Development of an Intelligent Oil Field Management System based on

Digital Twin and Machine Learning

NURDAULET TASMURZAYEV*, BIBARS AMANGELDY, YEDIL NURAKHOV,

SHONA SHINASSYLOV, SAMSON DAWIT BEKELE

Joldasbekov Institute of Mechanics and Engineering,

Building 2, Shevchenko Street, Medeusky District, Almaty,

KAZAKHSTAN

*Corresponding Author

Abstract: - This article introduces an innovative approach to oil field management using digital twin technology

and machine learning. A detailed experimental setup was designed using oil displacement techniques, equipped

with sensors, actuators, flow meters, and solenoid valves. The experiments focused on displacing oil using

water, polymer, and oil, from which valuable data was gathered. This data was pivotal in crafting a digital twin

model of the oil field. Utilizing the digital twin, ML algorithms were trained to predict oil production rates,

detect potential equipment malfunctions, and prevent operational issues. Our findings highlight a notable 10-

15% improvement in oil production efficiency, underscoring the transformative potential of merging DT and

ML in the petroleum industry.

Key-Words: - Digital Twin, Machine learning, Artificial Neural Networks, Oil displacement, Intelligent Control

System, Industrial Internet of Things, Sensor Network, SCADA, Energy Efficiency.

Received: March 9, 2023. Revised: October 5, 2023. Accepted: November 23, 2023. Published: December 31, 2023. 

1 Introduction

The global petroleum industry finds itself at a

crossroads, facing a variety of difficulties including

depleting reserves, surging operational costs, and

escalating environmental concerns. Innovative

solutions must be developed to improve operational

effectiveness and advance sustainable practices in

light of these challenges. This paper introduces a

groundbreaking Intelligent Oil Field Management

System, harnessing the synergistic power of

Machine Learning (ML) and Digital Twin (DT)

technologies.

The fusion of ML and DT technology, central to

our methodology, implicitly relies on several

assumptions. Firstly, the data from the oil field,

crucial for ML model training, is assumed to be both

reliable and accurate. This assumption is vital as

ML, a subset of Artificial Intelligence, leverages

extensive data to evolve. By creating a dynamic

virtual representation of real-world objects and

systems, DT technology, in concert with ML, opens

up new possibilities for operational optimization,

analysis, and monitoring in real-time, [1]. This

integration, much like the one described in [2],

significantly improves operational efficiency and

predictive accuracy, enhancing oil recovery and

simplifying drilling operations, [3], [4], [5], [6].

Similarly, our use of DT is justified as seen in [7],

emphasizing the creation of dynamic virtual models

for real-time operational optimization. Our approach

assumes that the integration of these technologies

will represent various oil field components

comprehensively, from pipelines to reservoirs,

facilitating informed decision-making and

preventive maintenance, and that our findings are

representative of broader, real-world scenarios. This

underscores the scalability and applicability of our

methodology in oil field management.

The use of ML, namely Artificial Neural

Networks (ANN) and Recurrent Neural Networks

(RNN), was crucial to our effort to improve the

efficiency of oil field management. The ANN's

architecture, which was based on the nervous

system of humans, was made up of interconnected

neurons that were dispersed throughout the input,

hidden, and output layers. This setup made it

possible to precisely define intricate connections

between inputs and outputs, which is essential in

situations where system parameters are unclear.

Furthermore, a specialized variant of RNN, the

Long Short-Term Memory (LSTM) network, was

employed to adeptly manage time-series data,

thereby allowing for precise predictions of

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

104

Volume 14, 2023

operational parameters based on both historical and

real-time data streams.

Our ML models were deployed on a single-board

Raspberry PI module, chosen for its cost-

effectiveness, compact size, and sufficient

computational power for preliminary data

processing and analysis. This configuration turned

out to be the pivot for forecasting data and making

decisions. An extensive data cleaning phase was

paramount to ensuring the accuracy and reliability

of our machine learning models. This process

involved filtering out noise and inconsistencies from

the training data, creating a more refined dataset for

model training.

