A method, device, equipment and medium for predicting the risk of shaft wall instability derivatives

Abstract

The present invention discloses a method, device, equipment and medium for predicting the risk of wellbore instability derivative, including: obtaining a real-time wellbore parameter set of multiple preset detection points in a target well section to be predicted; inputting the real-time wellbore parameter set of each preset detection point into a preset wellbore diameter expansion rate prediction model to obtain a predicted wellbore diameter expansion rate; according to the predicted wellbore diameter expansion rate of multiple preset detection points, according to the maximum wellbore diameter expansion rate influence factor, the preset weight of the maximum wellbore diameter expansion rate influence factor, the minimum wellbore diameter expansion rate influence factor, the preset weight of the minimum wellbore diameter expansion rate influence factor, the relative wellbore diameter expansion rate influence factor and the preset weight of the relative wellbore diameter expansion rate influence factor, the instability derivative risk of the target well section to be predicted is determined. The present invention belongs to the field of oil and gas drilling. The present invention can more accurately predict the risk of wellbore instability derivative.

Description

Technical Field

[0001] The present invention relates to the field of oil and gas drilling, and in particular to a method, device, equipment and medium for predicting the risk of wellbore instability derivatives. Background Art

[0002] The wellbore refers to the rock layer surrounding the wellbore during the exploration and development of rock formations such as oil and natural gas. Wellbore instability can manifest in the form of necking, expansion, lost circulation, block loss, and even collapse. This instability can lead to a series of complex downhole accidents, including stuck and buried drill bits, posing significant challenges and causing significant financial losses to drilling operations.

[0003] The research on wellbore stability mainly focuses on constitutive models and failure criteria, forming a method for constructing a wellbore instability prediction model based on the fluid-solid-chemical-thermal multi-field coupling effect, taking into account the effects of clay hydration expansion and weak structural planes; it also includes conducting wellbore instability risk assessment by establishing a pressure profile, that is, through the results of indoor rock mechanical properties experiments, combined with well logging data, the mud safety density window is calculated to evaluate the wellbore stability. However, the calculation process of the above method is cumbersome and the degree of automation is low; the collapse pressure, loss pressure, and fracture pressure are closely related and are not fixed values ​​for determining the wellbore formation, which leads to inaccurate evaluation of wellbore stability; the real-time situation downhole is complex, and changes in conditions may lead to deviations in the predicted pressure, which also leads to inaccurate evaluation of wellbore stability. Therefore, there is an urgent need to propose a more accurate and automated wellbore stability prediction method. Summary of the Invention

[0004] The embodiments of the present application solve the technical problem of inaccurate wellbore stability evaluation in the prior art by providing a method, device, equipment and medium for predicting the risk of wellbore instability derivatives, and achieve the technical effect of accurately predicting wellbore stability.

[0005] In a first aspect, the present application provides a method for predicting the risk of wellbore instability derivatives, the method comprising:

[0006] Acquire a real-time wellbore parameter set of a plurality of preset detection points in a target well section to be predicted, wherein the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule;

[0007] Input the real-time wellbore parameter set of each preset detection point into the preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point;

[0008] According to the predicted borehole expansion rates of multiple preset detection points, the maximum borehole expansion rate influencing factor, the minimum borehole expansion rate influencing factor, and the relative borehole expansion rate influencing factor of the target well section to be predicted are determined;

[0009] The instability derivative risk of the target well section to be predicted is determined based on the maximum wellbore expansion rate influencing factor, the preset weight of the maximum wellbore expansion rate influencing factor, the minimum wellbore expansion rate influencing factor, the preset weight of the minimum wellbore expansion rate influencing factor, the relative wellbore expansion rate influencing factor, and the preset weight of the relative wellbore expansion rate influencing factor.

[0010] Furthermore, based on the predicted borehole expansion rates of multiple preset detection points, the maximum borehole expansion rate influencing factor, the minimum borehole expansion rate influencing factor, and the relative borehole expansion rate influencing factor of the target well section to be predicted are determined, including:

[0011] determining a maximum wellbore expansion rate influencing factor according to a maximum value among a plurality of predicted wellbore expansion rates;

[0012] Determining a minimum wellbore expansion rate influencing factor according to a minimum value among a plurality of predicted wellbore expansion rates;

[0013] The relative wellbore expansion rate influencing factor is determined based on the maximum value, the minimum value and the preset empirical coefficient among multiple predicted wellbore expansion rates.

