Drill tool failure judgment method and device, storage medium and electronic equipment

Abstract

The present application relates to the technical field of drilling engineering, and particularly relates to a drilling tool failure judgment method and device, a storage medium and an electronic device, the method comprising: S100, collecting a group of drilling data for a first time length, wherein the drilling data comprises pump pressure and torque; S200, performing regression analysis on the current group of drilling data to obtain a regression equation of the current group of drilling data; S400, if the slope of the regression equation of the current group of drilling data meets a preset condition, and the slope of the regression equation of N groups of continuous drilling data meets the preset condition, determining that the drilling tool fails; the drilling tool failure can be timely warned and judged with less data.

Description

Technical Field

[0001] This invention relates to the field of drilling engineering technology, and in particular to a method, device, storage medium, and electronic equipment for determining drilling tool failure. Background Technology

[0002] For a long time, drilling safety has been one of the most important issues in the field of oil and gas drilling engineering. According to statistics, the time spent dealing with accidents during drilling accounts for about 6% to 8% of the drilling operation time. Among them, the problem of drill string failure is particularly prominent.

[0003] However, current intelligent prediction systems have the following problems: first, they require a large amount of data as a foundation; second, they require high-frequency data acquisition instruments, which are generally not available in existing logging technologies.

[0004] There is an urgent need in this field for a scheme to quantitatively determine drill string failure based on current data acquisition systems, a scheme that can quantitatively determine drill string failure without requiring a large amount of data. Summary of the Invention

[0005] This invention provides a method, apparatus, storage medium, and electronic device for determining drill string failure, which solves the technical problem of difficulty in quantitatively determining drill string failure based on a small amount of data.

[0006] In a first aspect, the present invention provides a method for determining drill string failure, comprising:

[0007] S100, collect a set of drilling data for the first duration, including pump pressure and torque;

[0008] S200, Regression analysis of the current group of drilling data yields the regression equation for the current group of drilling data;

[0009] S400: If the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition, the drill string is determined to be faulty.

[0010] In some embodiments, regression analysis includes linear regression analysis, and the regression equation includes a linear regression equation.

[0011] In some embodiments, before acquiring a set of drilling data for a first duration, the method further includes:

[0012] Obtain historical drilling datasets;

[0013] The historical drilling dataset is grouped according to the first time period to obtain multiple groups of historical drilling data;

[0014] Regression analysis was performed on the pump pressure data and torque data in each set of historical drilling data to obtain regression equations for multiple sets of pump pressure data and multiple sets of torque data.

[0015] By analyzing the slopes of the regression equations for multiple sets of pump pressure data and multiple sets of torque data, it was determined that when the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, it indicates that the drilling tool has failed.

[0016] In some embodiments, the preset condition includes: the slope of the linear regression equation for pump pressure data has the opposite sign to the slope of the linear regression equation for torque data.

[0017] In some embodiments, the preset conditions include: the slope of the linear regression equation for pump pressure data is negative, and the slope of the linear regression equation for torque data is positive.

[0018] In some embodiments, before step S400, the method further includes: S300, determining whether the slope of the regression equation of the current group of drilling data meets a preset condition, including:

[0019] Monitor whether the slope of the linear regression equation for pump pressure data changes from positive to negative within the first time period;

[0020] When the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first time period, it is detected whether the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period.

[0021] If the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period, then the slope of the regression equation for the current group of drilling data meets the preset condition.

[0022] In some embodiments, if the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N-1 consecutive sets of drilling data meets the preset condition, then a set of drilling data for the first duration is collected.

[0023] When continuing to collect a set of drilling data for the first duration, start collecting a set of drilling data for the first duration from the first drilling data in the set of drilling data where the slope of the regression equation in the (N-1)th set meets the preset conditions.

[0024] Secondly, the present invention provides a drill bit failure detection device, comprising:

[0025] The data acquisition module is used to acquire a set of drilling data for the first time period, including pump pressure and torque.

[0026] The data regression module is used to perform regression analysis on the current group of drilling data to obtain the regression equation for the current group of drilling data;

[0027] The failure determination module is used to determine that the drilling tool has failed if the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition.

[0028] In some embodiments, regression analysis includes linear regression analysis, and the regression equation includes a linear regression equation.

[0029] In some embodiments, before acquiring a set of drilling data for a first duration, the method further includes:

[0030] Obtain historical drilling datasets;

[0031] The historical drilling dataset is grouped according to the first time period to obtain multiple groups of historical drilling data;

[0032] Regression analysis was performed on the pump pressure data and torque data in each set of historical drilling data to obtain regression equations for multiple sets of pump pressure data and multiple sets of torque data.

[0033] By analyzing the slopes of the regression equations for multiple sets of pump pressure data and multiple sets of torque data, it was determined that when the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, it indicates that the drilling tool has failed.

