A slag removal method for a construction system based on an impact drill rig

Abstract

The present invention discloses a slag removal method for a construction system based on an impact drill rig, and relates to the technical field of geotechnical engineering construction, including collecting real-time geological data of the drilling area; based on the real-time geological data, applying an adaptive algorithm to calculate the slag removal force, slag removal frequency and slag removal path of each layer, and generating an optimized layered and segmented slag removal strategy; using a multi-stage slag removal feedback method to dynamically optimize the slag removal path in the layered and segmented slag removal strategy; according to the optimized slag removal path, controlling the drilling rig to perform slag removal operations; real-time monitoring of the residue removal efficiency during the slag removal operation, and feeding back the monitoring parameters to the adaptive algorithm to adjust the layered and segmented slag removal strategy. The present invention uses a multi-stage feedback method to correct the slag removal path and parameters in real time, ensuring that the slag removal process is efficient and accurate, and significantly improving the construction efficiency, equipment service life and slag removal intelligence level.

Description

Technical Field

[0001] The invention relates to the technical field of geotechnical engineering construction, in particular to a slag removal method of a construction system based on an impact drill rig. Background Art

[0002] With the continuous development of engineering construction technology, impact drills have been widely used in geotechnical engineering construction, especially in the fields of deep hole drilling and geological survey. However, since a large amount of residue is generated during the drilling process, including rock chips, mud and dust, how to efficiently remove these residues has become a key issue affecting construction quality and efficiency. At present, traditional slag removal methods mostly rely on fixed parameters and empirical rules, which cannot adapt to complex geological conditions in real time, and easily lead to residue accumulation, low slag removal efficiency and increased equipment wear. In addition, the lack of real-time monitoring and dynamic adjustment of the slag removal process further limits the intelligence and precision of slag removal operations.

[0003] The shortcomings of existing slag removal technology are mainly reflected in the following two aspects: first, the slag removal path planning and the adjustment of slag removal intensity and frequency lack linkage with geological conditions, making it difficult to optimize slag removal parameters in real time for complex geological environments; second, the slag removal process fails to effectively use real-time feedback data for dynamic adjustment, resulting in low residue removal efficiency and unstable equipment operation. In contrast, the present invention not only makes up for the shortcomings of traditional technology by introducing real-time geological data, adaptive algorithms and multi-stage feedback methods, but also significantly improves slag removal efficiency, construction accuracy and equipment service life. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a slag cleaning method for a construction system based on an impact drill rig to solve the adaptability problem of slag cleaning path planning and real-time adjustment of slag cleaning force and slag cleaning frequency during the slag cleaning process.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a slag removal method for a construction system based on an impact drill rig, which comprises collecting real-time geological data of a drilling area;

[0008] Based on real-time geological data, an adaptive algorithm is used to calculate the slag removal intensity, frequency and path of each layer, and an optimized layered and segmented slag removal strategy is generated;

[0009] The multi-stage slag cleaning feedback method is used to dynamically optimize the slag cleaning path in the layered and segmented slag cleaning strategy;

[0010] According to the optimized slag removal path, the drilling rig is controlled to perform slag removal operations;

[0011] The residue removal efficiency during the slag cleaning operation is monitored in real time, and the monitoring parameters are fed back to the adaptive algorithm to adjust the layered and segmented slag cleaning strategy.

[0012] As a preferred solution of the slag removal method of the construction system based on the impact drill rig of the present invention, the real-time geological data includes the formation hardness coefficient , formation friction coefficient , stratigraphic structure data , fluid characteristics in the hole and pore geometry .

