A method and system for real-time calculation of torque while drilling based on intelligent correction strategy

Abstract

The application provides a method and system for real-time calculation of torque while drilling based on an intelligent correction strategy, which loads well logging data and static data for constructing a model of friction torque while drilling, calculates full-well axial force and torque with surface hook load and torque as initial conditions, and draws a full-well axial force curve along well depth; then automatically identifies tripping conditions according to well logging data, and labels the surface hook load at different depths when the conditions are met, so as to select a curve with the largest similarity according to the Fréchet distance between the hook load calibration value and the axial force curve, and apply the corresponding optimal friction coefficient to the correction of the model of friction torque while drilling; finally, the model of friction torque while drilling is corrected and calculation is implemented. The scheme can optimize and correct the friction coefficient of the calculation model in real time during the implementation of the calculation, overcomes the defects of insufficient accuracy of the prior art, and improves the intelligence and timeliness of the calculation of friction torque while drilling.

Description

Technical Field

[0001] This invention relates to the field of oil drilling engineering optimization technology, and in particular to a method and system for real-time calculation of friction and torque while drilling based on intelligent correction strategies. Background Technology

[0002] Monitoring and controlling downhole friction torque is crucial for drilling success. By comparing and analyzing the differences between real-time monitoring data on hook load and rotary table torque and theoretical calculations, it is possible to evaluate wellbore cleanliness, identify complex downhole conditions such as wellbore necking and collapse, and promptly grasp changes in drilling fluid properties, wellbore trajectory smoothness, and the use of friction-reducing and torque-lowering tools. During drilling operations, when there is a significant difference between measured data and theoretical calculation models, it is necessary to use the measured data. Typically, this involves manually calculating the friction coefficient using a friction torque model, which is time-consuming and labor-intensive and cannot achieve real-time calculation and analysis. Furthermore, if the collected measured parameters are not precise tripping or bottom-out rotation data, it can lead to serious deviations in the results.

[0003] Some technicians have conducted research on real-time monitoring schemes for friction torque. For example, Tang Honglin, Sun Mingxin, and others conducted research on real-time monitoring methods for friction torque in the article "Monitoring Methods for Friction Torque in Extended Distance Wells". They continuously recorded the hook load when raising, lowering, and rotating the drill string during drilling, and recorded the combined drilling torque value and the rotation torque value when lifting the drill string from the bottom of the well under different well depths. The recorded values ​​were marked on the friction torque monitoring chart to form a comparison curve between real-time monitoring data and theoretical calculation data, which was then manually judged. Chen Weiqing, Sun Haifang, and others conducted research on the prediction and analysis of friction torque in horizontal gas-drilled wells in "Back Calculation and Analysis of Friction Torque Coefficient in Gas Drilling Horizontal Wells" based on field tests in horizontal gas-drilled sections in northeastern Sichuan. The simulation calculation and analysis showed that the friction coefficient under gas drilling conditions is much larger than that under conventional drilling conditions, which is the direct cause of severe friction torque in horizontal gas-drilled sections. In summary, existing studies all directly use existing static friction-torsion models for calculation. The friction coefficient of a static model is fixed, which cannot guarantee that the calculation results of this model are reliable for different working conditions or situations in drilling engineering.

[0004] The information disclosed in the background section of this invention is intended only to enhance the understanding of the general background of this invention, and should not be construed as an admission or in any way implying that such information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] To address the aforementioned problems, this invention provides a real-time calculation method for drilling friction and torque based on an intelligent correction strategy. This method identifies drilling conditions in real time and, combined with intelligent data mining and clustering methods, extracts valuable logging data for automatic intelligent correction of the drilling friction and torque model. This reduces human intervention, improves model calculation accuracy, and enables online real-time monitoring of the entire well's friction and torque, facilitating analysis of abnormal downhole conditions during drilling. In one embodiment, the method includes:

[0006] The data loading steps include collecting and loading real-time logging data of the well to be logged and static data used to construct the drilling friction torque model;

[0007] The steps for plotting the whole-well curve are as follows: using the surface hook load and torque as initial conditions, calculate the axial force and torque of the whole well respectively, and plot the curve of the calculation results along the well depth as the whole-well axial force curve;

[0008] The load labeling step involves automatically identifying the real-time tripping and running conditions using the real-time logging data, and labeling the hook load at different depths according to the set parameters when the set target conditions are met.