[0014] Furthermore, a preset wellbore expansion rate prediction model is constructed, including:

[0015] Obtaining several historical wellbore parameter sets and the historical measured wellbore expansion rates corresponding to each historical wellbore parameter set;

[0016] Establish an initial neural network prediction model;

[0017] Input the historical wellbore parameter set into the initial neural network prediction model;

[0018] Based on the output of the initial neural network prediction model and the historical measured wellbore expansion rate corresponding to the historical wellbore parameter set, it is determined whether there is a need to update the initial neural network prediction model;

[0019] If there is an update requirement, continue to input any other historical wellbore parameter set into the initial neural network prediction model; when the difference between the output result of the updated initial neural network prediction model and the corresponding historical measured wellbore diameter expansion rate is less than the preset threshold, the updated initial neural network prediction model is used as the preset wellbore diameter expansion rate prediction model.

[0020] Furthermore, the method further comprises:

[0021] The stability of the total well section is determined based on the stability of multiple target well sections to be predicted in the same total well section.

[0022] Furthermore, the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule, including:

[0023] The preset detection points are distributed at equal distances in the target well section to be predicted.

[0024] Furthermore, the method further comprises:

[0025] The length of the target well section to be predicted is determined according to the depth of the target well section to be predicted.

[0026] Furthermore, the real-time wellbore parameter set of the preset detection points includes:

[0027] Differential stress, differential stress coefficient, formation pressure coefficient, uniaxial compressive strength of rock, cohesion, internal friction angle, Poisson's ratio, open hole length index, azimuth offset coefficient, wellbore deviation coefficient, wellbore curvature, wellbore penetration index, deep lateral index, crushing index, shale content, GR value, Na, Al, Si, S, Cl, Ca and Fe.

[0028] In a second aspect, the present application provides a device for predicting the risk of wellbore instability derivatives, the device comprising:

[0029] An acquisition module is used to acquire a real-time wellbore parameter set of a plurality of preset detection points in a target well section to be predicted, wherein the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule;

[0030] A prediction module is used to input the real-time wellbore parameter set of each preset detection point into a preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point;

[0031] A factor determination module is used to determine the maximum wellbore expansion rate influencing factor, the minimum wellbore expansion rate influencing factor, and the relative wellbore expansion rate influencing factor of the target well section to be predicted based on the predicted wellbore expansion rates of multiple preset detection points;

[0032] The instability derivative risk determination module is used to determine the instability derivative risk of the target well section to be predicted based on the maximum wellbore expansion rate influence factor, the preset weight of the maximum wellbore expansion rate influence factor, the minimum wellbore expansion rate influence factor, the preset weight of the minimum wellbore expansion rate influence factor, the relative wellbore expansion rate influence factor, and the preset weight of the relative wellbore expansion rate influence factor.

[0033] In a third aspect, the present application provides an electronic device, comprising:

[0034] processor;

[0035] a memory for storing processor-executable instructions;

[0036] The processor is configured to execute to implement a wellbore instability derivative risk prediction method as provided in the first aspect.

[0037] In a fourth aspect, the present application provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to implement a method for predicting the risk of wellbore instability derivatives as provided in the first aspect.