[0013] As a preferred solution of the slag cleaning method of the construction system based on the impact drill rig of the present invention, wherein: based on the real-time geological data, an adaptive algorithm is applied to calculate the slag cleaning force, slag cleaning frequency and slag cleaning path of each layer, and an optimized layered and segmented slag cleaning strategy is generated. The specific steps are as follows:

[0014] Through fuzzy logic, fuzzy reasoning is performed on the formation hardness coefficient, formation friction coefficient, formation structure data, fluid characteristics in the hole and hole geometry characteristics in real-time geological data;

[0015] In fuzzy reasoning, the membership function is used to map the geological data of each layer to the membership function value and construct fuzzy rules;

[0016] Dynamic fuzzy measurement and nonlinear Choquet integral are used to optimize the membership function value in fuzzy rules and generate the optimized value of each layer;

[0017] Through reinforcement learning, the real-time geological data in each layer of optimization value is used as the state space, the combination of slag cleaning force, slag cleaning frequency and slag cleaning path is used as the action space, and the weighted sum of the target of slag cleaning efficiency, drill wear and energy consumption is used as the reward function;

[0018] According to the geological characteristics of each layer and fuzzy reasoning, the optimized slag cleaning intensity, frequency and path of each layer are output to form a layered and segmented slag cleaning strategy.

[0019] As a preferred solution of the slag cleaning method of the construction system based on the impact drill rig of the present invention, wherein: the dynamic fuzzy measurement and nonlinear Choquet integral are used to optimize the membership function value in the fuzzy rule to generate the optimized value of each layer. The specific steps are as follows:

[0020] For the membership function value in the fuzzy rule, the dynamic fuzzy measurement function is used to optimize the influence degree and mutual correlation of the target, and the expression is:

[0021] ;

[0022] ;

[0023] in, represents the fuzzy measure function, Represents a collection of real-time geological data factors, An index variable representing real-time geological data, Indicates Real-time value of real-time geological data, Indicates The expected value of real-time geological data, is the square of the standard deviation, is an exponential function, Indicates The square difference between the actual value and the expected value of real-time geological data;

[0024] Based on Choquet integral, the membership function value and the dynamic fuzzy measurement function are integrated, and the expression is:

[0025] ;

[0026] ;

[0027] in, represents the calculation result of Choquet integral, represents the membership function value, Represents a single factor in a real-time geological data set, Representing fuzzy measure The incremental value of represents the mathematical definition of Choquet integral, represents the total number of slag cleaning related factors, Indicates the sorted The membership function value of real-time geological data, Before The fuzzy measurement value after the real-time geological data is sorted, Before The fuzzy measurement value after the real-time geological data is sorted;

[0028] The mathematical definition of Choquet integral is applied to the cleaning intensity, cleaning frequency and cleaning path of each layer to generate the optimized value for each layer.

[0029] As a preferred solution of the slag cleaning method of the construction system based on the impact drill rig of the present invention, wherein: the multi-stage slag cleaning feedback method is used to dynamically optimize the slag cleaning path in the layered and segmented slag cleaning strategy, and the specific steps are as follows:

[0030] Real-time collection of the residue rate, slag cleaning path deviation, drilling rig vibration amplitude, energy consumption and slag cleaning efficiency during the slag cleaning process as slag cleaning feedback data ;

[0031] Utilizing slag removal feedback data A dynamic optimization model is constructed, and the recursive Bayesian estimation is used to adjust the slag removal path. The expression is:

[0032] ;

[0033] in, represents the optimized slag removal path, Represents the predicted value of the current slag removal path, represents the Kalman gain, Represents the mapping matrix between feedback data and slag removal path, For the slag removal path, Indicates a point in time;

[0034] In the slag removal path When adjusting the slag removal path, the correction value of the slag removal path is calculated with the goal of minimizing the residual slag rate and the slag removal path deviation. ;

[0035] Correction value based on slag removal path and optimized slag removal path , update the slag removal path for the next stage in real time;

[0036] In the process of updating the slag removal path for the next stage, cubic spline interpolation is applied to smooth the slag removal path;

[0037] The smoothed slag cleaning path is divided into several small sections, and the initial length of each slag cleaning path is adaptively adjusted through fuzzy logic reasoning, and the slag cleaning path is optimized and corrected at the same time;

[0038] After each stage of slag cleaning is completed, the residual rate and the slag cleaning path deviation are calculated in real time, and the slag cleaning path of the next stage is adjusted through fuzzy reasoning and recursive Bayesian estimation. , the expression is:

[0039] ;

[0040] in, is the feedback gain coefficient, The difference between the current stage residue rate and the expected value.

