A directional drilling tool face angle and steering rate joint control method based on double-channel fuzzy reasoning

Abstract

The application discloses a directional drilling tool face angle and steering rate joint control method based on a double-channel fuzzy inference, and relates to the technical field of automatic control of oil drilling. The method establishes a deviation of inclination and a deviation of azimuth between an actual drilling track and a target track, respectively establishes an inclination control channel and an azimuth control channel, and generates a build-up rate and a twist azimuth rate by combining with fuzzy inference on corresponding deviation change trends; on the basis, a tool face angle TF and a steering rate SR control instruction are further formed, so that real-time closed-loop correction on a directional drilling track attitude is realized.

Description

Technical Field

[0001] This invention relates to the field of automatic control technology for oil drilling, and in particular to a method for joint control of the face angle and steering ratio of directional drilling tools based on dual-channel fuzzy inference. Background Technology

[0002] In modern oil and gas exploration and development, rotary steerable systems are a crucial technology for trajectory control in extended reach wells, horizontal wells, and complex three-dimensional directional wells. Their core task is to adjust the steerable behavior of the drill string in real time based on the deviation between the actual drilled wellbore trajectory and the designed trajectory, ensuring the wellbore trajectory extends along the designed path. For rotary steerable drilling, the trajectory deviation typically needs to be further converted into control commands for tool face angle (TF) and steering ratio (SR). Therefore, how to stably and rationally generate TF and SR control commands under complex downhole conditions is a key issue in trajectory control.

[0003] Currently, existing directional well trajectory control methods still largely rely on traditional manual experience for open-loop or semi-open-loop control. Engineers acquire real-time inclination and azimuth data through a measurement-while-drilling system, compare this data with the target inclination and azimuth data, and then, based on experience, determine the necessary tool face and steering ratio settings. Control commands are then sent down via channels such as mud pulses. This open-loop mode, based on manual control, inevitably introduces significant latency and heavily depends on the operator's experience.

[0004] To improve the automation level of trajectory control, existing technologies have developed directional drilling control methods based on closed-loop control. Common methods include Proportional-Integral-Derivative (PID) control, Model Predictive Control (MPC), and some control methods based on empirical or analytical models. These methods typically compare actual attitude parameters such as the current wellbore inclination and azimuth with target values ​​to calculate the corresponding tool face angle and steering ratio control quantities, thus forming a closed-loop correction mechanism. Compared with manual control, these methods improve the real-time performance and automation level to some extent. However, actual drilling processes occur in high-temperature, high-pressure, and highly disturbed downhole environments, exhibiting significant nonlinearity, time-varying characteristics, complexity, and uncertainty, making it difficult for relevant control models to accurately describe real-world conditions. Traditional PID control methods, in particular, are prone to large overshoot, slow convergence, and large steady-state errors under complex conditions; while methods such as MPC typically involve complex model building and online solution processes, placing high demands on computational resources and real-time performance.

[0005] Furthermore, to address the strong nonlinearity, hysteresis, and uncertainties inherent in drilling systems, existing research has introduced intelligent control methods such as fuzzy control, reinforcement learning, robust control, and sliding mode control. For example, some studies employ fuzzy logic control, interval type II fuzzy control, or methods combined with reinforcement learning to track and control well deviation and azimuth trajectories, thereby improving the system's adaptability to uncertainties and disturbances. While these methods enhance the robustness of the control system to some extent, they still have some shortcomings. The algorithm structure is relatively complex, involving numerous parameter tunings, neural network training, or online iterative calculations, which is not conducive to real-time implementation in downhole environments with limited computing resources.

[0006] Therefore, in view of the problems of existing directional drilling trajectory control methods under complex downhole conditions, such as strong reliance on experience, limited model adaptability, complex algorithm implementation, and inconvenient coordination adjustment of well inclination and azimuth, there is an urgent need for a control method that can combine actual engineering control requirements and realize closed-loop correction of trajectory attitude under controllable computational complexity, thereby improving the rationality, real-time performance, and stability of tool face angle (TF) and steering ratio (SR) control command generation. Summary of the Invention

[0007] The purpose of this invention is to provide a method for joint control of the face angle and steering ratio of directional drilling tools based on dual-channel fuzzy inference, which aims to solve or improve at least one of the above-mentioned technical problems.