[0038] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0039] The present application provides a method for predicting the risk of wellbore instability derivatives, comprising: obtaining a real-time wellbore parameter set of a plurality of preset detection points in a target well section to be predicted, the preset detection points being distributed in the target well section to be predicted according to a preset distribution rule; inputting the real-time wellbore parameter set of each preset detection point into a preset wellbore diameter expansion rate prediction model to obtain a predicted wellbore diameter expansion rate corresponding to each preset detection point; determining a maximum wellbore diameter expansion rate influencing factor, a minimum wellbore diameter expansion rate influencing factor, and a relative wellbore diameter expansion rate influencing factor of the target well section to be predicted based on the predicted wellbore diameter expansion rates of the plurality of preset detection points; and determining the risk of instability derivatives of the target well section to be predicted based on the maximum wellbore diameter expansion rate influencing factor, the preset weight of the maximum wellbore diameter expansion rate influencing factor, the minimum wellbore diameter expansion rate influencing factor, the preset weight of the minimum wellbore diameter expansion rate influencing factor, the relative wellbore diameter expansion rate influencing factor, and the preset weight of the relative wellbore diameter expansion rate influencing factor. The present application can predict the predicted wellbore expansion rate of the target well section to be predicted by acquiring the real-time wellbore parameter set (a total of 23 categories) of the target well section to be predicted in real time, and determine the instability derivative risk of the target well section to be predicted based on multiple predicted wellbore expansion rates of the target well section to be predicted. It has a high degree of automation, and compared with the existing technology, it cannot accurately judge the obstruction and stuck drill risks derived from the instability of the target well section to be predicted based on the real-time wellbore parameter set acquired in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 A flow chart of a wellbore instability derivative risk prediction method provided in this application;

[0042] Figure 2 A schematic diagram of the structure of a wellbore instability derivative risk prediction device provided in this application;

[0043] Figure 3This is a schematic diagram of the structure of an electronic device provided in this application. DETAILED DESCRIPTION

[0044] The embodiment of the present application solves the technical problem of inaccurate wellbore stability evaluation in the prior art by providing a method for predicting the risk of wellbore instability derivatives.

[0045] The technical solution of the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0046] A method for predicting the risk of wellbore instability derivatives, the method comprising: obtaining real-time wellbore parameter sets of multiple preset detection points in a target well section to be predicted, the preset detection points being distributed in the target well section according to a preset distribution rule; inputting the real-time wellbore parameter sets of each preset detection point into a preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point; determining a maximum wellbore diameter expansion rate influencing factor, a minimum wellbore diameter expansion rate influencing factor, and a relative wellbore diameter expansion rate influencing factor of the target well section to be predicted based on the predicted wellbore diameter expansion rates of the multiple preset detection points; and determining the risk of instability derivatives of the target well section to be predicted based on the maximum wellbore diameter expansion rate influencing factor, the preset weight of the maximum wellbore diameter expansion rate influencing factor, the minimum wellbore diameter expansion rate influencing factor, the preset weight of the minimum wellbore diameter expansion rate influencing factor, the relative wellbore diameter expansion rate influencing factor, and the preset weight of the relative wellbore diameter expansion rate influencing factor.

[0047] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0048] First, the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. Furthermore, the character " / " in this document generally indicates an "or" relationship between the associated objects.

[0049] This application provides Figure 1 A method for predicting the risk of wellbore instability derivatives is shown, comprising steps S11-S14:

[0050] Step S11 , obtaining a real-time wellbore parameter set of a plurality of preset detection points in the target well section to be predicted, wherein the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule.

[0051] Step S12: input the real-time wellbore parameter set of each preset detection point into a preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point.

[0052] Step S13, based on the predicted borehole diameter expansion rates of the plurality of preset detection points, determining the maximum borehole diameter expansion rate influencing factor, the minimum borehole diameter expansion rate influencing factor, and the relative borehole diameter expansion rate influencing factor of the target well section to be predicted.

[0053] Step S14, determining the instability derivative risk of the target well section to be predicted based on the maximum wellbore expansion rate influence factor, the preset weight of the maximum wellbore expansion rate influence factor, the minimum wellbore expansion rate influence factor, the preset weight of the minimum wellbore expansion rate influence factor, the relative wellbore expansion rate influence factor, and the preset weight of the relative wellbore expansion rate influence factor.

