Development of Models For the Description of Transient Multi-Phase Flows Using the Machine Learning Approach

Theme: "Development of Models For the Description of Transient Multi-Phase Flows Using the Machine Learning Approach". In this work, the problem of multi-phase flows forecasting in the oil and gas industry is studied. The aim of this work is to build a machine learning model that can predict the oil and gas flows using the available set of features. Keywords: transient multi-phase flows, oil and gas, machine learning, data science, linear regression, boosting. The paperwork consists of an introduction and seven chapters. A general conclusion is given at the end of the work. In the introduction, the key problems of predicting the oil and gas flows are mentioned. The first chapter describes the domain of the study. This chapter shows how the problem of transient multi-phase flows arises and why this is an important issue in the oil and gas industry. In the second section, the process of data preparation and generation is described. In the third chapter, the main objective of the study is formulated. Chapter four describes the machine learning methods used in this study. In the fifth chapter, it is spoken in details about the performed experiments. The metrics and prediction results are also described in this chapter. The sixth chapter gives an analysis of the results and further work is mentioned. In chapter seven, it is given the potential economic and technical impact on the oil and gas industry of this work. In conclusion are mentioned the main results of the work.