[0008] To achieve the above objectives, the present invention provides the following solution: A method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference includes: Obtain the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters. Calculate the well inclination deviation and azimuth deviation based on the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters. Calculate the well inclination deviation change trend and azimuth deviation change trend based on the previous measuring point trajectory attitude parameters, the current measuring point trajectory attitude parameters, and the target measuring point trajectory attitude parameters. Establish a well inclination control channel and an azimuth control channel, and use the well inclination deviation and the trend of the well inclination deviation as input variables for the well inclination control channel, and use the azimuth deviation and the trend of the azimuth deviation as input variables for the azimuth control channel; The input variables of the well inclination control channel and the azimuth control channel are fuzzified respectively, and fuzzy reasoning is performed based on a preset fuzzy rule base to obtain the intermediate control quantity representing the inclination adjustment requirement and the intermediate control quantity representing the torsional azimuth adjustment requirement respectively. The intermediate control quantity is defuzzified to obtain the slope rate control component and the torsional azimuth rate control component. The tool face angle and the guiding rate are jointly calculated based on the inclination rate control component and the torsional azimuth rate control component, and the tool face angle and the guiding rate are output as control commands for the current control cycle to complete the joint control.

[0009] Optionally, the well inclination deviation is the difference between the target well inclination angle and the actual well inclination angle, and the azimuth deviation is the difference between the target azimuth angle and the actual azimuth angle after angle normalization; The trend of well inclination deviation is calculated based on the well inclination angle of the previous measuring point, the well inclination angle of the current measuring point, and the target well inclination angle. The trend of azimuth deviation is calculated based on the azimuth angle of the previous measuring point, the azimuth angle of the current measuring point, and the target azimuth angle after angle normalization. The current measuring point trajectory attitude parameters include at least the current measuring point well depth, the current measuring point well inclination angle, and the current measuring point azimuth angle. The target measuring point trajectory attitude parameters include at least the target measuring point well depth, the target measuring point well inclination angle, and the target measuring point azimuth angle. The previous measuring point trajectory attitude parameters include at least the previous measuring point well depth, the previous measuring point well inclination angle, and the previous measuring point azimuth angle.

[0010] Optionally, the fuzzification process includes: multiplying the well deviation, the well deviation change trend, the azimuth deviation, and the azimuth deviation change trend by the corresponding input compression factor to perform scaling transformation, mapping each scaled input variable to a corresponding fuzzy linguistic variable, and determining the degree of membership of each input variable in different fuzzy sets through a pre-set membership function.

[0011] Optionally, the fuzzy rule base of the well inclination control channel uses the well inclination deviation and the well inclination deviation change trend as antecedents, and the intermediate control quantity representing the directional adjustment requirement as consequents; the fuzzy rule base of the azimuth control channel uses the azimuth deviation and the azimuth deviation change trend as antecedents, and the intermediate control quantity representing the torsional azimuth adjustment requirement as consequents; in the fuzzy inference process, the well inclination control channel and the azimuth control channel perform fuzzy inference operations independently and in parallel.

[0012] Optionally, the defuzzification process employs the centroid method, determining the centroid position based on the comprehensive distribution of the output membership function, and using the value corresponding to the centroid position as the deterministic output value after defuzzification; the deterministic output value is multiplied by the corresponding output compression factor to obtain the slope control component and the torsional azimuth control component.

[0013] Optionally, the tool face angle is calculated as follows: using the slope control component and the torsional azimuth control component as two orthogonal components of a two-dimensional vector, the azimuth angle of the two-dimensional vector is calculated using the arctangent function to obtain the original value of the tool face angle, and the original value of the tool face angle is normalized.

[0014] Optionally, the guidance rate is calculated as follows: the current inclination rate is calculated based on the inclination rate control component, the azimuth rate control component, the current well inclination angle at the current measuring point, and the preset maximum inclination capacity, and the ratio of the current inclination rate to the preset maximum inclination capacity is used as the guidance rate.

