Oil production management based on neural network optimization of well operation at the pilot project site of the Vatyeganskoe field (Territorial Production Enterprise Povkhneftegaz)

Abstract

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.

Proxy modeling pf reservoir hydrodynamics with graph neural networks

“…Однако такие модели не только позволяют осуществлять прогноз и адаптацию гораздо быстрее, но и в некоторых случаях точнее обычных численных моделей [8]. В свете этого встречается мнение, что затраты на настройку численных моделей не оправданы и применение прокси-моделей предпочтительно [2].…”

“…54]. Статистический анализ осуществляется с использованием таких инструментов как коэффициенты Спирмена, разложения Фурье [1,3], и варианты ИНС, известных как гибкие аппроксиматоры нелинейных зависимостей: простых перцептронов [2], рекуррентных ИНС [14] и комбинированных архитектур, способных учитывать и некоторые известные характеристики пласта [24]. Практически такой подход вполне эффективен, но имеет существенную уязвимость: такие модели могут неправильно отражать зависимость между показателями, корреляция которых не проявилась в исторический период.…”

Modeling Results for the Real Horizontal Heavy-Oil-Production Well of Mechanical Solids

“…The type of the deposit is massive, with underlying bottom water, while the reservoir type is predominantly pore, the lithological and reservoir properties of which are sufficiently studied [1][2][3]. Sandstone of Cenomanian deposits is represented by loose, poorly cemented rocks, therefore during drilling and testing, they are characterized by their destruction, wall collapse, formation of cavities, and sand mobilization into the wellbore [4][5][6].…”