Prediction of temperature distribution along the oil wells during steam cycling

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