A method and system for predicting the occurrence of complex downhole conditions

Abstract

This invention discloses a method and system for predicting complex downhole conditions, comprising: real-time acquisition and preprocessing of drilling engineering parameter data at different depths of the target well; comparing the preprocessed real-time drilling engineering parameter data with reference data corresponding to at least one complex condition event in a complex condition database, and calculating the probability of occurrence of at least one complex condition event. This invention organizes complex conditions from previous operations and their corresponding reference data into a complex condition database in the form of case studies, solving the problem of missing or inaccurate data in the early stages, laying the foundation for future data mining. Furthermore, through a correlation coefficient algorithm, it can achieve prediction, diagnosis, and discrimination of complex drilling conditions, thereby supporting on-site personnel and experts in analyzing and processing complex drilling conditions, improving drilling safety, reducing losses caused by complex situations, and possessing certain field application value.

Description

Technical Field

[0001] This invention relates to the field of geological exploration technology, and in particular to a method and system for predicting complex downhole working conditions. Background Technology

[0002] Due to insufficient understanding of complex geological and engineering factors, many complex situations often arise during drilling. The identification and handling of these downhole complexities must be timely and accurate; improper handling can trigger chain reactions and even serious accidents, resulting in significant economic losses. Drilling engineering parameters can reflect downhole complexities in real time; therefore, drilling engineering data can be used to predict and diagnose these complexities, thereby reducing their occurrence on-site. Currently, many methods exist for diagnosing complex situations using drilling engineering parameters, including neural networks, grey theory, and other approaches.

[0003] A method for predicting drilling risk is disclosed in an existing patent document (publication number CN107153881A). This method involves acquiring a real-time data vector of the current depth of the target well; establishing a time window and creating a set of real-time data vectors at specified time intervals within the time window; processing the set of real-time data vectors and using it as a case vector to be predicted; acquiring existing case vectors that match the geographical features of the case vector to be predicted based on the neighboring wells of the target well; acquiring existing case vectors that match the case vector to be predicted; and predicting the drilling risk of the target well based on the neighboring wells corresponding to the existing case vectors that match the case vector to be predicted. However, it does not address the processing method for historical drilling engineering parameters or elaborate on how to match existing engineering parameters with historical engineering parameters.

[0004] However, some problems still exist. First, due to limitations in on-site data collection and construction conditions, many drilling engineering parameters are inaccurate or missing, resulting in poor direct utilization. It is necessary to clean and preprocess historical and real-time drilling engineering parameters. Second, the characteristic parameters of complex downhole drilling conditions vary widely and cannot be accurately characterized by precise data models. Furthermore, no corresponding algorithm has been proposed for curve fitting between real-time and historical engineering parameters, or the similarity algorithm is poor, which cannot more accurately describe the similarity relationship between the two. Summary of the Invention

[0005] The purpose of this invention is to provide a solution that fully considers historical engineering parameter data and uses it to predict the probability of drilling conditions, thereby solving the problem that existing technologies do not involve processing methods for historical drilling engineering parameters or explain how to match existing engineering parameters with historical engineering parameters, which leads to poor prediction results.

[0006] To address the aforementioned technical problems, embodiments of the present invention provide a method for predicting the occurrence of complex downhole conditions, comprising: real-time acquisition of drilling engineering parameter data at different depths of a target well and preprocessing the data; comparing the preprocessed real-time drilling engineering parameter data with reference data corresponding to at least one complex condition event in a complex condition database, and calculating the probability of occurrence of the at least one complex condition event, wherein the complex condition database includes reference data for at least one complex condition event, and the reference data consists of dynamic change data of several relevant drilling engineering parameters when the complex condition event occurs.

[0007] Preferably, the complex operating condition database is constructed based on historical drilling engineering parameter data. The complex operating condition database is constructed through the following steps: acquiring real-time data of drilling engineering parameters at different depths for all drilled wells within the same work area as the target well, and processing this data; identifying at least one complex operating condition event and extracting the drilling engineering parameters related to each complex operating condition event; extracting the dynamic change data of all relevant drilling engineering parameters within a specified time period before and after each complex operating condition event; and forming the complex operating condition database by establishing a mapping relationship between the complex operating condition event and the dynamic change data of all relevant drilling engineering parameters corresponding to the event.

