Control method and system for power head of coring drilling machine

Abstract

The invention provides a control method and system for a power head of a coring drilling machine, and relates to the technical field of drilling machines. The control method for the power head of the coring drilling machine comprises the steps that historical data of the working process of the coring drilling machine serve as training samples, and a neural network model is constructed to obtain a mapping relation; based on historical data and the mapping relation, constructing a visual digital twinborn model; monitoring vibration information of the drill bit in real time; inputting the vibration information, the initial wear information of the drill bit before the coring and the stratum information of the stratum with the coring completed by the drill bit into a digital twinborn model; predicting the hardness of the stratum currently acted by the drill bit through a digital twinborn model; and the output torque of the power head is dynamically adjusted, and the feeding speed of the power head is dynamically adjusted. According to the control method, the vibration information of the drill bit can be analyzed in real time, the hardness information of the stratum on which the drill bit acts currently is predicted, and dynamic adjustment of the output torque and the feeding speed of the power head is achieved.

Description

Technical Field

[0001] This application relates to the technical field of drilling rigs, and in particular, to a control method and system for the power head of a core drilling rig. Background Art

[0002] In the fields of geological exploration, mineral development, geotechnical engineering, etc., a core drilling rig is a key device for obtaining underground core samples. The core drilling rig cuts and extracts complete formation cores through the rotation and axial feed of the drill bit.

[0003] In actual operations, the formation conditions are complex and variable, and the hardness differences of formations at different depths are significant. In the prior art, the operation of the drilling rig mostly relies on manual experience or preset parameters, and it is difficult to accurately identify the change of formation hardness: when the drill bit encounters a high-hardness formation, if the torque of the power head is insufficient or the feed speed is too fast, it is easy to cause increased wear of the drill bit, core breakage, or even sticking of the drill; in a soft formation, if the parameter setting is too conservative, there will be problems such as low core-taking efficiency. And how to identify the formation hardness in real time and dynamically optimize the drilling rig parameters is an urgent problem to be solved currently. Summary of the Invention

[0004] The purpose of this application is to overcome the defects of the prior art and provide a control method and system for the power head of a core drilling rig to solve the problems in the prior art.

[0005] To solve the above problems, in the first aspect of the embodiments of this application, a control method for the power head of a core drilling rig is provided, including: Taking the historical data of the working process of the core drilling rig as training samples to construct a neural network model to obtain the mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during core taking, and the hardness data of the formation; Based on the historical data and the mapping relationship, constructing a visual digital twin model; wherein, the digital twin model includes a drilling rig model and a formation model; During the process of the drill bit taking core, real-time monitoring the vibration information of the drill bit; Inputting the vibration information, the initial wear information of the drill bit before this core taking, and the formation information of the formation where the drill bit has completed core taking into the digital twin model; Predicting the hardness of the formation where the drill bit is currently acting through the digital twin model and obtaining the predicted hardness information; Based on the vibration information, the initial wear information, and the predicted hardness information, and according to the torque equation, dynamically adjusting the output torque of the power head, and dynamically adjusting the feed speed of the power head according to the feed speed equation.

[0006] In a possible implementation manner, the torque equation is: ; The feed rate equation is as follows: ; where T represents the output torque of the power head; T max represents the maximum rated output torque of the power head; H represents the formation hardness coefficient; A represents the vibration amplitude of the drill bit; W represents the drill bit wear coefficient; n represents the current drilling rotation speed; n max represents the maximum allowable rotation speed of the drill bit; k1 represents the torque adjustment coefficient; k2 represents the feed rate base coefficient; α represents the vibration compensation coefficient; β represents the wear compensation coefficient; γ represents the rotation speed compensation coefficient; ν represents the feed rate; δ represents the vibration suppression coefficient; ε represents the wear suppression coefficient; ζ represents the hardness enhancement coefficient; The vibration information includes the vibration amplitude, the vibration compensation coefficient, and the vibration suppression coefficient. The initial wear information includes the drill bit wear coefficient, the wear compensation coefficient, and the wear suppression coefficient. The predicted hardness information includes the formation hardness coefficient and the hardness enhancement coefficient.