[0041] As a preferred solution of the slag cleaning method of the construction system based on the impact drill rig of the present invention, wherein: according to the optimized slag cleaning path, the drilling rig is controlled to perform the slag cleaning operation, and the specific steps are as follows:

[0042] Obtain the optimized slag removal path and parse it into control instructions;

[0043] Calibrate the initial position of the drill, check the equipment status, and load the parsed slag removal path instructions into the drill controller;

[0044] Start the drill to move along the planned slag removal path through the drill controller, dynamically adjust the tool movement speed and angle, and correct the deviation in real time;

[0045] Collect the slag cleaning process data, adjust the slag cleaning path through comparative feedback, and optimize the slag cleaning intensity and frequency;

[0046] After each section of the slag cleaning path is completed, the drill rig is calibrated to the starting point of the next section of the slag cleaning path, and the slag cleaning force, frequency and path are adjusted to adapt to the new geological conditions. The slag cleaning path smoothing algorithm is used to optimize the connection process.

[0047] As a preferred solution of the slag removal method of the construction system based on the impact drill rig of the present invention, wherein: the real-time monitoring of the residue removal efficiency during the slag removal operation is carried out, and the specific steps are as follows:

[0048] The sensors are used to collect the residue concentration, flow rate and image data of the slag cleaning area during the slag cleaning operation;

[0049] The collected residue concentration, flow rate and residue cleaning area image data are used to dynamically calculate the residue concentration change rate and the residue cleaning efficiency through the optical transmission method to obtain the residue cleaning efficiency index;

[0050] Mark the residue accumulation area based on the slag removal efficiency index;

[0051] Evaluate the cleaning coverage in the residue accumulation area through image processing algorithms;

[0052] The slag removal coverage is used to dynamically quantify the real-time efficiency of the slag removal operation process and generate a feedback value of the residue removal efficiency.

[0053] As a preferred solution of the slag cleaning method of the construction system based on the impact drill rig of the present invention, wherein: the monitoring parameters are fed back to the adaptive algorithm to adjust the layered and segmented slag cleaning strategy, the specific steps are as follows:

[0054] The feedback value of residue removal efficiency is used as a monitoring parameter;

[0055] Compare the monitored parameters with the expected efficiency values ​​after optimization at each layer and calculate the residuals;

[0056] According to the residual, the current slag removal path is adjusted through recursive Bayesian estimation;

[0057] The modified slag removal path is optimized using dynamic fuzzy measurement, the feedback value of residue removal efficiency is associated with the slag removal force, slag removal frequency and slag removal path, the weight distribution is recalculated, and a new optimization strategy value is generated;

[0058] The updated slag removal path is used as the state input of reinforcement learning, and the residue removal efficiency, equipment wear and energy consumption are used as the reward function to dynamically adjust the slag removal intensity, frequency and path, and generate an adjusted hierarchical and segmented optimized slag removal strategy.

[0059] The adjusted slag removal strategy is loaded into the drilling rig controller to execute a new round of slag removal operations. At the same time, the newly generated residue removal efficiency feedback value is monitored in real time as a monitoring parameter to perform dynamic iterative closed-loop optimization.

[0060] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the slag cleaning method of the construction system based on the impact drill rig as described in the first aspect of the present invention is implemented.

[0061] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the slag cleaning method for a construction system based on an impact drill rig as described in the first aspect of the present invention is implemented.

[0062] The beneficial effects of the present invention are as follows: the present invention realizes dynamic optimization of slag cleaning force, slag cleaning frequency and slag cleaning path through real-time geological data collection and application of adaptive algorithms, thereby significantly improving slag cleaning efficiency and construction quality; by real-time geological data collection and combining fuzzy logic reasoning and Choquet integral to optimize slag cleaning parameters, a reinforcement learning algorithm is used to dynamically adjust the layered and segmented slag cleaning strategy according to complex geological conditions, and a multi-stage feedback method is used to correct the slag cleaning path and parameters in real time, thereby ensuring that the slag cleaning process is efficient and accurate, thereby significantly improving construction efficiency, equipment service life and the level of slag cleaning intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0064] Figure 1 This is a flow chart of the slag cleaning method of the construction system based on the impact drill rig in Example 1.

