Increasing the efficiency of thermal recovery methods is an important and relevant task. This study is devoted to reducing heavy components (resins and asphaltenes) and quality improvement of heavy oil by catalytic hydrothermal treatment. The object of this study is a bituminous sandstone sample from the Ashal’cha reservoir. The catalytic (iron tallate) hydrothermal simulation was carried out under reservoir conditions (200 °C, 30 bar). The composition and physicochemical characteristics of the products were studied using elemental and SARA analysis, MALDI, GC-MS, FT-IR. Moreover, the extracted rock is analyzed in XRD and DSA (Drop Shape Analyzer). The introduction of catalyst in combination with a hydrogen donor reduces the content of resins by 22.0%wt. with an increase in the share of saturated hydrocarbons by 27%wt. The destructive hydrogenation leads to a decrease in the sulfur content of upgrading products. This is crucial for the oil reservoirs of the Tatarstan Republic, as their crude oils are characterized by high sulfur content. According to the wettability data, the hydrophilicity of the rock surface increases due to inhibition of the coke formation after the introduction of the catalytic complex. Thus, the oil recovery factor can be increased due to the alteration of the oil-wetting properties of reservoir rocks.
Summary: This paper presents the efficiency of using artificial neural networks for solving problems of processing and interpreting geophysical data obtained by scanning magnetic introscopy. Neural networks of various architectures have been implemented to solve the problems of processing primary material, searching for well structure objects,identifying casing defects. The analysis of the capabilities of neural networks in comparison with mathematical algorithms is carried out. To test machine learning algorithms and mathematical algorithms for processing, visualizing and storing the results, a software shell was created in which all tasks are solved using a set of tools. It was found that the use of artificial neural networks can significantly speed up the process of data processing and interpretation, as well as improve the quality of the results in comparison with individual mathematical algorithms. Nevertheless, the use of mathematical algorithms in solving some problems gives consistently better results. In particular, the problematic aspects were identified at the stage of interpretation when identifying defects. This is due to the presence of conventions in the isolation of defects by the operator at the stage of preparing data for training neural networks, which is a subjective factor and requires a deeper study.
About Me
Deputy Director for Innovation Technologies of Institute of geology and petroleum technologies
Deputy Director for Innovation Technologies of Institute of geology and petroleum technologies