[0054] Before executing steps S11-S14, a preset wellbore expansion rate prediction model may be constructed, including:

[0055] Acquire several historical wellbore parameter sets and the historical measured wellbore diameter expansion rates corresponding to each historical wellbore parameter set; establish an initial neural network prediction model; input the historical wellbore parameter set into the initial neural network prediction model; determine whether there is a need to update the initial neural network prediction model based on the output result of the initial neural network prediction model and the historical measured wellbore diameter expansion rate corresponding to the historical wellbore parameter set; if there is a need to update, continue to input any other historical wellbore parameter set into the initial neural network prediction model; when the difference between the output result of the updated initial neural network prediction model and the corresponding historical measured wellbore diameter expansion rate is less than a preset threshold, use the updated initial neural network prediction model as the preset wellbore diameter expansion rate prediction model.

[0056] The historical wellbore parameter set refers to the wellbore parameter set of the past history. The wellbore parameter set can be composed of 23 types of parameters, including: differential stress, differential stress coefficient, formation pressure coefficient, rock uniaxial compressive strength, cohesion, internal friction angle, Poisson's ratio, open hole length index, azimuth offset coefficient, wellbore deviation offset coefficient, wellbore curvature, wellbore penetration index, deep lateral index, crushing index, mud content, GR value, Na, Al, Si, S, Cl, Ca and Fe.

[0057] The 23 types of parameters in the wellbore parameter set can all affect the wellbore expansion rate of the wellbore. It can be understood that the "real-time wellbore parameter set" described later is also composed of 23 types of parameters.

[0058] Some parameters can be directly obtained through corresponding sensors or direct measurements, while some parameters need to be further calculated. The parameters that need to be further calculated include:

[0059] Naked eye length index P H :

[0060]

[0061] Among them, P H is the open hole length index, H is the actual drilling depth, H TD To complete the drilling depth.

[0062] Azimuth deviation coefficient P Φ :

[0063]

[0064] Among them, P Φ is the azimuth offset coefficient, φ is the well inclination azimuth, and δ is the well inclination azimuth correction coefficient.

[0065] Well deviation coefficient P α :

[0066]

[0067] Among them, α is the well inclination angle, ε is the well inclination correction coefficient, P α is the well deviation coefficient.

[0068] Deep lateral index P D :

[0069] P D =lnR D

[0070] Among them, P D is the deep lateral index, R D is the deep lateral resistivity.

[0071] The crushing index is P b :

[0072] P b =|lnR D -ln R S |

[0073] Among them, P b is the crushing index, R D is the deep lateral resistivity, R S is the deep lateral resistivity.

[0074] The wellbore penetration index is P GR :

[0075]

[0076] Where: P GR is the wellbore penetration index, GR i is the natural gamma value at well depth i, and n is a constant (can be 8).

[0077] It is understandable that a historical wellbore parameter set or a real-time wellbore parameter set described below refers to 23 types of parameters at a certain depth of a wellbore, and the 23 types of parameters at the wellbore depth correspond to a wellbore expansion rate.

[0078] For example, a historical wellbore parameter set of a well at a depth of 103 m on December 13, 2023 is obtained. The historical wellbore parameter set of a well at a depth of 103 m on December 13, 2023 corresponds to a historical measured wellbore expansion rate.

[0079] After obtaining several historical wellbore parameter sets and the historical measured wellbore diameter expansion rates corresponding to the historical wellbore parameters, it is necessary to process the several historical wellbore parameter sets and the historical measured wellbore diameter expansion rates, including:

[0080] Several historical wellbore parameter sets are used as input sets and normalized, including:

[0081]

[0082] Among them, x is the parameter, y is the parameter after normalization, and y max is the maximum value of the normalized parameter, y min is the minimum value of the normalized parameter, x max is the maximum value of the parameter before normalization, x min is the minimum value of the parameter before normalization.

[0083] Then, an initial neural network prediction model is constructed, specifically including: setting grid parameters, setting the number of nodes according to the empirical formula of the number of hidden layer nodes, setting the target training target error and learning rate, and selecting an iterative algorithm to construct the initial neural network prediction model. Among them, the above-mentioned normalized historical wellbore parameter sets and historical measured wellbore expansion rates can be divided into training sets, test sets and validation sets. The division ratio can be determined according to actual conditions, for example, 7:1.5:1.5.