The choice of Root Mean Square Error (RMSE)

and Stochastic Gradient Descent (SGD) in our

project was driven by specific needs. RMSE is

valuable as it emphasizes larger errors in

predictions, which is crucial for our objective of

minimizing inaccuracies in forecasting oil field

operational parameters, [8], [9]. On the other hand,

SGD was chosen for its ability to handle large

datasets efficiently and converge faster, making the

learning process quicker and more effective, [10],

[11]. This is particularly beneficial in our setup with

extensive data, where timely insights are vital for

optimizing oil production operations.

There are numerous examples in the literature

that demonstrate the use of ANN and RNN in the

field of oil recovery and production optimization.

An investigation highlighted ANN's ability to

forecast CO2 storage capacity and oil recovery,

shedding light on the technology's potential to

manage the inherent uncertainty in oil recovery

procedures, [12]. Another investigation showcased

the deployment of RNN for modeling oil field

production, highlighting the importance of adeptly

handling substantial data for precise oil data

prediction, [13]. These studies demonstrate the

growing importance of ML in oil field management

and, when combined with DT, open the door to a

new era of operational excellence in the petroleum

sector.

Our project aimed to create a smarter way to

manage oil fields using DT technology and ML,

targeting enhanced operational efficiency. The

primary objective of this study was to revolutionize

oil field management by effectively integrating

these advanced technologies, thereby addressing key

industry challenges like resource depletion and

environmental impact. We set up a special stand

based on oil displacement technology for our

experiments, which is instrumental in efficiently

extracting more oil from the ground. This stand was

equipped with various sensors, valves, and flow

meters to analyze the efficacy of different fluid

injections in oil displacement. The data collected

was crucial in creating a virtual model (Digital

Twin) of the oil field, subsequently used to train our

ML algorithms. These algorithms are intricately

designed to predict oil output, identify potential

equipment failures, and preemptively address

operational issues, [14], [15].

Additionally, the incorporation of SCADA

systems ensures ease and safety in operation,

offering real-time monitoring and control. The

unique contribution of our research lies in the real-

time modeling capabilities of our system, achieved

through the innovative fusion of ML and DT

technology. This approach, combining real-time

data analysis with adaptive control strategies,

significantly enhances operational efficiency, as

evidenced by a noticeable 10-15% increase in oil

production. It marks a significant innovation in oil

field management, underlining our system's impact

and distinctiveness in the field. Ultimately, our

research strives to set a new benchmark in

sustainable and efficient oil field management,

contributing to the broader goal of creating more

environmentally conscious and resource-efficient

practices in the industry.

2 Architecture of the System

Building a bridge between theory and practice is

crucial in developing our DT and ML-based Oil

Field Management System. Our architecture is

carefully designed to mimic real-world oil field

conditions, while also providing a controlled setting

for detailed testing and data gathering. The

architecture of our system is depicted in Figure 1.

Fig. 1: Architecture of the System

The core constituents of our system are described

in the following subsections.

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

105

Volume 14, 2023

2.1 Oil Reservoir Simulator

At the core of our experimental setup is the Oil

Reservoir Simulator, which has been carefully

engineered to replicate the underground conditions

of an oil reservoir. It comes equipped with an array

of sensors for monitoring essential parameters like

pressure, temperature, and oil flow, along with

electromagnetic valves and flow meters. These

sensors utilize the IEEE 754, 32-bit floating-point

format to convert measured field values, ensuring

high precision in data acquisition.

Our experimental setup comprises terminal

blocks for connecting sensors and actuators, fluid

reservoirs, electromagnetic valves, connecting

pipes, a logic block (which is an industrial

controller), and a router for internet connectivity as

seen in Figure 5 and Figure 6. This intricate setup

not only enables the simulation of various oil field

scenarios but also lays the foundation for data

collection and analysis—crucial for the creation of a

DT and training of our ML models.

2.2 SCADA Integration

The SCADA system is like the nervous system of

our setup. It collects real-time data from the Oil

Reservoir Simulator and other devices. SCADA is

very important for keeping track of what’s

happening in Digital Oil Fields as mentioned in

[16]. The SCADA seamlessly connects with devices

such as Siemens SIMATIC S7-1200 and Siemens

SIMATIC IoT 2040.