[0015] Optionally, the current build-up rate is calculated by multiplying the build-up rate control component and the torsional azimuth rate control component by the square root of the sum of the squares of the squares of the sine of the current measuring point well inclination angle, to obtain the current build-up rate.

[0016] Optionally, it also includes: trajectory attitude closed-loop iterative update; The trajectory attitude closed-loop iterative update process is as follows: The tool face angle and the guidance rate are input into the trajectory response model. The well inclination angle and azimuth angle at the end of the current control cycle are updated according to the trajectory response model. The updated well inclination angle and azimuth angle are used as the current measurement point trajectory attitude parameters for the next control cycle for iterative calculation until the attitude tracking control of the entire designed trajectory is completed.

[0017] Optionally, the trajectory response model updates the well inclination angle and azimuth angle based on the well inclination angle change rate formula and the azimuth angle change rate formula; the well inclination angle change rate is determined based on the mechanical drilling rate, the tool face angle, the steering ratio, the preset maximum build-up capacity, and the natural deviation term; the azimuth angle change rate is determined based on the mechanical drilling rate, the tool face angle, the steering ratio, the preset maximum build-up capacity, the natural steering offset, and the current well inclination angle.

[0018] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects: This invention discloses a joint control method for the face angle and steering ratio of directional drilling tools based on dual-channel fuzzy inference. The method includes: acquiring the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters; calculating the well deviation and azimuth deviation based on the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters; and calculating the well deviation change trend and azimuth deviation change trend based on the previous measuring point trajectory attitude parameters, the current measuring point trajectory attitude parameters, and the target measuring point trajectory attitude parameters; establishing a well deviation control channel and an azimuth control channel, using the well deviation and the well deviation change trend as input variables for the well deviation control channel, and using the azimuth deviation... The deviation and the trend of the azimuth deviation are used as input variables for the azimuth control channel. The input variables for the well inclination control channel and the azimuth control channel are fuzzified, and fuzzy inference is performed based on a preset fuzzy rule base to obtain intermediate control quantities representing the inclination adjustment demand and the torsional azimuth adjustment demand, respectively. The intermediate control quantities are defuzzified to obtain the inclination rate control component and the torsional azimuth rate control component. The tool face angle and steering ratio are jointly calculated based on the inclination rate control component and the torsional azimuth rate control component, and the tool face angle and steering ratio are output as control commands for the current control cycle to complete the joint control.

[0019] This invention generates tool face angle (TF) and steering ratio (SR) control commands based on well deviation, azimuth deviation, and their changing trends, enabling automatic closed-loop correction of the directional drilling trajectory attitude. By employing a dual-channel fuzzy control structure, this invention transforms well deviation and azimuth adjustment requirements, which originally relied on manual experience, into an executable fuzzy control process. This achieves continuous correction of the directional drilling trajectory attitude and tracking control of the target well deviation angle and target azimuth angle, making it suitable for downhole trajectory control scenarios with high nonlinearity, time-varying characteristics, and uncertainties. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of the dual-channel fuzzy closed-loop control structure in this embodiment; Figure 2 This is a schematic diagram of the azimuth membership function in this embodiment; Figure 3 This is a schematic diagram of the well inclination membership function in this embodiment; Figure 4 This is the output variable graph in this embodiment; Figure 5 This is a comparison chart of the target well inclination angle and the actual well inclination angle in the well section with a depth of 800m to 1106m in this embodiment. Figure 6 This is a comparison diagram of the target azimuth and the actual azimuth for the well section with a depth of 800m to 1106m in this embodiment. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] The purpose of this invention is to provide a method for joint control of the face angle and steering ratio of directional drilling tools based on dual-channel fuzzy inference, which aims to solve or improve at least one of the above-mentioned technical problems.

[0024] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0025] like Figure 1 As shown, this invention provides a method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference, comprising: Step 1: Obtain the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters. Calculate the well inclination deviation and azimuth deviation based on the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters. Calculate the well inclination deviation change trend and azimuth deviation change trend based on the previous measuring point trajectory attitude parameters, the current measuring point trajectory attitude parameters, and the target measuring point trajectory attitude parameters.

[0026] As a further embodiment, the well inclination deviation is the difference between the target well inclination angle and the actual well inclination angle, and the azimuth deviation is the difference between the target azimuth angle and the actual azimuth angle after angle normalization.

