PNIPU: Neural network for digital monitoring of oil field development

Main article:

• Neural networks (neural networks)
• Machine Learning

2022: Creation of a neural network for digital monitoring of oil field development

On July 1, 2022, Perm Polytech"" reported that it scientists was created software product on the basis of methods, artificial intelligence which at any time simulates the virtual study of the well with the determination of formation pressure.

Perm Krai, Sukharev Field

Determining reservoir pressure in well production areas is a key task of monitoring hydrocarbon field development. Direct measurements of reservoir pressure require prolonged shut-in of wells, which leads to a shortage in the production of raw materials and creates the possibility of technical problems with the subsequent start-up of wells.

The results of the work of polytechnics are published in the journal Notes of the Mining Institute. 2022 "- Russian a publication about problems. subsurface use Lev Zakharov, engineer of LLC LUKOIL "- Engineering," also took part in the study. The development was carried out within the framework of the Priority-2030 Academic Strategic Leadership Program.

Monitoring reservoir pressure in well drainage areas is a priority for monitoring oil field development. Up-to-date and reliable information is required at all stages of oil reservoir development, in particular, for production forecasting and well performance analysis, development modeling and rock mass analysis. To facilitate the assessment of the real energy state of the deposit, scientists have created a neural network method, which was subsequently tested at several oil fields in the Perm Territory with various properties.

"The method of determining reservoir pressure, based on the use of artificial intelligence methods, is implemented in the form of a module of a comprehensive software product for the digitalization of oil field development Data Stream Analytic (DSA). The program is used to solve practical problems by specialists of the subsoil user enterprise, " shared Inna Ponomareva, Professor, Department of Oil and Gas Technologies

"Based on the reservoir pressure calculated using machine learning methods, it is possible to determine the current reservoir development mode, design the reservoir pressure maintenance system in advance or evaluate its effectiveness, and reasonably make further rational decisions on the development of oil fields." reports Dmitry Martyushev, Ph.D., Associate Professor, Department of Oil and Gas Technologies

The area of ​ ​ scientific research implemented by scientists corresponds to the strategy of digital transformation of the oil industry as a key branch of the economy of the Russian Federation.