[0008] Preferably, the data processing includes missing value filling, curve noise smoothing, and normalization. The step of filling the historical real-time data of drilling engineering parameters includes: filling the missing data in the historical drilling engineering parameter data using regression analysis based on the historical drilling engineering parameter data at different depths.

[0009] Preferably, the well depth where the data to be filled is located is determined, and the depth range to be processed is determined; the parameter type of the missing data is taken as the target parameter item, and the measured data of the target parameter item at different well depths within the depth range to be processed are extracted; based on the measured data of the target parameter item at different well depths, a regression equation is established using the least squares method; data corresponding to the well depth where the data to be filled is located is extracted from the regression equation, and this data is used as the filling value.

[0010] Preferably, the preprocessing includes curve noise smoothing and normalization. The step of comparing the preprocessed real-time drilling engineering parameter data with reference data corresponding to at least one complex operating condition event in the complex operating condition database, and calculating the probability of occurrence of the at least one complex operating condition event, includes: calculating the correlation between the real-time measurement curves of several related drilling engineering parameters corresponding to the at least one complex operating condition event and the historical dynamic measurement curves in the reference data, obtaining the corresponding correlation coefficients; and calculating the probability of occurrence of the current at least one complex operating condition event based on the correlation coefficients of several related drilling engineering parameters corresponding to the at least one complex operating condition event, using the influence weight of each related drilling engineering parameter in its respective complex operating condition event.

[0011] Preferably, the correlation coefficient is calculated using the Pearson similarity coefficient calculation method, wherein the correlation coefficient is calculated using the following expression:

[0012]

[0013] Where r represents the correlation coefficient, x i y represents the real-time measurement data of the relevant drilling engineering parameters corresponding to the i-th well depth. i This represents the historical measurement data of the relevant drilling engineering parameters corresponding to the i-th well depth, and n represents the total number of data points within the time period corresponding to the reference data segment.

[0014] Preferably, the probability of occurrence is calculated using the following expression:

[0015]

[0016] Where P represents the probability of occurrence, m represents the number of relevant drilling engineering parameters in the complex operating condition event, and r i w represents the similarity coefficient of the i-th relevant drilling engineering parameter. i This represents the influence weight of the i-th relevant drilling engineering parameter.

[0017] Preferably, the method further includes: issuing an early warning for the corresponding complex operating condition event when the probability of occurrence of the at least one complex operating condition event exceeds a preset threshold.

[0018] On the other hand, embodiments of the present invention provide a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method described in any one or more of the above embodiments.

[0019] In another aspect, embodiments of the present invention also provide a system for predicting the probability of occurrence of drilling conditions, comprising: a data acquisition module configured to collect drilling engineering parameter data at different depths of a target well in real time and preprocess it; and an occurrence probability prediction module configured to compare the preprocessed real-time drilling engineering parameter data with reference data corresponding to at least one complex condition event in a complex condition database, and calculate the occurrence probability of the at least one complex condition event, wherein the complex condition database includes reference data for at least one complex condition event, and the reference data is dynamic change data of several related drilling engineering parameters when the complex condition event occurs.

[0020] Compared with the prior art, one or more embodiments of the above solutions may have the following advantages or beneficial effects:

[0021] This invention proposes a method and system for predicting complex downhole conditions. The method and system construct a complex condition database, organizing past complex conditions and corresponding reference data into case studies. This database solves the problem of missing or inaccurate data in the early stages, laying the foundation for future data mining. Furthermore, due to the diversity of complex downhole conditions, it is difficult to describe them using precise data models. Therefore, by employing a correlation coefficient algorithm, it is possible to predict, diagnose, and identify complex drilling conditions. This enables on-site personnel and experts to analyze and process complex drilling conditions, improving drilling safety and reducing losses caused by complex situations, thus possessing significant field application value.

