Method and device for determining early-warning threshold value of jamming of drilling tool and medium

Abstract

The invention relates to the technical field of petroleum and natural gas drilling engineering, and discloses a method and device for determining a jamming early warning threshold value and a medium, and the method comprises the steps: obtaining current drilling working condition data and a plurality of pieces of historical jamming working condition data; on the basis of a current drilling working condition feature vector of the current drilling working condition data and historical drilling jamming working condition data feature vectors of the multiple pieces of historical drilling jamming working condition data, the similarity between the current drilling working condition data feature vector and the multiple pieces of historical drilling jamming working condition data feature vectors is determined; according to the plurality of similarities, determining drill jamming early warning weights corresponding to the similarities; and according to the critical maximum friction resistance in the plurality of pieces of historical drilling tool jamming working condition data and the plurality of drilling tool jamming early-warning weights, obtaining a drilling tool jamming early-warning threshold value corresponding to the current drilling working condition data. The accuracy, the stability and the engineering applicability of determining the early-warning threshold value of the drilling tool jamming under the complex working condition are improved.

Description

Technical Field

[0001] This application relates to the field of oil and gas drilling engineering technology, specifically to a method, device, and medium for determining a stuck drill warning threshold. Background Technology

[0002] In oil drilling operations, stuck pipe accidents are a key issue restricting drilling efficiency due to their high incidence and harmfulness. Stuck pipe early warning relies on monitoring the stuck pipe early warning threshold.

[0003] However, traditional methods rely on human experience to set fixed thresholds (such as triggering a stuck pipe warning when torque suddenly increases by 30%) or to determine the stuck pipe warning threshold by analyzing real-time logging dynamic data through a single model. This results in a serious disconnect between the setting of the stuck pipe warning threshold and the actual drilling situation. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, and medium for determining a stuck drilling warning threshold, in order to solve the technical defect in the prior art where the setting of the stuck drilling warning threshold is seriously out of sync with the actual drilling situation.

[0005] To achieve the above objectives, the first aspect of this application provides a method for determining a stuck drill warning threshold, the method comprising:

[0006] Acquire current drilling condition data and multiple historical stuck-piston condition data; Based on the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe data feature vectors of multiple historical stuck pipe data, the similarity between the current drilling condition data feature vector and the feature vectors of multiple historical stuck pipe data is determined. Based on multiple similarities, determine the corresponding early warning weight for each similarity level; Based on the critical maximum friction and multiple stuck-pipe warning weights from multiple historical stuck-pipe data, the stuck-pipe warning threshold corresponding to the current drilling condition data is obtained.

[0007] In this embodiment of the application, the determination of the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe condition data feature vector of multiple historical stuck pipe condition data includes: Based on a pre-trained large model, multiple historical stuck-pipe condition data are retrieved. The current drilling condition data and multiple historical stuck-pipe condition data are then structured and feature-encoded to obtain the current drilling condition feature vector of the current drilling condition data and the historical stuck-pipe condition feature vector of the multiple historical stuck-pipe condition data.

[0008] In this embodiment of the application, based on the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe data feature vectors of multiple historical stuck pipe data, the similarity between the current drilling condition data feature vector and the multiple historical stuck pipe data feature vectors is determined, including determining the similarity according to the following formula:

[0009] In the formula, This represents the similarity between the feature vector of the current drilling condition data and the feature vector of the i-th historical stuck-hole condition data. This represents the feature vector of the current drilling condition data. Let represent the feature vector of the i-th historical stuck drill condition data.

[0010] In this embodiment of the application, the stuck drill warning weight is determined based on multiple similarities, including determining the stuck drill warning weight according to the following formula:

[0011] In the formula, Indicates the weight of the drill jam warning. This represents the similarity between the feature vector of the current drilling condition data and the feature vector of the i-th historical stuck-hole condition data. This represents the similarity between the feature vector of the current drilling condition data and the feature vector of the j-th historical stuck drilling condition data. This represents the total number of historical stuck drill operating data.

[0012] In this embodiment of the application, the stuck pipe warning threshold corresponding to the current drilling condition data is obtained based on the critical maximum friction from multiple historical stuck pipe condition data and multiple stuck pipe warning weights, including obtaining the stuck pipe warning threshold according to the following formula:

[0013] In the formula, Indicates the stuck drill warning threshold. Indicates the weight of the drill jam warning. This represents the critical maximum friction in the i-th historical stuck drill condition data. This represents the total number of historical stuck drill operating data.

