FIELD: oil industry.
SUBSTANCE: invention relates to the field of data analysis in the oil industry; it can be used for predicting discharge characteristics of the flow in the well bore using machine learning methods. A computer method for predicting discharge characteristics of the flow in the well bore penetrating into the underground hydrocarbon reservoir is proposed. This method includes storing in a database of primary well data obtained from multiple active wells and containing historical static parameters accumulated for operational wells and dynamic parameters measured on the surface and accumulated historical characteristics of the flow in the well bore of at least one well, measured during start-up and production by one or more units of field equipment installed on the surface or inside the wells; storing in the knowledge database of secondary downhole data containing static and output wellhead dynamic parameters obtained by numerical modeling and discharge characteristics of the flow in the well bore for various scenarios of a set of static and input dynamic parameters of the well; performing the analysis of the specified primary well data by the machine learning system; performing the analysis of the specified secondary well data by the machine learning system; input into the machine learning system of the static parameters of the well that characterize the well under study, and the dynamic parameters of the well under study measured on the surface; prediction using the machine learning system of the discharge characteristics of the flow in the well bore in the specified well under study based on the obtained first and second relationships; assessment of whether the projected discharge characteristics of the flow in the well bore meet the safety requirements of the operating parameters during the start-up and production of the well under study, and based on this assessment, adjustment, if necessary, of the control parameters of the ground equipment to meet the requirements for safe operation. The system for implementation the specified method is also revealed.
EFFECT: proposed method allows predicting discharge characteristics of the flow in the well bore and in the well bottom where these characteristics are usually unknown.
7 cl, 6 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR DETERMINATION OF HYDRODYNAMIC CONNECTION BETWEEN SECTIONS OF PRODUCTIVE FORMATION AND FILTRATION-VOLUMETRIC PROPERTIES OF INTERWELL SPACE OF CENOMANIAN DEPOSIT AT FIELD START-UP AFTER SHUTDOWNS BASED ON RESULTS OF INTEGRAL HYDRAULIC INTERFERENCE TESTING AT WELLS | 2023 |
|
RU2819121C1 |
METHOD OF FORMATION BREAKDOWN SIMULATION AND ITS ESTIMATION, AND COMPUTER-READ CARRIER | 2008 |
|
RU2486336C2 |
METHOD FOR CHOOSING THE OPTIMAL HYDRAULIC FRACTURING DESIGN BASED ON THE INTELLIGENT ANALYSIS OF FIELD DATA TO INCREASE THE PRODUCTION OF HYDROCARBON RAW MATERIALS | 2021 |
|
RU2775034C1 |
METHOD FOR ADAPTATION OF GEOLOGICAL AND HYDRODYNAMIC RESERVOIR MODEL | 2021 |
|
RU2754741C1 |
METHOD AND COMPUTER SYSTEM FOR CONTROL OF DRILLING OF THE WELLS | 2019 |
|
RU2723805C1 |
DEVICE, METHOD AND SYSTEM OF STOCHASTIC INVESTIGATION OF FORMATION AT OIL-FIELD OPERATIONS | 2008 |
|
RU2496972C2 |
METHOD FOR DETERMINING FILTRATION-CAPACITY PROPERTIES OF INTER-WELL INTERVAL OF RESERVOIR | 2020 |
|
RU2747959C1 |
SYSTEM AND TOOL FOR IMPROVING PREDICTION ACCURACY OF MATURE DEPOSITS MODEL | 2018 |
|
RU2718042C2 |
PREDICTING PROPERTIES OF UNDERGROUND FORMATION | 2008 |
|
RU2462755C2 |
Method for Monitoring Energy Consumption of Oil and Gas Production Equipment | 2023 |
|
RU2801699C1 |
Authors
Dates
2021-07-22—Published
2017-06-20—Filed