[0009] The correction coefficient decision-making steps include calculating the Frescher distance between the hook load calibration value and the axial force curve of the whole well, determining whether there is a need for correction, and if so, selecting the curve with the highest similarity, using the friction coefficient of the corresponding curve as the target optimal friction coefficient, and applying it to the correction of the drilling friction torque model.

[0010] The calculation and implementation steps involve using the modified drilling friction torque model to calculate the real-time friction torque during the well logging process.

[0011] Preferably, in one embodiment, in the data loading step, the real-time logging data includes: drilling pressure, rotational speed, and torque data; the static data includes: wellbore trajectory data, wellbore structure data, drill string assembly, and drilling fluid parameters.

[0012] Furthermore, in one embodiment, the method further includes, after the data loading step, designing a real-time calculation model input and output data interface based on the soft rod friction torque model, and developing a real-time friction torque calculation model as a drilling friction torque model.

[0013] Specifically, in one embodiment, the data loading step further includes: if it is the first correction, then based on the preset data setting principle, set the initial three sets of casing and open hole friction coefficients for the constructed drilling friction torque model; otherwise, based on the friction coefficient used in the previous correction, fluctuate up and down by 0.1 to form three sets of friction coefficients, and perform friction torque calculation for the next well section.

[0014] In an optional embodiment, during the load marking step, real-time tripping and tripping conditions are identified through the following steps:

[0015] The drilling condition identification model automatically determines the current drilling condition based on real-time logging data.

[0016] Once it is determined that the drilling operation is in the tripping or tripping condition, the current motion acceleration of the drill string is calculated by the change in the drill bit position.

[0017] When the acceleration of the drill bit is less than the set threshold, the current working condition is determined to meet the target working condition, so as to ensure that the drill bit moves at a constant speed and is in a relatively stable state.

[0018] Furthermore, in one embodiment, in the load marking step, the loads on the hooks at different depths are marked by the following operations:

[0019] Record the hook load values ​​at different depths of the well to be tested, marking them every 10m until the maximum lifting depth is reached, and draw the hook load marking points on the axial force diagram.

[0020] Specifically, in one embodiment, the correction coefficient decision step includes the following steps:

[0021] Based on the Frescher distance between the hook load calibration values ​​at different well depths and multiple sets of theoretical axial force curves, a similarity evaluation algorithm F(A, B) is established with each marker point corresponding to a distance value.

[0022] The friction coefficient of the curve with the highest similarity is selected as the current optimal friction coefficient. The drilling friction torque model is corrected with the optimal friction coefficient until the similarity between the measured hook load and the theoretical curve meets the set conditions, and the correction ends.

[0023] The coefficients α and β of the evaluation algorithm are obtained by multivariate regression of real-time data.

[0024] Optionally, in one embodiment, a similarity evaluation algorithm F(A, B) is established by summing the Fraser distances of all depth points of the two lines.

[0025] Based on other aspects of the methods described in any one or more of the foregoing embodiments, the present invention also provides a storage medium storing program code that can implement the methods described in any one or more of the foregoing embodiments.

[0026] Based on the application aspects of the methods described in any one or more of the above embodiments, the present invention also provides a real-time drilling friction and torque calculation system based on an intelligent correction strategy, which executes the methods described in any one or more of the above embodiments.

[0027] Compared with the closest prior art, the present invention also has the following beneficial effects:

[0028] This invention provides a real-time calculation method and system for drilling friction and torque based on an intelligent correction strategy. The method first loads logging data and static data for constructing a drilling friction and torque model, and then automatically identifies tripping and running conditions based on the logging data. This invention identifies drilling conditions based on logging data combined with intelligent data mining methods, extracts valuable data from complex real-time logging data for model self-correction, avoids the involvement of intermediate data, fundamentally ensures data accuracy, reduces human intervention, and enhances intelligence.