[0084] The training set is input into the initial neural network prediction model. The output of the initial neural network prediction model is compared with the corresponding historically measured wellbore diameter expansion rate. If the error between the output and the historically measured wellbore diameter expansion rate is greater than a preset threshold, it means that the initial neural network prediction model does not meet the requirements. The grid parameters can be adjusted, the training set can be input again, and the training results can be compared with the corresponding historically measured wellbore diameter expansion rate. If the difference between the output of the updated initial neural network prediction model and the corresponding historically measured wellbore diameter expansion rate is less than a preset threshold, the updated initial neural network prediction model is used as the preset wellbore diameter expansion rate prediction model.

[0085] Regarding step S11, a real-time wellbore parameter set of a plurality of preset detection points in the target well section to be predicted is obtained, and the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule.

[0086] The target well section to be predicted refers to a well section where there is a need for detection of instability derivative risk (the instability derivative risk in the full text refers to the stability of the well wall. The target well section to be predicted has multiple preset detection points. The multiple preset detection points on the target well section to be predicted can be distributed according to a preset distribution rule. Specifically, the preset detection points are distributed at equal distances in the target well section to be predicted.

[0087] For example, the distance between each preset detection point is 0.125m, 0.25 or 0.5, etc.

[0088] Generally speaking, the length of the target well section to be predicted should not be too long, for example, 2m, 2.5m or 3.5m, etc. The length of the target well section to be predicted can be determined according to the depth of the target well section to be predicted.

[0089] It is understandable that as the depth of the target well section increases, the formation lithology becomes more complex and heterogeneous, increasing the risk of wellbore instability. Therefore, the length of the target well section can be reduced. Real-time wellbore parameter sets can be acquired at multiple preset detection points within the target well section, that is, the 23 types of parameters described above can be acquired in real time.

[0090] Regarding step S12, the real-time wellbore parameter set of each preset detection point is input into a preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point.

[0091] After obtaining the real-time wellbore parameter sets of multiple preset detection points in the target well section to be predicted, the real-time wellbore parameter sets of each preset detection point can be input into the preset wellbore expansion rate prediction model to obtain the predicted wellbore expansion rate corresponding to each preset detection point. Each real-time wellbore parameter set corresponds to a predicted wellbore expansion rate.

[0092] Regarding step S13, based on the predicted borehole expansion rates of multiple preset detection points, the maximum borehole expansion rate influencing factor, the minimum borehole expansion rate influencing factor, and the relative borehole expansion rate influencing factor of the target well section to be predicted are determined.

[0093] After obtaining the predicted borehole diameter expansion rate corresponding to each preset detection point, the maximum borehole diameter expansion rate influencing factor can be determined based on the maximum value of the multiple predicted borehole diameter expansion rates of the target well section to be predicted; the minimum borehole diameter expansion rate influencing factor can be determined based on the minimum value of the multiple predicted borehole diameter expansion rates of the target well section to be predicted. For details, please refer to Table 1:

[0094] Table 1

[0095]

[0096] Among them, K is the predicted wellbore expansion rate, K max K is the maximum value among multiple predicted wellbore expansion rates in the target well section to be predicted, min is the minimum value of multiple predicted wellbore expansion rates in the target well section to be predicted, R1 is the maximum wellbore expansion rate influencing factor, and R2 is the minimum wellbore expansion rate influencing factor.

[0097] After determining the maximum wellbore expansion rate influencing factor and the minimum wellbore expansion rate influencing factor of the target well section to be predicted, the relative wellbore expansion rate influencing factor of the target well section to be predicted can be determined based on the maximum wellbore expansion rate influencing factor and the minimum wellbore expansion rate influencing factor, specifically including:

[0098]

[0099] Among them, K max is the maximum value among multiple predicted wellbore expansion rates, K min is the minimum value among multiple predicted wellbore expansion rates, a is the empirical coefficient of the relative wellbore expansion rate influencing factor, and R3 is the relative wellbore expansion rate influencing factor (which can be taken as 1.2).