It facilitates real-time data acquisition from the

Oil Reservoir Simulator and other connected

apparatus, creating a dynamic representation of the

experimental stand. This setup is pivotal for keeping

a tab on the ongoing processes and conditions

within our simulated oil field environment, thereby

mirroring the potential real-world scenarios of oil

fields.

2.3 Cloud Server and Database Integration

All the data from the SCADA system and sensors

are sent to a cloud server. This server keeps the data

safe and makes it easy to access whenever needed.

Using a cloud server is a modern way to handle big

amounts of data with high reliability as discussed in

some studies, [17]. It manages all the computing,

storage, and network resources, making sure

everything is well-organized and optimized, [18]. Its

SQL system ensures a structured data storage

approach.

2.4 SCADA Interface (Human Machine

Interface)

The SCADA interface is a window to our

experimental setup, offering a real-time

visualization that empowers operators and

researchers to steer experiments and make judicious

decisions based on visual feedback. This interface is

instrumental for monitoring, controlling, and

tweaking various processes in a simulated setting,

thereby forming a crucial link between data

acquisition and actionable insights.

Figure 2 shows the SCADA HMI for our

experimental stand.

Fig. 2: SCADA Human Machine Interface

2.5 Historical Data Analysis

Preservation of all experimental data for historical

analysis is an essential aspect of our system. It

enables a thorough assessment of the impact of

diverse operational strategies over time. By sifting

through historical data, we can discern trends and

patterns that are instrumental for informed future

decision-making and for enhancing efficiency over

prolonged operational timelines. Live data recording

in MySQL database can be seen in Figure 3.

Fig. 3: Live data registration in MySQL database

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

106

Volume 14, 2023

2.6 Machine Learning Methods

Our ML models learn from the collected data from

our experimental stand to predict how oil will move

and to fine-tune operational settings. These models

use different methods to understand oil field

behavior. Employing a blend of regression and

classification algorithms such as random forest and

XGBoost, these models delve into the integrated

data to forecast oil displacement behavior, thereby

aiding in experiment optimization. This segment of

our architecture is the heart for harnessing data-

driven insights to augment operational efficacy.

2.7 LSTM Modelling

To support data forecasting and decision-making, a

single-board Raspberry PI computer is used. On this

platform, we deploy our LSTM neural network and

train it using data recorded in the database. The

neural network accepts an input data of shape (12,

8), where 12 is the number of time steps (12 time

slots) and 8 is the number of features per time step

(representing the data from 8 sensors at each time

slot). Following the input layer, the network features

an LSTM layer with 128 units, which is particularly

suited for time-series data due to its ability to

remember information over long periods and to

capture temporal dependencies. It is followed by a

dense layer of 256 neurons, and an output layer of

one neuron. Figure 4 shows the architecture of the

neural network used.

Fig. 4: Architecture of the neural network

2.8 Optimization and Intelligent Control

The architecture also embraces optimization and

intelligent control mechanisms to tweak operational

parameters for enhanced performance and

efficiency. Intelligent control is achieved through

the SCADA system which has been utilized in

various research for the scientific management of oil

fields, [19]. The decision support system nested

within the Digital Twin furnishes real-time

recommendations for optimizing oil displacement

methods. It's adept at alerting operators about

potential issues such as equipment malfunctions,

thus proactively averting costly downtime.

2.9 Intelligent Remote Module for Real-Time

Operation

The foundation of our intelligent remote-control

module is laid by the sensors, which are specifically

designed to capture both discrete and analog signals,

typically in the range of 4-20 milliamperes and 0-10

volts.

Once these signals are collected, they are

forwarded to the Programmable Logic Controller

(PLC). The PLC is adept at interpreting these

signals, converting both discrete and analog

readings into a digital format which can then be

processed further.

Upon processing, the PLC communicates with

the OPC Server and Gateway. This server plays a

dual role: firstly, it ensures the secure and efficient

transmission of data to the cloud for storage. This

cloud storage not only acts as a backup but also as a

centralized data repository that can be accessed

from various endpoints. Secondly, the OPC Server

transmits this data to the SCADA HMI system.

Here, the data is visualized, providing operators

with a real-time overview of the system and

allowing them to make informed decisions.