[0029] When the working conditions are met, the hook load at different depths is marked. Based on the Frescher distance between the hook load calibration value and the axial force curve, the curve with the highest similarity is selected. The corresponding optimal friction coefficient is applied to the correction of the drilling friction torque model. Intelligent automatic parameter adjustment is achieved for the drilling friction torque model, and reliable self-correction of the model is completed. This effectively improves the accuracy of model calculation and realizes reliable online monitoring of friction torque throughout the well.

[0030] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the description, claims, and drawings. Attached Figure Description

[0031] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0032] Figure 1 This is a flowchart illustrating a real-time calculation method for drilling friction and torque based on an intelligent correction strategy provided in an embodiment of the present invention.

[0033] Figure 2 This is a detailed implementation diagram of the real-time calculation method for drilling friction and torque based on an intelligent correction strategy provided in another embodiment of the present invention;

[0034] Figure 3 This is an example diagram of the calculation results of the real-time calculation method for drilling friction and torque based on intelligent correction strategy provided in the embodiments of the present invention;

[0035] Figure 4 This is a schematic diagram of the structure of a real-time calculation system for drilling friction and torque based on an intelligent correction strategy provided in another embodiment of the present invention. Detailed Implementation

[0036] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples. Those skilled in the art will then fully understand how the present invention uses technical means to solve technical problems and achieve technical effects, and will be able to implement the present invention specifically based on the above-described implementation process. It should be noted that, as long as there is no conflict, the various embodiments and features of the present invention can be combined with each other, and the resulting technical solutions are all within the protection scope of the present invention.

[0037] Although the flowchart describes the operations as sequential processes, many of these operations can be performed in parallel, concurrently, or simultaneously. The order of the operations can be rearranged. A process can terminate when its operation is complete, but it may also have additional steps not included in the diagram. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.

[0038] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the exemplary embodiments. Unless the context clearly indicates otherwise, the singular forms “a” and “an” as used herein are also intended to include the plural. It should also be understood that the terms “comprising” and / or “including” as used herein specify the presence of the stated features, integers, steps, operations, units, and / or components, without excluding the presence or addition of one or more other features, integers, steps, operations, units, components, and / or combinations thereof.

[0039] In the implementation of oil drilling projects, the monitoring and control of downhole friction torque is crucial to the success or failure of drilling. By comparing and analyzing the differences between real-time monitoring data on hook load and rotary table torque and theoretical calculation data, it is possible to evaluate the cleanliness of the wellbore, identify complex downhole conditions such as wellbore necking and collapse, and promptly grasp changes in drilling fluid performance, wellbore trajectory smoothness, and the use of friction-reducing and torque-reducing tools. During drilling operations, when there is a significant difference between measured data and theoretical calculation models, it is necessary to use the measured data. Usually, the friction coefficient is manually calculated from the friction torque model, which is time-consuming and labor-intensive and cannot achieve real-time calculation and analysis. In addition, if the collected measured parameters are not accurate tripping or rotation data, it will lead to serious deviations in the results.

[0040] Some technicians have conducted research on real-time monitoring schemes for friction torque. For example, ① Tang Honglin, Sun Mingxin, and others conducted research on real-time monitoring methods for friction torque in the article "Monitoring Methods for Friction Torque in Extended Distance Wells". They continuously recorded the hook load when raising, lowering, and rotating the drill string during drilling, and recorded the combined drilling torque value and the rotation torque value when lifting the drill string from the bottom of the well under different well depths. The recorded values ​​were marked on the friction torque monitoring chart to form a comparison curve between real-time monitoring data and theoretical calculation data, which was then manually judged.

[0041] ② In their paper "Intelligent Real-Time Analysis of Drill String Friction Torque and Prediction of Sticking Trend," Zhu Shuo, Song Xianzhi, et al., address the problems of inaccurate prediction of bottom hole drilling pressure torque and the blind determination of drill string friction coefficient by proposing an intelligent real-time analysis method for drill string friction torque. This method utilizes a neural network model to calculate the bottom hole drilling pressure torque in real time, and then combines it with a friction torque rigid rod model to use a bisection method to invert the friction coefficient in real time, accurately analyzing the stress on the drill string. Considering that the drill string friction coefficient, to a certain extent, characterizes the sticking trend, this method is further used to predict the sticking trend in drilling.

