Method and device for evaluating formation steering characteristics

Through the extraction of feature terms of factors affecting the slope and the establishment of multiple regression models, the accuracy of stratigraphic orientation characteristics evaluation is solved, and the guiding ability of rotation guidance in complex strata is improved.

CN115508885BActive Publication Date: 2024-11-12CHINA OILFIELD SERVICES LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202211158984.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-09-22
Publication Date
2024-11-12
Estimated Expiration
2042-09-22

AI Technical Summary

Technical Problem

In the field of petroleum exploration and drilling, it is difficult for the existing technology to accurately evaluate the stratigraphic guidance characteristics, resulting in insufficient guiding capabilities of rotary guidance in complex stratigraphic environments and lack of effective quantitative analysis and optimization analysis.

Method used

By extracting feature terms based on the influencing factors of the formation slope, performing correlation analysis and multiple regression, selecting the optimal set of feature terms to establish a multiple regression model, stratigraphic orientation characteristics are evaluated, and precise evaluation is achieved by combining qualitative and quantitative analysis.

Benefits of technology

Accurate evaluation and analysis of stratigraphic guidance characteristics is achieved, and the guidance ability and accuracy of rotary guidance in various stratigraphic environments are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115508885B_ABST
    Figure CN115508885B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and device for evaluating formation steering characteristics, wherein the method for evaluating formation steering characteristics comprises: extracting feature items according to influencing factors of build-up rate to obtain a first feature item set; taking the build-up rate as a target item, performing correlation analysis on each feature item in the first feature item set to obtain a correlation coefficient between each feature item and the target item; selecting multiple second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; taking the build-up rate as a target item, performing multiple regressions based on multiple second feature item sets respectively, and selecting a multiple regression model corresponding to the optimal second feature item set; evaluating formation steering characteristics according to the multiple regression model corresponding to the optimal second feature item set. The present invention selects the multiple regression model corresponding to the optimal feature item based on the influencing factors of the build-up rate, thereby realizing accurate evaluation and analysis of formation steering characteristics.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of petroleum exploration and drilling, and in particular to a method and device for evaluating formation steering characteristics, a computing device and a computer storage medium. Background Art

[0002] In the current field of oil exploration and drilling, rotary steering, as a high-end directional drilling tool, is increasingly widely used in oil exploration, development and drilling construction projects. Rotary steering can control the trajectory of the wellbore to drill in a predetermined direction while the drill bit is rotating, but it is more sensitive to the complex formation environment when directional drilling in the actual formation. Therefore, mastering the guidance characteristics of the formation is very important in directional well design, trajectory optimization, steering tool selection, construction plan formulation, and field operation guidance.

[0003] Rotary steering field operations usually involve a large number of complex influencing factors, especially the complexity of the formation. However, there is currently a lack of effective technical analysis methods to describe and evaluate the steering characteristics of the formation. The steering ability of field tools is usually determined by the construction process such as steering parameters and drilling parameters set by field engineers, and the influence of the downhole formation environment is not considered. Or, usually only a qualitative analysis of the above-mentioned steering characteristics is made, without further quantitative analysis and optimization analysis, making it difficult to accurately evaluate the steering characteristics of rotary steering in various formation environments. Summary of the invention

[0004] In view of the above problems, the present invention is proposed to provide a method and apparatus for evaluating formation steering characteristics, a computing device and a computer storage medium for overcoming the problem of low accuracy in evaluating formation steering characteristics.

[0005] According to one aspect of the present invention, a method for evaluating formation steering characteristics is provided, comprising:

[0006] Extract characteristic items according to the influencing factors of the build-up rate to obtain a first characteristic item set;

[0007] Taking the inclination rate as the target item, a correlation analysis is performed on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item;

[0008] According to the correlation coefficient between each feature item in the first feature item set and the target item, multiple second feature item sets are selected; with the ramp rate as the target item, multiple regression is performed based on the multiple second feature item sets respectively, and the multiple regression model corresponding to the optimal second feature item set is selected;

[0009] The formation steering characteristics are evaluated according to the multivariate regression model corresponding to the optimal second feature item set.

[0010] In an optional manner, the first feature item set includes active factor feature items and passive factor feature items;

[0011] The active factor feature items include: steering parameters and drilling parameters;

[0012] The passive factor characteristic items include: formation lithology parameters and formation change space parameters.