[0022] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0023] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0024] Figure 1 This is a schematic diagram illustrating the steps of a method for predicting complex downhole working conditions according to an embodiment of this application.

[0025] Figure 2 This is a flowchart illustrating a method for predicting complex downhole working conditions according to an embodiment of this application.

[0026] Figure 3This is a schematic diagram showing the result after curve noise smoothing in the method for predicting complex downhole working conditions according to an embodiment of this application.

[0027] Figure 4 This is an example diagram illustrating the trends of various similarity indicators in the method for predicting complex downhole working conditions according to embodiments of this application.

[0028] Figure 5 This is an example diagram showing the corresponding results of various similarity indices in the method for predicting complex downhole working conditions according to an embodiment of this application.

[0029] Figure 6 This is an example diagram of the test curve of the mathematical method in the method for predicting complex downhole working conditions according to an embodiment of this application.

[0030] Figure 7 This is an example diagram of the occurrence probability curve corresponding to the first example well in the method for predicting the occurrence of complex downhole working conditions in this application embodiment.

[0031] Figure 8 This is an example diagram of the occurrence probability curve corresponding to the second example well in the method for predicting the occurrence of complex downhole working conditions in this application embodiment.

[0032] Figure 9 This is an example diagram illustrating the real-time monitoring of a third example well in the method for predicting complex downhole conditions according to embodiments of this application.

[0033] Figure 10 This is a schematic diagram of the system for predicting complex downhole working conditions according to an embodiment of this application. Detailed Implementation

[0034] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples, so that the process of how the present invention uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly. It should be noted that, as long as there is no conflict, the various embodiments and features in the various embodiments of the present invention can be combined with each other, and the resulting technical solutions are all within the protection scope of the present invention.

[0035] Furthermore, the steps illustrated in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in a different order than that shown here.

[0036] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms “a” and “an” as used herein are also intended to include the plural. It should also be understood that the terms “comprising” and / or “including” as used herein specify the presence of the stated features, integers, steps, operations, units, and / or components, without excluding the presence or addition of one or more other features, integers, steps, operations, units, components, and / or combinations thereof.

[0037] Due to insufficient understanding of complex geological and engineering factors, many complex situations often arise during drilling. The identification and handling of these downhole complexities must be timely and accurate; improper handling can trigger chain reactions and even serious accidents, resulting in significant economic losses. Drilling engineering parameters can reflect downhole complexities in real time; therefore, drilling engineering data can be used to predict and diagnose these complexities, thereby reducing their occurrence on-site. Currently, many methods exist for diagnosing complex situations using drilling engineering parameters, including neural networks, grey theory, and other approaches.

[0038] A method for predicting drilling risk is disclosed in an existing patent document (publication number CN107153881A). This method involves acquiring a real-time data vector of the current depth of the target well; establishing a time window and creating a set of real-time data vectors at specified time intervals within the time window; processing the set of real-time data vectors and using it as a case vector to be predicted; acquiring existing case vectors that match the geographical features of the case vector to be predicted based on the neighboring wells of the target well; acquiring existing case vectors that match the case vector to be predicted; and predicting the drilling risk of the target well based on the neighboring wells corresponding to the existing case vectors that match the case vector to be predicted. However, it does not address the processing method for historical drilling engineering parameters or elaborate on how to match existing engineering parameters with historical engineering parameters.

[0039] However, some problems still exist. First, due to limitations in on-site data collection and construction conditions, many drilling engineering parameters are inaccurate or missing, resulting in poor direct utilization. It is necessary to clean and preprocess historical and real-time drilling engineering parameters. Second, the characteristic parameters of complex downhole drilling conditions vary widely and cannot be accurately characterized by precise data models. Furthermore, no corresponding algorithm has been proposed for curve fitting between real-time and historical engineering parameters, or the similarity algorithm is poor, which cannot more accurately describe the similarity relationship between the two.