[0042] ③ In their paper "Back Calculation and Analysis of Friction-Torque Coefficient in Gas Drilling Horizontal Wells," Chen Weiqing, Sun Haifang, and others, combining field tests of gas drilling horizontal sections in northeastern Sichuan, conducted research on the prediction and analysis of friction-torque in gas drilling horizontal sections. Simulation calculations and analysis showed that the friction coefficient under gas drilling conditions is much higher than that under conventional drilling, which is the direct cause of severe friction-torque in gas drilling horizontal sections. In summary, existing studies all directly use existing static friction-torque models for calculation, without involving intelligent algorithms to automatically correct the friction coefficient and achieve online real-time friction-torque calculation. The friction coefficient of the static model is fixed, which cannot guarantee the reliability of the calculation results for different working conditions or situations in drilling engineering, resulting in insufficient accuracy. Therefore, achieving intelligent automatic parameter adjustment and self-correction of the friction-torque model based on logging data is an unavoidable problem for realizing real-time monitoring of friction-torque.

[0043] Another approach employed by technicians involved a dynamic friction torque calculation method for complex well structures based on similarity theory. This method first establishes a dynamic model corresponding to the full-well drill string system of a standard well, then uses the finite element method to calculate the dynamic friction torque experienced by the drill string. The calculated data is then extended to a wider range of well inclination angles using interpolation. Next, the finite element dynamic model is used to calculate the influence of mechanical parameters on the friction torque calculation results, quantifying the proportion of each mechanical parameter in the friction torque calculation results and establishing numerical patterns. A standard well similar to the simulated well is then matched to assess the similarities and differences between the standard well and the simulated well. Finally, the similarities and differences between the simulated well and the standard well are converted into calculated values, and the calculation results for the simulated well are obtained through linear superposition. However, this method is obviously slow, hindering field application and lacking practicality. Furthermore, the calculation involves numerous intermediate parameters and theoretical calculations, resulting in insufficient accuracy.

[0044] To address the aforementioned issues, this invention provides a method and system for real-time calculation of friction and torque while drilling based on an intelligent correction strategy. This invention proposes an intelligent automatic parameter adjustment for the friction and torque model based on logging data, enabling model self-correction. Based on this, combined with intelligent data mining methods, drilling conditions are identified, and valuable data is extracted from complex real-time logging data for model self-correction, reducing the need for human intervention and achieving real-time monitoring of friction and torque.

[0045] During implementation, this invention identifies drilling conditions in real time and combines intelligent data mining and clustering methods to extract valuable logging data for automatic intelligent correction of the drilling friction torque model, thereby improving the accuracy of model calculations and enabling online real-time monitoring of the entire well's friction torque to facilitate analysis of abnormal downhole conditions during drilling.

[0046] The following describes the detailed flow of the method according to an embodiment of the present invention with reference to the accompanying drawings, the steps of which can be executed in a computer system containing, for example, a set of computer-executable instructions. Although the logical order of the steps is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0047] Example 1

[0048] Figure 1 This diagram illustrates a flowchart of the real-time calculation method for drilling friction and torque based on an intelligent correction strategy provided in Embodiment 1 of the present invention. (Refer to...) Figure 1 As can be seen, the method includes the following steps.

[0049] The data loading steps include collecting and loading real-time logging data of the well to be logged and static data used to construct the drilling friction torque model;

[0050] The steps for plotting the whole-well curve are as follows: using the surface hook load and torque as initial conditions, calculate the axial force and torque of the whole well respectively, and plot the curve of the calculation results along the well depth as the whole-well axial force curve;

[0051] The load labeling step involves automatically identifying the real-time tripping and running conditions using the real-time logging data, and labeling the hook load at different depths according to the set parameters when the set target conditions are met.

[0052] The correction coefficient decision-making steps include calculating the Frescher distance between the hook load calibration value and the axial force curve of the whole well, determining whether there is a need for correction, and if so, selecting the curve with the highest similarity, using the friction coefficient of the corresponding curve as the target optimal friction coefficient, and applying it to the correction of the drilling friction torque model.

