Method for determining comprehensive friction coefficient of friction torque, early warning method and device

Abstract

The application provides a method and device for determining a comprehensive friction coefficient of a friction torque, and a method for early warning, wherein the method for determining comprises the following steps: acquiring a basic data set corresponding to each position in the well depth direction of a current well; segmenting the current well along the well depth direction based on the basic data set corresponding to each position, and determining a basic data set corresponding to each segment in the current well; determining a hyperparameter corresponding to each segment according to the basic data set corresponding to each segment in the current well; setting a multi-parameter nonlinear inversion algorithm corresponding to each segment according to the hyperparameter corresponding to each segment; and calculating a predicted value of the comprehensive friction coefficient corresponding to each segment by using the multi-parameter nonlinear inversion algorithm corresponding to each segment according to the basic data set corresponding to each segment in the current well. The application can improve the calculation accuracy of the comprehensive friction coefficient of the friction torque, and the friction torque can be further calculated by using the predicted value of the comprehensive friction coefficient, thereby improving the calculation accuracy of the friction torque.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of oil drilling, in particular, to a method for determining a comprehensive friction coefficient of friction torque, a pre-warning method and device. BACKGROUND

[0002] With the gradual expansion of the oil and gas field to deep, low, sea, non, and old, the difficulty of drilling and development is increasing, and the number of horizontal wells and extended reach wells is increasing. The complex well structure leads to very complex mechanical behavior of the downhole string: during tripping, interface rupture or downhole resistance caused by excessive tripping load or excessive running resistance; during sliding drilling, the excessive pressure caused by the phenomenon of supporting pressure leads to low drilling speed or even inability to drill; during rotary drilling, excessive torque leads to strength damage of the drill string; long-term rotation of the drill string leads to severe wear due to excessive friction; and excessive resistance during casing running makes it difficult to run the casing to the bottom. The existence of the above problems seriously restricts the efficiency and safety of downhole string operation. Friction torque has an impact on the tripping load and running resistance during tripping, the supporting pressure phenomenon during sliding drilling, and the torque during rotary drilling. Therefore, improving the calculation accuracy of friction torque to guide drilling optimization design and safe operation and meet the needs of fine construction due to the increasing difficulty of exploration and development has become an urgent problem to be solved.

[0003] The current widely used method for analyzing and calculating friction torque by drilling companies is as follows: according to whether the well wall of the downhole string is cased, the friction torque calculation profile is divided into a cased section and an open hole section, and the initial value of the comprehensive friction coefficient of the cased section and the open hole section is set by the engineer according to personal experience, and the friction torque profile is calculated using the value. Then, the calculation results are fitted combined with the field data, the comprehensive friction coefficient is adjusted, and the final coefficient of the region is obtained. This calculation method cannot fit the final coefficient when the initial value of the comprehensive friction coefficient is set with a large deviation, and therefore it has a strong dependence on the experience of the engineer in setting parameters; due to frequent fluctuations in field data, the "two-section" friction torque calculation results cannot be accurately fitted with the actual friction torque value, resulting in a lack of calculation results, only providing a trend reference, and cannot be used for drilling optimization design of complex structure wells.

[0004] Since friction torque is calculated by using the comprehensive friction coefficient, in order to improve the calculation accuracy of friction torque, it is necessary to further improve the calculation accuracy of the comprehensive friction coefficient. Therefore, there is an urgent need for a method for determining the comprehensive friction coefficient of friction torque, which can improve the calculation accuracy of the comprehensive friction coefficient of friction torque. SUMMARY

[0005] The purpose of the embodiments of the present application is to provide a method for determining the comprehensive friction coefficient of friction torque, a pre-warning method and device, to improve the calculation accuracy of the comprehensive friction coefficient of friction torque.

[0006] To achieve the above object, in one aspect, the embodiments herein provide a method for determining a comprehensive friction coefficient of a frictional torque, comprising:

[0007] obtaining a basic data set corresponding to each position in the well in the well depth direction;

[0008] segmenting the well in the well depth direction based on the basic data set corresponding to each position, and determining a basic data set corresponding to each segment in the well;

[0009] determining a hyperparameter corresponding to each segment according to the basic data set corresponding to each segment in the well;

[0010] setting a multi-parameter nonlinear inversion algorithm corresponding to each segment according to the hyperparameter corresponding to each segment;

[0011] calculating a predicted value of the comprehensive friction coefficient corresponding to each segment by using the multi-parameter nonlinear inversion algorithm corresponding to each segment according to the basic data set corresponding to each segment in the well.

[0012] Preferably, the segmenting the well in the well depth direction based on the basic data set corresponding to each position, and determining a basic data set corresponding to each segment in the well further comprises:

[0013] initially segmenting the well in the well depth direction based on the basic data set corresponding to each position;

[0014] refining the segmentation of each segment after the initial segmentation according to the basic data set corresponding to each position in each segment after the initial segmentation.

[0015] Preferably, the refining the segmentation of each segment after the initial segmentation according to the basic data set corresponding to each position in each segment after the initial segmentation further comprises:

[0016] determining a comprehensive value corresponding to each position by using the basic data in the basic data set corresponding to each position in each segment after the initial segmentation, and a weight corresponding to the basic data;

[0017] refining the segmentation of each segment after the initial segmentation according to the comprehensive value corresponding to each position in each segment after the initial segmentation, wherein the difference between the comprehensive values corresponding to any two positions in each segment after the refining is not more than a set difference value.