[0007] In a possible implementation, the establishment of the neural network model includes: Obtain a sample set, and the sample set includes multiple training samples; in the same sample set, the wear degree of the drill bit in each training sample is at the same level; The training sample includes input data and output data. The input data includes first data, and the output data includes second data; where the first data includes the vibration data when the drill bit cores a preset formation, and the second data includes the measured hardness data of the preset formation; Use the input data and the output data to train the neural network; where if the eigenvalue of the hardness data of the formation predicted by the neural network model conforms to the eigenvalue of the hardness data of the actually measured formation, the training ends and the neural network model is obtained.

[0008] In a possible implementation, after each coring operation of the drill bit, the core taken out by the drill bit is detected to obtain the measured hardness information of the core, and the formation model is updated.

[0009] In a possible implementation, if the measured hardness information does not match the predicted hardness information, the mapping relationship is corrected based on the measured hardness information.

[0010] In a possible implementation, the method for determining the initial wear information includes: After each coring operation of the drill bit, clean the drill bit; Perform three-dimensional scanning on the drill bit and establish a three-dimensional model; Compare the three-dimensional model with the standard model of the drill bit to obtain the measured wear data of the drill bit; Update the initial wear information based on the measured wear data.

[0011] In a possible implementation manner, input the updated initial wear information into the digital twin model and update the wear data of the drill bit model in the drill rig model.

[0012] In a possible implementation manner, determine the wear grade of the drill bit based on the measured wear data. If the wear grade of the drill bit reaches the preset wear grade, it is determined that the drill bit is unqualified.

[0013] In a possible implementation manner, before the drill bit takes a core, control the power head to output a preset torque and drive the drill bit to rotate idly; Real-time monitor the initial vibration characteristics of the drill bit within a preset time; Analyze the initial vibration characteristics; wherein, if the initial vibration characteristics conform to the preset vibration characteristics, it is determined that the core drilling rig meets the working requirements.

[0014] The second aspect of the embodiments of the present application provides a control system for the power head of a core drilling rig, including: A training module, configured to use the historical data of the working process of the core drilling rig as training samples to construct a neural network model, so as to obtain the mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during core taking, and the hardness data of the formation; A digital twin module, configured to construct a visual digital twin model based on the mapping relationship; wherein, the digital twin model includes a drill rig model and a formation model; A monitoring module, configured to real-time monitor the vibration information of the drill bit during the process of the drill bit taking a core; An input module, configured to input the vibration information, the initial wear information of the drill bit before this core taking, and the formation information of the formation where the drill bit has completed core taking into the digital twin model; A prediction module, configured to predict the hardness of the formation where the drill bit is currently acting through the digital twin model and obtain prediction hardness information; An adjustment module, configured to dynamically adjust the output torque of the power head based on the vibration information, the initial wear information, and the prediction hardness information, and dynamically adjust the feed speed of the power head according to the feed speed equation.

[0015] The beneficial effects of the present application include: The control method of the core drill power head proposed in this application uses a neural network model trained with historical data to establish a mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during core sampling, and the hardness data of the formation. Based on the mapping relationship, a visual digital twin model is constructed. During the core sampling process of the drill bit, the vibration information of the drill bit is monitored in real time. The vibration information, the wear information of the drill bit before the current core sampling, and the formation information of the formation where the drill bit has completed core sampling are input into the digital twin model. In this way, the digital twin model can predict the hardness of the formation where the drill bit is currently acting based on the mapping relationship and obtain the predicted hardness information, and dynamically adjust the output torque and feed speed of the power head based on the known and predicted relevant information. In addition, since the digital twin model includes a drill rig model and a formation model, it can intuitively display the relevant information of the drill rig and the formation hardness distribution, facilitating virtual commissioning by the operator.

[0016] The method proposed in this application can analyze the vibration information of the drill bit in real time, predict the hardness information of the formation where the drill bit is currently acting, and realize the dynamic adjustment of the output torque and feed speed of the power head: when the drill bit encounters a formation with high hardness, appropriately increase the output torque of the power head and reduce the feed speed; in a soft formation, appropriately increase the feed speed to improve the core sampling efficiency, etc. Brief Description of the Drawings

[0017] To more clearly illustrate the technical solutions of the embodiments of this application, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of this application, so they should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can also be obtained based on these drawings without creative efforts.