Simultaneously, the processed data is also stored

in a dedicated database. From this database, the

Raspberry Pi, equipped with a Machine Learning

(ML) model, fetches the data for training. By

training on this data, the ML model can derive

patterns and insights which it then uses to send

intelligent, predictive outputs back to the SCADA

system. This mechanism ensures that the SCADA

system isn't just a passive display but an interactive

control panel that benefits from the predictive

capability of the ML model.

3 Results

We undertook a range of tests using our oil

displacement technology set up to gauge the

efficacy of our digital twin and machine

learning-focused oil field management

approach. These tests simulated situations

typical of real-world oil fields, especially

secondary and enhanced oil extraction

techniques. Our experiments yielded several

notable results: The marriage of digital twins

and machine learning significantly boosted oil

extraction in our simulation, surpassing

traditional techniques. By perpetually refining

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

107

Volume 14, 2023

operational metrics, a greater volume of oil was

mobilized from the reserve.

Furthermore, the real-time monitoring

capabilities and predictive maintenance aspects

of the digital twin system enabled us to

proactively identify potential equipment

failures. This proactive approach was rigorously

validated through deliberately introducing

components with known defects, ensuring a

robust test of the system's predictive acumen.

The experimental stand built can be seen below.

The crucial connection points and the

meticulous detail in our experimental stand can

be seen in Figure 6. Moreover, the logical and

control block with PLC of the digital twin stand

can be seen in Figure 7.

Our SCADA system recorded live metrics

like reservoir pressure, temperature, and oil

migration. This data was fed into our digital

twin system, generating a live model of the

testing environment. The system's control and

operational management are conducted via the

SCADA interface, as illustrated in Figure 8.

Fig. 5: Experimental digital oil field test bench

Fig. 6: Terminal block of digital twin stand

Fig. 7: Logical and control block with PLC of

digital twin stand

Fig. 8: Visualization in SCADA

Employing the developed LSTM algorithm,

we decoded the combined data to predict oil

displacement tendencies.

Upon comparing the actual temperature

measurements with the predictions from our

neural network, we found a strong

correspondence between the two, indicating a

high level of predictive accuracy by the

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

108

Volume 14, 2023

network. The difference between real and

predicted data were minimal, showing the

model's efficiency. This minimal difference was

quantitatively assessed using RMSE, which

showed low values, reflecting the model's

ability to closely mirror actual conditions. The

consistent decrease in prediction inaccuracies

across successive epochs further substantiates

the model's learning efficacy and its capacity to

refine its predictions over time.

The results of our analysis showed an r2 score

range of 90–95%. Moreover, our findings

highlight a notable 10-15% improvement in oil

production efficiency, providing insight into the

transformative potential of merging DT and ML

in the petroleum industry.

This study emphasizes the potential of a

machine learning-based tool to enhance the

management and operational efficiency of oil

field test setups. Our roadmap envisions the

integration of features such as oil transfer

speed, tank pressure, and oil consistency. The

advisory platform of the digital twin also played

a crucial role in identifying and addressing

equipment defects, including those induced

intentionally as part of our system's resilience

and fault-tolerance testing. This approach

allowed us to simulate potential issues and

assess the system's response to such anomalies,

thereby enhancing the robustness and reliability

of our oil displacement methods.

4 Conclusion

The integration of digital twins and machine

learning in oil field management marks a

monumental shift for the oil and gas sector. This

union harnesses real-time analytics, predictive

foresight, and data-fueled decision-making, leading

to enhanced safety, efficiency, and optimal resource

deployment.

In our pilot setup mimicking oil displacement

technology, we showcased the tangible advantages

of this methodology. Merging Digital Twin tech,

SCADA systems, and machine learning, we

dynamically fine-tuned oil field operations, showing

a significant enhancement in oil production

efficiency by 10-15%.

Key outcomes from our endeavor:

Our intelligent framework routinely amplified oil

extraction rates by dynamically refining operation

metrics and offering on-the-spot recommendations.

The ability to predict maintenance needs,

coupled with preemptive alerts, curtailed operational

downtime and bolstered safety—warding off

equipment breakdowns and potential hazards.

The newfound precision in resource distribution

ensured optimal utilization, thus ramping up

production outputs.