[0040] Example 1

[0041] Figure 1 This is a schematic diagram illustrating the steps of a method for predicting complex downhole working conditions according to an embodiment of this application. Figure 2This is a flowchart illustrating a method for predicting complex downhole working conditions according to an embodiment of this application. The following is in conjunction with... Figure 1 and Figure 2 The specific process of the method for predicting complex downhole working conditions (hereinafter referred to as the "prediction method") described in the embodiments of the present invention will be explained.

[0042] Step S110: Real-time acquisition of drilling engineering parameter data at different depths of the target well, and preprocessing of the drilling engineering parameter data at different depths.

[0043] Drilling engineering parameter data at different depths of the target well are collected in real time. Then, in order to avoid interference from noise data, the collected drilling engineering parameter data is preprocessed to improve the accuracy of data application.

[0044] In this embodiment, the preprocessing includes curve noise smoothing and normalization.

[0045] Specifically, the reason for smoothing the drilling engineering parameter data is that the collected data contains errors, anomalies, and deviations from expected values. A support vector machine algorithm is used to detect these isolated data points. Figure 3 These are the curve changes of two main drilling engineering parameters after standardization. In particular, when considering only a single drilling engineering parameter, the gray-marked points are also within the normal range of variation and belong to normal and reasonable values.

[0046] The reason for normalizing drilling engineering parameter data is to address the significant differences in magnitude between different drilling engineering parameters, which can affect the calculation results. Normalizing the drilling engineering parameter data involves a linear transformation, restricting the values ​​of all drilling engineering parameter data to the range [0, 1]. The specific mapping calculation formula is shown below:

[0047]

[0048] Where x′ represents the normalized drilling engineering parameter data, x represents the real-time collected drilling engineering parameter data, max represents the maximum value among all drilling engineering parameter data, and min represents the minimum value among all drilling engineering parameters.

[0049] Step S120: Compare the preprocessed real-time drilling engineering parameter data with the reference data corresponding to at least one complex working condition event in the complex working condition database, and calculate the probability of occurrence of at least one complex working condition event.

[0050] refer to Figure 2First, the historical drilling engineering parameter data of the drilled wells is processed. Then, a complex working condition database is constructed based on the processed historical drilling engineering parameter data. Finally, the preprocessed real-time drilling engineering parameter data is compared with the reference data corresponding to at least one complex working condition event in the complex working condition database to obtain the probability of occurrence of at least one complex working condition.

[0051] In this embodiment, the complex operating condition database includes reference data for at least one complex operating condition event. This reference data consists of dynamic changes in several relevant drilling engineering parameters when the complex operating condition event occurs.

[0052] In one embodiment, the complex operating condition database is constructed based on historical drilling engineering parameter data. Specifically, the construction of the complex operating condition database includes the following steps A1-A4:

[0053] Step A1: Obtain real-time data of drilling engineering parameters of all drilled wells in the same work area as the target well at different depths, and perform data processing on the real-time data of drilling engineering parameters at different depths.

[0054] Step A2: Identify at least one complex operating condition event and extract the drilling engineering parameters associated with each complex operating condition event.

[0055] Step A3: Extract the dynamic change data of all relevant drilling engineering parameters within a specified time period before and after each complex working condition event.

[0056] Step A4 involves establishing a complex operating condition database by creating a mapping relationship between complex operating condition events and the dynamic changes of all relevant drilling engineering parameters corresponding to those events.

[0057] refer to Figure 2 First, real-time data of drilling engineering parameters at different depths for all drilled wells in the same work area as the target well are acquired, and the real-time data of drilling engineering parameters at different depths are processed. Then, at least one complex working condition event is identified. Next, engineering parameters related to each complex working condition event are extracted from all historical drilling engineering parameter data, and dynamic change data is extracted from historical drilling engineering parameters based on the engineering parameters. Finally, a complex working condition database is formed by establishing a mapping relationship between the dynamic data of all relevant drilling engineering parameters within a specified time period before and after the occurrence of the complex working condition event.

[0058] In step A1, data processing includes null value imputation, curve noise smoothing, and normalization.

[0059] Specifically, the data processing mainly includes null value imputation, curve noise smoothing, and normalization. The process of curve noise processing and normalization is as shown in step S110 and will not be described in detail here.