[0053] The calculation and implementation steps involve using the modified drilling friction torque model to calculate the real-time friction torque during the well logging process.

[0054] In practical applications, the first step is to design a real-time calculation model input and output data interface based on the currently mature and commonly used soft rod friction torque model, and develop a real-time friction torque calculation model as a drilling friction torque model.

[0055] Based on the scheme in the above embodiments, by identifying drilling conditions in real time and combining intelligent data mining methods, valuable logging data is extracted for automatic correction of the friction and torque model, reducing manual intervention in the real-time monitoring process, and improving the accuracy of the calculation model. This enables real-time monitoring of friction and torque, helps identify downhole complexities and risks, and ensures safe and efficient drilling.

[0056] Figure 2 The following is a detailed implementation diagram of the real-time calculation method for drilling friction and torque based on an intelligent correction strategy provided in this embodiment of the invention, as shown in the figure. Figure 2 As shown, in a practical application, in one embodiment, the real-time logging data in the data loading step includes: drilling pressure, rotation speed and torque data; the static data includes: wellbore trajectory data, wellbore structure data, drill string assembly and drilling fluid parameters.

[0057] Furthermore, in one embodiment, the data loading step further includes: if it is the first correction, setting initial three sets of casing and open hole friction coefficients for the constructed drilling friction torque model according to preset data setting principles; otherwise, using the friction coefficients used in the previous correction as a basis, with fluctuations of 0.1 up and down to form three sets of friction coefficients, and performing friction torque calculations for the next well section. The preset data setting principles can be set and stored by professionals based on their experience for different reservoirs, for later retrieval.

[0058] In an optional embodiment, during the load marking step, real-time tripping and tripping conditions are identified through the following steps:

[0059] The drilling condition identification model automatically determines the current drilling condition based on real-time logging data.

[0060] Once it is determined that the drilling operation is in the tripping or tripping condition, the current motion acceleration of the drill string is calculated by the change in the drill bit position.

[0061] When the acceleration of the drill string is less than a set threshold, the current working condition is determined to meet the target working condition, ensuring that the drill string moves at a constant speed and is in a relatively stable state. The drilling condition identification model is formed by constructing different logical rules based on logging parameters such as well depth, drill bit position, drilling pressure, rotational speed, torque, and displacement. For example, during drilling, if the well depth minus the drill bit position is less than 0.1m and the rotational speed is greater than 0.

[0062] Specifically, in the load marking step, the loads on the large hooks at different depths are marked through the following operations:

[0063] Record the hook load values ​​at different depths of the well to be tested, marking them every 10m until the maximum lifting depth is reached, and draw the hook load marking points on the axial force diagram.

[0064] Furthermore, in one embodiment, the correction coefficient decision step includes the following steps:

[0065] When the deviation between the calculated theoretical curve and the measured value reaches the set requirements (e.g., similarity < 0.7), it is determined that there is a need for correction. When it is determined that there is a need for correction, based on the Frescher distance between the hook load calibration value at different well depths and multiple sets of theoretical axial force curves, each mark point depth corresponds to a distance value. The Frescher distances of all depth points on the two lines are summed to establish a similarity evaluation algorithm F(A, B).

[0066] The friction coefficient of the curve with the highest similarity is selected as the current optimal friction coefficient. The drilling friction torque model is corrected with the optimal friction coefficient until the similarity between the measured hook load and the theoretical curve meets the set conditions, and the correction ends.

[0067] The coefficients α and β of the evaluation algorithm are obtained by multivariate regression of real-time data such as drilling pressure, rotation speed, torque, and hook load. If the theoretical calculation curve is found to deviate from the measured value, it is determined that there is a need for correction.

[0068] Then, the modified drilling friction torque model is used to calculate the friction torque in real time during the drilling process of the well to be logged, as shown in the attached figure. Figure 3 As shown.

[0069] This technology has been implemented in oil wells of the Northwest Oilfield Company. Taking the Permian drilling project of well SHB5-16H as an example, the implementation and application are carried out according to the following steps:

[0070] (1) Based on the discrete element friction torque model, design the input and output data interface of the real-time calculation model, and develop the real-time calculation model of friction torque.

