CN-121980930-A - Logging while drilling risk prediction method, device and system based on digital twinning

CN121980930ACN 121980930 ACN121980930 ACN 121980930ACN-121980930-A

Abstract

The invention relates to a logging-while-drilling risk prediction method, device and system based on digital twinning, belonging to the technical field of logging risk prediction, wherein the method comprises the steps of simulating through a virtual digital twinning body of a physical drilling system to obtain simulation state information of the physical drilling system; the method comprises the steps of inputting simulation state information and/or actual measurement state information of a physical drilling system into a trained risk prediction model to obtain first risk information, obtaining second risk information according to the simulation state information and the physical principle followed by the physical drilling system, and comprehensively determining the risk of the physical drilling system according to the first risk information and the second risk information. The invention combines a physical mechanism and an artificial intelligence algorithm to cooperatively predict the drilling risk, and can improve the reliability and scientificity of a risk prediction result.

Inventors

ZHOU LUOYU
LIU ZHIYANG
LUO MINGZHANG
LI HAORAN
KANG PEI
LIU XIN
WANG JIANI

Assignees

长江大学

Dates

Publication Date: 20260505
Application Date: 20260112

Claims (10)

1. A method for predicting logging while drilling risk based on digital twinning, comprising: simulating by a virtual digital twin body of a physical drilling system to obtain simulation state information of the physical drilling system; Inputting the simulation state information and/or the actually measured state information of the physical drilling system into a trained risk prediction model to obtain first risk information; According to the simulation state information, combining physical principles followed by the physical drilling system to obtain second risk information; and comprehensively determining the risk of the physical drilling system according to the first risk information and the second risk information.
2. The method of claim 1, wherein the first risk information comprises an overflow probability and the second risk information comprises a ratio of bottom hole pressure to formation pressure, wherein the comprehensively determining the risk of the physical drilling system based on the first risk information and the second risk information comprises: The overflow risk index is calculated according to the following formula: In the formula, As the weight coefficient of the light-emitting diode, For the bottom hole pressure, In order to be the formation pressure, For the probability of flooding, For the increment of the mud pit, Is the threshold volume of the mud pit.
3. The digital twinning-based logging-while-drilling risk prediction method of claim 1, wherein the first risk information comprises a drilling tool fault type, wherein comprehensively determining the risk of the physical drilling system based on the first risk information and the second risk information comprises: calculating the cumulative damage degree of the drilling tool according to the following formula: In the formula, At the stress level for drilling tools The number of cycles to be performed is the following, (M) is the drilling tool at the stress level Failure cycle times under the type of drilling tool failure; And comprehensively determining the risk of the physical drilling system according to the accumulated damage degree of the drilling tool and the second risk information.
4. The method for predicting risk of logging while drilling based on digital twinning as set forth in claim 3, wherein the risk prediction model comprises a drilling tool fault type recognition model, wherein the inputting the simulation state information and/or the actual measurement state information of the physical drilling system into the trained risk prediction model to obtain first risk information comprises: Generating a vibration spectrum image of a drilling tool of the physical drilling system according to the simulation state information or the actually measured state information of the physical drilling system; and inputting the vibration spectrum image into a trained drilling tool fault type identification model to obtain the drilling tool fault type.
5. The method for predicting risk of logging while drilling based on digital twinning according to claim 1, wherein the obtaining second risk information according to the simulation state information in combination with physical principles followed by the physical drilling system includes: according to the simulation state information, combining a mole-coulomb criterion to obtain a well wall stability evaluation result; and combining the simulation state information with the borehole track covariance analysis to obtain the collision risk of the adjacent well.
6. The digital twinning-based logging-while-drilling risk prediction method of claim 1, wherein the simulating by a virtual digital twinning body of a physical drilling system comprises: constructing a virtual digital twin body and a multi-physical field model of a physical drilling system, wherein the digital twin body comprises a physical entity model of the physical drilling system and a simulation engine; And performing simulation by the simulation engine based on the multi-physical field model and the physical entity model.
7. The method of claim 6, wherein the physical entity model comprises a geological model, a borehole trajectory model, a drill string system model, and a fluid system model, and the multi-physics model comprises a wellbore multiphase flow transient model, an electromagnetic field propagation and inversion model, and a drill string dynamics model.
8. The digital twinning-based logging-while-drilling risk prediction method of claim 1, further comprising: and carrying out parameter updating on the virtual digital twin body through extended Kalman filtering.
9. A digital twinning-based logging-while-drilling risk prediction apparatus, comprising: The simulation module is used for simulating through a virtual digital twin body of the physical drilling system to obtain simulation state information of the physical drilling system; the first fault prediction module is used for inputting the simulation state information and/or the actual measurement state information of the physical drilling system into a trained risk prediction model to obtain first risk information; The second fault prediction module is used for combining the physical principles followed by the physical drilling system according to the simulation state information to obtain second risk information; And the drilling risk determining module is used for comprehensively determining the risk of the physical drilling system according to the first risk information and the second risk information.
10. The system is characterized by comprising a data acquisition device, a well site server, a cloud platform and terminal equipment which are sequentially in communication connection; The data acquisition device is arranged at the well site and is used for acquiring multi-source data of the well site; The well site server is used for preprocessing the multi-source data and then sending the multi-source data to the cloud platform; The cloud platform is used for executing the steps in the logging while drilling risk prediction method based on digital twin according to any one of claims 1 to 8 based on the preprocessed multi-source data; the terminal equipment is used for presenting an interactive interface of the cloud platform.