[0034] In some embodiments, the preset condition includes: the slope of the linear regression equation for pump pressure data has the opposite sign to the slope of the linear regression equation for torque data.

[0035] In some embodiments, the preset conditions include: the slope of the linear regression equation for pump pressure data is negative, and the slope of the linear regression equation for torque data is positive.

[0036] In some embodiments, before step S400, the method further includes: S300, determining whether the slope of the regression equation of the current group of drilling data meets a preset condition, including:

[0037] Monitor whether the slope of the linear regression equation for pump pressure data changes from positive to negative within the first time period;

[0038] When the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first time period, it is detected whether the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period.

[0039] If the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period, then the slope of the regression equation for the current group of drilling data meets the preset condition.

[0040] In some embodiments, if the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N-1 consecutive sets of drilling data meets the preset condition, then a set of drilling data for the first duration is collected.

[0041] When continuing to collect a set of drilling data for the first duration, start collecting a set of drilling data for the first duration from the first drilling data in the set of drilling data where the slope of the regression equation in the (N-1)th set meets the preset conditions.

[0042] Thirdly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method of the first aspect.

[0043] Fourthly, the present invention provides an electronic device including a processor and a memory, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the method of the first aspect.

[0044] The technical solution of the present invention involves collecting a set of drilling data for a first duration, wherein the drilling data includes pump pressure and torque; performing regression analysis on the current set of drilling data to obtain the regression equation of the current set of drilling data; if the slope of the regression equation of the current set of drilling data meets a preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition, the drill string is determined to be faulty; thus, timely warning and judgment of drill string failure can be made with less data. Attached Figure Description

[0045] The invention will now be described in more detail with reference to embodiments and the accompanying drawings:

[0046] Figure 1 This is a schematic diagram of a drill bit failure judgment method provided in an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of a drill bit failure judgment method provided in an embodiment of the present invention;

[0048] Figure 3 This is a schematic diagram of pump pressure and torque during normal drilling provided in an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram illustrating the pump pressure and torque changes when the drill bit fails, as provided in an embodiment of the present invention.

[0050] Figure 5 This is a schematic diagram of the slope change of the normal pump pressure regression equation provided in an embodiment of the present invention;

[0051] Figure 6 This is a schematic diagram of the slope change of the normal torque regression equation provided in an embodiment of the present invention;

[0052] Figure 7This is a schematic diagram of the slope change of the abnormal pump pressure regression equation provided in an embodiment of the present invention;

[0053] Figure 8 This is a schematic diagram illustrating the slope change of the abnormal torque regression equation provided in an embodiment of the present invention;

[0054] Figure 9 This is a schematic diagram of the regression equation for pump pressure changes from 0 to 10 minutes provided in an embodiment of the present invention;

[0055] Figure 10 This is a schematic diagram of the 0-10 min torque variation regression equation provided in an embodiment of the present invention;

[0056] Figure 11 This is a schematic diagram of the regression equation for pump pressure changes over 10-20 minutes provided in an embodiment of the present invention.

[0057] Figure 12 This is a schematic diagram of the regression equation for torque variation over 10-20 minutes provided in an embodiment of the present invention.

[0058] Figure 13 This is a schematic diagram of the regression equation for pump pressure changes over 20-30 minutes provided in an embodiment of the present invention.

[0059] Figure 14 This is a schematic diagram of the regression equation for torque variation over 20-30 minutes provided in an embodiment of the present invention;

[0060] Figure 15 This is a schematic diagram of the regression equation for pump pressure change over 30-40 minutes provided in an embodiment of the present invention.

[0061] Figure 16 This is a schematic diagram of the torque change regression equation for 30-40 min provided in an embodiment of the present invention;

[0062] Figure 17 A schematic diagram of drilling tool failure in a well in Northwest China, which is an application example of the present invention;

[0063] Figure 18 This is a schematic diagram of a drill bit failure detection device provided in an embodiment of the present invention.

[0064] In the accompanying drawings, the same parts are referred to by the same reference numerals, and the drawings are not drawn to scale. Detailed Implementation

[0065] To enable those skilled in the art to better understand the present invention and to fully understand and implement the process of how the present invention uses technical means to solve technical problems and achieve corresponding technical effects, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. The embodiments of the present invention and the various features therein can be combined with each other without conflict, and the resulting technical solutions are all within the protection scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0066] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0067] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0068] This invention belongs to the field of oil and gas drilling engineering, and specifically relates to a method for judging drill string failure based on linear regression analysis.