[0014] In this embodiment of the application, the current drilling condition data includes the current drill bit depth, and the historical stuck drill condition data includes the historical drill bit depth. The method further includes: Determine the well depth correction factor based on the current drill bit depth and the average of multiple historical drill bit depths; The target stuck pipe warning threshold is obtained based on the well depth correction factor and the stuck pipe warning threshold.

[0015] In this embodiment of the application, the well depth correction factor is determined based on the current drill bit depth and the average of multiple historical drill bit depths, including determining the well depth correction factor according to the following formula:

[0016] In the formula, represents the well depth correction factor, Represents the depth sensitivity coefficient. Indicates the current drill bit depth. This represents the average depth of multiple historical drill bits. This represents the nonlinear adjustment index.

[0017] In this embodiment of the application, the method further includes: The deep sensitivity coefficient and nonlinear adjustment index are optimized based on reinforcement learning algorithms.

[0018] A second aspect of this application provides a device for determining a stuck drill warning threshold, comprising: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing the instructions, to implement the method for determining the jam warning threshold as provided in the first aspect above.

[0019] A third aspect of this application provides a machine-readable storage medium storing instructions for causing a machine to perform the method for determining a stuck drill warning threshold as described in the first aspect above.

[0020] Through the above technical solution, this application embodiment obtains current drilling condition data and multiple historical stuck pipe condition data; based on the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe condition feature vectors of the multiple historical stuck pipe condition data, it determines the similarity between the current drilling condition data feature vector and the feature vectors of the multiple historical stuck pipe condition data; based on the multiple similarities, it determines the stuck pipe warning weight corresponding to each similarity; based on the critical maximum friction in the multiple historical stuck pipe condition data and the multiple stuck pipe warning weights, it obtains the stuck pipe warning threshold corresponding to the current drilling condition data. This application embodiment effectively overcomes the problem that traditional methods relying on fixed experience stuck pipe warning thresholds are insufficiently adaptable to complex working conditions, improves the accuracy, stability, and engineering applicability of stuck pipe warning threshold determination under complex working conditions, helps to improve the intelligent risk prevention and control level of oil and gas drilling operations, reduces non-productive time and accident handling costs, and significantly improves the safety and efficiency of drilling operations.

[0021] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0022] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1 The illustration shows a flowchart of a method for determining a stuck drill warning threshold according to an embodiment of this application. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0024] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with relevant laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0025] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0026] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0027] In oil drilling operations, stuck pipe accidents are a key issue restricting drilling efficiency due to their high incidence and harmfulness. Stuck pipe early warning relies on monitoring the stuck pipe early warning threshold.

[0028] However, traditional methods rely on human experience to set fixed thresholds (such as triggering a stuck pipe warning when torque suddenly increases by 30%) or to determine the stuck pipe warning threshold by analyzing real-time logging dynamic data through a single model. This results in a serious disconnect between the setting of the stuck pipe warning threshold and the actual drilling situation.

[0029] Figure 1 The illustration schematically shows a flowchart of a method for determining a stuck drill warning threshold according to an embodiment of this application. Figure 1 As shown in the figure, this application provides a method for determining a stuck drill warning threshold, which may include the following steps: Step S110: Obtain current drilling condition data and multiple historical stuck-piston condition data; Step S120: Based on the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe data feature vectors of multiple historical stuck pipe data, determine the similarity between the current drilling condition data feature vector and the feature vectors of multiple historical stuck pipe data respectively. Step S130: Determine the drilling jam warning weight corresponding to each similarity based on multiple similarities; Step S140: Based on the critical maximum friction and multiple stuck-pipe warning weights in multiple historical stuck-pipe data, obtain the stuck-pipe warning threshold corresponding to the current drilling condition data.

[0030] In step S110, the current drilling condition data represents the real-time status of the current drilling process, and the historical stuck pipe condition data represents the condition data of the stuck pipe events that have already occurred.

[0031] In step S120, based on the current drilling condition data and multiple historical stuck-pipe condition data, the current drilling condition feature vector of the current drilling condition data and the historical stuck-pipe condition feature vectors of the multiple historical stuck-pipe condition data are obtained respectively, to determine the similarity between the current drilling condition data feature vector and the feature vectors of the multiple historical stuck-pipe condition data. Specifically, the current drilling condition feature vector of the current drilling condition data and the historical stuck-pipe condition feature vectors of the multiple historical stuck-pipe data are generated by semantic fusion and scale unification of multi-source engineering parameters and textual information using a large model, thereby ensuring the comparability of numerical parameters, category parameters, and textual descriptions within the same feature space.