[0071] (2) Load real-time logging data (such as drilling pressure, rotation speed, torque, etc.) and static data for constructing friction torque calculation, including wellbore trajectory data, well structure, drill string assembly, drilling fluid parameters, etc., and set 3 sets of casing and open hole friction coefficients. Using the surface hook load and torque as initial conditions, calculate the axial force and torque of the whole well and draw the variation curve along the well depth.

[0072] (3) The drilling condition identification model is used to automatically determine the tripping and running conditions using logging data;

[0073] (4) When the drill bit is being pulled up, the current acceleration of the drill bit is calculated by the change in the position of the drill bit. If the acceleration is less than 0.1, it is considered that the drill bit is moving at a constant speed and is in a relatively stable state.

[0074] (5) Start recording the hook load values ​​at different depths, marking them every 10m until the maximum lifting depth is reached, and draw the hook load marking points on the axial force diagram.

[0075] (6) Based on the Fraser distance between the hook load calibration values ​​at different well depths and multiple sets of theoretical axial force curves, a similarity evaluation algorithm F(A, B) is established, with each marked point corresponding to a distance value. The algorithm coefficients α and β are obtained by multivariate regression of real-time data on drilling pressure, rotational speed, torque, and hook load. The friction coefficient of the curve with the highest similarity is the current optimal friction coefficient.

[0076] (7) Correct the real-time friction torque calculation model with the optimal friction coefficient, and use the corrected model to calculate the friction torque of the next well section.

[0077] (8) When the drill string is pulled up or down again, a set of hook loads is automatically marked, and the Frescher distance between the set of hook loads and the current axial force curve is automatically calculated. If the theoretical calculation curve is found to deviate from the measured value, the correction mode is activated.

[0078] (9) Based on the current friction coefficient, fluctuate it up and down by 0.1 to form 3 sets of friction coefficients, and calculate the friction torque of the next well section;

[0079] (10) Repeat (6) until the measured hook load basically matches the theoretical curve, then the correction is completed and the calculation continues.

[0080] Based on the above logic and the trial application process in multiple wells in the Northwest Engineering Area, the results show that the calculation results are basically consistent with the Landmark software. At 4:50 AM on September 13, 2020, the system automatically identified the drilling tool lifting condition and calculated and plotted the whole-well friction torque curve in real time. After calibration, the friction coefficients of the casing and open hole were 0.25 and 0.36, respectively. An anomaly was found by back-calculating the suspended weight, and after verification, it was confirmed that there was indeed a stuck condition. It can be seen that the drilling friction torque data calculated by the method of the embodiment of the present invention can truly reflect the current working condition at the bottom of the well.

[0081] The solution provided by this invention identifies drilling conditions in real time and combines intelligent data mining and clustering methods to extract valuable logging data for automatic intelligent correction of the downhole friction torque model, reducing human intervention. Compared with existing technologies, this not only improves intelligence and computational timeliness but also effectively enhances the model's computational accuracy, enabling online real-time monitoring of the entire well's friction torque for downhole abnormal condition analysis during drilling.

[0082] For the foregoing method embodiments, in order to simplify the description, they are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0083] It should be noted that, in other embodiments of the present invention, the method can also be combined with one or more of the above embodiments to obtain a new real-time calculation method for drilling friction and torque, so as to achieve reliable optimization of drilling engineering.

[0084] It should be noted that, based on the methods in any one or more embodiments of the present invention described above, the present invention also provides a storage medium storing program code that can implement the methods described in any one or more embodiments. When the program code is executed by the operating system, it can implement the real-time calculation method of drilling friction and torque based on the intelligent correction strategy as described above.

[0085] Example 2

[0086] The methods described in detail in the above-disclosed embodiments of the present invention can be implemented using various forms of devices or systems. Therefore, based on other aspects of the methods described in any one or more of the above embodiments, the present invention also provides a real-time drilling friction and torque calculation system based on an intelligent correction strategy. This system is used to execute the real-time drilling friction and torque calculation method based on an intelligent correction strategy described in any one or more of the above embodiments. Specific embodiments are given below for detailed description.

