Intelligent control method for drill rod fixing card

Abstract

The present invention discloses an intelligent control method for a drill rod fixing card, which specifically relates to the technical field of drill rod control. By collecting and preprocessing sensor data during the drill rod operation process, two key features, namely the drill rod motion trend change rate and the clamping force fluctuation amplitude, are extracted, and a comprehensive evaluation index is generated to reflect the accuracy of the control parameters. When the comprehensive evaluation index exceeds a preset threshold, the controller parameters are dynamically adjusted according to the characteristic parameter change trend until the index converges to a stable range, thereby realizing intelligent optimization of the controller parameters. This technical solution can effectively suppress system oscillations and malfunctions caused by small disturbances, and improve the stability, reliability and operating efficiency of the drill rod fixing card system in complex operating environments.

Description

Technical Field

[0001] The present invention relates to the technical field of drill rod control, and in particular to an intelligent control method for a drill rod fixing card. Background Art

[0002] Intelligent control of drill rod clamps uses sensors, actuators, and control systems to automate and intelligently manage and adjust the opening, closing, clamping, and release of drill rod clamps, enabling precise and reliable drill rod clamping based on actual operational needs. The system senses parameters such as drill rod position and force in real time, automatically determining the timing of operations and optimizing clamping force, improving operational efficiency and safety while reducing human error and labor intensity.

[0003] The existing technology has the following shortcomings:

[0004] In the intelligent control of drill rod clamps, improper parameter design (e.g., excessively high proportional gain) when using PID or fuzzy control algorithms can easily lead to system oversensitivity to minor disturbances, resulting in oscillation. This manifests as repeated opening and closing of the clamp, frequent switching between clamping and releasing, and ultimately triggering a system self-protection shutdown or deadlock. For example, in tunnel construction, highly slippery conditions can cause slight deviations in the drill rod, leading to fluctuations in the position sensor signal. This in turn triggers violent oscillations in the PID controller output, causing frequent alarm shutdowns. Such issues severely reduce work efficiency, accelerate equipment wear, and even cause major failures. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent control method for a drill rod fixing clamp to solve the shortcomings of the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a drill rod fixing card intelligent control method, comprising:

[0007] Collect sensor data during drill rod operation and pre-process the sensor data to obtain drill rod motion information and clamping force information;

[0008] Extracting a first characteristic parameter and a second characteristic parameter from the preprocessed data, wherein the first characteristic parameter is a rate of change of a drill rod movement trend, and the second characteristic parameter is a clamping force fluctuation amplitude;

[0009] Performing a comprehensive calculation based on the first characteristic parameter and the second characteristic parameter to generate a comprehensive evaluation index for reflecting the accuracy of the current control parameter setting;

[0010] Comparing the comprehensive evaluation index with a preset threshold, and when the comprehensive evaluation index exceeds the preset threshold, determining that the current control parameter setting is inaccurate;

[0011] For inaccurate situations, the controller parameters are adjusted according to the changes of the first characteristic parameter and the second characteristic parameter in the comprehensive evaluation index until the comprehensive evaluation index converges to a stable range.

[0012] Preferably, the sensor data includes position data collected by position sensors installed around the drill rod fixing clamp or on the clamp body, and clamping force data collected by force sensors installed in the clamping jaws or the fixing clamp structure.

[0013] Preferably, the preprocessing includes performing digital filtering on the original sensor signal, and the digital filtering adopts a low-pass filter or a moving average filter to remove high-frequency noise and smooth the sampled data.

[0014] Preferably, the method for obtaining the drill rod movement trend change rate is: collecting and obtaining the continuous position data sequence of the drill rod in a certain axial direction and recording it as: x(t i-1 ), x(t i ), x(t i+1 ); where x(t) is the spatial position of the drill pipe in a certain direction, t is the corresponding time point, and the sampling interval is Δt; the velocity at two adjacent moments is calculated using the expression: ; Calculate the rate of change of drill pipe movement trend, the expression is: ; A i is the rate of change of motion trend at moment i.