[0018] Preferably, the determining a hyperparameter corresponding to each segment according to the basic data set corresponding to each segment in the well further comprises:

[0019] selecting a selected segment from a plurality of known segments, wherein the basic data in the basic data set corresponding to the selected segment is the same as the basic data in the basic data set corresponding to the current segment in the well;

[0020] The hyperparameter corresponding to the selected well section is taken as the hyperparameter corresponding to the current section in the current well.

[0021] Preferably, the method further comprises:

[0022] According to the actual working condition data corresponding to the known well section, the real value of the comprehensive friction coefficient corresponding to the known well section is calculated;

[0023] According to the basic data set corresponding to the known well section, the hyperparameter corresponding to the known well section is determined;

[0024] According to the hyperparameter corresponding to the known well section, the multi-parameter nonlinear inversion algorithm corresponding to the known well section is set;

[0025] The multi-parameter nonlinear inversion algorithm corresponding to the known well section is used to calculate the predicted value of the comprehensive friction coefficient corresponding to the known well section;

[0026] According to the error between the predicted value and the real value of the comprehensive friction coefficient corresponding to the known well section, the hyperparameter of the basic data set corresponding to the known well section is corrected.

[0027] On the other hand, the embodiments of the present application provide a warning method, which applies the determination method of the comprehensive friction coefficient of the friction torque described in any one of the above, to calculate the predicted value of the comprehensive friction coefficient corresponding to the current well section, and the warning method further comprises:

[0028] According to the actual working condition data corresponding to the current well section, the real value of the comprehensive friction coefficient corresponding to the current well section is calculated;

[0029] If the difference between the real value and the predicted value of the comprehensive friction coefficient corresponding to the current well section is greater than a set threshold, then

[0030] A target well section is selected from a plurality of known well sections, wherein the basic data in the basic data set corresponding to the target well section is the same as the basic data in the basic data set corresponding to the current well section;

[0031] According to the actual working condition data of the current well section and the target well section, the predicted value of the comprehensive friction coefficient, and the real value of the comprehensive friction coefficient, the warning information of the current well section is determined.

[0032] On the other hand, the embodiments of the present application provide a determination device of the comprehensive friction coefficient of the friction torque, which comprises:

[0033] The acquisition module is configured to acquire a basic data set corresponding to each position in the current well in the well depth direction;

[0034] The segmentation module is configured to segment the current well along the well depth direction based on the basic data set corresponding to each position, and determine the basic data set corresponding to each section in the current well.

[0035] a determination module configured to determine a hyperparameter corresponding to each section according to a basic data set corresponding to the each section in the current well;

[0036] a setting module configured to set a multi-parameter nonlinear inversion algorithm corresponding to each section according to the hyperparameter corresponding to the each section;

[0037] a predicted value calculation module configured to calculate a predicted value of the comprehensive friction coefficient corresponding to each section by using the multi-parameter nonlinear inversion algorithm corresponding to the each section according to the basic data set corresponding to the each section in the current well.

[0038] In another aspect, the embodiments provide a warning device, which applies the determination device of the comprehensive friction coefficient of the friction torque to calculate the predicted value of the comprehensive friction coefficient corresponding to the current well section, and the device further comprises:

[0039] a true value calculation module configured to calculate a true value of the comprehensive friction coefficient corresponding to the current well section according to actual working condition data corresponding to the current well section;

[0040] a warning information determination module configured to determine warning information of the current well section if the difference between the true value and the predicted value of the comprehensive friction coefficient corresponding to the current well section is greater than a set threshold.

[0041] selecting a target well section from a plurality of known well sections, wherein the basic data in the basic data set corresponding to the selected well section is the same as the basic data in the basic data set corresponding to the current well section;

[0042] determining the warning information of the current well section according to the actual working condition data, the predicted value of the comprehensive friction coefficient, and the true value of the comprehensive friction coefficient of the target well section.

[0043] In yet another aspect, the embodiments also provide a computer device, which comprises a memory, a processor, and a computer program stored in the memory, and when the computer program is run by the processor, the instructions of the method according to any one of the above embodiments are executed.

[0044] In yet another aspect, the embodiments also provide a computer readable storage medium, which stores a computer program, and when the computer program is run by a processor of a computer device, the instructions of the method according to any one of the above embodiments are executed.

[0045] As can be seen from the technical solutions provided by the embodiments, after the current well is segmented in the depth direction with high accuracy, the hyperparameter corresponding to each section is determined, the multi-parameter nonlinear inversion algorithm corresponding to each section is set according to the hyperparameter, and then the predicted value of the comprehensive friction coefficient is obtained. The friction torque can be further calculated by using the predicted value of the comprehensive friction coefficient, and the calculation accuracy of the friction torque is improved.

[0046] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings in which: BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings described below only only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 A flowchart of a method for determining a comprehensive friction coefficient of a friction torque is shown;

[0049] Figure 2 A flowchart of segmenting a current well along a well depth direction and determining a basic data set corresponding to each segment in the current well is shown;

[0050] Figure 3 A flowchart of refining each segment after initial segmentation is shown;

[0051] Figure 4 A flowchart of determining a hyperparameter corresponding to each segment is shown;

[0052] Figure 5 Another flowchart of a method for determining a comprehensive friction coefficient of a friction torque is shown;

[0053] Figure 6 A flowchart of a pre-warning method is shown;

[0054] Figure 7 A module structure diagram of a device for determining a comprehensive friction coefficient of a friction torque is shown;

[0055] Figure 8 A module structure diagram of a pre-warning device is shown;

[0056] Figure 9 A structure diagram of a computer device is shown.