[0087] Specifically, Figure 4 The diagram shows a schematic representation of the real-time drilling friction and torsion calculation system based on an intelligent correction strategy provided in an embodiment of the present invention. Figure 4 As shown, the system includes:

[0088] The data loading module 41 is configured to collect and load real-time logging data of the well to be logged and static data for constructing a drilling friction torque model.

[0089] The whole-well curve plotting module 43 is configured to use the surface hook load and torque as initial conditions to calculate the whole-well axial force and torque respectively, and plot the curve of the calculation results along the well depth as the whole-well axial force curve;

[0090] The load labeling module 45 is configured to automatically identify the real-time tripping and running conditions using the real-time logging data, and to label the hook load at different depths according to the set parameters when the set target conditions are met.

[0091] The correction coefficient decision module 47 is configured to select the curve with the highest similarity based on the Frescher distance between the hook load calibration value and the axial force curve of the whole well, and use the friction coefficient of the corresponding curve as the target optimal friction coefficient to correct the friction torque model while drilling.

[0092] The calculation implementation module 49 is configured to calculate the real-time friction torque during the well logging process using the modified drilling friction torque model.

[0093] Preferably, in one embodiment, the data loading module 41 is configured to set the real-time logging data to include: drilling pressure, rotation speed and torque data; the static data includes: wellbore trajectory data, wellbore structure data, drill string assembly and drilling fluid parameters.

[0094] Furthermore, in one embodiment, the system further includes a model development module 42, which is configured to design a real-time calculation model input and output data interface based on the soft rod friction torque model, and develop a real-time friction torque calculation model as a drilling friction torque model.

[0095] Specifically, in one embodiment, the data loading module 41 is configured as follows: if it is the first correction, it sets the initial three sets of casing and open hole friction coefficients for the constructed drilling friction torque model based on the preset data setting principle; otherwise, it uses the friction coefficients used in the previous correction as the basis, with fluctuations of 0.1 up and down to form three sets of friction coefficients, and performs friction torque calculation for the next well section.

[0096] In an optional embodiment, the load marking module 45 identifies real-time tripping and tripping conditions through the following steps:

[0097] The drilling condition identification model automatically determines the current drilling condition based on real-time logging data.

[0098] Once it is determined that the drilling operation is in the tripping or tripping condition, the current motion acceleration of the drill string is calculated by the change in the drill bit position.

[0099] When the acceleration of the drill bit is less than the set threshold, the current working condition is determined to meet the target working condition, so as to ensure that the drill bit moves at a constant speed and is in a relatively stable state.

[0100] Furthermore, in one embodiment, the load labeling module 45 is also configured to label the hook loads at different depths through the following operations:

[0101] Record the hook load values ​​at different depths of the well to be tested, marking them every 10m until the maximum lifting depth is reached, and draw the hook load marking points on the axial force diagram.

[0102] Specifically, in one embodiment, the correction coefficient decision step includes the following steps:

[0103] Based on the Frescher distance between the hook load calibration values ​​at different well depths and multiple sets of theoretical axial force curves, a similarity evaluation algorithm F(A, B) is established with each marker point corresponding to a distance value.

[0104] The friction coefficient of the curve with the highest similarity is selected as the current optimal friction coefficient. The drilling friction torque model is corrected with the optimal friction coefficient until the similarity between the measured hook load and the theoretical curve meets the set conditions, and the correction ends.

[0105] The coefficients α and β of the evaluation algorithm are obtained by multivariate regression of real-time data on drilling pressure, rotational speed, torque, and hook load.

[0106] Optionally, in one embodiment, the correction coefficient decision module 47 establishes a similarity evaluation algorithm F(A, B) by summing the Fraser distances of all depth points of the two lines.

[0107] In the real-time calculation system for drilling friction and torque based on intelligent correction strategy provided in this embodiment of the invention, each module or unit structure can operate independently or in combination according to actual monitoring and calculation needs to achieve the corresponding technical effects.

[0108] It should be understood that the embodiments disclosed herein are not limited to the specific structures, processing steps, or materials disclosed herein, but should be extended to equivalent substitutions of these features as understood by those skilled in the art. It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting.