[0069] For a long time, drilling safety has been one of the most important issues in the field of oil and gas drilling engineering. According to statistics, the time spent dealing with accidents during drilling accounts for about 6% to 8% of the drilling operation time. Among them, the problem of drill string failure is particularly prominent. Drill string failure is divided into two types: leakage and breakage. Generally, breakage occurs after the drill string has suffered severe leakage. The reason is that the small leakage was not detected by the field engineer in time. Under high pump pressure conditions, the small leakage gradually developed into a large leakage, eventually leading to drill string breakage and causing serious downhole accidents.

[0070] In some leading drilling failure prediction technologies, the application of efficient drilling-while-drilling (WDD) systems and intelligent systems has effectively shortened failure time. In other technologies, the on-site assessment of drill string failures primarily relies on manual qualitative judgment. This requires extensive field experience to monitor and track changes and trends in relevant parameters to make a judgment. However, the application of intelligent prediction systems faces the following problems: firstly, it requires a large amount of data as a foundation; secondly, it requires high-frequency data acquisition instruments, which are generally not available in logging systems used in related technologies. Based on these issues, in-depth research has not yet been conducted on quantitative methods for assessing drill string failures. There is an urgent need for a method that, based on current data acquisition systems, can quantitatively assess drill string failures without requiring a large amount of data.

[0071] Example 1

[0072] Figure 1 This is a schematic diagram of a drill string failure judgment method provided by an embodiment of the present invention. Figure 1 As shown, the method includes steps S100, S200 and S400.

[0073] S100, collect a set of drilling data for the first duration, including pump pressure and torque;

[0074] S200, Regression analysis of the current group of drilling data yields the regression equation for the current group of drilling data;

[0075] S400: If the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition, the drill string is determined to be faulty.

[0076] This embodiment collects a set of drilling data for a first duration and performs regression analysis to obtain the slope of the regression equation for the current set of drilling data. If the slope of the regression equation for the current set of drilling data meets the preset conditions, and the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, the drill string is determined to be faulty. This allows for timely warning and judgment of drill string failure with less data.

[0077] The solution in this embodiment can reduce the occurrence of downhole drill string breakage, increase production time, reduce misjudgments or omissions caused by reliance on human experience, and create a certain methodological foundation for intelligent drilling fault early warning.

[0078] Example 2

[0079] Based on the above embodiments, before collecting a set of drilling data for the first duration, the method further includes:

[0080] Obtain historical drilling datasets;

[0081] The historical drilling dataset is grouped according to the first time period to obtain multiple groups of historical drilling data;

[0082] Regression analysis was performed on the pump pressure data and torque data in each set of historical drilling data to obtain regression equations for multiple sets of pump pressure data and multiple sets of torque data.

[0083] By analyzing the slopes of the regression equations for multiple sets of pump pressure data and multiple sets of torque data, it was determined that when the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, it indicates that the drilling tool has failed.

[0084] Based on the current data acquisition system, this embodiment performs linear regression analysis on relevant parameters to discover the parameter change characteristics of drill string failure, and makes timely and quantitative judgments on the occurrence of drill string failure, thereby guiding on-site construction.

[0085] In some implementations, the regression analysis includes linear regression analysis, and the regression equation includes a linear regression equation.

[0086] In some implementations, the preset condition includes that the slope of the linear regression equation for pump pressure data has the opposite sign to the slope of the linear regression equation for torque data.

[0087] In some implementations, the preset conditions include: the slope of the linear regression equation for pump pressure data is negative, and the slope of the linear regression equation for torque data is positive.

[0088] In this embodiment, by grouping historical drilling datasets and performing linear regression analysis on each group, it was found that when the slope of the regression equation for three consecutive groups of drilling data meets a preset condition, it indicates drill string failure. The preset condition, for example, is that the slope of the linear regression equation for pump pressure data is negative, and the slope of the linear regression equation for torque data is positive. Therefore, based on the above findings of this embodiment, drill string failure can be determined or warned of with relatively little data.

[0089] Figure 2 This is a schematic diagram of a drill string failure judgment method provided by an embodiment of the present invention. Figure 2 As shown, this embodiment includes the following steps:

[0090] (1) The pump pressure and torque data collected on site were directly subjected to linear regression analysis and plotted into a graph. The normal drilling data graph was compared with the abnormal data graph to preliminarily find the failure characteristics of the drilling tool.

[0091] (2) Divide the pump pressure and torque data collected on site into time groups, with the first time period, for example, 10 minutes, as a group of data, and arrange them naturally according to time.

[0092] (3) Based on the linear regression analysis method, linear regression analysis was performed on 60 data points of pump pressure and torque every 10 minutes to obtain the linear regression equations of the changing trends of normal and abnormal pump pressure and torque, and the slope values ​​were plotted as graphs.