[0057] LIST OF ELEMENTS IN DRAWINGS

[0058] 100, an acquisition module;

[0059] 200, a segmentation module;

[0060] 300, determining module;

[0061] 400, setting module;

[0062] 500, prediction value calculation module;

[0063] 600, true value calculation module;

[0064] 700, early warning information determination module;

[0065] 902, computer device;

[0066] 904, processor;

[0067] 906, memory;

[0068] 908, drive mechanism;

[0069] 910, input / output module;

[0070] 912, input device;

[0071] 914, output device;

[0072] 916, presentation device;

[0073] 918, graphical user interface;

[0074] 920, network interface;

[0075] 922, communication link;

[0076] 924, communication bus. DETAILED DESCRIPTION

[0077] The technical solutions in the embodiments herein will be described clearly and completely below in combination with the accompanying drawings in the embodiments herein. Obviously, the described embodiments are only some of the embodiments herein, rather than all the embodiments. Based on the embodiments herein, all other embodiments obtained by those of ordinary skill in the art without any creative work fall within the scope of protection herein.

[0078] The current widely used friction torque analysis and calculation method for drilling companies is as follows: according to whether the well wall of the downhole pipe string is cased, the friction torque calculation profile is divided into cased sections and open hole sections, and the initial value of the comprehensive friction coefficient of the cased sections and open hole sections is set by the engineers according to their personal experience, and the friction torque profile is calculated by using the value. Then, the calculation results are fitted in combination with the field data, the comprehensive friction coefficient is adjusted, and finally the final coefficient of the region is obtained.

[0079] The calculation method cannot fit the final coefficient when the initial value of the comprehensive friction coefficient is set with a large deviation, and thus has a strong dependence on the experience of engineers in parameter setting; due to frequent fluctuations in field data, the calculation results of the "two-section type" friction and drag torque cannot be accurately fitted with the actual friction and drag torque values, resulting in a lack of calculation results, only providing a trend reference, and cannot be used for drilling optimization design of complex structure wells.

[0080] To solve the above problems, the embodiment of the present application provides a method for determining the comprehensive friction coefficient of friction and drag torque. Figure 1 is a step schematic diagram of a method for determining the comprehensive friction coefficient of friction and drag torque provided by the embodiment of the present application, and the present specification provides the method operation steps as described in the embodiment or flowchart, but more or fewer operation steps can be included based on conventional or non-creative labor. The order of steps listed in the embodiment is only one of the many execution orders, and does not represent the only execution order. When the system or device product is executed in practice, it can be executed in sequence or in parallel according to the method order shown in the embodiment or the drawing.

[0081] Reference Figure 1 A method for determining the comprehensive friction coefficient of friction and drag torque, comprising:

[0082] S101: Obtain a basic data set corresponding to each position in the depth direction of the current well;

[0083] S102: Based on the basic data set corresponding to each position, segment the current well along the depth direction, and determine the basic data set corresponding to each segment in the current well;

[0084] S103: Determine the hyperparameters corresponding to each segment according to the basic data set corresponding to each segment in the current well;

[0085] S104: Set the multi-parameter nonlinear inversion algorithm corresponding to each segment according to the hyperparameters corresponding to each segment;

[0086] S105: Calculate the predicted value of the comprehensive friction coefficient corresponding to each segment by using the multi-parameter nonlinear inversion algorithm corresponding to each segment according to the basic data set corresponding to each segment in the current well.

[0087] The current well refers to a well whose comprehensive friction coefficient is unknown, and the comprehensive friction coefficient of the current well needs to be obtained by the method described herein, and then the friction and drag torque is calculated to meet the needs of exploration and development. The basic data in the basic data set includes any one or a combination of multiple ones of well trajectory data, pipe string design data, drilling fluid data, formation data, and working condition data. The basic data in the basic data set corresponding to the current well is different, and the specific basic data needs to be determined according to the actual situation of the current well.

[0088] For example, for a certain current well, the wellbore trajectory data and the pipe string design data and the working condition data of the well can be obtained, and for another current well, the drilling fluid data, the formation data and the working condition data of the well can be obtained, and the basic data in the basic data set of the above two current wells are different. For any current well, which basic data can be obtained may be affected by various factors such as actual terrain, topography, etc.

[0089] The purpose of the design herein is to predict the comprehensive friction coefficient corresponding to the current well regardless of which basic data is included in the basic data set corresponding to the current well, so that the prediction of the comprehensive friction coefficient is not affected by the basic data set and has universality.

[0090] Further, the wellbore trajectory data includes: trajectory depth, trajectory inclination angle, azimuth angle and other parameters; the pipe string design data includes: drilling tool assembly condition, inner and outer diameters of each drilling tool, inner and outer diameters of joints, total length of drilling tools, linear weight, shear modulus, yield strength and other parameters; the drilling fluid data includes: drilling fluid density, plastic viscosity, dynamic shear force and other parameters; the formation data includes: formation name, formation top depth, formation thickness, rock density, creep coefficient and other parameters; the working condition data includes: hook load, tripping speed, rotation speed, drilling pressure, torque and other parameters.