[0018] Figure 1 Shows a schematic flow chart of a control method for the core drill power head; Figure 2 Shows a schematic flow chart of establishing a neural network model; Figure 3 Shows a schematic flow chart of a method for determining initial wear information; Figure 4 Shows a schematic diagram of a control system for the core drill power head.

[0019] Main Element Symbol Description: 110 - Training module; 120 - Digital twin module; 130 - Monitoring module; 140 - Input module; 150 - Prediction module; 160 - Adjustment module. Detailed Embodiments

[0020] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where like or similar reference numerals denote like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present application and should not be construed as limiting the present application.

[0021] In the description of the present application, it should be understood that the orientation or positional relationships indicated by the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. are based on the orientation or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present application.

[0022] Embodiment As Figure 1 shown, in this embodiment, a control method for the power head of a core drilling rig is proposed, including: S11, using the historical data of the working process of the core drilling rig as training samples to construct a neural network model to obtain the mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during core drilling, and the hardness data of the formation; S12, constructing a visual digital twin model based on the historical data and the mapping relationship; S13, during the core drilling process of the drill bit, real-time monitoring the vibration information of the drill bit; S14, inputting the vibration information, the initial wear information of the drill bit before the current core drilling, and the formation information of the formation where the drill bit has completed core drilling into the digital twin model; S15, predicting the hardness of the formation where the drill bit is currently acting through the digital twin model and obtaining the predicted hardness information; S16, dynamically adjusting the output torque of the power head based on the vibration information, the initial wear information, and the predicted hardness information, and dynamically adjusting the feed speed of the power head according to the feed speed equation.

[0023] The historical data includes the parameters of the drilling rig, the vibration information of the drill bit during core drilling, the information of the formation, the correlation between the vibration information and the formation hardness, etc. Among them, the parameters of the drilling rig include the parameters of the power head and the parameters of the drill bit, etc. The parameters of the power head include the output torque, the feed speed, etc. The parameters of the drill bit include the specifications of the drill bit, the wear data of the drill bit, etc.

[0024] The digital twin model includes a drill rig model and a formation model. Using the digital twin model, the staff can achieve virtual commissioning of the coring process. Among them, for the same borehole (the position of the borehole remains unchanged, only the depth of the borehole changes), the known formation information (the formation where coring has been completed) during the coring process can be intuitively reflected in the formation model.

[0025] The drill pipe is fixed on the chuck of the power head, and the drill bit is installed at one end of the drill pipe away from the power head. Among them, the feed speed of the drill bit is the same as that of the power head.

[0026] The control method proposed in this embodiment establishes a mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during the coring process, and the hardness data of the formation through a neural network model trained with historical data, and constructs a visual digital twin model based on the mapping relationship.

[0027] During the coring process of the drill bit, the vibration information of the drill bit is monitored in real time. Among them, the vibration information, the wear information of the drill bit before the current coring, and the formation information of the formation where the drill bit has completed coring are input into the digital twin model. The digital twin model predicts the hardness of the formation where the drill bit is currently acting based on the mapping relationship and obtains the predicted hardness information. Among them, the output torque and feed speed of the power head are dynamically adjusted according to the known and predicted relevant information.

[0028] Since the digital twin model includes a drill rig model and a formation model, it can intuitively display the relevant information of the drill rig and the formation hardness distribution, thus facilitating virtual commissioning by the operator. In addition, the digital twin model can simulate the coring process, and feedback the simulated data to the neural network model for training, so as to further optimize the mapping relationship.

[0029] In this embodiment, the torque equation is: ; The feed speed equation is: .

[0030] Based on the above equations, the influence of multiple factors on the output torque and feed speed can be quantified, avoiding the limitations of single-parameter adjustment, and improving the stability and reliability of the drill rig operation.

[0031] T represents the output torque of the power head.