[0013] In an optional manner, after taking the build inclination rate as the target item and performing correlation analysis on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item, the method further includes:

[0014] Sort the feature items in the first feature item set in descending order of correlation coefficient;

[0015] The selecting of a plurality of second feature item sets further comprises:

[0016] A plurality of second feature item sets are selected according to different preset sorting intervals.

[0017] In an optional manner, taking the build slope rate as the target item, performing multiple regression based on the multiple second feature item sets respectively, and selecting the multiple regression model corresponding to the optimal second feature item set further includes:

[0018] Based on the multiple second feature item sets, respectively establish a multivariate regression model;

[0019] Based on the measured data, calculate the goodness of fit value of the multivariate regression model corresponding to each second feature item set;

[0020] The multiple regression model with the maximum goodness of fit value is selected as the multiple regression model corresponding to the optimal second feature item set.

[0021] In an optional manner, after selecting the multivariate regression model corresponding to the optimal second feature item set, the method further includes:

[0022] Obtain the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set.

[0023] In an optional manner, the evaluating the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set further includes:

[0024] According to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, the influence of each feature item on the guidance effect is evaluated.

[0025] In an optional manner, the evaluating the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set further includes:

[0026] The build slope rate is quantitatively analyzed according to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, and the correlation coefficient between each feature item and the target item.

[0027] According to another aspect of the present invention, there is provided a device for evaluating formation steering characteristics, comprising:

[0028] A feature selection module is used to extract feature items according to the influencing factors of the build inclination rate to obtain a first feature item set;

[0029] A qualitative analysis module is used to perform correlation analysis on each feature item in the first feature item set with the slope rate as the target item, so as to obtain the correlation coefficient between each feature item and the target item;

[0030] A quantitative analysis module, configured to select a plurality of second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; taking the slope rate as the target item, performing multiple regressions based on the plurality of second feature item sets respectively, and selecting a multiple regression model corresponding to the optimal second feature item set;

[0031] An evaluation module is used to evaluate the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set.

[0032] According to another aspect of the present invention, there is provided a computing device, comprising: a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus;

[0033] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the above-mentioned formation steering characteristic evaluation method.

[0034] According to yet another aspect of the present invention, a computer storage medium is provided, wherein the storage medium stores at least one executable instruction, wherein the executable instruction enables a processor to execute operations corresponding to the above-mentioned formation steering characteristic evaluation method.

[0035] According to the scheme provided by the present invention, feature items are extracted according to the influencing factors of the build rate to obtain a first feature item set; with the build rate as the target item, correlation analysis is performed on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item; multiple second feature item sets are selected according to the correlation coefficient between each feature item in the first feature item set and the target item; with the build rate as the target item, multiple regressions are performed based on multiple second feature item sets respectively to select the multiple regression model corresponding to the optimal second feature item set; and the formation guidance characteristics are evaluated according to the multiple regression model corresponding to the optimal second feature item set. The present invention selects the multiple regression model corresponding to the optimal feature item based on the influencing factors of the build rate to achieve accurate evaluation and analysis of the formation guidance characteristics.

[0036] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0038] Figure 1 A schematic diagram showing a flow chart of a method for evaluating formation steering characteristics according to an embodiment of the present invention;

[0039] Figure 2 A schematic flow chart showing a method for evaluating formation steering characteristics according to another embodiment of the present invention;

[0040] Figure 3 A schematic diagram showing the distribution of build rate correlation scores and correlation coefficient characteristic items according to an embodiment of the present invention is shown;

[0041] Figure 4 A schematic diagram showing the comparison between the measured value and the predicted value of the build rate according to an embodiment of the present invention is shown;

[0042] Figure 5 A schematic diagram showing a formation steering characteristic description correlation matrix diagram according to an embodiment of the present invention;

[0043] Figure 6 A schematic diagram showing the structure of a formation steering characteristic evaluation device according to an embodiment of the present invention;

[0044] Figure 7 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0045] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0046] Figure 1 The flowchart of the method for evaluating the formation steering characteristics of an embodiment of the present invention is shown. The method extracts feature items based on multiple influencing factors of the build-up rate, performs multiple regression on the selected multiple feature items with the build-up rate as the target item, selects the multiple regression model corresponding to the optimal feature item, and accurately evaluates and analyzes the formation steering characteristics. Specifically, Figure 1 As shown, the following steps are included:

[0047] Step S101, extracting feature items according to the influencing factors of the build inclination rate to obtain a first feature item set.