[0015] Preferably, the method for obtaining the amplitude of the clamping force fluctuation is as follows: the signal of the original clamping force changing with time is denoted as f(t), the sampling time range is t∈[0,T], and the sampling interval is Δt; f(t) is subjected to EMD and decomposed into several intrinsic mode functions IMFs and a residual term ; Among them: IMF k (t) is the kth modal component, K is the total number of modal components, r(t) is the residual signal that cannot be decomposed any further; according to the energy distribution or frequency characteristics, several IMFs related to the clamping force fluctuation are selected to form the effective fluctuation signal f wave (t), the expression is: ; where: Ω is the selected IMF index set; IMFs with center frequencies in the range of 1–10 Hz are selected;

[0016] On each sliding window, calculate f wave The maximum and minimum values ​​of (t), the clamping force fluctuation amplitude A is defined as: A=max(f wave (t))-min(f wave (t)),t∈[t s ,t e ]; where: t s , t eThe start and end time of the analysis window.

[0017] Preferably, a comprehensive calculation is performed based on the first characteristic parameter and the second characteristic parameter to generate a comprehensive evaluation index for reflecting the accuracy of the current control parameter setting, specifically including:

[0018] The drill rod motion trend change rate and the clamping force fluctuation amplitude are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each set of comprehensive feature vectors to predict the accuracy value label of the current control parameter setting as the prediction target, and takes minimizing the sum of the prediction errors of the accuracy value labels of all current control parameter settings as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The accuracy value of the current control parameter setting is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0019] Preferably, the comprehensive evaluation index is compared with a preset threshold value, and when the comprehensive evaluation index exceeds the preset threshold value, it is determined that the current control parameter setting is inaccurate, specifically including:

[0020] The obtained accuracy value of the current control parameter setting is compared with a preset threshold value. If the accuracy value of the current control parameter setting is greater than or equal to the preset threshold value, it means that the current control parameters can effectively meet the stability and clamping accuracy requirements during the drill rod operation. Therefore, there is no need to adjust the controller parameters and the operation continues according to the current settings.

[0021] If the accuracy value of the current control parameter setting is less than the preset threshold, it means that the existing control parameters cannot effectively adapt to the actual operating status of the drill rod. Therefore, it is necessary to further adjust the controller parameters according to the changing trend of the comprehensive eigenvector to optimize the clamping response performance and improve the overall operation accuracy.

[0022] Preferably, for inaccurate situations, the controller parameters are adjusted according to the changes of the first characteristic parameter and the second characteristic parameter in the comprehensive evaluation index until the comprehensive evaluation index converges to a stable range. The specific steps include:

[0023] Step 1: Set the initial controller parameter set θ={θ1,θ2,…,θ n}, n is the total number of controller parameters; set the comprehensive evaluation index stability interval ;

[0024] Step 2: Calculate the accuracy value E(θ) of the current control parameter setting based on the first characteristic parameter drill rod movement trend change rate and the second characteristic parameter clamping force fluctuation amplitude collected in real time;

[0025] Step 3: The controller parameter settings are inaccurate, enter the parameter adjustment step;

[0026] Step 4: Calculate the gradient of the accuracy value E(θ) of the current control parameter setting with respect to the control parameter θ ; Calculate the Fisher information matrix F(θ) of the control parameter space, which is in the form of: ; where p(x|θ) represents the dependence distribution of the system state on the parameters, and T is the matrix transpose;

[0027] Step 5: Adjust the parameters according to the natural gradient descent formula: ; where η is the learning rate, F(θ) -1 is the inverse matrix of the Fisher information matrix, θ new are the adjusted controller parameters;

[0028] Step 6: Update the parameters θ new Applied to the controller; re-collect data, update the first characteristic parameter and the second characteristic parameter, and recalculate the comprehensive evaluation index E(θnew); if , then stop adjusting and the controller parameters converge; if they do not converge, return to step 4 and continue iterating.