[0091] Based on the basic data set corresponding to each position in the well depth direction, the current well can be segmented along the well depth direction, that is, the basic data in the basic data set with approximately the same data is classified into a segment, for example: if the wellbore trajectory data is included in the basic data set, the current well depth direction includes A, B, C, D……multiple position points, the wellbore trajectory data of A and B two position points is approximately the same, then A and B two position points are classified into a segment, the wellbore trajectory data of C and D two position points is approximately the same, then C and D two position points are classified into a segment.

[0092] For different segments in different current wells, the essence of the multi-parameter nonlinear inversion algorithm is the same, but the hyperparameters are different, and the hyperparameters are related to the basic data set corresponding to each segment.

[0093] Hyperparameters refer to parameters whose values are set before machine learning begins, rather than parameter data obtained through training. In general, hyperparameters need to be optimized to select a set of optimal hyperparameters for the learning machine to improve the performance and effect of learning.

[0094] After determining the hyperparameters corresponding to each segment, the hyperparameters are further determined to be substituted into the multi-parameter nonlinear inversion algorithm corresponding to the segment to predict the comprehensive friction coefficient.

[0095] The current well is segmented in the well depth direction in this paper, the corresponding hyperparameters of each segment are determined, and the corresponding multi-parameter nonlinear inversion algorithm of each segment is set according to the hyperparameters, and then the predicted value of the comprehensive friction coefficient is obtained. The predicted value of the comprehensive friction coefficient can be used to further calculate the friction torque, thereby improving the calculation accuracy of the friction torque.

[0096] With reference to Figure 2 In the embodiments of this paper, the basic data group corresponding to each position is segmented along the well depth direction of the current well, and the basic data group corresponding to each segment of the current well is further included:

[0097] S201: Segment the current well along the well depth direction based on the basic data group corresponding to each position;

[0098] S202: Refine the segmentation of each segment after initial segmentation according to the basic data group corresponding to each position in each segment.

[0099] Specifically, the initial segmentation method is different according to the different basic data in the basic data group of the current well. If the basic data group of the current well contains well trajectory data, the well curvature rate of change is calculated using the well trajectory minimum curvature interpolation method, and if the well curvature rate of change of adjacent position points A and B in the well depth direction is greater than the set curvature, it is determined that A and B belong to two different initial segments. The set curvature can be 0.07° / m, and other values can also be taken according to the actual working conditions.

[0100] If the basic data group of the current well contains pipe string design data, the initial segmentation is performed using the drill tool outer diameter change value, and when the drill tool outer diameter values of adjacent position points A and B in the well depth direction differ by more than a set change value, it is determined that A and B belong to two different initial segments. In this paper, the frequent outer diameter change of the measuring instrument near the drill bit is ignored, and the drill collar outer diameter value is used as the basis for determining the drill tool outer diameter value. Similarly, if the basic data group of the current well contains drilling fluid data, the drilling fluid system change is used as the initial segmentation basis; if the basic data group of the current well contains formation data, the stratigraphic era difference in the stratigraphic era division is used as the initial segmentation basis.

[0101] Each segment after initial segmentation can also be refined. Compared with only initial segmentation, the refined segmentation further refines each segment after initial segmentation, thereby improving the accuracy of the segmentation. Compared with only one refined segmentation, the initial segmentation and the refined segmentation are two consecutive segmentations, which improves the efficiency of the segmentation while ensuring the accuracy of the segmentation.

[0102] With reference to Figure 3Specifically, the refining segmentation of each segment after the initial segmentation further comprises:

[0103] S301: determining a comprehensive value corresponding to each position by the basic data in the basic data group corresponding to each position in each segment after the initial segmentation and the weight corresponding to the basic data;

[0104] S302: refining the segmentation of each segment according to the comprehensive value corresponding to each position in each segment after the initial segmentation, wherein the difference between the comprehensive values corresponding to any two positions in each segment after the refining segmentation does not exceed a set difference value.

[0105] For the basic data group corresponding to each position in each segment after the initial segmentation, the basic data contained therein can be any one or a combination of multiple of wellbore trajectory data, pipe string design data, drilling fluid data, formation data and working condition data. For each basic data, there is a corresponding weight. Generally, the comprehensive value of the corresponding position can be obtained by the product of the basic data and the weight corresponding thereto. In order to improve the efficiency of calculation, only the weight corresponding to the basic data that has a major impact needs to be determined, and then the comprehensive value corresponding to each position can be determined.

[0106] The refining segmentation is performed according to the comprehensive values of each position in each segment after the initial segmentation, and the basis for the refining segmentation is a set difference value, which can be determined according to the actual working condition.