[0032] T max represents the maximum rated output torque of the power head. Among them, T max is related to the model of the power head, etc.

[0033] H represents the formation hardness coefficient. The formation hardness is classified according to the actually measured hardness data, and the formation hardness coefficient is thus obtained.

[0034] A represents the vibration amplitude of the drill bit. An acceleration sensor or a vibration sensor is installed at the corresponding position of the drill bit to measure the vibration amplitude of the drill bit in three mutually perpendicular directions, which are the X direction, the Y direction, and the Z direction respectively (the X direction is the axial direction of the drill bit, and the Y direction and the Z direction are both the radial directions of the drill bit). The vibration amplitudes corresponding to the three directions are respectively set as x, y, and z. Among them, The inner wall of the drill bit can be provided with an installation groove, and the sensor is arranged in the installation groove. Among them, by strengthening and sealing the installation groove, the sensor can be protected. Conductive contacts are provided at the connection part between the drill bit and the drill pipe. A signal line is arranged inside the drill pipe. The sensor, the conductive contacts, and the signal line are electrically connected. A wireless communication module is arranged at one end of the signal line close to the power head. Among them, the signals detected by the sensor are transmitted to the wireless communication module through the conductive contacts and the signal line, so that the relevant signals can be transmitted to the corresponding upper computer.

[0035] n represents the current drilling speed.

[0036] n max represents the maximum allowable speed of the drill bit. Among them, n max is related to the models of the drill bit and the power head, etc.

[0037] W represents the drill bit wear coefficient; k1 represents the torque adjustment coefficient; k2 represents the feed speed basic coefficient; α represents the vibration compensation coefficient; β represents the wear compensation coefficient; γ represents the speed compensation coefficient; ν represents the feed speed; δ represents the vibration suppression coefficient; ε represents the wear suppression coefficient; ζ represents the hardness enhancement coefficient. The drill bit wear coefficient is related to the wear state of the drill bit; the torque adjustment coefficient is related to the power parameters of the power head; the feed speed basic coefficient is related to the performance parameters of the drilling rig, etc.; the vibration compensation coefficient is used to adjust the influence of vibration on torque; the wear compensation coefficient adjusts the influence of drill bit wear on torque; the speed compensation coefficient adjusts the influence of speed on torque; the vibration suppression coefficient is used to adjust the influence of vibration on the feed speed; the wear suppression coefficient is used to adjust the influence of drill bit wear on the feed speed; the hardness enhancement coefficient is used to adjust the influence of formation hardness on the feed speed.

[0038] The vibration information includes the vibration amplitude, the vibration compensation coefficient, and the vibration suppression coefficient. The initial wear information includes the drill bit wear coefficient, the wear compensation coefficient, and the wear suppression coefficient. The predicted hardness information includes the formation hardness coefficient and the hardness enhancement coefficient.

[0039] When the formation hardness is greater, the required torque is greater; when the vibration amplitude is greater, the torque needs to be appropriately increased to stabilize the drilling; when the output torque increases, the feed rate can be appropriately increased; when the vibration amplitude increases, the feed rate needs to be decreased to stabilize the drilling; when the drill bit wear increases, the feed rate needs to be decreased to extend the service life of the drill bit; when the formation hardness increases, the feed rate needs to be decreased to avoid sticking of the drill string and other situations.

[0040] During the coring process, the vibration condition of the drill pipe is monitored in real time, and the output torque and feed rate of the power head are dynamically adjusted according to the monitoring results to adapt to different formation conditions and drill pipe states. Specifically, during the coring process, the vibration condition of the drill bit is monitored in real time, and the output torque and feed rate of the power head are dynamically adjusted according to the monitoring results to adapt to different formation conditions and drill bit states. Thereby, while ensuring the coring efficiency, it can also play a role in protecting the drill bit and avoiding sticking of the drill string and other problems. When abnormal vibration conditions (such as sudden increase in vibration amplitude, abnormal frequency, etc.) are detected, a fault warning is issued in a timely manner and corresponding protective measures (such as reducing the output torque and feed rate, stopping the machine for inspection, etc.) are taken to avoid problems such as sticking of the drill string and cracking of the drill bit.