[0060] When performing gap filling on real-time data of drilling engineering parameters at different depths, missing data in the historical drilling engineering parameter data at different depths is filled using regression analysis. Specifically, the gap filling process includes the following sub-steps B1-B4:

[0061] Sub-step B1: Determine the well depth where the data to be filled is located, and determine the depth range to be processed.

[0062] Sub-step B2 takes the parameter type of the missing data as the target parameter item and extracts the measured data of the target parameter item at different well depths within the depth range to be processed.

[0063] Sub-step B3 involves establishing a regression equation using the least squares method based on the measured data of the target parameter at different well depths.

[0064] Sub-step B4: Extract data from the regression equation that corresponds to the well depth of the data to be filled, and use this data as the filling value.

[0065] Specifically, when filling in missing data, regression analysis was mainly used to predict the maximum possible value of the missing data. There are some null values ​​in the data. In order not to affect the calculation results, these null values ​​need to be processed during the preprocessing process, and the most likely value is used to fill in these missing data.

[0066] When filling in the missing data, regression analysis was mainly used. The main idea of ​​this method is as follows: if a certain drilling engineering parameter is not obtained at a well depth of h0 meters, that is, if there is no drilling engineering parameter data at that moment, the drilling engineering parameter data at a well depth of about h meters are statistically analyzed to establish a regression equation between the well depth and the drilling engineering parameter data. Then, h0 is entered into the regression equation to calculate the missing data filling value.

[0067] Using well depth h as the independent variable and drilling engineering parameter data y as the dependent variable, we first obtain n data points within the depth range of approximately h0 meters to be processed, namely (h1, y1), (h2, y2), (h3, y3)...(h...). n y n Then, the least squares method is used to calculate the regression equation. Finally, the significance of the established regression equation is checked to determine whether there is a univariate relationship between y and h that conforms to the regression equation. If such a relationship exists, h0 is added to the regression equation to obtain the missing data.

[0068] In sub-step B1, the specific value of the depth range to be processed is not limited and can be reasonably selected according to the actual application requirements.

[0069] In sub-step B3, the regression equation can be represented by the following expression:

[0070] y = β0 + β1h + β2h 2 +… (2)

[0071] Where y represents drilling engineering parameter data, h represents well depth, and β0, β1, and β2 all represent fitting coefficients.

[0072] In one embodiment, when calculating the probability of occurrence of at least one complex operating condition event, the correlation coefficients of different drilling engineering parameters are first calculated, and then the probability of occurrence is obtained based on the correlation coefficients and their corresponding influence weights. Specifically, step S120 includes the following sub-steps C1-C2:

[0073] Sub-step C1: Calculate the correlation between the real-time measurement curves of several relevant drilling engineering parameters corresponding to at least one complex working condition event and the historical dynamic measurement curves in the reference data, and obtain the corresponding correlation coefficients.

[0074] Sub-step C2: Based on the correlation coefficients of several relevant drilling engineering parameters corresponding to at least one complex working condition event, and using the influence weight of each relevant drilling engineering parameter in its respective complex working condition event, calculate the probability of occurrence of the current at least one complex working condition event.

[0075] In sub-step C1, the real-time measurement curve is a curve that uses well depth as the horizontal axis and drilling engineering parameter data at different depths as the vertical axis to obtain real-time measurement curves of different drilling engineering parameters.

[0076] In sub-step C1, the correlation coefficient is calculated using the Pearson similarity coefficient method. Specifically, the correlation coefficient is calculated using the following expression:

[0077]

[0078] Where r represents the correlation coefficient, x i y represents the real-time measurement data of the relevant drilling engineering parameters corresponding to the i-th well depth. i This represents the historical measurement data of the relevant drilling engineering parameters corresponding to the i-th well depth, and n represents the total number of data points within the time period corresponding to the reference data segment.

[0079] In particular, the closer the correlation coefficient is to 1, the stronger the correlation; the closer the correlation coefficient is to 0, the weaker the correlation.

[0080] In sub-step C2, the specific value of the weight is not limited and can be reasonably selected according to the actual application requirements.