[0029] The beneficial effects of the present invention are:

[0030] 1. This invention collects information on the motion state and clamping force during drill rod operation, extracts the rate of change in drill rod motion trends and the amplitude of clamping force fluctuations as key features, and dynamically evaluates the accuracy of control parameter settings based on a polynomial regression model. This effectively overcomes the problems of traditional PID or fuzzy control, which are overly sensitive to small disturbances and prone to oscillation and shutdown. Through real-time monitoring and intelligent judgment of comprehensive evaluation indicators, this invention can promptly identify control parameter mismatches, avoid frequent opening and closing of fixtures, mis-clamping, and equipment self-protection shutdowns, thereby significantly improving the operational stability, reliability, and safety of the drill rod fixing system in complex environments.

[0031] 2. This invention further introduces an adaptive control parameter optimization mechanism based on natural gradient descent. When comprehensive evaluation indicators deviate from the stable range, it automatically adjusts controller parameters and iteratively optimizes until system performance converges and stabilizes. Compared with traditional empirical parameter adjustment methods, this invention significantly shortens parameter setting time, reduces the need for manual intervention, reduces energy consumption and wear caused by equipment vibration and impact, and extends equipment life. It also enables intelligent and adaptive operation and maintenance of the drill rod fixing card control system, promising promising engineering applications and economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a mind map of the method of the present invention. DETAILED DESCRIPTION

[0033] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0034] Example 1, please refer to Figure 1 As shown, the intelligent control method of a drill rod fixing card of the present invention includes:

[0035] Collect sensor data during drill rod operation and pre-process the sensor data to obtain drill rod motion information and clamping force information;

[0036] Extracting a first characteristic parameter and a second characteristic parameter from the preprocessed data, wherein the first characteristic parameter is a rate of change of a drill rod movement trend, and the second characteristic parameter is a clamping force fluctuation amplitude;

[0037] Performing a comprehensive calculation based on the first characteristic parameter and the second characteristic parameter to generate a comprehensive evaluation index for reflecting the accuracy of the current control parameter setting;

[0038] Comparing the comprehensive evaluation index with a preset threshold, and when the comprehensive evaluation index exceeds the preset threshold, determining that the current control parameter setting is inaccurate;

[0039] For inaccurate situations, the controller parameters are adjusted according to the changes of the first characteristic parameter and the second characteristic parameter in the comprehensive evaluation index until the comprehensive evaluation index converges to a stable range.

[0040] During the drilling operation, in order to accurately obtain the real-time motion status and clamping force of the drill rod, the following types of sensors are set:

[0041] The position sensor is installed around the drill rod fixing clamp or on the fixture body to detect the spatial position of the drill rod relative to the fixture (such as X, Y, and Z axis displacement) and the opening and closing displacement of the fixture.

[0042] Commonly used devices: laser ranging sensor, magnetic encoder, linear displacement sensor (LVDT).

[0043] The force sensor (clamping force sensor) is installed inside the clamping jaw, fixed card structure or in the force path to detect the clamping force applied by the clamp on the drill pipe in real time.

[0044] Commonly used devices: strain gauge sensors, pressure sensors, and piezoelectric force sensors.

[0045] All sensor data are collected in real time through a synchronous sampling mechanism (such as unified trigger sampling and time stamp) to ensure consistency across different data sources.

[0046] Use industrial buses (such as CAN bus, Modbus, EtherCAT, etc.) or high-speed ADC modules to transmit sensor signals to the host computer or embedded controller in real time.

[0047] The sampling frequency of position and clamping force sensors is typically set to ≥100 Hz to ensure that they can capture rapid drill pipe movement or dynamic changes in the fixture. Vibration or torque data can be sampled at a higher frequency (e.g., 500 Hz or higher) as needed.

[0048] The collected raw signal is digitally filtered. Common methods include: low-pass filtering (such as a first-order Butterworth filter) to remove high-frequency noise; moving average filtering to smooth the sampled data.