[0100] Taking a target well section to be predicted with a length of 2m and preset detection points spaced 0.125m as an example, 16 predicted wellbore diameter expansion rates can be obtained through the above steps. The maximum and / or minimum values ​​of the 16 predicted wellbore diameter expansion rates are taken to obtain the maximum wellbore diameter expansion rate influencing factor, the minimum wellbore diameter expansion rate influencing factor, and the relative wellbore diameter expansion rate influencing factor of the target well section to be predicted.

[0101] Regarding step S14, the instability derivative risk of the target well section to be predicted is determined based on the maximum wellbore expansion rate influence factor, the preset weight of the maximum wellbore expansion rate influence factor, the minimum wellbore expansion rate influence factor, the preset weight of the minimum wellbore expansion rate influence factor, the relative wellbore expansion rate influence factor and the preset weight of the relative wellbore expansion rate influence factor.

[0102] Determine the maximum wellbore expansion rate influencing factor, minimum wellbore expansion rate influencing factor, and relative wellbore expansion rate influencing factor of the target well section to be predicted. The instability derivative risk of the target well section to be predicted can be determined based on the preset weights corresponding to each factor. Specifically, it includes:

[0103]

[0104] Among them, C is the wellbore instability derivative risk evaluation factor (used to evaluate the instability derivative risk of the target well section to be predicted), ω1 is the preset weight of the maximum wellbore expansion rate influencing factor, ω2 is the preset weight of the minimum wellbore expansion rate influencing factor, ω3 is the preset weight of the relative wellbore expansion rate influencing factor, R1 is the maximum wellbore expansion rate influencing factor, R2 is the minimum wellbore expansion rate influencing factor, and R3 is the relative wellbore expansion rate influencing factor.

[0105] The larger the value of the wellbore instability derivative risk evaluation factor of the target well section to be predicted is, the lower the instability derivative risk of the target well section to be predicted is, and the more likely it is to cause wellbore instability derivative accidents such as obstruction and stuck pipe.

[0106] Specifically, the values ​​of the wellbore instability derivative risk assessment factor are divided into multiple levels to evaluate the risk level of the target well section to be predicted. For example, when C>0.7, the risk is extremely high; 0.7≥C>0.6, the risk is high; 0.6≥C>0.5, the risk is medium to high; 0.5≥C>0.4, the risk is medium to low; and C≤0.4, the risk is low.

[0107] Different measures can be taken for different risk levels. For example, when the risk of the target well section to be predicted is extremely high, an audible and visual alarm signal can be issued to remind relevant staff; when the risk of the target well section to be predicted is high, a warning message can be sent to the target client for relevant staff to view.

[0108] In addition, the present application also provides a method for detecting the instability derivative risk of the total well section, including: determining the instability derivative risk of the total well section based on the instability derivative risks of multiple target well sections to be predicted in the same total well section.

[0109] Specifically, the total well section can be directly composed of multiple target well sections to be predicted. The instability derivative risk of the total well section is comprehensively determined based on the instability derivative risk of each target well section. For example, if the total well section is 100m long, the target well section is 2m long, and there are 50 target well sections in total, the instability derivative risk of the total well section is determined based on the instability derivative risk of each section. Specifically, the instability derivative risk of the total well section can be determined based on the preset weight of each target well section and the wellbore instability derivative risk evaluation factor of each target well section.

[0110] The total well section can also be composed of multiple overlapping target well sections. For example, if the total well section is 100 meters long and the target well section is 2 meters long, the first target well section is 0-2 meters, the second target well section is 0.125 meters to 2.125 meters, and so on, and the nth target well section is 99.875 meters to 100 meters. Therefore, the target well section overlaps with adjacent target well sections. The instability derivative risk of each target well section can be determined separately to comprehensively determine the instability derivative risk of the total well section.