[0093] (4) Based on the above analysis and the judgment method based on field experience, the main characteristic parameters of drill string failure were identified as the decrease in pump pressure and the increase in torque within the same time period. That is, the slope of the pump pressure regression equation is negative, and the torque regression equation is positive, which are the characteristic parameters A and B of the changing trends.

[0094] (5) Plot the trend characteristic parameters A and B in a table. When A is positive, it indicates that the pump pressure increases. When B is positive, it indicates that the torque increases. When A is negative, it indicates that the pump pressure decreases. When B is negative, it indicates that the torque decreases.

[0095] (6) Based on the changes in normal drilling characteristic parameters, a quantitative judgment method for drill string failure is obtained. That is, when N consecutive (e.g., 3) A values ​​are negative and N consecutive (e.g., 3) B values ​​are positive, the drill string is judged to be in failure.

[0096] In a specific example, the collected pump pressure and torque data during normal drilling are plotted to obtain... Figure 3 The pump pressure and torque data at the point of drill string failure were plotted to obtain... Figure 4 Comparative analysis clearly shows that the distribution trends of normal pump pressure and torque are parallel, while the distribution of pump pressure and torque in drill string failures exhibits a downward trend to the right at the end of the regression trend line.

[0097] The collected pump pressure and torque data were divided into 10-minute groups. Linear regression analysis was performed on each group to obtain the linear regression equation for each data point. Each linear regression equation for pump pressure and torque corresponds to a slope value, which is the characteristic value reflecting the trend of change. The slopes of the normal pump pressure and torque regression equations were plotted as follows: Figure 5 and Figure 6 Focusing on the peak values ​​corresponding to torque above 0, the slopes of the regression equations for pressure within the corresponding time intervals all show an upward trend. For pump pressure and torque curves indicating drill string failure, see... Figure 7 and Figure 8When torque shows an upward trend, pump pressure decreases. Based on comprehensive data analysis and field experience, the initial criterion for judging drill string leakage is a decrease in pump pressure and an increase in torque. However, due to the complex conditions in actual downhole drilling, through calculation of the characteristic values ​​of normal pump pressure and torque slope under actual drilling conditions over 24 hours (see data groups 11 / 81 / 112 / 120 / 129 in Table 1), irregular situations of negative pump pressure and positive torque occur, but these do not occur three or more times consecutively. Based on this characteristic, we ultimately conclude that the criterion for judging drill string failure is: three or more consecutive occurrences of negative pump pressure and positive torque.

[0098] Table 1 Characteristic values ​​of normal pump pressure and torque trend changes

[0099]

[0100]

[0101] Finally, based on the obtained drill string failure judgment criteria, linear regression analysis was performed on the target data of pump pressure and torque every 10 minutes to obtain the characteristic values ​​of pump pressure and torque changes. If three consecutive sets of pump pressure characteristic values ​​are negative and torque characteristic values ​​are positive, then drill string failure is determined to have occurred downhole. Therefore, three consecutive sets of negative pump pressure characteristic values ​​and positive torque characteristic values ​​are used as the judgment criterion for drill string failure.

[0102] The technical solution of this embodiment will be illustrated below through an application example.

[0103] This embodiment performs linear regression analysis on normal and abnormal pump pressure and torque data. Combined with field experience, the quantitative real-time judgment criterion for drill string failure is the occurrence of three consecutive negative pump pressure slopes and positive torque slopes. Thus, a drill string failure judgment method based on linear regression analysis is obtained.

[0104] An analytical test was conducted on a well in Northwest China, accurately predicting drill string failure and verifying the effectiveness of the method. This embodiment requires little data, has high accuracy, and allows for quantitative judgment. This embodiment can effectively reduce the risk of downhole drill string breakage, shorten the processing time for complex situations, and provide a methodological foundation for intelligent drilling anomaly prediction.

[0105] Based on the criteria for judging drill string failure, drilling string failure was assessed using logging data from a well in the Northwest work area. Linear regression analysis was performed in 10-minute intervals. First, a qualitative method was used to assess the data: an increase in pump pressure and torque within 0-10 minutes indicated no possibility of drill string failure. (See...) Figure 9 and Figure 10 If the pump pressure decreases and the torque increases within 10-20 minutes, there is a possibility of drill string failure. See [link / reference]. Figure 11 and Figure 12The pump pressure decreases and the torque increases after 20-30 minutes. Figure 13 and Figure 14 The pump pressure decreases and the torque increases after 30-40 minutes. Figure 15 and Figure 16 Three consecutive sets of pump pressure decreases and torque increases were observed. A quantitative method was then used to determine the failure. The slope of the regression equation for the trend within 0–40 minutes is shown in the first three sets of data in Table 2. The occurrence of three consecutive sets of negative pump pressure slopes and positive torque values ​​indicated a drill string failure. In the actual field situation, the drill string broke during retrieval. The drill string failure diagram is shown below. Figure 17 This indicates that the prediction method is effective.