[0049] Apply anomaly detection algorithms (such as statistical outlier removal within a sliding window) to remove transient abnormal data points caused by environmental disturbances.

[0050] Convert various sensor output signals (such as voltage and current) into engineering units (such as displacement mm and force N), and make corrections based on preset calibration curves to improve data accuracy.

[0051] Fusion processing of position, clamping force, vibration and other data, for example:

[0052] The drill rod status (stationary, moving, stuck) is determined based on the drill rod position and clamping force variation. The vibration amplitude and clamping force anomalies are used to determine whether the clamp is loose or slipping.

[0053] After the above processing, the system outputs two key categories of standardized, time-sequenced information: the drill rod's spatial displacement, velocity (displacement change rate), vibration amplitude, and possible rotational state, which are used for dynamic directional feature extraction. It also outputs real-time clamping force, clamping force variation curves, and clamping force fluctuation amplitude, which are used for static clamping stability assessment.

[0054] A first characteristic parameter and a second characteristic parameter are extracted from the preprocessed data, wherein the first characteristic parameter is the drill rod movement trend change rate, and the second characteristic parameter is the clamping force fluctuation amplitude.

[0055] The drill pipe motion trend change rate is used to reflect the degree of speed change of the drill pipe in unit time, that is, whether the drill pipe accelerates, decelerates or reverses direction in a short period of time, reflecting its dynamic stability.

[0056] The method for obtaining the drill rod motion trend change rate is as follows: collect and obtain the continuous position data sequence of the drill rod in a certain axial direction and record it as: x(t i-1 ), x(t i ), x(t i+1 ); where x(t) is the spatial position of the drill pipe in a certain direction (such as the X axis), t is the corresponding time point, and the sampling interval is Δt;

[0057] Calculate the velocity (displacement change rate) between two adjacent moments. The expression is: ; Calculate the rate of change of the drill pipe movement trend (i.e., the approximate value of acceleration), the expression is: ; A i is the rate of change of motion trend at moment i.

[0058] When the rate of change of the drill rod movement trend is greater, it means that the speed of the drill rod changes dramatically, and there is a strong acceleration or deceleration behavior, indicating that the drill rod is in an unstable state and is easily affected by external disturbances to produce vibration, impact or deviation. At this time, the clamp control system needs to have a higher dynamic response capability to avoid errors in clamping timing or force control.

[0059] On the contrary, when the rate of change of the drill rod movement trend is close to zero, it means that the speed of the drill rod remains stable, the dynamic disturbance is small, and the system is in a relatively stable state, which is conducive to achieving high-precision clamping control, reducing the risks of misclamping and slippage, and improving operation safety and clamping accuracy.

[0060] The clamping force fluctuation amplitude is used to reflect the range of change in the clamping force of the fixture on the drill pipe over a period of time, and can be used to assess whether the clamping is stable or there is a risk of loosening.

[0061] The method for obtaining the clamping force fluctuation amplitude is as follows: let the original clamping force signal changing with time be f(t), the sampling time range t∈[0,T], and the sampling interval be Δt; perform EMD on f(t) and decompose it into several intrinsic mode functions (IMFs) and a residual term ; Among them: IMF k (t) is the kth modal component, K is the total number of modal components, and r(t) is the irresolvable residual signal (usually a trend term).

[0062] According to the energy distribution or frequency characteristics, several IMFs related to the clamping force fluctuation are selected to form the effective fluctuation signal f wave (t), the expression is: Where Ω is the selected IMF index set. High- or medium-frequency IMFs are typically selected, as low-frequency IMFs often correspond to background trend changes. Based on experience, select IMFs containing at least 80% of the energy, or use Hilbert spectrum analysis to select IMFs with center frequencies within a certain range (e.g., 1–10 Hz).

[0063] On each sliding window (or globally), calculate f wave The maximum and minimum values ​​of (t), the clamping force fluctuation amplitude A is defined as: A=max(f wave (t))-min(f wave (t)),t∈[t s ,t e ]; where: t s , t e The start and end time of the analysis window.