[0111] In summary, the present application provides a method for predicting the risk of wellbore instability derivatives, including: obtaining a real-time wellbore parameter set of multiple preset detection points in the target well section to be predicted, the preset detection points being distributed in the target well section to be predicted according to a preset distribution rule; inputting the real-time wellbore parameter set of each preset detection point into a preset wellbore expansion rate prediction model to obtain the predicted wellbore expansion rate corresponding to each preset detection point; determining the maximum wellbore expansion rate influencing factor, the minimum wellbore expansion rate influencing factor, and the relative wellbore expansion rate influencing factor of the target well section to be predicted based on the predicted wellbore expansion rates of multiple preset detection points; determining the instability derivative risk of the target well section to be predicted based on the maximum wellbore expansion rate influencing factor, the preset weight of the maximum wellbore expansion rate influencing factor, the minimum wellbore expansion rate influencing factor, the preset weight of the minimum wellbore expansion rate influencing factor, the relative wellbore expansion rate influencing factor, and the preset weight of the relative wellbore expansion rate influencing factor. This application can predict the predicted borehole diameter expansion rate of the target well section to be predicted by acquiring the real-time wellbore parameter set (a total of 23 categories) of the target well section to be predicted in real time, and determine the instability derivative risk of the target well section to be predicted based on the multiple predicted borehole diameter expansion rates of the target well section to be predicted. It has a high degree of automation, and compared with the existing technology, it cannot accurately judge the obstruction and drill stuck risks derived from the instability of the target well section to be predicted due to the complexity of the real-time downhole situation. This application can accurately judge the instability derivative risk of the target well section to be predicted based on the real-time wellbore parameter set acquired in real time. This application, based on the construction of a neural network model to predict the borehole diameter expansion rate and establish a wellbore stability model, uses the prediction results to determine the wellbore instability derivative risk evaluation factor, and the derivative risk evaluation index formulated according to the wellbore block falling and diameter expansion characteristics can quantitatively evaluate the risk of safety drilling accidents such as obstruction and drill stuck derived from wellbore instability.

[0112] Based on the same inventive concept, the present application provides Figure 2 A device for predicting the risk of wellbore instability derivatives is shown, the device comprising:

[0113] An acquisition module 21 is used to acquire a real-time wellbore parameter set of a plurality of preset detection points in a target well section to be predicted, wherein the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule;

[0114] The prediction module 22 is used to input the real-time wellbore parameter set of each preset detection point into the preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point;

[0115] A factor determination module 23 is used to determine the maximum wellbore expansion rate influencing factor, the minimum wellbore expansion rate influencing factor, and the relative wellbore expansion rate influencing factor of the target well section to be predicted based on the predicted wellbore expansion rates of multiple preset detection points;

[0116] The instability derivative risk determination module 24 is used to determine the instability derivative risk of the target well section to be predicted based on the maximum wellbore expansion rate influence factor, the preset weight of the maximum wellbore expansion rate influence factor, the minimum wellbore expansion rate influence factor, the preset weight of the minimum wellbore expansion rate influence factor, the relative wellbore expansion rate influence factor, and the preset weight of the relative wellbore expansion rate influence factor.

[0117] Based on the same inventive concept, the present application also provides Figure 3 An electronic device as shown includes:

[0118] Processor 31;

[0119] a memory 32 for storing instructions executable by the processor 31;

[0120] The processor 31 is configured to execute and implement a wellbore instability derivative risk prediction method as provided above.

[0121] Based on the same inventive concept, the present application also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by the processor 31 of the electronic device, the electronic device can execute a wellbore instability derivative risk prediction method as provided above.

[0122] Since the electronic device described in this embodiment is an electronic device used to implement the information processing method in the embodiment of this application, based on the information processing method described in the embodiment of this application, those skilled in the art will be able to understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application will not be described in detail here. As long as those skilled in the art implement the electronic device used by the information processing method in the embodiment of this application, it falls within the scope of protection to be provided by this application.