[0048] Due to the sensitivity of rotary steerable tools to the formation environment, the steering ability of field tools is not only affected by the steering parameters and drilling parameters set by field engineers, but also by the downhole formation environmental factors. (Wellbore) deflection rate is a key link in the steerable drilling work of rotary steerable tools in actual formations. Among them, deflection rate, also known as deflection intensity, refers to the full bending angle of the borehole formed in the unit deflection drilling footage. Commonly used dimensions are degrees / meter, degrees / 10 meters, degrees / 100 meters, etc. If the full bending angle of the borehole formed by deflection drilling is on the plumb plane, it is the top angle deflection rate. If the full bending angle of the borehole formed by deflection drilling is on the horizontal plane, it is the azimuth angle deflection rate.

[0049] The size of the build-up rate is determined by a variety of factors, and the factors that affect the build-up rate are usually divided into active factors and passive factors. Among them, active factors usually refer to the guidance parameters and drilling parameters set by the field operation engineer for the system when directional drilling according to the trajectory design; passive factors mainly refer to the characteristics of the formation, such as the formation lithology, formation hardness, formation abrasiveness, formation inclination and formation change space that affect the guidance effect.

[0050] The above-mentioned influencing factors can be further divided into quantifiable characteristic items, such as steering parameters including steering force and steering tool face; drilling parameters including mechanical drilling speed, drilling pressure and rotation speed; formation lithology including gamma and density; formation change space including vertical depth, well depth, north displacement, east displacement, azimuth and well inclination.

[0051] In the process of evaluating and analyzing the formation guidance characteristics, since the build rate is affected by many factors mentioned above, especially by the characteristics of complex and sensitive formations, in this embodiment, it is necessary to first extract feature items according to the (multiple) influencing factors of the build rate to obtain more meaningful potential factors (called the first feature item set). Feature extraction refers to finding the most effective (invariance of similar samples, discrimination of different samples, robustness to noise) features from the original features.

[0052] Step S102 , taking the build inclination rate as the target item, performing correlation analysis on each feature item in the first feature item set to obtain a correlation coefficient between each feature item and the target item.

[0053] Each feature item in the first feature item set fails to reflect irrelevant features and features without differentiation. It is necessary to further use the build rate as the target item, conduct correlation analysis on each feature item in the first feature item set, determine which feature items are the dominant factors, secondary factors or irrelevant factors affecting the build rate through the correlation coefficient, determine the nature of the formation guidance characteristics according to the type of influencing factors (feature items), and qualitatively describe and analyze the formation guidance characteristics. Among them, the correlation coefficient is a statistical indicator used to reflect the closeness of the correlation between each feature item and the build rate.

[0054] Step S103, selecting multiple second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; taking the slope rate as the target item, performing multiple regression based on the multiple second feature item sets respectively, and selecting the multiple regression model corresponding to the optimal second feature item set.

[0055] Since the degree to which the correlation coefficient (the range of the correlation coefficient γ is [-1, +1]; γ>0 indicates positive correlation; γ<0 indicates negative correlation; γ=0 indicates no correlation) is close to ±1 is related to the number of feature items n, it is easy to create an illusion, that is, when n is small, the fluctuation of the correlation coefficient is large, and the absolute value of the correlation coefficient for some feature items is easy to be close to 1; especially when n=2, the absolute value of the correlation coefficient is always 1; when n is large, the absolute value of the correlation coefficient is easy to be small. Therefore, it is not accurate to judge the close relationship between the feature item and the target item only by the correlation coefficient.

[0056] In order to correct the problem that the correlation coefficient fluctuates greatly or the absolute value is easily small, in this embodiment, multiple second feature item sets are selected according to the correlation coefficients between each feature item in the first feature item set and the target item.

[0057] In order to further correct the influence of the above correlation coefficient, the second feature item set closest to the measured value is selected from multiple second feature item sets by model fitting (model training). Specifically, the slope rate is taken as the target item, and multiple regressions are performed based on multiple second feature item sets respectively, and the multiple regression model corresponding to the optimal second feature item set is selected. Since the multiple regression model is a regression model containing multiple explanatory variables (feature items), the slope rate can be intuitively described and quantitatively analyzed in the form of graphs / tables.