[0064] Large clamping force fluctuations indicate dramatic force variations during the clamping process, and the clamp's application of force to the drill pipe is unstable, potentially indicating loosening, impact, or delayed clamping force adjustment. In this state, the drill pipe is susceptible to displacement, slippage, or vibration due to insecure clamping, increasing operational risks, accelerating clamp wear, and reducing equipment reliability. Therefore, large clamping force fluctuations often indicate insufficient system dynamic control performance or significant environmental interference, necessitating timely optimization of the control strategy or improvement of the clamping mechanism's responsiveness.

[0065] When the clamping force fluctuation amplitude is small, it indicates that the clamping force applied to the drill pipe remains relatively stable, and the system can effectively maintain the predetermined clamping state despite external interference. This ensures good controllability of the drill pipe, a smooth clamping process, and high operational safety, contributing to high-precision and high-reliability drilling or drilling operations. Small clamping force fluctuation amplitude generally indicates that the control system parameters are properly set, the clamping structure is rigid, environmental interference is minimal, and the overall equipment is in excellent operating condition.

[0066] A comprehensive evaluation index is generated based on the first characteristic parameter and the second characteristic parameter to reflect the accuracy of the current control parameter setting, specifically including:

[0067] The drill rod motion trend change rate and the clamping force fluctuation amplitude are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each set of comprehensive feature vectors to predict the accuracy value label of the current control parameter setting as the prediction target, and takes minimizing the sum of the prediction errors of the accuracy value labels of all current control parameter settings as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The accuracy value of the current control parameter setting is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0068] Comparing the comprehensive evaluation index with a preset threshold, and determining that the current control parameter setting is inaccurate when the comprehensive evaluation index exceeds the preset threshold, specifically includes:

[0069] The obtained accuracy value of the current control parameter setting is compared with a pre-set threshold. If the accuracy value of the current control parameter setting is greater than or equal to the pre-set threshold, it indicates that the current control parameters can effectively meet the stability and clamping accuracy requirements during drill rod operation. At this point, after detecting the characteristic combination of the rate of change of the drill rod motion trend and the amplitude of the clamping force fluctuation, the system uses a trained polynomial regression model to evaluate that the drill rod has minimal dynamic disturbances during the clamping process, the clamping state is stable, and the clamping action is well matched with the drill rod motion state. Therefore, there is no need to adjust the controller parameters, and the system can continue to operate according to the current settings.

[0070] If the accuracy of the current control parameter settings is less than a pre-set threshold, it indicates that the existing control parameters are ineffective in adapting to the actual operating state of the drill pipe, potentially leading to control lag, unstable clamping, or excessive disturbances. In this case, the characteristic combination of the rate of change of the drill pipe's motion trend and the amplitude of the clamping force fluctuation, as predicted by the polynomial regression model, indicates that the clamp is unable to accurately and in real time respond to the dynamic changes of the drill pipe, potentially leading to risks such as clamping slippage, mis-clamping, or increased vibration. Therefore, it is necessary to further adjust the controller parameters based on the changing trend of the comprehensive eigenvector to optimize the clamping response performance and improve overall operational accuracy and equipment reliability.

[0071] For inaccurate situations, adjust the controller parameters according to the changes of the first characteristic parameter and the second characteristic parameter in the comprehensive evaluation index until the comprehensive evaluation index converges to a stable range. The specific steps include:

[0072] Step 1: Set the initial controller parameter set θ={θ1,θ2,…,θ n}, such as the proportional, integral, and differential parameters in PID, and n is the total number of controller parameters;

[0073] Set the stable range of comprehensive evaluation indicators ;

[0074] Step 2: Calculate the accuracy value E(θ) of the current control parameter setting based on the first characteristic parameter drill rod movement trend change rate and the second characteristic parameter clamping force fluctuation amplitude collected in real time;

[0075] Step 3: The controller parameter settings are inaccurate, enter the parameter adjustment step;