[0065] Figure 2This is a flow chart of the method for real-time monitoring of residue removal efficiency during the slag removal operation in Example 1. DETAILED DESCRIPTION

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0067] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0068] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0069] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a slag removal method for a construction system based on an impact drill rig, comprising the following steps:

[0070] S1. Collect real-time geological data of the drilling area.

[0071] Furthermore, the real-time geological data includes formation hardness coefficient, formation friction coefficient, formation structure data, pore fluid characteristics and pore geometry characteristics.

[0072] Specifically, during the drilling process, a hardness sensor is first installed on the drill bit or the front end of the drilling rig to measure the hardness value of the drill bit when it contacts the formation in real time, and the data fed back by the sensor is used to display the hardness change at each drilling depth; at the same time, the friction force generated by the drilling rig during the drilling process is monitored by force sensors and torque sensors, and the friction coefficient of the formation at each depth is calculated and recorded. When obtaining the structural characteristics of the formation, a geological radar or an acoustic wave sensor is used to scan along the borehole wall to collect structural data such as formation density, fracture distribution and bedding in real time, and calibrate it in combination with the drilling situation. The fluid characteristics in the hole are monitored in real time by installing a fluid sensor in the middle or bottom of the borehole to monitor the temperature, pressure, flow rate and other parameters of the fluid in the hole, providing data support for subsequent slag removal operations. Use a laser scanner or ultrasonic detector to scan the borehole, obtain the geometric data of the channel, such as diameter, depth and wall thickness, in real time, and update it regularly to ensure that the changes in the channel are accurately reflected.

[0073] S2. Based on real-time geological data, an adaptive algorithm is used to calculate the slag cleaning intensity, frequency and path of each layer, and an optimized layered and segmented slag cleaning strategy is generated.

[0074] Furthermore, fuzzy logic is used to perform fuzzy reasoning on the formation hardness coefficient, formation friction coefficient, formation structure data, fluid characteristics in the hole and hole geometry characteristics in the real-time geological data;

[0075] In fuzzy reasoning, the membership function is used to map the geological data of each layer to the membership function value and construct fuzzy rules;

[0076] For example, the formation hardness coefficient is mapped to a fuzzy value through the membership function, reflecting its "high hardness" or "low hardness" characteristics. Similarly, the friction coefficient, fluid characteristics, etc. are also fuzzy processed through the membership function. If the hardness H is high and the friction F is high, the slag cleaning force L is large; if the hole geometry C is complex, the slag cleaning path P needs to be more complex. These fuzzy rules provide the basis for subsequent decision-making.

[0077] Dynamic fuzzy measurement and nonlinear Choquet integral are used to optimize the membership function value in fuzzy rules and generate the optimized value of each layer;

[0078] Specifically, for the membership function value in the fuzzy rule, the dynamic fuzzy measurement function is used to optimize the influence degree and mutual correlation of the target, and the expression is:

[0079] ;

[0080] ;

[0081] in, represents the fuzzy measure function, Represents a collection of real-time geological data factors, An index variable representing real-time geological data, Indicates Real-time value of real-time geological data, Indicates The expected value of real-time geological data, is the square of the standard deviation, is an exponential function, Indicates The square difference between the actual value and the expected value of real-time geological data;

[0082] In the existing technical solutions, such as the traditional linear weighted average algorithm and the slag removal method based on single parameter optimization, these solutions usually rely on a single data source (such as geological hardness or friction coefficient) to adjust the slag removal strategy, and use a fixed weight model or a simple linear regression model as the basis for optimization. However, these methods are highly dependent on precise numerical inputs and have poor adaptability to complex geological layers and dynamically changing environments, especially when faced with multivariate coupling and uncertainty conditions. By introducing fuzzy logic, various types of geological data (such as hardness, friction, fluid properties, etc.) can be fused to form fuzzy rules for dynamic adjustment, thereby overcoming the shortcomings of traditional linear methods under uncertainty and complex conditions.