[0107] A friction torque refining segmentation method based on principal component analysis of influencing factors is constructed to have the functions of basic data compression and feature extraction: since the basic data contains multiple items (wellbore trajectory data, pipe string design data, drilling fluid data, etc., each of which is a large item), the weight of each item is affected by multiple parameters therein, and therefore, when the weight analysis and evaluation are performed, the high-dimensional related variables need to be reduced, and the original basic data matrix X is standardized:

[0108]

[0109] wherein, X ij is the element of the i-th row and the j-th column of the original basic data matrix X, X ij is the element of the i-th row and the j-th column of the standardized matrix X; is the average value of the j-th column element of the matrix X, and σ j is the variance of the j-th column element of the matrix X

[0110] After the original basic data matrix X is standardized, the covariance matrix of the standardized matrix is calculated:

[0111]

[0112] According to the covariance matrix C X m eigenvalues in descending order as λ1, λ2,..., λ m , and the cumulative contribution rate of the first p variables to the comprehensive friction coefficient is defined as:

[0113]

[0114] Select the first p basic terms with a cumulative contribution rate greater than 90% as the main influencing terms of the comprehensive friction coefficient in this section, and further obtain the principal component eigenvalues and eigenvectors of the covariance matrix:

[0115] C x P=PΛ;

[0116] Where P is the eigenvector of the main influencing term, and the numerical value in the vector corresponds to the weight parameter of the main influencing term; Λ is the eigenvalue matrix, and the eigenvalue is the corresponding hyperparameter. Thus, the weight of the main influencing term and the hyperparameter can be determined.

[0117] Referring to Figure 4 , in the embodiments of the present application, the determining of the hyperparameter corresponding to each section in the current well according to the basic data group corresponding to each section in the current well further comprises:

[0118] S401: Select a selected section from a plurality of known well sections, wherein the basic data in the basic data group corresponding to the selected section is the same as the basic data in the basic data group corresponding to the current section in the current well;

[0119] S402: Taking the hyperparameter corresponding to the selected section as the hyperparameter corresponding to the current section in the current well.

[0120] For a multi-parameter nonlinear inversion algorithm, the more reasonable the hyperparameter setting is, the higher the accuracy of the nonlinear inversion algorithm calculation is. In order to set the hyperparameter more reasonably, a selected section with the same basic data as the current section can be selected from the known well sections, and the hyperparameter corresponding to the selected section is taken as the hyperparameter of the current section.

[0121] It should be noted that the basic data expressed here refers not only to the same composition of basic data, but also to the approximate same value of each basic data. The so-called approximate same can set a deviation value range according to the actual basic data, as long as it can be identified as the same within the deviation value range.

[0122] Suppose the current section only contains well trajectory data, and the value corresponding to the well trajectory data is a, then a selected section needs to be selected from the known well sections, the selected section also only contains well trajectory data, and the value corresponding to the well trajectory data is a', and the difference between a and a' is within the deviation value range corresponding to the well trajectory data.

[0123] Referring to Figure 5 In the embodiments herein also includes:

[0124] S501: According to the actual working condition data corresponding to the known well section, the true value of the comprehensive friction coefficient corresponding to the known well section is calculated;

[0125] S502: According to the basic data set corresponding to the known well section, the hyperparameter corresponding to the known well section is determined;

[0126] S503: According to the hyperparameter corresponding to the known well section, the multi-parameter nonlinear inversion algorithm corresponding to the known well section is set;

[0127] S504: The multi-parameter nonlinear inversion algorithm corresponding to the known well section is used to calculate the predicted value of the comprehensive friction coefficient corresponding to the known well section;

[0128] S505: According to the error between the predicted value and the true value of the known well section, the hyperparameter of the basic data set of the known well section is corrected.

[0129] Since the known well section has experienced the drilling process, the known well section has actual working condition data, that is, the working condition data in the actual drilling process, and the true value of the comprehensive friction coefficient can be calculated by the hook load, drilling pressure and other parameters in the actual working condition data.

[0130] And for the known well section, the predicted value of the comprehensive friction coefficient corresponding to the known well section can still be calculated by the multi-parameter nonlinear inversion algorithm. For the hyperparameter of the known well section, when the known well section has not experienced the drilling process, the known well section belongs to the unknown well section, and the determination method of the hyperparameter is the same as the determination method of the hyperparameter in S401 to S402 described above, that is, the hyperparameter of the selected well section in the known well section is determined.

[0131] Of course, the initial hyperparameter can also be set, and the hyperparameter of the known well section is the initial hyperparameter. It can be understood that the two determination methods of the hyperparameter described above can be combined, and if the hyperparameter cannot be determined by the foregoing S401 to S402, that is, there is no selected well section, the hyperparameter of the known well section can be determined as the initial hyperparameter.

[0132] According to the error between the predicted value and the true value, the hyperparameters of the basic data set corresponding to the known well section are corrected, and then the hyperparameters are used for determining the hyperparameters of the current section in the current well. Thus, after the predicted value of the comprehensive friction coefficient of the current section in the current well is obtained, the current section becomes a known well section as the drilling progresses. The true value of the comprehensive friction coefficient can be calculated according to the actual working condition data, and then the hyperparameters of the basic data corresponding to the section are corrected according to the error between the true value and the predicted value.

[0133] Further, the hyperparameters, the basic data set, the actual working condition data, the true value of the comprehensive friction coefficient and the predicted value of the comprehensive friction coefficient of all known well sections can be counted and stored, which lays a foundation for the prediction of the comprehensive friction coefficient of subsequent unknown well sections. The counting and storage means can be in the form of a database table, a chart or any other feasible method.