[0027] The trend of well inclination deviation is calculated based on the well inclination angle of the previous measuring point, the well inclination angle of the current measuring point, and the target well inclination angle. The trend of azimuth deviation is calculated based on the azimuth angle of the previous measuring point, the azimuth angle of the current measuring point, and the target azimuth angle after angle normalization.

[0028] The current measuring point trajectory attitude parameters include at least the current measuring point well depth, the current measuring point well inclination angle, and the current measuring point azimuth angle. The target measuring point trajectory attitude parameters include at least the target measuring point well depth, the target measuring point well inclination angle, and the target measuring point azimuth angle. The previous measuring point trajectory attitude parameters include at least the previous measuring point well depth, the previous measuring point well inclination angle, and the previous measuring point azimuth angle.

[0029] Step 2: Establish the well inclination control channel and the azimuth control channel. Use the well inclination deviation and the trend of its change as input variables for the well inclination control channel, and use the azimuth deviation and the trend of its change as input variables for the azimuth control channel.

[0030] Step 3: Fuzzify the input variables of the well inclination control channel and the azimuth control channel respectively, and perform fuzzy inference based on the preset fuzzy rule base to obtain the intermediate control quantity representing the inclination adjustment requirement and the intermediate control quantity representing the torsional azimuth adjustment requirement respectively.

[0031] As a further solution, the fuzzification process includes: multiplying the well deviation, the well deviation change trend, the azimuth deviation, and the azimuth deviation change trend by the corresponding input compression factor to perform scaling transformation, mapping each scaled input variable to a corresponding fuzzy linguistic variable, and determining the degree of membership of each input variable in different fuzzy sets through a pre-set membership function.

[0032] The fuzzy rule base of the well inclination control channel uses the well inclination deviation and the well inclination deviation change trend as antecedents, and the intermediate control quantity representing the directional adjustment demand as consequents; the fuzzy rule base of the azimuth control channel uses the azimuth deviation and the azimuth deviation change trend as antecedents, and the intermediate control quantity representing the torsional azimuth adjustment demand as consequents; in the fuzzy inference process, the well inclination control channel and the azimuth control channel perform fuzzy inference operations independently and in parallel.

[0033] Step 4: Defuzzify the intermediate control variables to obtain the slope rate control component and the torsional azimuth rate control component.

[0034] As a further solution, the defuzzification process employs the centroid method, which determines the centroid position based on the comprehensive distribution of the output membership functions, and uses the value corresponding to the centroid position as the deterministic output value after defuzzification; the deterministic output value is multiplied by the corresponding output compression factor to obtain the slope control component and the torsional azimuth control component.

[0035] Step 5: Calculate the tool face angle and guide ratio based on the slope control component and the torsional azimuth control component, and output the tool face angle and guide ratio as the control command for the current control cycle to complete the joint control.

[0036] As a further solution, the tool face angle is calculated as follows: the slope control component and the torsional azimuth control component are used as two orthogonal components of a two-dimensional vector, and the azimuth angle of the two-dimensional vector is calculated by the arctangent function to obtain the original value of the tool face angle, and the original value of the tool face angle is normalized.

[0037] The steering ratio is calculated as follows: the current inclination rate is calculated based on the inclination rate control component, the azimuth rate control component, the current well inclination angle at the current measuring point, and the preset maximum inclination capacity. The ratio of the current inclination rate to the preset maximum inclination capacity is then used as the steering ratio.

[0038] The current build-up rate is calculated by multiplying the build-up rate control component and the torsional azimuth rate control component by the square root of the sum of the squares of the squares of the sine of the current well inclination angle, and then taking the current build-up rate.

[0039] In addition, this method also includes the step of trajectory attitude closed-loop iterative update, the specific process of which is as follows: The tool face angle and the guidance rate are input into the trajectory response model. The well inclination angle and azimuth angle at the end of the current control cycle are updated according to the trajectory response model. The updated well inclination angle and azimuth angle are used as the current measurement point trajectory attitude parameters for the next control cycle for iterative calculation until the attitude tracking control of the entire designed trajectory is completed.