[0083] Based on Choquet integral, the membership function value and the dynamic fuzzy measurement function are integrated, and the expression is:

[0084] ;

[0085] ;

[0086] in, represents the calculation result of Choquet integral, represents the membership function value, Represents a single factor in a real-time geological data set, Representing fuzzy measure The incremental value of represents the mathematical definition of Choquet integral, represents the total number of slag cleaning related factors, Indicates the sorted The membership function value of real-time geological data, Before The fuzzy measurement value after the real-time geological data is sorted, Before The fuzzy measurement value after the real-time geological data is sorted;

[0087] It should be noted that the dynamic fuzzy measurement function is a collection of factors used to evaluate real-time geological data It is a function of the comprehensive importance or weight of the factors. It takes into account the interrelationships and dynamic characteristics between factors; the fuzzy measure increment value Indicates that due to a single factor A collection of real-time geological data factors The key points to distinguish the two are shown in Table 1 below:

[0088] Table 1 Analysis of the differences between dynamic fuzzy measurement and incremental measurement

[0089] characteristic Dynamic fuzzy measure function g(A) Fuzzy measure increment dg(a) Scope The entire set A The marginal contribution of a single factor a to the set Calculation method Calculate the overall weight of the collection through the function Calculated by the difference of set weights Results reflect the content The overall fuzzy weight of the set The marginal effect of a single factor on the aggregate use Describe the combined importance of multiple factors Reflects the independent contribution of the newly added factors

[0090] Preferably, the optimization problem of the nonlinear relationship and interaction of multiple parameters in the slag removal process can be effectively solved by the calculation method based on the Choquet integral fusion of the membership function value and the dynamic fuzzy measure function. Specifically, the Choquet integral can dynamically consider the correlation between the parameters of the real-time geological data, rather than simply treating them independently; the dynamic fuzzy measure can flexibly respond to the changing environment under complex geological conditions by adjusting the weights of the parameters through real-time data; the accuracy and applicability of the optimization of the slag removal force, frequency and path are improved through nonlinear fusion, which significantly improves the slag removal efficiency, reduces the wear of the drill rig and optimizes the energy consumption. Compared with the traditional linear weighted method, it has stronger adaptability and robustness.

[0091] The mathematical definition of Choquet integral is applied to the cleaning intensity, cleaning frequency and cleaning path of each layer to generate the optimized value for each layer.

[0092] Through reinforcement learning, the real-time geological data in each layer of optimization value is used as the state space, the combination of slag cleaning force, slag cleaning frequency and slag cleaning path is used as the action space, and the weighted sum of the target of slag cleaning efficiency, drill wear and energy consumption is used as the reward function;

[0093] The reward function expression is:

[0094] ;

[0095] in, represents the cumulative reward value, represents the maximum number of time steps, represents the current time step, represents the discount factor, Indicates that at time step The instant reward you get after performing an action at any moment;

[0096] Specifically, is a A constant between , used to control the importance of future rewards. If is larger, it means that the reinforcement learning algorithm attaches more importance to future rewards; A smaller value means more focus on current rewards. Usually choose Values ​​close to 1 indicate that future rewards are still important, but their impact decreases over time.

[0097] It should also be noted that is at the time step The immediate reward obtained after performing an action at a certain moment. The value of the immediate reward is determined by the feedback from the environment. It will be calculated based on the following factors: Slag removal efficiency: If the slag removal efficiency is high, Larger, indicating good operating results; Drilling rig wear: If the drilling rig is worn out, Smaller, indicating unfavorable operating results; Energy consumption: If the energy consumption is high, Smaller values ​​indicate less energy-efficient operation.

[0098] According to the geological characteristics of each layer and fuzzy reasoning, the optimized slag cleaning intensity, frequency and path of each layer are output to form a layered and segmented slag cleaning strategy.

[0099] According to the geological characteristics of each layer and fuzzy reasoning, the optimized slag cleaning intensity, frequency and path of each layer are output to form a layered and segmented slag cleaning strategy.