[0058] Optionally, the multivariate regression model is a multivariate high-order regression model to analyze a more complex high-order relationship between the build slope rate and each characteristic item.

[0059] Optionally, the multivariate regression model is subjected to parameter testing by means of significance level and / or goodness of fit.

[0060] Optionally, the coefficients of the explanatory variables of the multivariate regression model are corrected by weighting and penalizing.

[0061] Optionally, after selecting the multivariate regression model corresponding to the optimal second feature item set, the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set is obtained.

[0062] Step S104: evaluating the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set.

[0063] The multivariate regression model obeys the various assumptions of the univariate regression model, including the explained variable (slope), explanatory variable (second characteristic term), intercept, slope / partial regression coefficient, random error term / unexplained term. All explanatory variables are known and have good interpretability. They can be used for point prediction, interval prediction and testing of various hypotheses.

[0064] In this embodiment, the evaluation of formation steering characteristics based on the multivariate regression model can be used for pre-drilling prediction, while-drilling evaluation, and post-drilling evaluation. For example, the while-drilling measurement data (bite pressure, torque, rotation speed, mechanical drilling speed, and hydraulic parameters) can be used to evaluate the steering characteristics of the drilled formation (including the pore pressure, lithology, drillability, and anisotropic characteristics of the formation) in real time.

[0065] The solution provided by the above embodiment of the present invention extracts feature items according to the influencing factors of the build rate to obtain a first feature item set; taking the build rate as the target item, performing correlation analysis on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item; selecting multiple second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; taking the build rate as the target item, performing multivariate regression based on multiple second feature item sets respectively, and selecting the multivariate regression model corresponding to the optimal second feature item set; evaluating the formation guidance characteristics according to the multivariate regression model corresponding to the optimal second feature item set. The present invention selects the multivariate regression model corresponding to the optimal feature item based on the influencing factors of the build rate, and uses a combination of qualitative analysis and quantitative analysis to achieve accurate evaluation and quantitative / intuitive analysis of the formation guidance characteristics.

[0066] Figure 2 A flow chart of another embodiment of the method for evaluating formation steering characteristics of the present invention is shown. In this embodiment, based on measured data, a parameter test is performed on the multivariate regression model corresponding to each second feature item set by a goodness of fit method to obtain each goodness of fit value, and the multivariate regression model with the maximum goodness of fit value is selected as the multivariate regression model corresponding to the optimal second feature item set. Specifically, Figure 2 As shown, the following steps are included:

[0067] Step S201, extracting feature items according to the influencing factors of the build inclination rate to obtain a first feature item set.

[0068] In this embodiment, feature items are extracted by an existing feature item extraction algorithm or feature item extraction toolkit. Specifically, feature items are extracted according to factors affecting the build-up rate (such as steering force, steering tool face, mechanical drilling speed, drilling pressure, rotation speed, gamma value, density, vertical depth, well depth, north displacement, east displacement, azimuth, and well inclination), and the extracted feature items are called the first feature item set.

[0069] Optionally, the weight coefficients of each feature in the factors affecting the slope are obtained by using machine learning algorithms and model training, and then the feature items are selected in descending order according to the weight coefficients. The weight coefficient represents the contribution or importance of the corresponding feature to the model. For example, the feature weight attribute in the decision tree model can list the contribution of each feature to the tree establishment, and find the most useful features for model establishment based on the contribution evaluation, which has a good effect on improving the effectiveness of the model.

[0070] Step S202 , taking the build inclination rate as the target item, performing correlation analysis on each feature item in the first feature item set to obtain a correlation coefficient between each feature item and the target item.

[0071] A correlation analysis is performed on each feature item (stratum steering characteristics) in the first feature item set to obtain the correlation coefficient between each feature item and the target item, and to analyze the dominant factors affecting the build rate. Specifically, with the build rate as the target item, a correlation analysis is performed on each feature item in the first feature item set, and the feature items are determined by sorting by correlation coefficients to determine which feature items are the dominant factors, secondary factors, and irrelevant factors of the build rate. After sorting, the nature of the stratum steering characteristics is determined according to the type of influencing factors, and a qualitative description of the stratum steering characteristics is performed. Figure 3 As shown in the figure, the upper and lower figures are the distribution of the relevant score feature items about a wellbore build rate (BuildRate) and the distribution of the correlation coefficient feature items about a wellbore build rate (BuildRate), respectively. For example, it can be seen from the figure below that the correlation coefficients between the wellbore build rate and the guiding force and drilling time are approximately 0.72 and -0.02. The correlation coefficient can determine that the guiding force is positively correlated with the wellbore build rate and is the dominant factor affecting the wellbore build rate; the drilling time is negatively correlated with the wellbore build rate and is a secondary factor.