[0081] In sub-step C2, the probability of occurrence is calculated using the following expression:

[0082]

[0083] Where P represents the probability of occurrence, m represents the number of relevant drilling engineering parameters in the complex operating condition event, and r i w represents the similarity coefficient of the i-th relevant drilling engineering parameter. i This represents the influence weight of the i-th relevant drilling engineering parameter.

[0084] In one embodiment, in order to avoid the impact of complex operating conditions on drilling conditions, the prediction method further includes step S130, which provides an early warning for the corresponding complex operating condition when the probability of occurrence of at least one complex operating condition exceeds a preset threshold.

[0085] The specific value of the preset threshold is not limited and can be reasonably selected according to the actual application requirements.

[0086] Example 2

[0087] Based on the above embodiment one, there are various indicators that can measure the correlation between real-time measurement curves and historical dynamic measurement curves. This embodiment compares and tests various indicators to determine the indicators suitable for establishing a complex working condition database.

[0088] In order to find an indicator that best represents the trend of the curve, the following data was mainly used for testing:

[0089] refer to Figure 4 Data 1 and Data 2 are real-time collected drilling engineering parameter data; Data 3 is the drilling engineering parameter data at time 5, which changes from decreasing to increasing based on the real-time collected drilling engineering parameter data; Data 4 is the drilling engineering parameter data at time 5 with one additional unit added based on Data 3; Data 5 is the drilling engineering parameter data with one additional unit added overall (i.e., the same trend as the real-time measurement curve); Data 6 is the drilling engineering parameter data with two additional units added overall (i.e., the same trend as the real-time measurement curve); Data 7 is a set of data fitted from the real-time collected drilling engineering parameter data, and the overall trend is similar to the actual drilling engineering parameter data; Data 8 has a completely opposite trend to the real-time collected drilling engineering parameter data.

[0090] The calculation results obtained by comparing and testing using multiple indicators are as follows: Figure 5 As shown. Reference Figure 5 It can be observed that the Pearson similarity coefficient method can represent the trend characteristics of the curve.

[0091] Example 3

[0092] Based on Embodiment 1 and Embodiment 2 above, this embodiment describes the specific process of applying the method for predicting the occurrence of complex downhole working conditions to predict the probability of complex drilling events in a certain drilling well.

[0093] refer to Figure 6 Several data methods for calculating curve distance were tested using a few case curves, and the results are shown in Table 1.

[0094] Table 1 Real-time measurement curves

[0095]

[0096]

[0097] As can be seen from Table 1, curves 2 and 3 have basically the same trend as curve 1, while curve 4 has a significantly different trend from curve 1. Therefore, the Pearson similarity coefficient method can more intuitively represent the trend characteristics and similarity of the curves.

[0098] Example 4

[0099] Based on the above embodiment one, the following describes the specific process of applying the method for predicting the occurrence of complex downhole working conditions described in the embodiments of the present invention to predict the probability of complex well leakage events in a certain well.

[0100] refer to Figure 7 The real-time drilling engineering parameter data of a certain well 20m ahead was compared with the reference data corresponding to at least one complex working condition event in the complex working condition database. The cases with the highest occurrence probability were Tuoxie 192 well (well leakage) and Gao 96 well (well leakage), with occurrence probabilities of 0.85 and 0.73, respectively.

[0101] Example 5

[0102] Based on the above embodiment one, the following describes the specific process of applying the method for predicting the occurrence of complex downhole working conditions described in the embodiment of the present invention to a certain well to predict the probability of the occurrence of complex events such as well sticking and stuck drilling.

[0103] refer to Figure 8The real-time drilling engineering parameter data of a certain well 20m before the start of the well was compared with the reference data corresponding to at least one complex working condition event in the complex working condition database. The cases with the highest occurrence probability were Yong 8-Ping 20 well (sticky and stuck drill), Yi 193 well (sticky and stuck drill), and Che 71 well (keyway stuck drill), with occurrence probabilities of 0.71, 0.51, and 0.39, respectively.