[0134] Reference Figure 6 Based on the method for determining the comprehensive friction coefficient of the friction torque described above, in the embodiments of the present application, a pre-warning method is further included, which applies the method for determining the comprehensive friction coefficient of the friction torque described above to calculate the predicted value of the comprehensive friction coefficient corresponding to the current well section. The pre-warning method further includes:

[0135] S601: According to the actual working condition data corresponding to the current well section, the true value of the comprehensive friction coefficient corresponding to the current well section is calculated;

[0136] S602: If the difference between the true value and the predicted value of the comprehensive friction coefficient corresponding to the current well section is greater than a set threshold, a target well section is selected from a plurality of known well sections, wherein the basic data in the basic data set corresponding to the target well section is the same as the basic data in the basic data set corresponding to the current well section; and according to the actual working condition data of the current well section and the target well section, the predicted value of the comprehensive friction coefficient and the true value of the comprehensive friction coefficient, the pre-warning information of the current well section is determined;

[0137] S603: If the difference between the true value and the predicted value of the comprehensive friction coefficient corresponding to the current well section is less than or equal to the set threshold, no pre-warning is needed for the current well section.

[0138] After the current well section is drilled, the actual working condition data in the drilling process can be obtained. After the true value of the comprehensive friction coefficient corresponding to the current well section is calculated according to the actual working condition data, the true value is compared with the predicted value of the comprehensive friction coefficient calculated by the multi-parameter nonlinear inversion algorithm. If the difference between the two is too large, i.e. greater than a set threshold, it means that the current well section may have an abnormality and needs to be pre-warned; if the difference between the two is not large, i.e. less than or equal to the set threshold, it means that the current well section has no abnormality and no pre-warning is needed.

[0139] If there is an anomaly in the current well section, the specific abnormal situation needs to be determined and a warning needs to be given. In the determination of the specific abnormal situation, the target well section in the known well section can be used, the basis data in the basis data group corresponding to the target well section is the same as the basis data in the basis data group corresponding to the current well section, and the basis data in the basis data group corresponding to the selected well section in the above S401 to S402 is also the same as the basis data in the basis data group corresponding to the current well section. According to this, the selected well section can be directly determined as the target well section, or a new target well section can be determined.

[0140] The actual working condition data of the current well section and the target well section, the predicted value of the comprehensive friction coefficient, and the true value of the comprehensive friction coefficient are compared to determine the warning information of the current well section.

[0141] For example, if the actual working condition data of the current well section and the target well section are the same, the predicted value of the comprehensive friction coefficient between the two is the same, but the true value of the comprehensive friction coefficient is quite different, for example, the true value is 20% higher than the predicted value, and the following is popped up: There may be a cuttings bed accumulation and a serious dogleg section, please check the data and adjust!

[0142] Based on the above-mentioned method for determining the comprehensive friction coefficient of the friction torque, the embodiments of the present application also provide a device for determining the comprehensive friction coefficient of the friction torque. The device can include a system (including a distributed system), software (application), module, component, server, client, etc. using the method described in the embodiments of the present application, and a device combined with necessary implementation hardware. Based on the same innovative concept, the device in one or more embodiments provided by the embodiments of the present application is as described in the following embodiments.

[0143] Since the implementation scheme of the device solves the problem and is similar to the method, the implementation of the specific device in the embodiments of the present application can be referred to the implementation of the foregoing method, and the repeated parts will not be described herein. The term "unit" or "module" used below can be a combination of software and / or hardware that realizes a predetermined function. Although the device described in the following embodiments is preferably realized in software, the realization of hardware or a combination of software and hardware is also possible and is conceived.

[0144] Specifically, Figure 7 is a module structure diagram of one embodiment of the device for determining the comprehensive friction coefficient of the friction torque provided by the embodiments of the present application, referring to Figure 7 As shown in the figure, the device for determining the comprehensive friction coefficient of the friction torque provided by the embodiments of the present application includes an acquisition module 100, a segmentation module 200, a determination module 300, a setting module 400, and a predicted value calculation module 500.

[0145] The acquisition module 100 is configured to acquire a basic data set corresponding to each position of the current well in the well depth direction.

[0146] The segmentation module 200 is configured to segment the current well along the well depth direction based on the basic data set corresponding to each position, and determine a basic data set corresponding to each segment of the current well.

[0147] The determination module 300 is configured to determine a hyperparameter corresponding to each segment according to the basic data set corresponding to each segment of the current well.

[0148] The setting module 400 is configured to set a multi-parameter nonlinear inversion algorithm corresponding to each segment according to the hyperparameter corresponding to each segment.

[0149] The predicted value calculation module 500 is configured to calculate a predicted value of the comprehensive friction coefficient corresponding to each segment by using the multi-parameter nonlinear inversion algorithm corresponding to each segment according to the basic data set corresponding to each segment of the current well.

[0150] Based on the above-mentioned early warning method, the embodiment of the present application further provides an early warning device. Specifically, Figure 8 is a module structure schematic diagram of one embodiment of the early warning device provided by the embodiment of the present application. As shown in Figure 8 , the early warning device provided by the embodiment of the present application applies the above-mentioned determination device of the comprehensive friction coefficient of the friction torque to calculate the predicted value of the comprehensive friction coefficient corresponding to the current well segment, and further comprises a true value calculation module 600 and an early warning information determination module 700.

[0151] The true value calculation module 600 is configured to calculate a true value of the comprehensive friction coefficient corresponding to the current well segment according to actual working condition data corresponding to the current well segment.

[0152] The early warning information determination module 700 is configured to, if the difference between the true value and the predicted value of the comprehensive friction coefficient corresponding to the current well segment is greater than a set threshold value,

[0153] select a target well segment from a plurality of known well segments, wherein the basic data in the basic data set corresponding to the target well segment is the same as the basic data in the basic data set corresponding to the current well segment.