[0072] Step S203: sorting the feature items in the first feature item set in descending order of correlation coefficient.

[0073] The feature items in the first feature item set are sorted in descending order of correlation coefficient to obtain the feature items arranged in order of primary and secondary.

[0074] Step S204, select multiple second feature item sets according to the correlation coefficients between each feature item in the first feature item set and the target item; establish multiple regression models based on the multiple second feature item sets respectively; calculate the goodness of fit value of the multiple regression model corresponding to each second feature item set based on the measured data; select the multiple regression model with the maximum goodness of fit value as the multiple regression model corresponding to the optimal second feature item set.

[0075] In this embodiment, the parameter test of the multivariate regression model is performed by the goodness of fit method. Specifically, multiple second feature item sets are selected according to the correlation coefficient between each feature item in the first feature item set and the target item. Optionally, multiple second feature item sets are selected according to different preset sorting intervals, for example, multiple feature item sets of the first 10%, 30%, 50%, 70%, 90%, and 100% intervals are selected in order of priority.

[0076] For example, based on multiple second feature item sets selected according to different preset sorting intervals, multiple regression models are established respectively. Optionally, since the influence of each feature item on the build-up rate is different at different depths of the drilling, that is, the correlation coefficient of each feature item on the build-up rate is also different, multiple second feature item sets are selected according to different depth intervals, and multiple regression models are established respectively.

[0077] Based on the measured data, the goodness of fit value of the multivariate regression model corresponding to each second feature item set is calculated, where the goodness of fit value is used to measure the gap between the expected value of the multivariate regression model and the measured data. Figure 4 As shown in the figure, the first 10%, 30%, 50%, 70%, 90%, and 100% feature items are taken in order of priority, and the multiple regression model with build rate as the target item is compared with the measured data, where R2 is the goodness of fit value of the corresponding multiple regression model. The closer the goodness of fit value is to 1, the better the fit of the multiple regression model to the measured value, and vice versa. The BuildRate prediction value_10 is expressed as the prediction value of the multiple regression model with the first 10% feature items taken in order of priority.

[0078] The multivariate regression model with the maximum goodness of fit value is selected as the multivariate regression model corresponding to the optimal second feature item set. Furthermore, the relevant items and irrelevant items that affect the formation deflection rate are distinguished according to the feature items of the multivariate regression model with the maximum goodness of fit, the weight values ​​of the feature items of the multivariate regression model are obtained, and the influence of each feature item is evaluated. For example, according to the weight values ​​of active factor parameters such as steering parameters and drilling parameters, the formation adaptability and deflection ability of the rotary steering tool are evaluated; according to the weight values ​​of passive factor parameters such as formation lithology and formation spatial displacement, the influence of formation lithology and spatial changes on the deflection rate is evaluated.

[0079] like Figure 4 As shown in the figure, the goodness of fit value of BuildRate prediction value_100 is the largest (R2 is 0.792), that is, the multivariate regression model corresponding to the first 100% feature items (all feature items) in the order of priority has the best fit; the goodness of fit value of BuildRate prediction value_90 is second (R2 is 0.791). It should be noted that in theory, the multivariate regression model with more selected feature items and sufficient training samples has the best fit. However, in the actual field environment, affected by the number of measurement parameters while drilling (or rotary steering tools), BuildRate prediction value_90 with the closest goodness of fit value to BuildRate prediction value_100 or the multivariate regression model corresponding to BuildRate prediction value_70 may be selected to evaluate the formation steering characteristics. Alternatively, multivariate regression models with different ranking intervals are selected in different formation areas and different formation depth intervals.

[0080] Step S205: evaluating the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set.