[0104] Example 6

[0105] Based on the above embodiment one, the following describes the specific process of applying the method for predicting the occurrence of complex downhole working conditions described in the embodiment of the present invention to a certain well to verify the occurrence of complex events.

[0106] The historical complex event was a drill string breakage at 1973 meters. The probability of this complex event occurring was predicted to be 0.8 using the method used to predict complex downhole conditions.

[0107] refer to Figure 9 The handling process for a specific well malfunction was as follows: At 07:00 on May 10th, drilling reached a depth of 1973.77 meters. The pump pressure dropped by 5 MPa. After checking the surface equipment and finding no problems, drilling was initiated. At 11:30, a broken drill collar was discovered; the bottommost drill collar had fallen into the well, and the male thread of the collar above it had broken. From 12:00 to 17:00, a drill bit was lowered for retrieval. The drill bit was damaged and could not continue to be used. From 17:00 to 18:30, the fallen drill bit was retrieved. From 18:30 to 00:00 on May 11th, drilling was initiated, and the drill string broke. From 00:00 to 05:00, drilling resumed normally. Therefore, the predicted probability of the complex operating condition event was accurate.

[0108] Example 7

[0109] Based on the above-described method for predicting complex downhole conditions, the present invention also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method described in any one or more of the above embodiments.

[0110] Example 8

[0111] Based on the above-described method for predicting the occurrence of complex downhole conditions, the present invention also provides a system for predicting the probability of drilling conditions occurring. This system for predicting the probability of drilling conditions is used to implement the method described above for predicting the occurrence of complex downhole conditions.

[0112] Figure 10 This is a schematic diagram of the system for predicting the probability of drilling conditions according to an embodiment of this application. Figure 10As shown, the system for predicting the probability of drilling conditions as described in this embodiment of the invention includes: a data acquisition module 1001 and an occurrence probability prediction module 1002.

[0113] Specifically, the data acquisition module 1001 is implemented according to the method described in step S110 above, and is configured to collect drilling engineering parameter data at different depths of the target well in real time and preprocess it; the occurrence probability prediction module 1002 is implemented according to the method described in step S120 above, and is configured to compare the preprocessed real-time drilling engineering parameter data with reference data corresponding to at least one complex working condition event in the complex working condition database, and calculate the occurrence probability of at least one complex working condition event.

[0114] The complex operating condition database includes reference data for at least one complex operating condition event. The reference data consists of dynamic changes in several relevant drilling engineering parameters when the complex operating condition event occurs.

[0115] This invention proposes a method and system for predicting complex downhole conditions. The method and system construct a complex condition database, organizing past complex conditions and corresponding reference data into case studies. This database solves the problem of missing or inaccurate data in the early stages, laying the foundation for future data mining. Furthermore, due to the diversity of complex downhole conditions, it is difficult to describe them using precise data models. Therefore, by employing a correlation coefficient algorithm, it is possible to predict, diagnose, and identify complex drilling conditions. This enables on-site personnel and experts to analyze and process complex drilling conditions, improving drilling safety and reducing losses caused by complex situations, thus possessing significant field application value.

[0116] The above description is merely a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

[0117] In the description of this invention, unless otherwise stated, "a plurality of" means two or more; the terms "upper," "lower," "left," "right," "inner," "outer," "front end," "rear end," "head," "tail," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," "third," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0118] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0119] It should be understood that the embodiments disclosed herein are not limited to the specific structures, processing steps, or materials disclosed herein, but should be extended to equivalent substitutions of these features as understood by those skilled in the art. It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.

[0120] The phrase "an embodiment" or "an embodiment" used in this specification means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Therefore, the phrase "an embodiment" or "an embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0121] While the embodiments disclosed in this invention are as described above, the content is merely for the purpose of facilitating understanding of the invention and is not intended to limit the invention. Any person skilled in the art to which this invention pertains may make any modifications and changes in form and detail of the implementation without departing from the spirit and scope disclosed herein; however, the scope of patent protection of this invention shall still be determined by the scope defined in the appended claims.