The implementation of our system in real-world

oil fields can revolutionize industry practices. By

integrating our intelligent framework into existing

infrastructure, oil companies can expect significant

improvements in operational efficiency and safety.

The system's predictive maintenance capabilities

and dynamic operation adjustments can be

particularly beneficial in large-scale operations,

where they can lead to substantial cost savings and

reduced environmental impact. This practical

application highlights the system's potential for

widespread adoption and its ability to address

current industry challenges.

Future work will explore enhancing the real-time

capabilities of the system, particularly focusing on

refining the accuracy of predictions and the

efficiency of the digital twin model. We also plan to

address current limitations such as scalability to

larger fields and integration with various types of oil

extraction technologies.

References:

[1] F. Shen, S. S. Ren, X. Y. Zhang, H. W. Luo,

and C. M. Feng, “A Digital Twin-Based

Approach for Optimization and Prediction of

Oil and Gas Production,” Math. Probl. Eng.,

vol. 2021, p. e3062841, Sep. 2021, doi:

10.1155/2021/3062841.

[2] C. Nunes, E. J. S. Pires, and A. Reis,

“Machine Learning and Deep Learning

applied to End-of-Line Systems: A review,”

WSEAS Transactions on Systems, vol. 21, pp.

147–156, 2022,

https://doi.org/10.37394/23202.2022.21.16.

[3] A. Sircar, K. Yadav, K. Rayavarapu, N. Bist,

and H. Oza, “Application of machine learning

and artificial intelligence in oil and gas

industry,” Pet. Res., vol. 6, no. 4, pp. 379–

391, Dec. 2021, doi:

10.1016/j.ptlrs.2021.05.009.

[4] R. van Dinter, B. Tekinerdogan, and C. Catal,

“Predictive maintenance using digital twins:

A systematic literature review,” Inf. Softw.

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

109

Volume 14, 2023

Technol., vol. 151, p. 107008, Nov. 2022, doi:

10.1016/j.infsof.2022.107008.

[5] Z. Ren, J. Wan, and P. Deng, “Machine-

Learning-Driven Digital Twin for Lifecycle

Management of Complex Equipment,” IEEE

Trans. Emerg. Top. Comput., vol. 10, no. 1,

pp. 9–22, Jan. 2022, doi:

10.1109/TETC.2022.3143346.

[6] N. O. Nikitin, I. Revin, A. Hvatov, P.

Vychuzhanin, and A. V. Kalyuzhnaya,

“Hybrid and Automated Machine Learning

Approaches for Oil Fields Development: the

Case Study of Volve Field, North Sea,”

Comput. Geosci., vol. 161, p. 105061, Apr.

2022, doi: 10.1016/j.cageo.2022.105061.

[7] A. Lektauers, J. Pecerska, V. Bolsakovs, A.

Romanovs, J. Grabis, and A. Teilans, “A

Multi-Model Approach for Simulation-Based

Digital Twin in Resilient Services,” WSEAS

Transactions on Systems and Control, vol. 16,

pp. 133–145, 2021,

https://doi.org/10.37394/23203.2021.16.10.

[8] T. O. Hodson, “Root-mean-square error

(RMSE) or mean absolute error (MAE): when

to use them or not,” Geosci. Model Dev., vol.

15, no. 14, pp. 5481–5487, Jul. 2022, doi:

10.5194/gmd-15-5481-2022.

[9] T. Chai, “Root Mean Square,” in

Encyclopedia of Mathematical Geosciences,

B. S. Daya Sagar, Q. Cheng, J. McKinley, and

F. Agterberg, Eds., in Encyclopedia of Earth

Sciences Series, Cham: Springer

International Publishing, 2020, pp. 1–3. doi:

10.1007/978-3-030-26050-7_280-1.

[10] M. Tang, L. Qiao, Z. Huang, X. Liu, Y. Peng,

and X. Liu, “Accelerating SGD using flexible

variance reduction on large-scale datasets,”

Neural Comput. Appl., vol. 32, no. 12, pp.

8089–8100, Jun. 2020, doi: 10.1007/s00521-

019-04315-5.