[0041] As Figure 2 shown, in this embodiment, the establishment of the neural network model includes: S21, obtaining a sample set, and each sample set includes a plurality of training samples; in the same sample set, the wear degree of the drill bit in each training sample is at the same level; S22, the training sample includes input data and output data, the input data includes the first data, and the output data includes the second data; wherein, the first data includes the vibration data when the drill bit cores the preset formation, and the second data includes the measured hardness data of the preset formation; historical data can include input data and output data; S23, using the input data and output data to train the neural network; wherein, if the eigenvalue of the hardness data of the formation predicted by the neural network model conforms to the eigenvalue of the hardness data of the actually measured formation, the training ends and the neural network model is obtained.

[0042] After each coring of the drill bit, the core taken out by the drill bit is detected to obtain the measured hardness information of the core, and the formation model is updated, thereby ensuring the accuracy of the formation model and realizing the closed-loop feedback of the data.

[0043] Furthermore, if the measured hardness information does not match the predicted hardness information, the mapping relationship is corrected based on the measured hardness information. Thereby, further optimization of the neural network model and the digital twin model can be realized.

[0044] As Figure 3 shown, the method for determining the initial wear information includes: S31. After each core sampling operation of the drill bit, clean the drill bit; S32. Perform three-dimensional scanning on the drill bit and establish a three-dimensional model; S33. Compare the three-dimensional model with the standard model of the drill bit to obtain the measured wear data of the drill bit; S34. Update the initial wear information based on the measured wear data.

[0045] Through the above method, the wear data of the drill bit can be obtained efficiently and accurately.

[0046] Input the updated initial wear information into the digital twin model and update the wear data of the drill bit model in the drill rig model.

[0047] Determine the wear grade of the drill bit based on the measured wear data. If the wear grade of the drill bit reaches the preset wear grade, it is determined that the drill bit is unqualified, and at this time, the drill bit needs to be replaced.

[0048] Before the drill bit takes a core, control the power head to output a preset torque and drive the drill bit to idle; monitor the initial vibration characteristics of the drill bit in real time within a preset time; analyze the initial vibration characteristics. The initial vibration characteristics include the vibration amplitudes in the X direction, Y direction, and Z direction, and whether the vibration in each direction is linear vibration.

[0049] Among them, if the initial vibration characteristics conform to the preset vibration characteristics, it is determined that the core drilling rig meets the working requirements; if the initial vibration characteristics do not conform to the preset vibration characteristics, it is determined that the core drilling rig does not meet the working requirements, and at this time, it is necessary to troubleshoot the cause of the failure, for example, whether there is a failure in the power head, whether the drill bit is installed in place, etc. For example, when the vibration amplitudes in the X direction, Y direction, and Z direction are respectively less than the corresponding preset values, and the vibration in each direction is linear vibration, it is determined that the core sampling assembly meets the working requirements.

[0050] As Figure 4 shown, in this embodiment, a control system for the power head of a core drilling rig is also proposed, including: A training module 110, which is used to use the historical data of the working process of the core drilling rig as training samples to construct a neural network model to obtain the mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during core sampling, and the hardness data of the formation; A digital twin module 120, which is used to construct a visual digital twin model based on the mapping relationship; among them, the digital twin model includes a drill rig model and a formation model; A monitoring module 130, which is used to monitor the vibration information of the drill bit in real time during the core sampling process of the drill bit; An input module 140 for inputting vibration information, initial wear information of the drill bit before the current coring, and formation information of the formation where the drill bit has completed coring into the digital twin model; A prediction module 150 for predicting the hardness of the formation where the drill bit is currently acting through the digital twin model and obtaining predicted hardness information; An adjustment module 160 for dynamically adjusting the output torque of the power head based on the vibration information, initial wear information, and predicted hardness information and according to the torque equation, and dynamically adjusting the feed speed of the power head according to the feed speed equation.