Claims

1. A method for predicting complex downhole operating conditions, characterized in that, include: Real-time acquisition and preprocessing of drilling engineering parameter data at different depths of the target well; The preprocessed real-time drilling engineering parameter data is compared with reference data corresponding to at least one complex operating condition event in the complex operating condition database to calculate the probability of occurrence of the at least one complex operating condition event. The complex operating condition database includes reference data for at least one complex operating condition event, and the reference data is dynamic change data of several relevant drilling engineering parameters when the complex operating condition event occurs.

2. The method according to claim 1, characterized in that, The complex operating condition database is constructed based on historical drilling engineering parameter data, and is constructed through the following steps: Real-time data of drilling parameters of all drilled wells in the same work area as the target well at different depths are obtained and processed. Identify at least one complex operating condition event and extract drilling engineering parameters associated with each complex operating condition event; Extract dynamic change data of all relevant drilling engineering parameters within a specified time period before and after each complex working condition event; The complex operating condition database is formed by establishing a mapping relationship between complex operating condition events and the dynamic changes of all relevant drilling engineering parameters corresponding to the events.

3. The method according to claim 2, characterized in that, The data processing includes missing value filling, curve noise smoothing, and normalization. Specifically, the step of filling historical real-time data of drilling engineering parameters includes: Based on historical drilling engineering parameter data at different depths, regression analysis was used to fill in the missing data in the historical drilling engineering parameter data.

4. The method according to claim 3, characterized in that, Determine the well depth where the data to be filled is located, and determine the depth range to be processed; The parameter types of the missing data are used as target parameter items, and the measured data of the target parameter items at different well depths within the depth range to be processed are extracted. Based on the measured data of the target parameters at different well depths, a regression equation is established using the least squares method. Extract the data corresponding to the well depth of the data to be filled from the regression equation, and use this data as the filling value.

5. The method according to any one of claims 1 to 4, characterized in that, The preprocessing includes curve noise smoothing and normalization. The step of comparing the preprocessed real-time drilling engineering parameter data with reference data corresponding to at least one complex operating condition event in the complex operating condition database, and calculating the probability of occurrence of the at least one complex operating condition event, includes: Calculate the correlation between the real-time measurement curves of several relevant drilling engineering parameters corresponding to at least one complex working condition event and the historical dynamic measurement curves in the reference data, and obtain the corresponding correlation coefficients; Based on the correlation coefficients of several relevant drilling engineering parameters corresponding to at least one complex working condition event, the probability of occurrence of the current at least one complex working condition event is calculated using the influence weight of each relevant drilling engineering parameter in its respective complex working condition event.

6. The method according to claim 5, characterized in that, The correlation coefficient is calculated using the Pearson similarity coefficient method, wherein the correlation coefficient is obtained using the following expression: Where r represents the correlation coefficient, x i y represents the real-time measurement data of the relevant drilling engineering parameters corresponding to the i-th well depth. i This represents the historical measurement data of the relevant drilling engineering parameters corresponding to the i-th well depth, and n represents the total number of data points within the time period corresponding to the reference data segment.

7. The method according to claim 5 or 6, characterized in that, The probability of occurrence is calculated using the following expression: Where P represents the probability of occurrence, m represents the number of relevant drilling engineering parameters in the complex operating condition event, and r i w represents the similarity coefficient of the i-th relevant drilling engineering parameter. i This represents the influence weight of the i-th relevant drilling engineering parameter.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: When the probability of occurrence of at least one complex operating condition event exceeds a preset threshold, an early warning is issued for the corresponding complex operating condition event.

9. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method as described in any one of claims 1 to 8.

10. A system for predicting the probability of drilling conditions, characterized in that, include: The data acquisition module is configured to collect drilling engineering parameter data at different depths of the target well in real time and preprocess it. The probability prediction module is configured to compare the preprocessed real-time drilling engineering parameter data with reference data corresponding to at least one complex working condition event in the complex working condition database, and calculate the probability of occurrence of the at least one complex working condition event. The complex working condition database includes reference data for at least one complex working condition event, and the reference data is dynamic change data of several relevant drilling engineering parameters when the complex working condition event occurs.

Images