[0106] Table 2. Characteristic values ​​of pump pressure and torque slope of a well in Northwest China

[0107] 0 [0.00239381279746166] [0.0059816393442622917] 1 [-0.00120703331570585] [0.0056763617133791505] 2 [-0.0027916446324695964] [0.0059847911158117412] 3 [-0.002522792173452708] [0.00508725542041249]

[0108] (1) In this embodiment, in order to address the problem of lack of real-time judgment basis for drill bit failure, the pump pressure and torque are grouped and all data are linearly regressed to obtain the slope of the regression equation of each group of pump pressure and torque and plot it as a curve. Combined with actual field experience, the judgment basis for drill bit failure is that the pump pressure slope is negative and the torque slope is positive within the same time period.

[0109] (2) In this embodiment, in order to address the problem of lack of real-time quantitative judgment of drilling tool failure, linear regression analysis is performed on the trend of pump pressure and torque changes to obtain a table of regression equation slope values. Based on the fact that the pump pressure slope is negative and the torque slope is positive within the same time period, timely and quantitative judgment is made on whether the downhole drilling tool has failed.

[0110] (3) The timely judgment of drilling tool failure in this embodiment can effectively reduce the risk of downhole drilling tool breakage, reduce the processing time of complex situations, and improve production efficiency. In addition, it also creates a certain methodological basis for intelligent drilling anomaly prediction.

[0111] Example 3

[0112] Based on the above embodiment, before step S400, the method further includes: S300, determining whether the slope of the regression equation of the current group of drilling data meets a preset condition, including:

[0113] Monitor whether the slope of the linear regression equation for pump pressure data changes from positive to negative within the first time period;

[0114] When the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first time period, it is detected whether the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period.

[0115] If the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period, then the slope of the regression equation for the current group of drilling data meets the preset condition.

[0116] Based on the above embodiments, if the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N-1 consecutive sets of drilling data meets the preset condition, then continue to collect a set of drilling data for the first duration.

[0117] When continuing to collect a set of drilling data for the first duration, start collecting a set of drilling data for the first duration from the first drilling data in the set of drilling data where the slope of the regression equation in the (N-1)th set meets the preset conditions.

[0118] In this embodiment, the first duration is, for example, 10 minutes, 20 minutes, 30 minutes, etc. In this embodiment, the first duration is described as 10 minutes; the value of N is, for example, an integer value such as 3, 4, 5, etc. In this embodiment, the value of N is described as 3.

[0119] In this embodiment, if the slope of the linear regression equation for the pump pressure data does not change from positive to negative within the first time period, the slope is continuously monitored at a frequency of, for example, once per minute. If the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first 10 minutes (e.g., 13:02 to 13:12), and the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period (13:02 to 13:12), then the slope of the regression equation for the current drilling data group meets a preset condition. The current time (e.g., 13:12) can be used as the drill string failure warning time, and a primary warning can be initiated, with pump pressure and torque data monitored at a higher frequency (e.g., twice per minute). It is understood that the frequency in this embodiment can also be a fixed 1 time per minute, i.e., without frequency adjustment.

[0120] Starting from the drill string failure warning time (e.g., 13:12), monitor pump pressure and torque data. When the first duration of 10 minutes is reached again, calculate whether the slope of the linear regression equation of the pump pressure and torque data within the first duration (13:12 to 13:22) from the drill string failure warning time (e.g., 13:12) meets the preset conditions.

[0121] Specifically, during the first 10 minutes of monitoring pump pressure and torque data starting from the drill string failure warning time (e.g., 13:12), no linear regression is performed on the pump pressure and torque data to reduce the amount of computation and ensure that the computational performance of data acquisition at a high frequency is not affected.

[0122] Specifically, after monitoring pump pressure and torque data for 10 minutes from the moment of drill string failure warning, an XOR method is used to determine whether the slopes of the linear regression equations for the pump pressure and torque data meet preset conditions. For example, in computer storage, the first bit of the data represents the sign; therefore, the sign values ​​of the two slopes are XORed. If the output is 1, it indicates that the two slopes have different signs. Thus, warnings can be issued simply by comparing the XOR values ​​of the two slopes, improving the speed of warnings.

[0123] If the slope of the linear regression equation for the pump pressure and torque data within the first time period (13:12 to 13:22) starting from the drill string failure warning time (e.g., 13:12) meets the preset conditions, then the intermediate warning is activated; if the slope of the linear regression equation for the pump pressure and torque data within the first time period (13:12 to 13:22) starting from the drill string failure warning time (e.g., 13:12) does not meet the preset conditions, then the warning is deactivated.