[0032] In step S130, the sticking warning weight corresponding to each similarity can be obtained by comparing the current drilling condition data feature vector with the feature vectors of multiple historical stuck drilling condition data.

[0033] In step S140, the historical stuck pipe data includes frictional resistance, and the critical maximum frictional resistance represents the maximum frictional resistance before stuck pipe occurs. By using the critical maximum frictional resistance from multiple historical stuck pipe data points and multiple stuck pipe warning weights, the stuck pipe warning threshold corresponding to the current drilling condition data is calculated. The stuck pipe warning threshold corresponding to the current drilling condition data is also the hook load threshold corresponding to the current drilling condition data. The hook load threshold is a preset safe upper limit value for the hook load during drilling operations to ensure safety, used for real-time monitoring and early warning of whether the drill string has experienced a stuck pipe abnormality.

[0034] This application embodiment acquires current drilling condition data and multiple historical stuck pipe condition data; based on the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe condition feature vectors of the multiple historical stuck pipe condition data, it determines the similarity between the current drilling condition data feature vector and the feature vectors of the multiple historical stuck pipe condition data; based on the multiple similarities, it determines the stuck pipe warning weight corresponding to each similarity; based on the critical maximum friction in the multiple historical stuck pipe condition data and the multiple stuck pipe warning weights, it obtains the stuck pipe warning threshold corresponding to the current drilling condition data. This application embodiment effectively overcomes the problem that traditional methods relying on fixed experience stuck pipe warning thresholds are insufficiently adaptable to complex working conditions, improves the accuracy, stability, and engineering applicability of stuck pipe warning threshold determination under complex working conditions, helps to improve the intelligent risk prevention and control level of oil and gas drilling operations, reduces non-productive time and accident handling costs, and significantly improves the safety and efficiency of drilling operations.

[0035] Furthermore, the determination of the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe condition data feature vector of multiple historical stuck pipe condition data in step S120 of the embodiments of this application may include the following steps: Step S121: Based on the pre-trained large model, retrieve multiple historical stuck-pipe condition data, and encode the structured features of the current drilling condition data and multiple historical stuck-pipe condition data to obtain the current drilling condition feature vector of the current drilling condition data and the historical stuck-pipe condition data feature vector of the multiple historical stuck-pipe condition data.

[0036] In step S121 of this embodiment, the pre-trained large model retrieves historical stuck-pipe condition data stored in the knowledge base through retrieval enhancement generation technology, and performs structured feature encoding on the current drilling condition data and multiple historical stuck-pipe condition data for semantic fusion and scale unification, so that the current drilling condition data and multiple historical stuck-pipe condition data are comparable in the same feature space, and finally obtains the current drilling condition feature vector of the current drilling condition data and the historical stuck-pipe condition data feature vector of the multiple historical stuck-pipe condition data.

[0037] Furthermore, the similarity between the current drilling condition data feature vector and the feature vectors of multiple historical stuck-pipe data in step S120 includes determining the similarity according to the following formula:

[0038] In the formula, This represents the similarity between the feature vector of the current drilling condition data and the feature vector of the i-th historical stuck-hole condition data. This represents the feature vector of the current drilling condition data. Let represent the feature vector of the i-th historical stuck drill condition data.

[0039] This application embodiment calculates the cosine similarity between the feature vector of the current drilling condition data and the feature vectors of multiple historical stuck-pipe conditions to ensure that the higher the similarity, the greater the contribution of the historical stuck-pipe condition data to the stuck-pipe warning weight in subsequent steps, thereby enabling the stuck-pipe warning weight to be obtained more accurately in subsequent steps.

[0040] Furthermore, the jamming warning weights corresponding to each similarity in step S130 are determined according to the following formula:

[0041] In the formula, Indicates the weight of the drill jam warning. This represents the similarity between the feature vector of the current drilling condition data and the feature vector of the i-th historical stuck-hole condition data. This represents the similarity between the feature vector of the current drilling condition data and the feature vector of the j-th historical stuck drilling condition data. This represents the total number of historical stuck drill operating data.

[0042] In order to ensure that the contributions of different historical stuck drill conditions to the stuck drill warning threshold are comparable, the similarity is normalized to define the stuck drill warning weight.