[0076] Step 4: Calculate the gradient of the accuracy value E(θ) of the current control parameter setting with respect to the control parameter θ ;

[0077] Calculate the Fisher information matrix F(θ) of the control parameter space in the form of: ; where p(x|θ) represents the dependence distribution of the system state on the parameters, which can be approximately solved by the rate of change of the characteristic data, and T is the matrix transpose;

[0078] Step 5: Adjust the parameters according to the natural gradient descent formula: ; Where η is the learning rate (step size), which is generally set to a small positive value; F(θ) -1 is the inverse matrix of the Fisher information matrix, which is used to adjust the gradient direction and improve the convergence stability. new are the adjusted controller parameters;

[0079] Step 6: Update the parameters θ new Applied to the controller; re-collect data, update the first characteristic parameter and the second characteristic parameter, and recalculate the comprehensive evaluation index E(θnew); if , then stop adjusting and the controller parameters converge; if they do not converge, return to step 4 and continue iterating.

[0080] The present embodiment relates to an intelligent control method for a drill rod fixing card, which aims to improve the clamping stability and control accuracy during the drill rod operation process. The method collects the drill rod motion state and clamping force data in real time, extracts two key features of the drill rod motion trend change rate and the clamping force fluctuation amplitude through preprocessing, and combines them into a comprehensive feature vector. The comprehensive feature vector is trained and predicted based on the polynomial regression model to evaluate the accuracy of the current control parameter settings in real time. When the accuracy is insufficient, the natural gradient descent algorithm is further adopted to adaptively adjust the controller parameters according to the change trend of each characteristic parameter in the comprehensive evaluation index until the system stability index converges to the set threshold range. Through the above scheme, the present embodiment effectively suppresses the control oscillation and mis-clamping caused by small disturbances, and improves the operation safety, stability and intelligence level of the drill rod fixing card system in complex environments.

[0081] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0082] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via wired or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0083] It should be understood that the term "and / or" herein is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone, where A and B may be singular or plural. In addition, the character " / " herein generally indicates that the objects associated with each other are in an "or" relationship, but it may also indicate an "and / or" relationship, which can be understood by referring to the context. A person of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0084] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. A drill rod fixing card intelligent control method, characterized by: include: Collect sensor data during drill rod operation and pre-process the sensor data to obtain drill rod motion information and clamping force information; Extracting a first characteristic parameter and a second characteristic parameter from the preprocessed data, wherein the first characteristic parameter is a rate of change of a drill rod movement trend, and the second characteristic parameter is a clamping force fluctuation amplitude; Specifically, the method for obtaining the drill rod movement trend change rate is as follows: collect and obtain the continuous position data sequence of the drill rod in a certain axial direction and record it as: x(t i-1 ), x(t i ), x(t i+1 ); where x(t) is the spatial position of the drill pipe in a certain direction, t is the corresponding time point, and the sampling interval is Δt; the velocity at two adjacent moments is calculated using the expression: ; Calculate the drill pipe movement trend change rate, the expression is: ; A i is the rate of change of movement trend at moment i; The method for obtaining the clamping force fluctuation amplitude is as follows: let the original clamping force signal changing with time be f(t), the sampling time range t∈[0,T], and the sampling interval be Δt; perform EMD on f(t) and decompose it into several intrinsic mode functions IMFs and a residual term ; Among them: IMF k (t) is the kth modal component, K is the total number of modal components, r(t) is the residual signal that cannot be decomposed any further; according to the energy distribution or frequency characteristics, several IMFs related to the clamping force fluctuation are selected to form the effective fluctuation signal f wave (t), the expression is: ; Where: Ω is the selected IMF index set; IMFs with center frequencies in the range of 1–10 Hz are selected; On each sliding window, calculate f wave The maximum and minimum values ​​of (t), the clamping force fluctuation amplitude A is defined as: A=max(f wave (t))-min(f wave (t)),t∈[t s ,t e ]; where: t s , t e The start and end time of the analysis window; Performing a comprehensive calculation based on the first characteristic parameter and the second characteristic parameter to generate a comprehensive evaluation index for reflecting the accuracy of the current control parameter setting; Comparing the comprehensive evaluation index with a preset threshold, and when the comprehensive evaluation index exceeds the preset threshold, determining that the current control parameter setting is inaccurate; For inaccurate situations, the controller parameters are adjusted according to the changes of the first characteristic parameter and the second characteristic parameter in the comprehensive evaluation index until the comprehensive evaluation index converges to a stable range.