[11] L. Bottou, “Large-Scale Machine Learning

with Stochastic Gradient Descent,” in

Proceedings of COMPSTAT’2010, Y.

Lechevallier and G. Saporta, Eds.,

Heidelberg: Physica-Verlag HD, 2010, pp.

177–186. doi: 10.1007/978-3-7908-2604-

3_16.

[12] H. Vo Thanh, Y. Sugai, and K. Sasaki,

“Application of artificial neural network for

predicting the performance of CO2 enhanced

oil recovery and storage in residual oil zones,”

Sci. Rep., vol. 10, no. 1, Art. no. 1, Oct. 2020,

doi: 10.1038/s41598-020-73931-2.

[13] R. Al-Shabandar, A. Jaddoa, P. Liatsis, and A.

J. Hussain, “A deep gated recurrent neural

network for petroleum production

forecasting,” Mach. Learn. Appl., vol. 3, p.

100013, Mar. 2021, doi:

10.1016/j.mlwa.2020.100013.

[14] N. Tasmurzayev, B. Amangeldy, Y.

Nurakhov, D. Akhmed-Zaki, and Zh.

Baigarayeva, “Intelligent Thermal

Accumulator Operation Control System based

on Renewable Energy Sources:” in

Proceedings of the 19th International

Conference on Informatics in Control,

Automation, and Robotics, Lisbon, Portugal:

SCITEPRESS - Science and Technology

Publications, 2022, pp. 737–742. doi:

10.5220/0011319300003271.

[15] K. E. Nolan, W. Guibene, and M. Y. Kelly,

“An evaluation of low power wide area

network technologies for the Internet of

Things,” 2016 Int. Wirel. Commun. Mob.

Comput. Conf. IWCMC, pp. 439–444, Sep.

2016, doi: 10.1109/IWCMC.2016.7577098.

[16] Z. Sun and X. Tian, “SCADA in oilfields,”

Meas. Control, vol. 43, pp. 176–178, Jul.

2010, doi: 10.1177/002029401004300603.

[17] X. Yang, O. Bello, L. Yang, D. Bale, and R.

Failla, “Intelligent Oilfield - Cloud Based Big

Data Service in Upstream Oil and Gas,” Mar.

2019. doi: 10.2523/IPTC-19418-MS.

[18] D. Du, X. Zhang, Q. Guo, B. Zhang, and G.

Zhang, “Smart Oilfield Technology,” in

Proceedings of the International Field

Exploration and Development Conference

2018, J. Lin, Ed., in Springer Series in

Geomechanics and Geoengineering.

Singapore: Springer, 2020, pp. 685–694. doi:

10.1007/978-981-13-7127-1_63.

[19] H. Wang, Y. Xu, B. Shi, C. Zhu, and Z.

Wang, “Optimization and intelligent control

for operation parameters of multiphase

mixture transportation pipeline in oilfield: A

case study,” J. Pipeline Sci. Eng., vol. 1, no.

4, pp. 367–378, Dec. 2021, doi:

10.1016/j.jpse.2021.07.002.

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

110

Volume 14, 2023

This research was funded by a grant from the

Ministry of Education and Science of the Republic

of Kazakhstan BR18574136 "Development of deep

learning and intellectual analysis methods for

solving complex problems of mechanics and

robotics” (2022-2024).

Conflict of Interest

The authors have no conflicts of interest to declare.

Creative Commons Attribution License 4.0

(Attribution 4.0 International, CC BY 4.0)

This article is published under the terms of the

Creative Commons Attribution License 4.0

https://creativecommons.org/licenses/by/4.0/deed.en

_US

WSEAS TRANSACTIONS on ELECTRONICS

DOI: 10.37394/232017.2023.14.12

Nurdaulet Tasmurzayev, Bibars Amangeldy,

Yedil Nurakhov, Shona Shinassylov, Samson Dawit Bekele

E-ISSN: 2415-1513

111

Volume 14, 2023

Contribution of Individual Authors to the

Creation of a Scientific Article (Ghostwriting

Policy)

The authors equally contributed in the present

research, at all stages from the formulation of the

problem to the final findings and solution.

Sources of Funding for Research Presented in a

Scientific Article or Scientific Article Itself