[0043] Furthermore, the stuck pipe warning threshold corresponding to the current drilling condition data in step S140 includes the threshold obtained according to the following formula:

[0044] In the formula, This indicates the stuck drill warning threshold (hook load threshold). Indicates the weight of the drill jam warning. This represents the critical maximum friction in the i-th historical stuck drill condition data. This represents the total number of historical stuck drill operating data.

[0045] Current drilling condition data includes the current drill bit depth, and historical stuck drill condition data includes historical drill bit depths. Furthermore, the method for determining the drill bit warning threshold in this application embodiment may also include the following steps: Step S210: Determine the well depth correction factor based on the current drill bit depth and the average of multiple historical drill bit depths; Step S220: Obtain the target stuck pipe warning threshold based on the well depth correction factor and the stuck pipe warning threshold.

[0046] In steps S210-S220 of this application embodiment, by introducing a nonlinear well depth correction factor that considers the friction characteristics of the drill string, the stuck pipe warning threshold can be dynamically adjusted with the changes in drill bit depth and well inclination to obtain the target stuck pipe warning threshold. This adapts to the practical engineering problem of the expansion of the normal fluctuation range of parameters during the increase of well depth, significantly reduces the false alarm and missed alarm problems caused by unreasonable setting of the stuck pipe warning threshold in the prior art, and improves the matching degree between the warning result and the actual working conditions.

[0047] Furthermore, the well depth correction factor in step S210 is determined according to the following formula:

[0048] In the formula, represents the well depth correction factor, Represents the depth sensitivity coefficient. Indicates the current drill bit depth. This represents the average depth of multiple historical drill bits. This represents the nonlinear adjustment index. In this application, an embodiment is designed with a nonlinear well depth correction factor to address the engineering principle that increases drill string friction torque with increasing drill bit depth.

[0049] Furthermore, embodiments of this application may also include the following steps: Step S310: Optimize the depth sensitivity coefficient and nonlinear adjustment index based on reinforcement learning algorithm.

[0050] In step S310, in order to overcome the problem that the fixed parameter depth sensitivity coefficient and the fixed nonlinear adjustment index are not adaptable to complex working conditions, the parameter depth sensitivity coefficient and the nonlinear adjustment index in the well depth correction factor are continuously corrected and evolved so that the stuck drill warning threshold can automatically approach the optimal state as the drilling working conditions change.

[0051] In actual operation, the current drilling status is first comprehensively characterized to form a working condition state vector. This vector includes, but is not limited to, the fluctuation characteristics of real-time parameters such as current well depth, well inclination angle, formation lithology, drill string assembly parameters, hook load, torque, and pump pressure. Based on the description of the working condition state, the parameter depth sensitivity coefficient and nonlinear adjustment index are slightly adjusted to generate new parameter depth sensitivity coefficients and new nonlinear adjustment indices, and the stuck pipe warning threshold is updated accordingly.

[0052] After the updated stuck pipe warning threshold is implemented, its warning effect during actual drilling is continuously monitored. A comprehensive evaluation index is constructed based on the actual operating results. This comprehensive evaluation index measures the rationality of the current parameter combination, considering both warning accuracy and stability. The calculation formula for the comprehensive evaluation index includes:

[0053]

[0054]

[0055] In the formula, This represents the comprehensive evaluation indicators. Indicates the accuracy rate of early warnings regarding the risk of stuck drill pipe. The false alarm rate, which indicates the risk of stuck drill pipe, This indicates the adjustment magnitude of the updated depth sensitivity coefficient and nonlinear adjustment exponent relative to the previous time step. This represents the number of times a stuck drill warning has been successfully issued when a stuck drill situation actually occurs or when a stuck drill trend is confirmed manually. This indicates the number of times a drill bit actually jams or shows a tendency to jam without issuing a jam warning. This indicates the number of times a stuck drill warning was falsely issued when no actual stuck drill occurred and the operating conditions were normal. This indicates the number of times a stuck drill warning was not issued when no actual stuck drill occurred and the operating conditions were normal. This represents the first weighting coefficient. This represents the second weighting coefficient. This represents the third weighting coefficient.

[0056] When the comprehensive evaluation index increases, the weight of the adjustment direction of the current depth sensitivity coefficient and the current nonlinear adjustment index is increased; when the comprehensive evaluation index decreases, the adjustment direction and magnitude are automatically corrected. Through the closed-loop process of "state perception - parameter adjustment - effect evaluation - feedback correction" described above, the depth sensitivity coefficient and the nonlinear adjustment index gradually converge to the optimal range that matches the current well type, formation and working conditions during continuous drilling.