[0081] According to the multivariate regression model corresponding to the optimal set of second characteristic items, the formation steering characteristics can be explained, predicted and tested for various hypotheses. For example, the formation steering characteristics are described as a whole, and the characteristic items are arranged according to the type of influencing factors, in the order of active factors including steering parameters and drilling parameters, and passive factors including lithology parameters and spatial displacement parameters, and a correlation matrix is ​​constructed together with the slope target item. Figure 5 The formation steering characteristic description correlation matrix diagram shown is a correlation matrix (symmetric matrix) composed of correlation coefficients between columns (characteristic items). For example, the value (0.73) in the first row and second column of the correlation matrix diagram represents the correlation coefficient between the build-up rate and the steering force.

[0082] Optionally, the influence of each feature item on the guidance effect is evaluated according to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set.

[0083] Optionally, the slope rate is quantitatively analyzed according to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, and the correlation coefficient between each feature item and the target item. As shown in Table 1, the correlation coefficient and influence weight of each factor affecting the slope rate are quantitatively analyzed.

[0084] Table 1

[0085] Influencing factors Guiding force Drilling time Gamma Drilling pressure Well deviation position well deep Vertical Depth Correlation coefficient 0.727 -0.019 -0.093 -0.015 0.01 -0.204 0.204 0.395 Impact Weight 0.04 -0.028 -0.012 -0.038 -0.547 0.601 0.013 1.207

[0086] It can be seen from Table 1 that the correlation coefficient between the guiding force and the build rate is the largest (0.727), but the influence weight is only 0.04; the correlation coefficient between the vertical depth and the build rate is second (0.395), but the influence weight is the largest (1.207).

[0087] The solution provided by the above-mentioned embodiment of the present invention establishes multivariate regression models based on multiple second feature item sets, calculates the goodness-of-fit value of the multivariate regression model corresponding to each second feature item set based on the measured data, selects the multivariate regression model with the maximum goodness-of-fit value as the multivariate regression model corresponding to the optimal second feature item set, and performs parameter testing on the multivariate regression model by means of goodness-of-fit method, thereby further improving the accuracy of the multivariate regression model.

[0088] Figure 6 The structural schematic diagram of the formation steering characteristic evaluation device according to the embodiment of the present invention is shown. The formation steering characteristic evaluation device 600 comprises: a feature selection module 610 , a qualitative analysis module 620 , a quantitative analysis module 630 and an evaluation module 640 .

[0089] The feature selection module 610 is used to extract feature items according to the influencing factors of the build inclination rate to obtain a first feature item set;

[0090] The qualitative analysis module 620 is used to perform correlation analysis on each feature item in the first feature item set with the build inclination rate as the target item, so as to obtain the correlation coefficient between each feature item and the target item;

[0091] The quantitative analysis module 630 is used to select multiple second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; take the slope rate as the target item, perform multiple regression based on the multiple second feature item sets respectively, and select the multiple regression model corresponding to the optimal second feature item set;

[0092] The evaluation module 640 is used to evaluate the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set.

[0093] In an optional manner, the first feature item set includes active factor feature items and passive factor feature items;

[0094] The active factor feature items include: steering parameters and drilling parameters;

[0095] The passive factor characteristic items include: formation lithology parameters and formation change space parameters.

[0096] In an optional manner, the qualitative analysis module 620 is further used to:

[0097] Sort the feature items in the first feature item set in descending order of correlation coefficient;

[0098] The quantitative analysis module 630 is further used to:

[0099] A plurality of second feature item sets are selected according to different preset sorting intervals.

[0100] In an optional manner, the quantitative analysis module 630 is further used to:

[0101] Based on the multiple second feature item sets, respectively establish a multivariate regression model;

[0102] Based on the measured data, calculate the goodness of fit value of the multivariate regression model corresponding to each second feature item set;

[0103] The multiple regression model with the maximum goodness of fit value is selected as the multiple regression model corresponding to the optimal second feature item set.

[0104] In an optional manner, the quantitative analysis module 630 is further used to:

[0105] Obtain the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set.

[0106] In an optional manner, the evaluation module 640 is further configured to:

[0107] According to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, the influence of each feature item on the guidance effect is evaluated.

[0108] In an optional manner, the evaluation module 640 is further configured to:

[0109] The build slope rate is quantitatively analyzed according to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, and the correlation coefficient between each feature item and the target item.