[0154] Determine the early warning information of the current well segment according to the actual working condition data of the current well segment and the target well segment, the predicted value of the comprehensive friction coefficient, and the true value of the comprehensive friction coefficient.

[0155] Referring to Figure 9As shown, based on the determination method of the comprehensive friction coefficient of the friction torque described above, an embodiment of the present disclosure further provides a computer device 902, wherein the above method runs on the computer device 902. The computer device 902 can include one or more processors 904, such as one or more central processing units (CPUs) or graphics processing units (GPUs), each of which can implement one or more hardware threads.

[0156] The computer device 902 can further include any memory 906 for storing any kind of information, such as code, settings, data, etc. In an embodiment, the memory 906 stores a computer program that can be run on the processor 904, and when the computer program is run by the processor 904, the computer program can execute instructions according to the above method.

[0157] Non-limitingly, for example, the memory 906 can include any one or a combination of any type of RAM, any type of ROM, a flash memory device, a hard disk, an optical disk, etc. More generally, any memory can store information using any technology. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 902.

[0158] In one case, the computer device 902 can perform any of the operations of the associated instructions when the processor 904 executes the associated instructions stored in any memory or combination of memories. The computer device 902 further includes one or more drive mechanisms 908 for interacting with any memory, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0159] The computer device 902 can further include an input / output module 910 (I / O) for receiving various inputs (via input devices 912) and for providing various outputs (via output devices 914). One particular output mechanism can include a presentation device 916 and an associated graphical user interface 918 (GUI).

[0160] In other embodiments, the input / output module 910 (I / O), the input devices 912, and the output devices 914 can also not be included, only as a computer device in a network. The computer device 902 can further include one or more network interfaces 920 for exchanging data with other devices via one or more communication links 922. One or more communication buses 924 couple the above-described components together.

[0161] The communication links 922 can be implemented in any manner, such as through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication links 922 can include any combination of hardwired links, wireless links, routers, gateway functionality, name servers, etc., governed by any protocol or combination of protocols.

[0162] Corresponding to the method in Figures 1-6 The embodiments provided herein further provide a computer readable storage medium, having stored thereon a computer program, which when executed by a processor, performs the steps of the method described above.

[0163] The embodiments provided herein further provide a computer readable instruction, wherein when a processor executes the instruction, the program therein causes the processor to perform the method as shown in Figures 1 to 6 .

[0164] It should be understood that the size of the sequence number of each process described above in various embodiments herein does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments herein.

[0165] It should also be understood that in the embodiments herein, the term "and / or" is only a description of the association relationship of the associated objects, which means that there can be three relationships. For example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are in an "or" relationship.

[0166] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of each example have been described in the above description in a general manner. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this paper.

[0167] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system, device and unit described above can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0168] In several embodiments provided herein, it should be understood that the disclosed system, device and method can be implemented in other ways.

[0169] For example, the apparatus embodiments described above are merely illustrative, and the division of the units is merely a logical functional division. In actual implementation, another division manner can be used, for example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed.

[0170] In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, units or components, and can be electrical, mechanical or other form of connection.

[0171] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, can be located in one place or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments.

[0172] In addition, the functional units in each of the embodiments can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0173] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions in the present application, the essential part or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments.

[0174] The storage medium mentioned above includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage medium capable of storing program codes.

[0175] The principles and implementation manners of the embodiments are described in the present application. The above description of the embodiments is only used to help understand the methods and their core ideas; meanwhile, for those skilled in the art, according to the ideas of the present application, the specific implementation manners and application ranges can be changed. In summary, the content of the present application should not be understood as a limitation.

Claims

1. A method for determining the comprehensive friction coefficient of frictional resistance torque, characterized in that, include: Obtain the basic data set corresponding to each position of the current well in the well depth direction. The basic data set includes any one or a combination of wellbore trajectory data, tubing design data, drilling fluid data, formation data, and operating condition data. Based on the basic data sets corresponding to each location, the current well is segmented along the well depth direction, and the basic data set corresponding to each segment in the current well is determined. Based on the basic data set corresponding to each segment in the current well, determine the hyperparameters corresponding to each segment; Based on the hyperparameters corresponding to each segment, set up a multi-parameter nonlinear inversion algorithm for each segment; Based on the basic data set corresponding to each segment in the current well, the predicted value of the comprehensive friction coefficient corresponding to each segment is calculated using the multi-parameter nonlinear inversion algorithm corresponding to each segment. The determination of the hyperparameters corresponding to each segment based on the base data set corresponding to each segment in the current well further includes: Select a well segment from several known well segments, wherein the basic data in the basic data group corresponding to the selected well segment is the same as the basic data in the basic data group corresponding to the current segment in the current well; Use the hyperparameters corresponding to the selected well section as the hyperparameters corresponding to the current section in the current well. The hyperparameters corresponding to the current segment are determined as follows: The original basic data matrix is ​​constructed based on the basic data corresponding to the current segment; the original basic data matrix is ​​standardized to obtain the standardized matrix; the covariance matrix of the standardized matrix is ​​calculated, and the eigenvalues ​​of the covariance matrix are sorted in descending order. The top p basic terms whose cumulative contribution rate to the overall friction coefficient is greater than a preset threshold are selected as the main influencing terms, and the eigenvalues ​​in the covariance matrix corresponding to the main influencing terms are used as the hyperparameters of that segment.