[0057] This application embodiment also provides a device for determining a stuck drill warning threshold, including: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing instructions, to implement the method for determining the jam warning threshold as described above.

[0058] It is understood that the device for determining the stuck drill warning threshold provided in this application embodiment can realize each process of the method for determining the stuck drill warning threshold in the above embodiment and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0059] This application also provides a machine-readable storage medium storing instructions for causing a machine to execute the method for determining the stuck drill warning threshold as described above.

[0060] It is understood that the machine-readable storage medium provided in the embodiments of this application can implement each process of the method for determining the stuck drill warning threshold in the above embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0061] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0062] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0063] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The function specified in one or more boxes.

[0064] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0065] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0066] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0067] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0068] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0069] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A method for determining a stuck-casing early-warning threshold, comprising: The method includes: Acquire current drilling condition data and multiple historical stuck-piston condition data; Based on the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe data feature vectors of multiple historical stuck pipe data, the similarity between the current drilling condition data feature vector and the multiple historical stuck pipe data feature vectors is determined. Based on the multiple similarities, determine the jamming warning weight corresponding to each of the aforementioned similarities; Based on the critical maximum friction in multiple historical stuck-pipe condition data and multiple stuck-pipe warning weights, the stuck-pipe warning threshold corresponding to the current drilling condition data is obtained.

2. The method of claim 1, wherein, The determination of the current drilling condition feature vector of the current drilling condition data and the historical stuck pipe condition data feature vectors of multiple historical stuck pipe condition data includes: Based on a pre-trained large model, multiple historical stuck-pipe condition data are retrieved, and the current drilling condition data and multiple historical stuck-pipe condition data are structured feature encoded to obtain the current drilling condition feature vector of the current drilling condition data and the historical stuck-pipe condition data feature vector of the multiple historical stuck-pipe condition data.

3. The method of claim 1, wherein, The method of determining the similarity between the current drilling condition feature vector and the multiple historical stuck-pipe data feature vectors based on the current drilling condition feature vector and the multiple historical stuck-pipe data feature vectors includes determining the similarity according to the following formula: wherein, represents a similarity between the current drilling operation condition data feature vector and the i-th historical stuck condition data feature vector, represents the current drilling operation condition data feature vector, represents the i-th historical stuck condition data feature vector.

4. The method of claim 1, wherein, The step of determining the stuck drill warning weight corresponding to each of the multiple similarities includes determining the stuck drill warning weight according to the following formula: In the formula, represents the stuck alerting early warning weight, represents the similarity between the current drilling operation data feature vector and the i-th historical stuck operation data feature vector, represents the similarity between the current drilling operation data feature vector and the j-th historical stuck operation data feature vector, represents the total number of historical stuck operation data.

5. The method of claim 1, wherein, The step of obtaining the stuck pipe warning threshold corresponding to the current drilling condition data based on the critical maximum friction from multiple historical stuck pipe condition data and multiple stuck pipe warning weights includes obtaining the stuck pipe warning threshold according to the following formula: In the formula, represents the stuck alert threshold, represents the stuck alert weight, represents the critical maximum friction of the i-th historical stuck working condition data, represents the total number of historical stuck working condition data.

6. The method of claim 1, wherein, The current drilling condition data includes the current drill bit depth, and the historical stuck drill condition data includes historical drill bit depths. The method further includes: The well depth correction factor is determined based on the current drill bit depth and the average of multiple historical drill bit depths; The target stuck pipe warning threshold is obtained based on the well depth correction factor and the stuck pipe warning threshold.

7. The method of claim 6, wherein, The step of determining the well depth correction factor based on the current drill bit depth and the average of multiple historical drill bit depths includes determining the well depth correction factor according to the following formula: wherein, represents the well depth correction factor, represents the depth sensitivity coefficient, represents the current bit depth, represents the mean of the plurality of historical bit depths, represents the non-linear adjustment exponent.

8. The method of claim 7, wherein, The method further includes: The deep sensitivity coefficient and the nonlinear adjustment index are optimized based on a reinforcement learning algorithm.

9. A device for determining a stuck-casing early-warning threshold, characterized in that include: The memory is configured to store instructions; The processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the method for determining the stuck drill warning threshold according to any one of claims 1 to 8.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the method for determining the stuck drill warning threshold according to any one of claims 1 to 8.

Images