[0124] After entering the intermediate warning stage, a set of drilling data for the first 10 minutes is collected. During this collection, the first set of drilling data is collected starting from the first drilling data in the second set of drilling data where the slope of the regression equation meets a preset condition. For example, the first drilling data is the data from 13:17. That is, after entering the intermediate warning stage, data from 13:22 to 13:27 is collected and spliced ​​with the data from 13:17 to 13:22 to form a first 10-minute set of drilling data. This data is used to determine whether the slope of the linear regression equation for pump pressure and torque data meets the preset condition. If the slope of the linear regression equation for pump pressure and torque data meets the preset condition, the drill string is determined to have failed. It is understood that in this embodiment, data can be collected from any time between 13:12 and 13:22, not just the data from 13:17. For example, data can be collected from 13:16, in which case the data collected from 13:16 to 13:22 is concatenated with the data collected from 13:22 to 13:26; data can also be collected from 13:18, in which case the data collected from 13:18 to 13:22 is concatenated with the data collected from 13:22 to 13:28.

[0125] Because this embodiment continuously monitors the slopes of the linear regression equations for pump pressure data and torque data using a sliding time window monitoring method, it can initiate a drill string failure warning within, for example, one minute after the slope reaches a preset condition. This reduces the judgment time for the first set of data from a previous duration (e.g., 10 minutes) to, for example, one minute. Furthermore, after entering the intermediate warning stage, this embodiment predicts whether the Nth set of data meets preset conditions by splicing a portion of the (N-1)th set of data with newly monitored data. This reduces the judgment time for the Nth set of data from a previous duration (e.g., 10 minutes) to, for example, 5 minutes (depending on how much data from the (N-1)th set of data is used). Therefore, this embodiment not only enables drill string failure judgment with less data but also significantly shortens the judgment time.

[0126] Example 4

[0127] Figure 18 This is a schematic diagram of a drill bit failure detection device provided in an embodiment of the present invention. Figure 18 As shown, based on the above embodiments, this embodiment provides a drill bit failure judgment device, including:

[0128] The data acquisition module is used to acquire a set of drilling data for the first time period, including pump pressure and torque.

[0129] The data regression module is used to perform regression analysis on the current group of drilling data to obtain the regression equation for the current group of drilling data;

[0130] The failure determination module is used to determine that the drilling tool has failed if the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition.

[0131] The drill string failure detection device of this embodiment collects a set of drilling data for a first duration through the data acquisition module 100, wherein the drilling data includes pump pressure and torque; the data regression module 200 performs regression analysis on the current set of drilling data to obtain the regression equation of the current set of drilling data; if the slope of the regression equation of the current set of drilling data meets a preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition, the failure detection module 400 determines that the drill string has failed; it can provide timely warning and judgment of drill string failure with less data.

[0132] In some implementations, the regression analysis includes linear regression analysis, and the regression equation includes a linear regression equation.

[0133] In some implementations, the method further includes, prior to acquiring a set of drilling data for a first duration:

[0134] Obtain historical drilling datasets;

[0135] The historical drilling dataset is grouped according to the first time period to obtain multiple groups of historical drilling data;

[0136] Regression analysis was performed on the pump pressure data and torque data in each set of historical drilling data to obtain regression equations for multiple sets of pump pressure data and multiple sets of torque data.

[0137] By analyzing the slopes of the regression equations for multiple sets of pump pressure data and multiple sets of torque data, it was determined that when the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, it indicates that the drilling tool has failed.

[0138] In some implementations, the preset condition includes that the slope of the linear regression equation for pump pressure data has the opposite sign to the slope of the linear regression equation for torque data.

[0139] In some implementations, the preset conditions include: the slope of the linear regression equation for pump pressure data is negative, and the slope of the linear regression equation for torque data is positive.

[0140] In some implementations, before step S400, the method further includes: S300, determining whether the slope of the regression equation for the current group of drilling data meets a preset condition, including:

[0141] Monitor whether the slope of the linear regression equation for pump pressure data changes from positive to negative within the first time period;

[0142] When the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first time period, it is detected whether the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period.

[0143] If the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period, then the slope of the regression equation for the current group of drilling data meets the preset condition.

[0144] In some implementations, if the slope of the regression equation of the current set of drilling data meets a preset condition, and the slope of the regression equation of N-1 consecutive sets of drilling data meets the preset condition, then a set of drilling data for the first duration is collected.

[0145] When continuing to collect a set of drilling data for the first duration, start collecting a set of drilling data for the first duration from the first drilling data in the set of drilling data where the slope of the regression equation in the (N-1)th set meets the preset conditions.

[0146] Example 5

[0147] Based on the above embodiments, this embodiment also provides a computer-readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, server, etc., which stores a computer program. When the computer program is executed, it can implement the drill string failure judgment method in the above embodiments, including:

[0148] S100, collect a set of drilling data for the first duration, including pump pressure and torque;

[0149] S200, Regression analysis of the current group of drilling data yields the regression equation for the current group of drilling data;

[0150] S400: If the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition, the drill string is determined to be faulty.