2. The method for determining the comprehensive friction coefficient of frictional torque according to claim 1, characterized in that, The step of segmenting the current well along the well depth direction based on the basic data sets corresponding to each location, and determining the basic data set corresponding to each segment in the current well, further includes: Based on the basic data sets corresponding to each location, the current well is initially segmented along the well depth direction; Based on the basic data set corresponding to each position in each segment after the initial segmentation, each segment after the initial segmentation is further segmented.

3. The method for determining the comprehensive friction coefficient of frictional torque according to claim 2, characterized in that, The step of refining each segment after the initial segmentation based on the basic data group corresponding to each position in each segment further includes: The comprehensive value corresponding to each position is determined by the basic data in the basic data group corresponding to each position in each segment after the initial segmentation, and the weights corresponding to the basic data. Each segment is further subdivided based on the comprehensive value corresponding to each position in each segment after the initial segmentation, wherein the difference between the comprehensive values ​​corresponding to any two positions in each segment after the subdivision does not exceed a set difference.

4. The method for determining the comprehensive friction coefficient of frictional torque according to claim 1, characterized in that, Also includes: Based on the actual working condition data corresponding to the known well section, the true value of the comprehensive friction coefficient corresponding to the known well section is calculated; Based on the basic data set corresponding to the known well section, determine the hyperparameters corresponding to the known well section; Based on the hyperparameters corresponding to the known well section, a multi-parameter nonlinear inversion algorithm corresponding to the known well section is set. Using the multi-parameter nonlinear inversion algorithm corresponding to the known well section, the predicted value of the comprehensive friction coefficient corresponding to the known well section is calculated; Based on the error between the predicted value and the actual value corresponding to the known well section, the hyperparameters of the basic data set corresponding to the known well section are corrected.

5. An early warning method, characterized in that, Using the method for determining the comprehensive friction coefficient of frictional torque as described in any one of claims 1-4, the predicted value of the comprehensive friction coefficient corresponding to the current well section is calculated, and the early warning method further includes: Based on the actual working condition data corresponding to the current well section, the true value of the comprehensive friction coefficient corresponding to the current well section is calculated; If the difference between the actual and predicted values ​​of the comprehensive friction coefficient for the current well section is greater than a set threshold, then A target well section is selected from several known well sections, wherein the basic data in the basic data group corresponding to the target well section is the same as the basic data in the basic data group corresponding to the current well section; Based on the actual operating data of the current well section and the target well section, the predicted value of the comprehensive friction coefficient, and the actual value of the comprehensive friction coefficient, the early warning information for the current well section is determined.

6. A device for determining the comprehensive friction coefficient of frictional resistance and torque, characterized in that, The device includes: The acquisition module is used to acquire the basic data set corresponding to each position of the current well in the well depth direction. The basic data set includes any one or a combination of wellbore trajectory data, tubing design data, drilling fluid data, formation data and operating condition data. The segmentation module is used to segment the current well along the well depth direction based on the basic data group corresponding to each location, and to determine the basic data group corresponding to each segment in the current well. The determination module is used to determine the hyperparameters corresponding to each segment based on the basic data set corresponding to each segment in the current well. The configuration module is used to configure the multi-parameter nonlinear inversion algorithm for each segment based on the hyperparameters corresponding to each segment. The prediction value calculation module is used to calculate the predicted value of the comprehensive friction coefficient for each segment based on the basic data set corresponding to each segment in the current well and using the multi-parameter nonlinear inversion algorithm corresponding to each segment. The determination of the hyperparameters corresponding to each segment based on the base data set corresponding to each segment in the current well further includes: Select a well segment from several known well segments, wherein the basic data in the basic data group corresponding to the selected well segment is the same as the basic data in the basic data group corresponding to the current segment in the current well; Use the hyperparameters corresponding to the selected well section as the hyperparameters corresponding to the current section in the current well. The hyperparameters corresponding to the current segment are determined as follows: The original basic data matrix is ​​constructed based on the basic data corresponding to the current segment; the original basic data matrix is ​​standardized to obtain the standardized matrix; the covariance matrix of the standardized matrix is ​​calculated, and the eigenvalues ​​of the covariance matrix are sorted in descending order; the top p basic terms that contribute more than a preset threshold to the cumulative contribution rate of the comprehensive friction coefficient are selected as the main influencing terms, and the eigenvalues ​​in the covariance matrix corresponding to the main influencing terms are used as the hyperparameters corresponding to the segment.

7. An early warning device, characterized in that, Using the device for determining the comprehensive friction coefficient of frictional torque as described in claim 6, a predicted value of the comprehensive friction coefficient corresponding to the current well section is calculated, and the device further includes: The true value calculation module is used to calculate the true value of the comprehensive friction coefficient corresponding to the current well section based on the actual working condition data corresponding to the current well section. The early warning information determination module is used to determine if the difference between the actual and predicted values ​​of the comprehensive friction coefficient for the current well section exceeds a set threshold. A target well section is selected from several known well sections, wherein the basic data in the basic data group corresponding to the target well section is the same as the basic data in the basic data group corresponding to the current well section; Based on the actual operating data of the current well section and the target well section, the predicted value of the comprehensive friction coefficient, and the actual value of the comprehensive friction coefficient, the early warning information for the current well section is determined.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, When the computer program is run by the processor, it executes the instructions of the method according to any one of claims 1-5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is run by the processor of the computer device, it executes the instructions of the method according to any one of claims 1-5.

Images