[0100] S3. Utilize the multi-stage slag cleaning feedback method to dynamically optimize the slag cleaning path in the layered and segmented slag cleaning strategy.

[0101] Furthermore, the residual rate of slag, slag cleaning path deviation, drilling rig vibration amplitude, energy consumption and slag cleaning efficiency during the slag cleaning process are collected in real time as slag cleaning feedback data. ;

[0102] Utilizing slag removal feedback data A dynamic optimization model is constructed, and the recursive Bayesian estimation is used to adjust the slag removal path. The expression is:

[0103] ;

[0104] in, represents the optimized slag removal path, Represents the predicted value of the current slag removal path, represents the Kalman gain, Represents the mapping matrix between feedback data and slag removal path, For the slag removal path, Indicates a point in time;

[0105] It should be noted that the mapping matrix between the slag removal path and the feedback data is defined as:

[0106] ;

[0107] in, Indicates feedback data Parameters and cleaning paths The influence coefficient between the dimensions;

[0108] It should also be noted that the current slag removal path prediction value The source is the dynamic optimization model of the slag cleaning path. Specifically, the dynamic optimization model combines the historically collected slag cleaning path data and real-time feedback data (such as residual slag rate, slag cleaning path deviation, etc.) to predict the slag cleaning path through recursive Bayesian estimation or Kalman filtering method; for example, the optimized slag cleaning path data of the previous time period can be used as the initial prediction value of the slag cleaning path in the current time period.

[0109] Preferably, the recursive Bayesian estimation method is adopted to dynamically adjust the slag cleaning path by combining the predicted slag cleaning path with real-time feedback data so that it can adapt to the complex dynamic geological environment; at the same time, the Kalman gain is introduced to balance the uncertainty weight between the predicted value and the observed value, and the correction amplitude of the slag cleaning path is flexibly adjusted according to the feedback data, thereby ensuring the accuracy and adaptability of the slag cleaning path, effectively reducing the wear and energy consumption of the drilling rig, and significantly improving the slag cleaning efficiency and process stability.

[0110] In the slag removal path When adjusting the slag removal path, the correction value of the slag removal path is calculated with the goal of minimizing the residual slag rate and the slag removal path deviation. ;

[0111] Specifically, in the slag cleaning path When adjusting the slag cleaning path, first collect the slag cleaning feedback data, including parameters such as the residue residual rate and the slag cleaning path deviation, and define the optimization target based on these data, with minimizing the residue residual rate and the slag cleaning path deviation as the core optimization target; then, express the optimization target as a weighted objective function, in which the weight coefficient is used to balance the importance of the residue residual rate and the slag cleaning path deviation to the slag cleaning path adjustment; then, using the correlation between the feedback data and the slag cleaning path, the residue residual rate and the slag cleaning path deviation are converted into the influence on the slag cleaning path through the mapping matrix, and then the direction and amplitude of the correction value are calculated. On this basis, the gradient descent method is used to iteratively calculate the slag cleaning path correction value. .

[0112] Correction value based on slag removal path and optimized slag removal path , update the slag removal path for the next stage in real time;

[0113] In the process of updating the slag removal path for the next stage, cubic spline interpolation is applied to smooth the slag removal path;

[0114] Specifically, in the process of updating the slag cleaning path of the next stage, discrete point sampling is performed on the optimized slag cleaning path to extract the coordinate data of key slag cleaning path points, and these discrete points are used as control points of cubic spline interpolation to construct the interpolation function of the slag cleaning path; then the cubic spline interpolation formula is used to solve the cubic polynomial coefficients between each slag cleaning path point to ensure the continuity and smoothness of the interpolation curve at each control point, and at the same time, the continuity constraint of the second-order derivative at the boundary of the slag cleaning path segment is used to reduce the sudden change of the slag cleaning path; finally, the generated interpolation function is fitted to the continuous slag cleaning path curve to obtain a smoothed slag cleaning path, which is used to guide the slag cleaning operation of the next stage.