[0040] As a further solution, the trajectory response model updates the well inclination angle and azimuth angle based on the well inclination angle change rate formula and the azimuth angle change rate formula; the well inclination angle change rate is determined based on the mechanical drilling rate, the tool face angle, the steering ratio, the preset maximum build-up capacity, and the natural deviation term; the azimuth angle change rate is determined based on the mechanical drilling rate, the tool face angle, the steering ratio, the preset maximum build-up capacity, the natural steering offset, and the current well inclination angle.

[0041] Based on the above technical solution, the following embodiments are provided.

[0042] This embodiment uses the closed-loop correction process of directional drilling trajectory attitude in a well section with a depth of 800m to 1106m as an example. One control cycle is selected as an example below, where the previous measuring point, the current measuring point, and the target measuring point are all taken from three adjacent measuring points in this well section, as shown in Table 1.

[0043] Table 1 Input Parameter Table for Specific Embodiments

[0044] Step 1: Input parameters to obtain the deviation variable.

[0045] The maximum slope of the known tool The trajectory and attitude parameters of the previous measurement point, the current measurement point, and the target measurement point: Previous measuring point: Well depth , well inclination angle and azimuth ; Current measuring point: Well depth , well inclination angle and azimuth ; Target measurement point: Well depth , well inclination angle and azimuth .

[0046] Calculate well deviation This characterizes the degree of deviation of the current trajectory from the target trajectory in the well inclination direction: Calculate azimuth deviation The azimuth angle represents the degree of deviation of the current trajectory from the target trajectory in the azimuth direction. Since the azimuth angle is a circular angle quantity, its value range is usually [missing value]. Therefore, when calculating the deviation between the current azimuth and the target azimuth, angle normalization is required. After normalization, .

[0047] Calculating the trend of deviation change allows the subsequent fuzzy control process to consider not only the current magnitude of the deviation but also whether the deviation tends to increase or decrease. (Calculating the trend of wellbore deviation change) This characterizes the change in wellbore deviation relative to the previous measuring point: Calculate the trend of azimuth deviation This characterizes the change in azimuth deviation relative to the previous measuring point. Since the azimuth angle is a circular angle quantity, it needs to be normalized. Finally, the well deviation was obtained. Orientation deviation Trend of well deviation and the trend of azimuth deviation This provides output parameters for the fuzzification and fuzzy inference processes in the subsequent well inclination control channel and azimuth control channel.

[0048] Step 2: Constructing a dual-channel fuzzy controller.

[0049] Establish a wellbore inclination control channel and an azimuth control channel. The input variable for the wellbore inclination control channel is the wellbore inclination deviation. Trend of well deviation The output variable is the intermediate control quantity characterizing the tilting adjustment. The input variable for the azimuth control channel is the azimuth deviation. and the trend of azimuth deviation The output variable is the intermediate control quantity characterizing the torsional azimuth adjustment. As shown in Table 2.

[0050] First, scale the input variables: Where k represents the scale transformation factor corresponding to the corresponding input variable, and its value can be determined according to factors such as formation characteristics, guide tool performance and control requirements; This indicates the deviation of the well inclination angle after scaling. This indicates the trend of well inclination angle deviation after scaling. This indicates the azimuth deviation after scaling. This indicates the trend of azimuth deviation after scaling.

[0051] In this example, take , , , .

[0052] Calculated , , , .

[0053] Table 2 Input Compression Factor and Scaling Results

[0054] Set up fuzzy linguistic variables and corresponding membership functions: Input value fuzzy language: negative large NB, negative small NS, zero ZE, positive small PS, and positive large PB; The output variable build is in fuzzy language: large slope DH, small slope DS, zero ZE, small slope BS, and large slope BH; Output variables in fuzzy language: Left twist large LH, Left twist small LS, Zero ZE, Right twist small RS, and Right twist large RH.

[0055] In this embodiment, the membership functions of the input and output variables adopt the triangular membership function and the trapezoidal membership function, respectively, to calculate the membership degree of the input variable on its respective fuzzy linguistic variable, and convert the continuously changing input variable into the corresponding fuzzy set, that is, to map the current well deviation, azimuth deviation and its changing trend into fuzzy input information suitable for fuzzy inference.