Description

Logging while drilling risk prediction method, device and system based on digital twinning Technical Field The invention relates to the technical field of logging risk prediction, in particular to a logging-while-drilling risk prediction method, device and system based on digital twinning. Background The logging while drilling technology is a key means for acquiring downhole information and stratum parameters in real time in modern oil and gas drilling operation, and can continuously acquire and monitor various parameters such as resistivity, sound waves, gamma, pressure and the like through a downhole sensor and a real-time data transmission system, so that an important basis is provided for drilling decisions. However, existing logging while drilling methods still have significant limitations in terms of security risk pre-warning. The existing methods rely on empirical formulas for underground state judgment and risk identification, and the methods have high early warning false alarm and false alarm rate and cannot meet the advanced and accurate early warning requirements on safety risks in high-difficulty operations such as deep wells, wells with complex structures and the like. Disclosure of Invention In view of the foregoing, it is necessary to provide a method, a device and a system for predicting logging while drilling risk based on digital twinning, which are used for solving the problem of insufficient accuracy of the existing logging while drilling safety risk early warning. To solve the above problems, in a first aspect, the present invention provides a logging-while-drilling risk prediction method based on digital twinning, including: simulating by a virtual digital twin body of a physical drilling system to obtain simulation state information of the physical drilling system; Inputting the simulation state information and/or the actually measured state information of the physical drilling system into a trained risk prediction model to obtain first risk information; According to the simulation state information, combining physical principles followed by the physical drilling system to obtain second risk information; and comprehensively determining the risk of the physical drilling system according to the first risk information and the second risk information. In one possible implementation, the first risk information includes an overflow probability, the second risk information includes a ratio of bottom hole pressure to formation pressure, and the comprehensively determining the risk of the physical drilling system according to the first risk information and the second risk information includes: The overflow risk index is calculated according to the following formula: In the formula, As the weight coefficient of the light-emitting diode,For the bottom hole pressure,In order to be the formation pressure,For the probability of flooding,For the increment of the mud pit,Is the threshold volume of the mud pit In one possible implementation, the first risk information includes a drilling tool failure type, and comprehensively determining the risk of the physical drilling system according to the first risk information and the second risk information includes: calculating the cumulative damage degree of the drilling tool according to the following formula: In the formula, At the stress level for drilling toolsThe number of cycles to be performed is the following,(M) is the drilling tool at the stress levelFailure cycle times under the type of drilling tool failure; And comprehensively determining the risk of the physical drilling system according to the accumulated damage degree of the drilling tool and the second risk information. In one possible implementation manner, the risk prediction model includes a drilling tool fault type identification model, and the step of inputting the simulation state information and/or the actual measurement state information of the physical drilling system into the trained risk prediction model to obtain first risk information includes: Generating a vibration spectrum image of a drilling tool of the physical drilling system according to the simulation state information or the actually measured state information of the physical drilling system; and inputting the vibration spectrum image into a trained drilling tool fault type identification model to obtain the drilling tool fault type. In one possible implementation manner, the obtaining the second risk information according to the simulation state information and the physical principle followed by the physical drilling system includes: according to the simulation state information, combining a mole-coulomb criterion to obtain a well wall stability evaluation result; and combining the simulation state information with the borehole track covariance analysis to obtain the collision risk of the adjacent well. In one possible implementation, the simulating by a virtual digital twin of a physical drilling system includes: cons