[0110] The solution provided by the above embodiment of the present invention extracts feature items according to the influencing factors of the build rate to obtain a first feature item set; taking the build rate as the target item, performing correlation analysis on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item; selecting multiple second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; taking the build rate as the target item, performing multivariate regression based on multiple second feature item sets respectively, and selecting the multivariate regression model corresponding to the optimal second feature item set; evaluating the formation guidance characteristics according to the multivariate regression model corresponding to the optimal second feature item set. The present invention selects the multivariate regression model corresponding to the optimal feature item based on the influencing factors of the build rate, and uses a combination of qualitative analysis and quantitative analysis to achieve accurate evaluation and quantitative / intuitive analysis of the formation guidance characteristics.

[0111] Figure 7 A schematic diagram of the structure of an embodiment of a computing device of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the computing device.

[0112] like Figure 7 As shown, the computing device may include: a processor (processor) 702 , a communications interface (Communications Interface) 704 , a memory (memory) 706 , and a communication bus 708 .

[0113] The processor 702, the communication interface 704, and the memory 706 communicate with each other via a communication bus 708. The communication interface 704 is used to communicate with other devices such as a client or other server network elements. The processor 702 is used to execute a program 710, which can specifically execute the relevant steps in the above-mentioned embodiment of the method for evaluating formation steering characteristics.

[0114] Specifically, the program 710 may include program codes, which include computer operation instructions.

[0115] The processor 702 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention. The one or more processors included in the computing device may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0116] The memory 706 is used to store the program 710. The memory 706 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0117] The program 710 may be specifically configured to enable the processor 702 to perform the following operations:

[0118] Extract characteristic items according to the influencing factors of the build-up rate to obtain a first characteristic item set;

[0119] Taking the inclination rate as the target item, a correlation analysis is performed on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item;

[0120] According to the correlation coefficient between each feature item in the first feature item set and the target item, multiple second feature item sets are selected; with the ramp rate as the target item, multiple regression is performed based on the multiple second feature item sets respectively, and the multiple regression model corresponding to the optimal second feature item set is selected;

[0121] The formation steering characteristics are evaluated according to the multivariate regression model corresponding to the optimal second feature item set.

[0122] In an optional manner, the first feature item set includes active factor feature items and passive factor feature items;

[0123] The active factor feature items include: steering parameters and drilling parameters;

[0124] The passive factor characteristic items include: formation lithology parameters and formation change space parameters.

[0125] In an optional manner, the program 710 enables the processor to perform the following operations:

[0126] Sort the feature items in the first feature item set in descending order of correlation coefficient;

[0127] A plurality of second feature item sets are selected according to different preset sorting intervals.

[0128] In an optional manner, the program 710 enables the processor to perform the following operations:

[0129] Based on the multiple second feature item sets, respectively establish a multivariate regression model;

[0130] Based on the measured data, calculate the goodness of fit value of the multivariate regression model corresponding to each second feature item set;

[0131] The multiple regression model with the maximum goodness of fit value is selected as the multiple regression model corresponding to the optimal second feature item set.

[0132] In an optional manner, the program 710 enables the processor to perform the following operations:

[0133] Obtain the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set.

[0134] In an optional manner, the program 710 enables the processor to perform the following operations:

[0135] According to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, the influence of each feature item on the guidance effect is evaluated.

[0136] In an optional manner, the program 710 enables the processor to perform the following operations:

[0137] The build slope rate is quantitatively analyzed according to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, and the correlation coefficient between each feature item and the target item.

[0138] The solution provided by the above embodiment of the present invention extracts feature items according to the influencing factors of the build rate to obtain a first feature item set; taking the build rate as the target item, performing correlation analysis on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item; selecting multiple second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; taking the build rate as the target item, performing multivariate regression based on multiple second feature item sets respectively, and selecting the multivariate regression model corresponding to the optimal second feature item set; evaluating the formation guidance characteristics according to the multivariate regression model corresponding to the optimal second feature item set. The present invention selects the multivariate regression model corresponding to the optimal feature item based on the influencing factors of the build rate, and uses a combination of qualitative analysis and quantitative analysis to achieve accurate evaluation and quantitative / intuitive analysis of the formation guidance characteristics.

[0139] An embodiment of the present invention provides a non-volatile computer storage medium, wherein the computer storage medium stores at least one executable instruction, and the computer executable instruction can execute the method for evaluating formation steering characteristics in any of the above method embodiments.

[0140] The algorithm or display provided herein is not inherently related to any particular computer, virtual system or other equipment. Various general purpose systems can also be used together with the teachings based on this. According to the above description, it is obvious to construct the structure required for this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description made to specific languages ​​above is for disclosing the best mode of the present invention.