[0051] Further, the torque equation is: ; The feed speed equation is: ; where T represents the output torque of the power head; T max represents the maximum rated output torque of the power head; H represents the formation hardness coefficient; A represents the vibration amplitude of the drill bit; W represents the drill bit wear coefficient; n represents the current drilling rotation speed; n max represents the maximum allowable rotation speed of the drill bit; k1 represents the torque adjustment coefficient; k2 represents the feed speed base coefficient; α represents the vibration compensation coefficient; β represents the wear compensation coefficient; γ represents the rotation speed compensation coefficient; ν represents the feed speed; δ represents the vibration suppression coefficient; ε represents the wear suppression coefficient; ζ represents the hardness enhancement coefficient; The vibration information includes the vibration amplitude, the vibration compensation coefficient, and the vibration suppression coefficient, the initial wear information includes the drill bit wear coefficient, the wear compensation coefficient, and the wear suppression coefficient, and the predicted hardness information includes the formation hardness coefficient and the hardness enhancement coefficient.

[0052] Further, a training module 110 is specifically configured to: Obtain a sample set, where the sample set includes multiple training samples; in the same sample set, the wear degree of the drill bit in each training sample is at the same level; The training sample includes input data and output data, the input data includes first data, and the output data includes second data; where the first data includes vibration data when the drill bit cores a preset formation, and the second data includes the measured hardness data of the preset formation; Train a neural network using the input data and the output data; where if the eigenvalue of the hardness data of the formation predicted by the neural network model conforms to the eigenvalue of the hardness data of the actually measured formation, the training ends and the neural network model is obtained.

[0053] Further, the system further includes: a detection module, configured to detect the core taken out by the drill bit each time the drill bit completes coring, so as to obtain the measured hardness information of the core; and a digital twin module 120, further configured to update the formation model.

[0054] Further, the training module 110 is further configured to, if the measured hardness information does not match the predicted hardness information, correct the mapping relationship based on the measured hardness information.

[0055] Further, the method for determining the initial wear information includes: After the drill bit completes coring each time, clean the drill bit; Perform three-dimensional scanning on the drill bit and establish a three-dimensional model; Compare the three-dimensional model with the standard model of the drill bit to obtain the measured wear data of the drill bit; Update the initial wear information based on the measured wear data.

[0056] Further, the digital twin module 120 is further configured to input the updated initial wear information into the digital twin model and update the wear data of the drill bit model in the drill rig model.

[0057] Further, the system further includes: a judgment module, configured to determine the wear level of the drill bit based on the measured wear data, and if the wear level of the drill bit reaches a preset wear level, determine that the drill bit is unqualified.

[0058] Further, the adjustment module 160 is further configured to: Before the drill bit cores, control the power head to output a preset torque and drive the drill bit to rotate idly; Real-time monitor the initial vibration characteristics of the drill bit within a preset time; Analyze the initial vibration characteristics; wherein, if the initial vibration characteristics conform to the preset vibration characteristics, it is determined that the core drilling rig meets the working requirements.

[0059] In the description of this specification, the descriptions referring to terms such as "one embodiment", "some embodiments", "examples", "specific examples", or "some examples", etc., mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0060] Although the embodiments of this application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting this application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A control method for the power head of a core drilling rig, characterized in that, Including: Taking the historical data of the working process of the core drilling rig as training samples to construct a neural network model to obtain the mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during core sampling, and the hardness data of the formation; Constructing a visual digital twin model based on the historical data and the mapping relationship; wherein, the digital twin model includes a drilling rig model and a formation model; During the process of core sampling by the drill bit, the vibration information of the drill bit is monitored in real time; Inputting the vibration information, the initial wear information of the drill bit before the current core sampling, and the formation information of the formation where the drill bit has completed core sampling into the digital twin model; Predicting the hardness of the formation where the drill bit is currently acting through the digital twin model and obtaining predicted hardness information; Based on the vibration information, the initial wear information, and the predicted hardness information, dynamically adjusting the output torque of the power head according to the torque equation, and dynamically adjusting the feed speed of the power head according to the feed speed equation.

