usinskoye field.

Keywords
steam cycling, GIS 55, Usinskoye field, oil, oil reservoir, well, forecasting, neural network, temperature

Tests and implementation of a subsystem for detecting unusual events at a multi-pipe main gas-pipeline

Bukhvalov I.R., Evseev S.V.

DOI: 10.24412/2076-6785-2021-6-80-84

Abstract
The present paper objective is the test process description of the subsystem for detecting unusual events (SDUE) Unified Telemechanics Complex (UTC) at a multi-pipe main gas-pipeline (MGP).
The paper presents:
• a principle of designing a test bench for debugging and checking SDUE on the basis of on-line mathematical model and MGP map as a flow chart;
• the tests complex and their results referred to SDUE operation for detecting unusual events;
• obtained specifications of SDUE.

Materials and methods
Full-scale experiments for defining front characteristics, amplitude and duration of the gas pressure drop caused by “partial pipeline rapture” of the main gas pipeline (MGP) as well as gas pressure drop propagation rate in MGP. Tests at operating gaspipeline.

Keywords
telemechanics, tests, unusual events (UE), specifications

Problem solving for emergency early detection at gas-main multi-pipeline linear part by linear telemechanics systems

Sergey V. Yevseyev

DOI:10.24411/2076-6785-2020-10089

Abstract
The present work object is to add the telemechanics system by methods for detecting gas-main multi-pipeline points of leakage. There are proposed algorithms for detecting gas pressure decrease at the sensor arising at the beginning of the leak and updating mathematical map of gas-main multi-pipeline (GMMP). Analysis of dispatcher actions when eliminating real breakdown in case of gas-pipeline partial break at the boundary of two linear production areas (LPA) was carried out. As a result of the analysis there is proposed a solution for accurate defining the point of leakage within LPA at the basis of providing additional communication channel between the end supervised stations.

Materials and methods
The work presents the algorithm for detecting pressure decrease at telemechanics supervised stations, the method for generating an integrated information card of gas-main multi-pipeline, an example of the real breakdown is studied and a conclusion was drawn about the necessity of interaction between the adjacent sections of the gas-main pipeline.

Keywords
Telemechanics, leak detection system, fault isolation

Problem of defining leakage at multi line gas-main pipeline by standard linear telemetering gear

Sergey V. Yevseyev

The present work objective is to define the main reasons causing complexity of defining leakage location at a multi-line gas-pipeline by a shift dispatching personnel on the basis of the information received from the linear telemechanics system. Analysis of dispatcher actions in case of real breakdown elimination when the gas-pipeline is broken completely was carried out. As a result of the analysis there are indicated available telemechanics systems basic shortcomings and the ways to solve the said problems. An important aspect presented in the work is the necessity of using system approach to the information recorded by the linear telemechanics system and creating additional methods and algorithms for automated processing this information in order to define the time and location of the emerged leakage without specialized sensors.


DOI: 10.24411/2076-6785-2019-10065

Control of sand in production gas wells (based on well tests and industrial operations)

Evgenij V. Popov, Sergej.S. Savastjuk, Stanislav A. Ezhov, Vladimir M. Karjuk, Ivan V. Morozov

The article is devoted to fundamentals of automation system, necessary for registration the mechanical impurities (sand) in gas producing wells.RVTF “KADET” VN1228, the solids carryover recording device, manufactured in the country, is described in the article; it is able to determine the occurrence of the sand in gas current and fractional change of sand quantity, taking into account the unit of time.

output wells the recording device of sand production detecting system

Modeling and optimization of development of gas fields group

Alexander N. Solomatin, Vladimir R. Khachaturov, Alexander K. Skiba

The unstable economic conditions dictate the need of development of new gas production regions and the analysis of long-term prospects of their operation. The mathematical apparatus and software providing forming the strategy of development of gas fields group on the basis of joint use of simulation, fuzzy mathematics, discrete and multicriteria optimization are considered in article.

group of gas fields development strategy simulation discrete optimization

The use of mobile wireless measuring system for registration the sloughing of sand from gas production wells

Alexey V. Kolmakov, Valeriy P. Ustinov, Sergey S. Savastyuk, Vladimir M. Karuk, Ivan V. Morozov

This publication describes the relevance of creating a mobile telemetry complex on the basis of wireless technologies to ensure the operational control ofthe gas production. In article was paid special attention to risks associated with sloughing of sand from thegas production wells. A practical implementation of a mobile monitoring complex "Parus" of domestic production was presented. This complex solves the problem of registration the sloughing of sand from gas production wells in real time. It were described the complex’s construction and its structure. It were described the hardware of building two-level information system, shown the various options for its implementation, allowing to carry out telemetry at different structures hardware of complex, including in its structure of acoustic emission sand registration system. In this article was described registration method of sand in gas stream, which has a difference from analogues as is isolation the sensitivity zone.

registration system mobile complex wireless network gas wells transducer of sand sloughing gas production

Application of elements models intellectual data analysis for estimation of serviceability of maritime drilling complexes

Sergei G. Chernyi

It was researched and developed the mining model conditions of operator offshore drilling platforms. The analysis of modern information products and add-ons, which are used in the field. The analysis of methods and tools for data cleansing offshore drilling platforms in the emerging information systems. It is presented a clear process of communication and add-in SQL Server Management Studio, and as part of the storage and presentation of data.

storage cases database algorithm drilling rig

A formal approach to the definition of the optimum telemetry aperture value

Alexey G. Zebzeev

Usually the infrastructure of oil producing companies is distributed geographically and has distant objects. Data transmittion from all objects to control point can bring to problems related to the lack of system performance. This paper considersthe issue of the regime of sporadic transmission. It is proposed to use the optimization techniques to dynamically determine the basic characteristicsof sporadic transmission - apertures telemetry to eliminate high congestion of communication channels and ensure normal operation.

sporadic data transmission telemetry aperture optimality criterion

Application of neural network approaches in creating a monitoring system of technological parameters of wells operated by steam assisted gravity drainage

Oleg V. Denisov, Ruslan G. Girfanov, Bulat F. Zakiyev, Arslan V. Nasybullin

In this article were presented results of the application of neural network approach in the creation of a monitoring system of technological parameters of wells operated by steamassisted gravity drainage. Showcased visual representation of design criteria deviations.

control of technological parameters Kohonen sel

Automation and data transmission of the measuring system for accounting the mass of heavy and high temperature oil

Ravil N. Akhmadiev, Azat F. Shigapov, Rafis R. Kazihanov

In present paper considered the issue of automation and data transmission of the measuring system for metering the mass of heavy and high temperature oil to the control center of the field office. The main objective is to obtain reliable information about the measuring process. This data is used not only for technological purposes, but also to have government benefits.

automation data transfer accounting for the mass of high viscosity oil and high temperature oil