2. The intelligent control method for a drill rod fixing card according to claim 1, characterized in that: The sensor data includes position data collected by position sensors installed around the drill rod fixing clamp or on the clamp body, and clamping force data collected by force sensors installed in the clamping jaws or the fixing clamp structure.

3. The intelligent control method for a drill rod fixing card according to claim 2, characterized in that: The preprocessing includes performing digital filtering on the original sensor signal. The digital filtering adopts a low-pass filter or a moving average filter to remove high-frequency noise and smooth the sampled data.

4. The intelligent control method for a drill rod fixing card according to claim 3, characterized in that: A comprehensive evaluation index is generated based on the first characteristic parameter and the second characteristic parameter to reflect the accuracy of the current control parameter setting, specifically including: The drill rod motion trend change rate and the clamping force fluctuation amplitude are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as the input of the machine learning model. The machine learning model uses each set of comprehensive feature vectors to predict the accuracy value label of the current control parameter setting as the prediction target, and takes minimizing the sum of the prediction errors of the accuracy value labels of all current control parameter settings as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The accuracy value of the current control parameter setting is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. The intelligent control method for a drill rod fixing card according to claim 4, characterized in that: Comparing the comprehensive evaluation index with a preset threshold, and determining that the current control parameter setting is inaccurate when the comprehensive evaluation index exceeds the preset threshold, specifically includes: The obtained accuracy value of the current control parameter setting is compared with a preset threshold value. If the accuracy value of the current control parameter setting is greater than or equal to the preset threshold value, it means that the current control parameters can effectively meet the stability and clamping accuracy requirements during the drill rod operation. Therefore, there is no need to adjust the controller parameters and the operation continues according to the current settings. If the accuracy value of the current control parameter setting is less than the preset threshold, it means that the existing control parameters cannot effectively adapt to the actual operating status of the drill rod. Therefore, it is necessary to further adjust the controller parameters according to the changing trend of the comprehensive eigenvector to optimize the clamping response performance and improve the overall operation accuracy.

6. The intelligent control method for a drill rod fixing card according to claim 5, characterized in that: For inaccurate situations, adjust the controller parameters according to the changes of the first characteristic parameter and the second characteristic parameter in the comprehensive evaluation index until the comprehensive evaluation index converges to a stable range. The specific steps include: Step 1: Set the initial controller parameter set θ={θ1,θ2,…,θ n }, n is the total number of controller parameters; set the comprehensive evaluation index stability interval ; Step 2: Calculate the accuracy value E(θ) of the current control parameter setting based on the first characteristic parameter drill rod movement trend change rate and the second characteristic parameter clamping force fluctuation amplitude collected in real time; Step 3: The controller parameter settings are inaccurate, enter the parameter adjustment step; Step 4: Calculate the gradient of the accuracy value E(θ) of the current control parameter setting with respect to the control parameter θ ; Calculate the Fisher information matrix F(θ) of the control parameter space, which is in the form of: ; where p(x|θ) represents the dependence distribution of the system state on the parameters, and T is the matrix transpose; Step 5: Adjust the parameters according to the natural gradient descent formula: ; where η is the learning rate, F(θ) -1 is the inverse matrix of the Fisher information matrix, θ new are the adjusted controller parameters; Step 6: Update the parameters θ new Applied to the controller; re-collect data, update the first characteristic parameter and the second characteristic parameter, and recalculate the comprehensive evaluation index E(θnew); if , then stop adjusting and the controller parameters converge; if they do not converge, return to step 4 and continue iterating.

Images