2. The control method of the core drill power head according to claim 1, characterized in that The torque equation is: ； The feed speed equation is: ； where T represents the output torque of the power head; T max represents the maximum rated output torque of the power head; H represents the formation hardness coefficient; A represents the vibration amplitude of the drill bit; W represents the drill bit wear coefficient; n represents the current drilling rotation speed; n max represents the maximum allowable rotation speed of the drill bit; k1 represents the torque adjustment coefficient; k2 represents the feed speed base coefficient; α represents the vibration compensation coefficient; β represents the wear compensation coefficient; γ represents the rotation speed compensation coefficient; ν represents the feed speed; δ represents the vibration suppression coefficient; ε represents the wear suppression coefficient; ζ represents the hardness enhancement coefficient; The vibration information includes the vibration amplitude, the vibration compensation coefficient, and the vibration suppression coefficient. The initial wear information includes the drill bit wear coefficient, the wear compensation coefficient, and the wear suppression coefficient. The predicted hardness information includes the formation hardness coefficient and the hardness enhancement coefficient.

3. The control method of the core drill power head according to claim 1, characterized in that, The establishment of the neural network model includes: Obtaining a sample set, and the sample set all includes a plurality of the training samples; in the same sample set, the wear degrees of the drill bits in each of the training samples are at the same level; The training sample includes input data and output data. The input data includes first data, and the output data includes second data; wherein, the first data includes the vibration data when the drill bit cores a preset formation, and the second data includes the measured hardness data of the preset formation; Training the neural network by using the input data and the output data; wherein, if the eigenvalue of the hardness data of the formation predicted by the neural network model conforms to the eigenvalue of the hardness data of the actually measured formation, the training ends and the neural network model is obtained.

4. The control method of the core drill power head according to claim 1, characterized in that, After the drill bit finishes core sampling each time, detecting the core taken out by the drill bit to obtain the measured hardness information of the core and updating the formation model.

5. The control method of the core drill power head according to claim 4, characterized in that, If the measured hardness information does not match the predicted hardness information, the mapping relationship is corrected based on the measured hardness information.

6. The control method of the core drill power head according to claim 1, characterized in that, The determination method of the initial wear information includes: After the drill bit finishes core sampling each time, cleaning the drill bit; Performing three-dimensional scanning on the drill bit and establishing a three-dimensional model; Comparing the three-dimensional model with the standard model of the drill bit to obtain the measured wear data of the drill bit; Updating the initial wear information based on the measured wear data.

7. The control method of the core drill power head according to claim 6, characterized in that, Inputting the updated initial wear information into the digital twin model and updating the wear data of the drill bit model in the drilling rig model.

8. The control method of the core drill power head according to claim 6, characterized in that, Determine the wear grade of the drill bit based on the measured wear data. If the wear grade of the drill bit reaches the preset wear grade, it is determined that the drill bit is unqualified.

9. The control method of the core drill power head according to claim 1, characterized in that, Before the drill bit takes a core, control the power head to output a preset torque and drive the drill bit to rotate idly. Real-time monitor the initial vibration characteristics of the drill bit within a preset time. Analyze the initial vibration characteristics. Among them, if the initial vibration characteristics conform to the preset vibration characteristics, it is determined that the core drilling rig meets the working requirements.

10. A control system for the power head of a core drill, characterized in that, Include: A training module for using the historical data of the working process of the core drilling rig as training samples to construct a neural network model to obtain the mapping relationship between the wear data of the drill bit, the vibration data of the drill bit during core taking, and the hardness data of the formation. A digital twin module for constructing a visual digital twin model based on the mapping relationship. Among them, the digital twin model includes a drilling rig model and a formation model. A monitoring module for real-time monitoring the vibration information of the drill bit during the core taking process of the drill bit. An input module for inputting the vibration information, the initial wear information of the drill bit before this core taking, and the formation information of the formation where the drill bit has completed core taking into the digital twin model. A prediction module for predicting the hardness of the formation currently acted on by the drill bit through the digital twin model and obtaining prediction hardness information. An adjustment module for dynamically adjusting the output torque of the power head based on the vibration information, the initial wear information, and the prediction hardness information and according to the torque equation, and dynamically adjusting the feed speed of the power head according to the feed speed equation.

Images