[0151] In some implementations, the regression analysis includes linear regression analysis, and the regression equation includes a linear regression equation.

[0152] In some implementations, the method further includes, prior to acquiring a set of drilling data for a first duration:

[0153] Obtain historical drilling datasets;

[0154] The historical drilling dataset is grouped according to the first time period to obtain multiple groups of historical drilling data;

[0155] Regression analysis was performed on the pump pressure data and torque data in each set of historical drilling data to obtain regression equations for multiple sets of pump pressure data and multiple sets of torque data.

[0156] By analyzing the slopes of the regression equations for multiple sets of pump pressure data and multiple sets of torque data, it was determined that when the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, it indicates that the drilling tool has failed.

[0157] In some implementations, the preset condition includes that the slope of the linear regression equation for pump pressure data has the opposite sign to the slope of the linear regression equation for torque data.

[0158] In some implementations, the preset conditions include: the slope of the linear regression equation for pump pressure data is negative, and the slope of the linear regression equation for torque data is positive.

[0159] In some implementations, before step S400, the method further includes: S300, determining whether the slope of the regression equation for the current group of drilling data meets a preset condition, including:

[0160] Monitor whether the slope of the linear regression equation for pump pressure data changes from positive to negative within the first time period;

[0161] When the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first time period, it is detected whether the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period.

[0162] If the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period, then the slope of the regression equation for the current group of drilling data meets the preset condition.

[0163] In some implementations, if the slope of the regression equation of the current set of drilling data meets a preset condition, and the slope of the regression equation of N-1 consecutive sets of drilling data meets the preset condition, then a set of drilling data for the first duration is collected.

[0164] When continuing to collect a set of drilling data for the first duration, start collecting a set of drilling data for the first duration from the first drilling data in the set of drilling data where the slope of the regression equation in the (N-1)th set meets the preset conditions.

[0165] This embodiment collects a set of drilling data for a first duration and performs regression analysis to obtain the slope of the regression equation for the current set of drilling data. If the slope of the regression equation for the current set of drilling data meets the preset conditions, and the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, the drill string is determined to be faulty. This allows for timely warning and judgment of drill string failure with less data.

[0166] Based on the current data acquisition system, this embodiment performs linear regression analysis on relevant parameters to discover the parameter change characteristics of drill string failure, and makes timely and quantitative judgments on the occurrence of drill string failure, thereby guiding on-site construction.

[0167] The solution in this embodiment can reduce the occurrence of downhole drill string breakage, increase production time, reduce misjudgments or omissions caused by reliance on human experience, and create a certain methodological foundation for intelligent drilling fault early warning.

[0168] Example 6

[0169] Based on the above embodiments, this application provides an electronic device, which may be a mobile phone, computer, or tablet computer, or drilling equipment, including a memory and a processor. The memory stores a calculator program, which, when executed by the processor, implements the drill string failure judgment method as described in the above embodiments, including:

[0170] S100, collect a set of drilling data for the first duration, including pump pressure and torque;

[0171] S200, Regression analysis of the current group of drilling data yields the regression equation for the current group of drilling data;

[0172] S400: If the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition, the drill string is determined to be faulty.

[0173] In some implementations, the regression analysis includes linear regression analysis, and the regression equation includes a linear regression equation.

[0174] In some implementations, the method further includes, prior to acquiring a set of drilling data for a first duration:

[0175] Obtain historical drilling datasets;

[0176] The historical drilling dataset is grouped according to the first time period to obtain multiple groups of historical drilling data;

[0177] Regression analysis was performed on the pump pressure data and torque data in each set of historical drilling data to obtain regression equations for multiple sets of pump pressure data and multiple sets of torque data.

[0178] By analyzing the slopes of the regression equations for multiple sets of pump pressure data and multiple sets of torque data, it was determined that when the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, it indicates that the drilling tool has failed.

[0179] In some implementations, the preset condition includes that the slope of the linear regression equation for pump pressure data has the opposite sign to the slope of the linear regression equation for torque data.

[0180] In some implementations, the preset conditions include: the slope of the linear regression equation for pump pressure data is negative, and the slope of the linear regression equation for torque data is positive.

[0181] In some implementations, before step S400, the method further includes: S300, determining whether the slope of the regression equation for the current group of drilling data meets a preset condition, including:

[0182] Monitor whether the slope of the linear regression equation for pump pressure data changes from positive to negative within the first time period;

[0183] When the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first time period, it is detected whether the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period.

[0184] If the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period, then the slope of the regression equation for the current group of drilling data meets the preset condition.