[0056] In this embodiment, by substituting the scaled input values ​​into the corresponding membership functions, the membership status of each input variable on the fuzzy linguistic variable can be obtained. Figure 2 It can be seen that the azimuth deviation The main fuzzy sets fall within ZE and NS, and the trend of azimuth deviation changes is as follows. It mainly falls into the ZE fuzzy set; by Figure 3 It can be seen that the well deviation The main set falls within the ZE and NS fuzzy sets, and the trend of well deviation variation is shown. The results mainly fall into the ZE fuzzy set. For ease of explanation, the main membership fuzzy sets of each input variable are listed, and the results are shown in Table 3.

[0057] Table 3. Example of input variable fuzzification results

[0058] Step 3: Dual-channel fuzzification and fuzzy inference After fuzzifying the input variables, fuzzy inference was performed based on the fuzzy rule bases of the inclination control channel and the azimuth control channel, respectively. The fuzzy rules for the inclination control channel are shown in Table 4, and the fuzzy rules for the azimuth control channel are shown in Table 5.

[0059] Table 4 Fuzzy Rule Table for Well Inclination Control Channel

[0060] Among them, BH indicates large inclination, BS indicates small inclination, ZE indicates zero, DS indicates small descent, and DH indicates large descent.

[0061] Table 5. Fuzzy Rule Table for Orientation Control Channel

[0062] Where LH represents large left turn, LS represents small left turn, ZE represents zero, RS represents small right turn, and RH represents large right turn.

[0063] In this embodiment, the main rules triggered in the well inclination control channel are: The current control cycle requires relatively little well deviation adjustment and tends to favor slight well deviation adjustment.

[0064] The main rules triggered in the orientation control channel are: The azimuth adjustment requirement is relatively small during the current control cycle, and there is a tendency for slight rightward azimuth adjustment.

[0065] After completing the fuzzy inference, the output variables are... and The fuzzy output results are defuzzified. This example uses the centroid method, determining the centroid position based on the comprehensive distribution of the output membership function, and using the corresponding value as the fixed value of the output variable to obtain the original output values ​​of the well inclination control channel. The raw output value of the azimuth control channel (like Figure 4 (As shown).

[0066] The current embodiment takes and Taking the value 1.2, we get the final output variable. and .

[0067] Step 4: Calculate the tool face and guide ratio.

[0068] After obtaining the intermediate variables build and walk, calculate the tool face angle TF: in, For tool face, the unit is radians. The tool face is shown in angles.

[0069] Then, the tool face angles are normalized.

[0070] Determine tool face angle Then, the guidance rate was further calculated. The guidance rate is used to characterize the strength of the guidance control within the current control cycle, and is calculated based on... , , Current well inclination angle and current build-up rate : in, This represents the current well inclination angle at the measuring point.

[0071] Thus, the guidance rate is obtained. : In this example, the calculation is as follows: for , for .

[0072] Step 5: Perform single-segment trajectory simulation verification and attitude update based on the trajectory response model.

[0073] In steps one through four above, the acquisition of input parameters, the construction of deviation and deviation change trends, dual-channel fuzzy inference, and tool face angles have been illustrated using a single control cycle example. and guidance rate The calculation process is described below. To further verify the effect of the dual-channel fuzzy closed-loop control method on the correction effect of directional drilling trajectory attitude, this embodiment further illustrates the process using the entire trajectory attitude closed-loop drilling process as an example.

[0074] Within each control cycle, the calculated tool face angle will be... and guidance rate As a trajectory response model for control command input, it updates and calculates the well inclination angle and azimuth angle within the current control cycle, continuously iterates, and corrects the trajectory attitude parameters.

[0075] The trajectory is mainly updated using formulas for the rate of change of inclination angle and the rate of change of azimuth angle: in, The rate of change of well inclination angle. The azimuth rate of change For wellbore inclination drilling speed, For the natural slant term, For equivalent skew input, For natural steering bias.

[0076] From the rate of change of well inclination angle and the rate of change of azimuth angle, the actual well inclination angle and the actual azimuth angle are further calculated. These values ​​are used as new feedback inputs to reconstruct the well inclination deviation, azimuth deviation, and their changing trends. These values ​​are then input again into the well inclination control channel and the azimuth control channel for fuzzy inference to form a new toolface angle. and guidance rate The control commands complete the closed-loop correction process for the entire trajectory attitude.