[0115] The smoothed slag cleaning path is divided into several small sections, and the initial length of each slag cleaning path is adaptively adjusted through fuzzy logic reasoning, and the slag cleaning path is optimized and corrected at the same time;

[0116] Specifically, a fuzzy logic rule base is first established for the initial length of each section of the slag cleaning path. The input variables include the formation hardness coefficient, the formation friction coefficient and the fluid characteristics in the hole, and the output variable is the adjustment coefficient of the slag cleaning path length. Then, the membership function is used to fuzzify the input variables and map them into fuzzy values. The adjustment coefficient of each section of the slag cleaning path is obtained through fuzzy reasoning calculation. Finally, the adjusted slag cleaning path length is input into the optimization model, and the parameters of the slag cleaning path are corrected in combination with recursive Bayesian estimation. The optimization results of each section of the slag cleaning path are updated in real time to ensure that the length of the slag cleaning path matches the actual geological conditions.

[0117] After each stage of slag cleaning is completed, the residual rate and the slag cleaning path deviation are calculated in real time, and the slag cleaning path of the next stage is adjusted through fuzzy reasoning and recursive Bayesian estimation. , the expression is:

[0118] ;

[0119] in, is the feedback gain coefficient, The difference between the current stage residue rate and the expected value.

[0120] It should be noted that by introducing recursive Bayesian estimation and fuzzy logic reasoning, the slag removal path optimization no longer relies on a single initial planning, but continuously optimizes the slag removal path through real-time feedback and dynamic adjustment, so that the slag removal efficiency, rig life and energy utilization are comprehensively improved. At the same time, the adaptive adjustment of the length of the segmented slag removal path overcomes the limitations of the fixed slag removal path under complex geological conditions, and further improves the flexibility and adaptability of the slag removal process.

[0121] S4. According to the optimized slag removal path, control the drilling rig to perform slag removal operations.

[0122] Furthermore, the optimized slag removal path is obtained and parsed into control instructions;

[0123] Specifically, based on a multi-parameter analytical algorithm for real-time slag cleaning path planning, the geometric coordinates of the slag cleaning path points, the slag cleaning force and the slag cleaning frequency data are converted into operating instructions executable by the drilling rig controller.

[0124] Calibrate the initial position of the drill, check the equipment status, and load the parsed slag removal path instructions into the drill controller;

[0125] Start the drill to move along the planned slag removal path through the drill controller, dynamically adjust the tool movement speed and angle, and correct the deviation in real time;

[0126] Specifically, first, the initial moving speed and angle of the tool are set according to the optimized slag cleaning path, and the built-in sensor is started to collect the real-time operation status of the drill rig, including the current position, tool offset and drill vibration amplitude; the controller adjusts the tool movement speed through the proportional-integral-differential (PID) algorithm according to the collected offset data to ensure that the drill rig remains stable in the curvature change area of ​​the slag cleaning path; when the sensor detects that there is a deviation between the tool angle and the target value of the slag cleaning path planning, the controller uses the servo motor to drive the tool to adjust the angle to make it consistent with the planned slag cleaning path, and verifies whether the adjustment result meets the expectations through feedback. If there is still a deviation, a secondary correction is performed in real time, and the correction parameters are recorded for subsequent optimization.

[0127] Collect the slag cleaning process data, adjust the slag cleaning path through comparative feedback, and optimize the slag cleaning intensity and frequency;

[0128] Specifically, embedded sensors are used to collect key data in the slag cleaning process in real time, including the amount of residue, drilling rig vibration amplitude, slag cleaning path deviation and slag cleaning efficiency per unit time. These data are analyzed using edge computing, and the preset slag cleaning path and target value are compared to calculate the deviation of the current slag cleaning path execution. According to the analysis results, the recursive feedback algorithm is used to dynamically adjust the slag cleaning force and slag cleaning frequency parameters, and the deviation value is used as the input variable to optimize the real-time execution parameters of the slag cleaning path. At the same time, the tool movement speed and pressure are updated to match the adjusted slag cleaning force and slag cleaning frequency, ensuring that the efficiency of the slag cleaning operation and the consistency of the slag cleaning path are in the optimal state.