[0185] In some implementations, if the slope of the regression equation of the current set of drilling data meets a preset condition, and the slope of the regression equation of N-1 consecutive sets of drilling data meets the preset condition, then a set of drilling data for the first duration is collected.

[0186] When continuing to collect a set of drilling data for the first duration, start collecting a set of drilling data for the first duration from the first drilling data in the set of drilling data where the slope of the regression equation in the (N-1)th set meets the preset conditions.

[0187] This embodiment collects a set of drilling data for a first duration and performs regression analysis to obtain the slope of the regression equation for the current set of drilling data. If the slope of the regression equation for the current set of drilling data meets the preset conditions, and the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, the drill string is determined to be faulty. This allows for timely warning and judgment of drill string failure with less data.

[0188] Based on the current data acquisition system, this embodiment performs linear regression analysis on relevant parameters to discover the parameter change characteristics of drill string failure, and makes timely and quantitative judgments on the occurrence of drill string failure, thereby guiding on-site construction.

[0189] The solution in this embodiment can reduce the occurrence of downhole drill string breakage, increase production time, reduce misjudgments or omissions caused by reliance on human experience, and create a certain methodological foundation for intelligent drilling fault early warning.

[0190] It is understood that electronic devices may also include multimedia components, input / output (I / O) interfaces, and communication components.

[0191] The processor is used to execute all or part of the steps in the drill string failure determination method as described in the above embodiments. The memory is used to store various types of data, which may include, for example, instructions for any application or method in the electronic device, as well as application-related data.

[0192] The processor can be implemented as an Application Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), controller, microcontroller, microprocessor, or other electronic components, and is used to execute all or part of the steps in the drill string failure judgment method in the above embodiments.

[0193] Memory can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0194] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0195] It should be noted that, in this invention, 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 a process, method, article, or apparatus. Without further limitation, an element limited 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.

[0196] While the embodiments disclosed in this invention are as described above, the above content is merely for the purpose of facilitating understanding of this 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 in this invention; 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 determining drill string failure, characterized in that, include: S100, Collect a set of drilling data for a first duration, wherein the drilling data includes pump pressure and torque; S200, Regression analysis of the current group of drilling data yields the regression equation for the current group of drilling data; S400, if the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition, the drill string is determined to be faulty. The regression analysis includes linear regression analysis, and the regression equation includes a linear regression equation. Prior to acquiring a set of drilling data for the first duration, the method further includes: Obtain historical drilling datasets; The historical drilling dataset is grouped by a first time period to obtain multiple groups of historical drilling data; Regression analysis was performed on the pump pressure data and torque data in each set of historical drilling data to obtain regression equations for multiple sets of pump pressure data and multiple sets of torque data. By analyzing the slopes of the regression equations for multiple sets of pump pressure data and multiple sets of torque data, it is determined that when the slope of the regression equation for N consecutive sets of drilling data meets the preset conditions, it characterizes the failure of the drilling tool. The preset conditions include: the slope of the linear regression equation for the pump pressure data and the slope of the linear regression equation for the torque data have opposite signs; The preset conditions include: the slope of the linear regression equation for the pump pressure data is negative, and the slope of the linear regression equation for the torque data is positive. Prior to step S400, the method further includes: S300, determining whether the slope of the regression equation for the current group of drilling data meets preset conditions, including: Monitor whether the slope of the linear regression equation for pump pressure data changes from positive to negative within the first time period; When the slope of the linear regression equation for the pump pressure data changes from positive to negative within the first time period, it is detected whether the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period. If the slope of the linear regression equation for the torque data does not change from positive to negative within the corresponding time period, then the slope of the regression equation for the current group of drilling data meets the preset condition.

2. The method according to claim 1, characterized in that, If the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N-1 consecutive sets of drilling data meets the preset condition, then continue to collect a set of drilling data for the first duration. When continuing to collect a set of drilling data for the first duration, start collecting a set of drilling data for the first duration from the first drilling data in the set of drilling data where the slope of the regression equation in the (N-1)th set meets the preset conditions.

3. A drill string failure judgment device based on the drill string failure judgment method according to any one of claims 1 to 2, characterized in that, include: The data acquisition module is used to acquire a set of drilling data for a first duration, wherein the drilling data includes pump pressure and torque; The data regression module is used to perform regression analysis on the current group of drilling data to obtain the regression equation for the current group of drilling data; The failure determination module is used to determine that the drilling tool has failed if the slope of the regression equation of the current set of drilling data meets the preset condition, and the slope of the regression equation of N consecutive sets of drilling data meets the preset condition.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 2.

5. An electronic device comprising a processor and a memory, characterized in that, The memory stores a computer program, and the processor executes the computer program to implement the method of any one of claims 1 to 2.

Images