[0077] In this embodiment, the well depth is 800m. The 1106m well section was used as the closed-loop drilling verification object. The above-mentioned closed-loop control process was implemented point by point in this well section, and the actual trajectory obtained was compared and analyzed with the target trajectory. Figure 4 The comparison results between the target well inclination angle and the actual well inclination angle for this well section are presented. It can be seen that during the closed-loop control process, the actual well inclination angle generally progresses steadily along the trend of the target well inclination angle and always maintains a small deviation. Figure 5 The comparison between the target azimuth and the actual azimuth of this well section is presented. It can be seen that the actual azimuth continuously adjusts with changes in the target azimuth, and the overall trend is basically consistent with the target azimuth. Figure 5 and Figure 6 As can be seen, the dual-channel fuzzy closed-loop control method described in this proposal can continuously generate tool face angle and steering ratio control commands based on trajectory deviation, and achieve continuous tracking and correction of the target trajectory attitude. The calculation results for point-by-point closed-loop control in this well section are detailed in Appendix Table 1.

[0078] In summary, the fuzzy control method employed in this embodiment includes three basic processes: fuzzification, fuzzy inference, and defuzzification. First, the deviation between the target wellbore inclination and the actual wellbore inclination, the trend of wellbore inclination deviation, the deviation between the target azimuth and the actual azimuth, and the trend of azimuth deviation are used as input variables, and corresponding fuzzy linguistic variables are defined for each. A membership function is set for each input variable to determine its membership degree in different fuzzy sets. Then, based on a preset fuzzy rule base, fuzzy inference is performed on the wellbore inclination control channel and the azimuth control channel to obtain fuzzy output results representing wellbore inclination adjustment requirements and azimuth adjustment requirements, respectively. Finally, the fuzzy output results are defuzzified to obtain the corresponding intermediate control quantities (build control quantity representing build rate requirements and walk control quantity representing torsional azimuth rate requirements), and further, tool face angle (TF) and steering ratio (SR) control commands are formed. A compression factor is also involved, which adjusts the controller's input sensitivity and output strength according to different formation hardness and downhole response characteristics, thereby achieving adaptive adjustment of the control intensity.

[0079] Existing directional drilling trajectory control schemes mostly generate control commands based on single displacement deviation, curvature error, technical wellbore deviation, or artificial intelligence prediction results. Some schemes combine well inclination and azimuth trajectory tracking with reinforcement learning. This proposal uses well inclination deviation, azimuth deviation, and their changing trends as core inputs, establishing well inclination control channels and azimuth control channels respectively. Intermediate control quantities are generated through dual-channel fuzzy inference, and further, tool face angle (TF) and steering ratio (SR) control commands are formed, thus constituting a dual-channel fuzzy closed-loop control method for directional drilling trajectory attitude correction.

[0080] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0081] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference, characterized in that, include: Obtain the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters. Calculate the well inclination deviation and azimuth deviation based on the current measuring point trajectory attitude parameters and the target measuring point trajectory attitude parameters. Calculate the well inclination deviation change trend and azimuth deviation change trend based on the previous measuring point trajectory attitude parameters, the current measuring point trajectory attitude parameters, and the target measuring point trajectory attitude parameters. Establish a well inclination control channel and an azimuth control channel, and use the well inclination deviation and the trend of the well inclination deviation as input variables for the well inclination control channel, and use the azimuth deviation and the trend of the azimuth deviation as input variables for the azimuth control channel; The input variables of the well inclination control channel and the azimuth control channel are fuzzified respectively, and fuzzy reasoning is performed based on a preset fuzzy rule base to obtain the intermediate control quantity representing the inclination adjustment requirement and the intermediate control quantity representing the torsional azimuth adjustment requirement respectively. The intermediate control quantity is defuzzified to obtain the slope rate control component and the torsional azimuth rate control component. The tool face angle and the guiding rate are jointly calculated based on the inclination rate control component and the torsional azimuth rate control component, and the tool face angle and the guiding rate are output as control commands for the current control cycle to complete the joint control.

2. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 1, characterized in that, The well inclination deviation is the difference between the target well inclination angle and the actual well inclination angle, and the azimuth deviation is the difference between the target azimuth angle and the actual azimuth angle after angle normalization. The trend of well inclination deviation is calculated based on the well inclination angle of the previous measuring point, the well inclination angle of the current measuring point, and the target well inclination angle. The trend of azimuth deviation is calculated based on the azimuth angle of the previous measuring point, the azimuth angle of the current measuring point, and the target azimuth angle after angle normalization. The current measuring point trajectory attitude parameters include at least the current measuring point well depth, the current measuring point well inclination angle, and the current measuring point azimuth angle. The target measuring point trajectory attitude parameters include at least the target measuring point well depth, the target measuring point well inclination angle, and the target measuring point azimuth angle. The previous measuring point trajectory attitude parameters include at least the previous measuring point well depth, the previous measuring point well inclination angle, and the previous measuring point azimuth angle.

3. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 1, characterized in that, The fuzzification process includes: multiplying the well deviation, the well deviation trend, the azimuth deviation, and the azimuth deviation trend by the corresponding input compression factors to perform scaling transformation, mapping each scaled input variable to a corresponding fuzzy linguistic variable, and determining the degree of membership of each input variable in different fuzzy sets through a pre-set membership function.

4. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 1, characterized in that, The fuzzy rule base of the well inclination control channel takes the well inclination deviation and the well inclination deviation change trend as antecedents and the intermediate control quantity that characterizes the inclination adjustment requirement as consequents. The fuzzy rule base of the azimuth control channel uses the azimuth deviation and the trend of the azimuth deviation as antecedents, and the intermediate control quantity representing the azimuth adjustment requirement as consequents. During the fuzzy inference process, the well inclination control channel and the azimuth control channel perform fuzzy inference operations independently and in parallel.

5. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 1, characterized in that, The defuzzing process employs the centroid method, which determines the centroid position based on the comprehensive distribution of the output membership function, and uses the value corresponding to the centroid position as the deterministic output value after defuzzification. The deterministic output value is multiplied by the corresponding output compression factor to obtain the slope control component and the torsional azimuth control component.

6. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 1, characterized in that, The tool face angle is calculated as follows: the slope control component and the torsional azimuth control component are used as two orthogonal components of a two-dimensional vector. The azimuth angle of the two-dimensional vector is calculated by the arctangent function to obtain the original value of the tool face angle. The original value of the tool face angle is then normalized.

7. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 1, characterized in that, The steering ratio is calculated as follows: the current inclination rate is calculated based on the inclination rate control component, the azimuth rate control component, the current well inclination angle at the current measuring point, and the preset maximum inclination capacity. The ratio of the current inclination rate to the preset maximum inclination capacity is then used as the steering ratio.

8. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 7, characterized in that, The current build-up rate is calculated by multiplying the build-up rate control component and the torsional azimuth rate control component by the square root of the sum of the squares of the squares of the sine of the current well inclination angle, and then taking the current build-up rate.

9. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 1, characterized in that, Also includes: Iterative updates of trajectory and attitude closed loop; The trajectory attitude closed-loop iterative update process is as follows: The tool face angle and the guidance rate are input into the trajectory response model. The well inclination angle and azimuth angle at the end of the current control cycle are updated according to the trajectory response model. The updated well inclination angle and azimuth angle are used as the current measurement point trajectory attitude parameters for the next control cycle for iterative calculation until the attitude tracking control of the entire designed trajectory is completed.

10. The method for joint control of directional drilling tool face angle and steering ratio based on dual-channel fuzzy inference according to claim 9, characterized in that, The trajectory response model updates the well inclination angle and azimuth angle based on the well inclination angle change rate formula and the azimuth angle change rate formula; the well inclination angle change rate is determined based on the mechanical drilling rate, the tool face angle, the steering ratio, the preset maximum build-up capacity, and the natural deviation term; the azimuth angle change rate is determined based on the mechanical drilling rate, the tool face angle, the steering ratio, the preset maximum build-up capacity, the natural steering offset, and the current well inclination angle.

Images