[0109] The phrase "an embodiment" in the specification means that a specific feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the invention. Therefore, the phrase "an embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment.

[0110] While the embodiments disclosed in this invention are as described above, the content is merely for the purpose of facilitating understanding of the invention and is not intended to limit the invention. Any person skilled in the art to which this invention pertains may make any modifications and variations in form and detail of the implementation without departing from the spirit and scope disclosed herein; however, the scope of patent protection for this invention shall still be determined by the scope defined in the appended claims.

Claims

1. A method for real-time calculation of drilling friction and torque based on an intelligent correction strategy, characterized in that, The method includes: Data loading steps: Collect and load real-time logging data of the well to be logged and static data for constructing the drilling friction torque model; Steps for plotting the whole-well curve: Using the surface hook load and torque as initial conditions, calculate the whole-well axial force and torque respectively, and plot the curve of the calculation results along the well depth as the whole-well axial force curve; The load labeling step involves automatically identifying the real-time tripping and running conditions using the real-time logging data, and labeling the hook load at different depths according to the set parameters when the set target conditions are met. Correction coefficient decision steps: Calculate the Frescher distance between the hook load calibration value and the axial force curve of the whole well, determine whether there is a need for correction, if so, select the curve with the highest similarity, and use the friction coefficient of the corresponding curve as the target optimal friction coefficient, and apply it to the correction of the drilling friction torque model. Calculation implementation steps: The real-time friction torque during the well logging process is calculated using the modified drilling friction torque model; The data loading step includes: if it is the first correction, then based on the preset data setting principle, set the initial 3 sets of casing and open hole friction coefficients for the constructed drilling friction torque model; otherwise, based on the friction coefficient used in the previous correction, fluctuate up and down by 0.1 to form 3 sets of friction coefficients, and perform friction torque calculation for the next well section. The correction coefficient decision step includes the following steps: Based on the Frescher distance between the hook load calibration values ​​at different well depths and multiple theoretical axial force curves, a similarity evaluation algorithm F(A, B) is established with each marker point corresponding to a distance value. The friction coefficient of the curve with the highest similarity is selected as the current optimal friction coefficient. The drilling friction torque model is corrected with the optimal friction coefficient until the similarity between the measured hook load and the theoretical curve meets the set conditions, and the correction ends. The coefficients α and β of the evaluation algorithm are obtained by multivariate regression of real-time data.

2. The method according to claim 1, characterized in that, In the data loading step, the real-time logging data includes: drilling pressure, rotation speed, and torque data; the static data includes: wellbore trajectory data, wellbore structure data, drill string assembly, and drilling fluid parameters.

3. The method according to claim 1, characterized in that, The method further includes, after the data loading step, designing a real-time calculation model input and output data interface based on the soft rod friction torque model, and developing a real-time friction torque calculation model as a drilling friction torque model.

4. The method according to claim 1, characterized in that, In the load marking step, the real-time tripping and running conditions are identified through the following steps: The drilling condition identification model automatically determines the current drilling condition based on real-time logging data. Once it is determined that the drilling operation is in the tripping or tripping condition, the current motion acceleration of the drill string is calculated by the change in the drill bit position. When the acceleration of the drill bit is less than the set threshold, the current working condition is determined to meet the target working condition, so as to ensure that the drill bit moves at a constant speed and is in a relatively stable state.

5. The method according to claim 1, characterized in that, In the load marking step, the loads on the large hooks at different depths are marked through the following operations: Record the hook load values ​​at different depths of the well to be tested, marking them every 10m until the maximum lifting depth is reached, and draw the hook load marking points on the axial force diagram.

6. The method according to claim 1, characterized in that, A similarity evaluation algorithm F(A, B) is established by summing the Fraser distances of all depth points on the two lines.

7. A storage medium, characterized in that, The storage medium stores program code that can implement the method as described in any one of claims 1 to 6.

8. A real-time drilling friction and torque calculation system based on an intelligent correction strategy, characterized in that, The system performs the method as described in any one of claims 1 to 6.

Images