[0141] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0142] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, the various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than the features explicitly recited in each claim. More specifically, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Therefore, the claims that follow the specific embodiment are hereby expressly incorporated into the specific embodiment, with each claim itself serving as a separate embodiment of the present invention.

[0143] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0144] In addition, those skilled in the art will appreciate that, although some embodiments herein include certain features included in other embodiments but not other features, the combination of features of different embodiments is meant to be within the scope of the present invention and form different embodiments. For example, in the claims below, any one of the claimed embodiments may be used in any combination.

[0145] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all functions of some or all components according to embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., computer program and computer program product) for executing part or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0146] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

Claims

1. A method for evaluating formation steering characteristics, characterized in that: The method comprises: Extract characteristic items according to the influencing factors of the build-up rate to obtain a first characteristic item set; Taking the inclination rate as the target item, a correlation analysis is performed on each feature item in the first feature item set to obtain the correlation coefficient between each feature item and the target item; According to the correlation coefficient between each feature item in the first feature item set and the target item, multiple second feature item sets are selected; with the ramp rate as the target item, multiple regression is performed based on the multiple second feature item sets respectively, and the multiple regression model corresponding to the optimal second feature item set is selected; The formation steering characteristics are evaluated according to the multivariate regression model corresponding to the optimal second feature item set.

2. The method according to claim 1, characterized in that The first feature item set includes active factor feature items and passive factor feature items; The active factor feature items include: steering parameters and drilling parameters; The passive factor characteristic items include: formation lithology parameters and formation change space parameters.

3. The method according to claim 1, characterized in that After performing correlation analysis on each feature item in the first feature item set with the build inclination rate as the target item to obtain the correlation coefficient between each feature item and the target item, the method further includes: Sort the feature items in the first feature item set in descending order of correlation coefficient; The selecting of a plurality of second feature item sets further comprises: A plurality of second feature item sets are selected according to different preset sorting intervals.

4. The method according to claim 1, characterized in that: The step of taking the ramp rate as the target item, performing multiple regressions based on the plurality of second feature item sets respectively, and selecting the multiple regression model corresponding to the optimal second feature item set further comprises: Based on the multiple second feature item sets, respectively establish a multivariate regression model; Based on the measured data, calculate the goodness of fit value of the multivariate regression model corresponding to each second feature item set; The multiple regression model with the maximum goodness of fit value is selected as the multiple regression model corresponding to the optimal second feature item set.

5. The method according to claim 1, characterized in that After selecting the multivariate regression model corresponding to the optimal second feature item set, the method further includes: Obtain the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set.

6. The method according to claim 5, characterized in that The evaluating of the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set further comprises: According to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, the influence degree of each feature item on the guidance effect is evaluated.

7. The method according to claim 1, characterized in that The evaluating of the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set further comprises: The build slope rate is quantitatively analyzed according to the weight value of each feature item in the multivariate regression model corresponding to the optimal second feature item set, and the correlation coefficient between each feature item and the target item.

8. A device for evaluating formation guidance characteristics, characterized in that: include: A feature selection module is used to extract feature items according to the influencing factors of the build inclination rate to obtain a first feature item set; A qualitative analysis module is used to perform correlation analysis on each feature item in the first feature item set with the slope rate as the target item, so as to obtain the correlation coefficient between each feature item and the target item; A quantitative analysis module, configured to select a plurality of second feature item sets according to the correlation coefficient between each feature item in the first feature item set and the target item; taking the slope rate as the target item, performing multiple regressions based on the plurality of second feature item sets respectively, and selecting a multiple regression model corresponding to the optimal second feature item set; An evaluation module is used to evaluate the formation steering characteristics according to the multivariate regression model corresponding to the optimal second feature item set.

9. A computing device comprising: A processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the method for evaluating formation steering characteristics as described in any one of claims 1-7.

10. A computer storage medium, wherein at least one executable instruction is stored in the storage medium, and wherein the executable instruction enables a processor to execute operations corresponding to the method for evaluating formation steering characteristics according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Method for reconstructing logging curve

    CN104533400A

  • Drilling process build-up rate prediction method and system based on genetic algorithm optimization

    CN111144053A

  • Method, device, and program for making prediction model by multiple regression analysis

    WO2008126209A1