[0123] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0124] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0125] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0126] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0127] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0128] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for predicting the risk of shaft instability derivatives, characterized in that: The method comprises: Acquire a real-time wellbore parameter set of a plurality of preset detection points in a target well section to be predicted, wherein the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule; The real-time wellbore parameter set of each preset detection point is input into the preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point. The construction of the preset wellbore diameter expansion rate prediction model includes: Obtaining a number of historical wellbore parameter sets and the historical measured wellbore expansion rates corresponding to each historical wellbore parameter set; Establish an initial neural network prediction model; Inputting a historical wellbore parameter set into the initial neural network prediction model; According to the output result of the initial neural network prediction model and the historical measured borehole expansion rate corresponding to the historical wellbore parameter set, determining whether there is a need to update the initial neural network prediction model; If there is an update requirement, continue to input any other historical wellbore parameter set into the initial neural network prediction model; when the difference between the output result of the updated initial neural network prediction model and the corresponding historical measured wellbore diameter expansion rate is less than a preset threshold, the updated initial neural network prediction model is used as the preset wellbore diameter expansion rate prediction model; According to the predicted borehole diameter expansion rate of multiple preset detection points, the maximum borehole diameter expansion rate influencing factor, the minimum borehole diameter expansion rate influencing factor, and the relative borehole diameter expansion rate influencing factor of the target well section to be predicted are determined, specifically including: Determining the maximum wellbore expansion rate influencing factor according to a maximum value among a plurality of predicted wellbore expansion rates; Determining the minimum wellbore expansion rate influencing factor according to a minimum value among a plurality of predicted wellbore expansion rates; Determining the relative wellbore expansion rate influencing factor according to the maximum value, the minimum value and the preset empirical coefficient among the multiple predicted wellbore expansion rates; According to the maximum wellbore expansion rate influence factor, the preset weight of the maximum wellbore expansion rate influence factor, the minimum wellbore expansion rate influence factor, the preset weight of the minimum wellbore expansion rate influence factor, the relative wellbore expansion rate influence factor and the preset weight of the relative wellbore expansion rate influence factor, the instability derivative risk of the target well section to be predicted is determined.

2. A method for predicting the risk of shaft instability derivatives as claimed in claim 1, characterized in that: The method further comprises: According to the instability derivative risks of multiple target well sections to be predicted in the same overall well section, the instability derivative risk of the overall well section is determined.

3. A method for predicting the risk of shaft instability derivatives as claimed in claim 1, characterized in that: The preset detection points are distributed in the target well section to be predicted according to a preset distribution rule, including: The preset detection points are distributed at equal distances in the target well section to be predicted.

4. A method for predicting the risk of shaft instability derivatives as claimed in claim 1, characterized in that: The method further comprises: The length of the target well section to be predicted is determined according to the depth of the target well section to be predicted.

5. A method for predicting the risk of shaft instability derivatives as claimed in claim 1, characterized in that: Real-time wellbore parameter set for preset inspection points, including: Differential stress, differential stress coefficient, formation pressure coefficient, uniaxial compressive strength of rock, cohesion, internal friction angle, Poisson's ratio, open hole length index, azimuth offset coefficient, wellbore deviation offset coefficient, wellbore curvature, wellbore penetration index, deep lateral index, crushing index, mud content, GR value, Na, Al, Si, S, Cl, Ca and Fe.

6. A device for predicting the risk of shaft wall instability, characterized in that: The device comprises: An acquisition module, used to acquire a real-time wellbore parameter set of a plurality of preset detection points in a target well section to be predicted, wherein the preset detection points are distributed in the target well section to be predicted according to a preset distribution rule; A prediction module is used to input the real-time wellbore parameter set of each preset detection point into a preset wellbore diameter expansion rate prediction model to obtain the predicted wellbore diameter expansion rate corresponding to each preset detection point; A factor determination module, for determining the maximum wellbore diameter expansion rate influencing factor, the minimum wellbore diameter expansion rate influencing factor, and the relative wellbore diameter expansion rate influencing factor of the target well section to be predicted according to the predicted wellbore diameter expansion rates of multiple preset detection points; The instability derivative risk determination module is used to determine the instability derivative risk of the target well section to be predicted based on the maximum wellbore expansion rate influence factor, the preset weight of the maximum wellbore expansion rate influence factor, the minimum wellbore expansion rate influence factor, the preset weight of the minimum wellbore expansion rate influence factor, the relative wellbore expansion rate influence factor and the preset weight of the relative wellbore expansion rate influence factor.

7. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute and implement a method for predicting the risk of wellbore instability derivatives as described in any one of claims 1 to 5.

8. A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to implement a method for predicting the risk derived from wellbore instability as described in any one of claims 1 to 5.

Images