[0129] After each section of the slag cleaning path is completed, the drill rig is calibrated to the starting point of the next section of the slag cleaning path, and the slag cleaning force, frequency and path are adjusted to adapt to the new geological conditions. The slag cleaning path smoothing algorithm is used to optimize the connection process.

[0130] S5. Real-time monitoring of the residue removal efficiency during the slag removal operation, and feedback of monitoring parameters to the adaptive algorithm to adjust the layered and segmented slag removal strategy.

[0131] Furthermore, the feedback value of the residue removal efficiency is used as a monitoring parameter;

[0132] Compare the monitored parameters with the expected efficiency values ​​after optimization at each layer and calculate the residuals;

[0133] It should be noted that the expected efficiency value refers to the target value of slag cleaning efficiency generated by reinforcement learning, in which reinforcement learning takes the real-time geological data in each layer of optimization value (such as formation hardness coefficient, friction coefficient, fluid characteristics in the hole and pore geometry characteristics) as the state space, and the combination of slag cleaning force, slag cleaning frequency and slag cleaning path as the action space, and is calculated with the target weighted sum of slag cleaning efficiency, drilling rig wear and energy consumption as the reward function.

[0134] Specifically, the monitoring parameters collected in real time (such as the feedback value of the residue removal efficiency) are matched one by one with the pre-generated expected efficiency values, and the monitoring parameters and the expected efficiency values ​​are aligned in the time dimension using the linear interpolation method to eliminate the deviation caused by the sampling time difference; then, the difference between the matched monitoring parameters and the expected efficiency values ​​is calculated point by point to obtain the residual value, where the feedback value of the monitoring parameter is used for the actual operation performance, the expected efficiency value is used as the target standard, and the residual is used as the core data for quantifying the current operation deviation for subsequent optimization and adjustment of the slag removal path.

[0135] According to the residual, the current slag removal path is adjusted through recursive Bayesian estimation;

[0136] Specifically, the calculated residual value is used as input, and combined with the predicted value of the current slag cleaning path, the adjustment range of the slag cleaning path is determined. By analyzing the credibility of the monitoring parameters and the stability of the historical data, the adjustment weight is dynamically calculated to balance the contribution of the predicted value and the residual to the optimization of the slag cleaning path. Subsequently, according to the weight ratio, the slag cleaning path is updated to make it closer to the actual slag cleaning effect. At the same time, considering the volatility of the feedback data, the update range is dynamically adjusted to avoid excessive adjustment. Throughout the process, the slag cleaning path is gradually optimized through recursive iteration to ensure the accuracy and stability of the slag cleaning path adjustment, and to achieve dynamic matching of the slag cleaning path with the real-time slag cleaning needs.

[0137] The modified slag removal path is optimized using dynamic fuzzy measurement, the feedback value of residue removal efficiency is associated with the slag removal force, slag removal frequency and slag removal path, the weight distribution is recalculated, and a new optimization strategy value is generated;

[0138] Specifically, the corrected slag cleaning path is optimized through dynamic fuzzy measurement. First, a fuzzy rule base is established for the relationship between the slag cleaning path and the feedback value, and the membership function is used to map the residual removal efficiency feedback value to the fuzzy membership function value of the slag cleaning force, slag cleaning frequency and slag cleaning path; then, the weight of each parameter is adjusted through the dynamic fuzzy measurement function to express the nonlinear correlation between the slag cleaning force, slag cleaning frequency and slag cleaning path, while considering the influence of the residual removal efficiency feedback value on these parameters; then, the Choquet integral is combined to fuse the values ​​of each membership function and comprehensively generate the optimized weight of each parameter; finally, the relative priorities of the slag cleaning force, slag cleaning frequency and slag cleaning path are redistributed according to the optimized weights, and a new optimization strategy value is output to guide subsequent slag cleaning operations.

[0139] The updated slag removal path is used as the state input of reinforcement learning, and the residue removal efficiency, equipment wear and energy consumption are used as the reward function to dynamically adjust the slag removal intensity, frequency and path to generate a hierarchical and segmented optimized slag removal strategy.

[0140] The optimized slag removal strategy is loaded into the drilling rig controller to execute a new round of slag removal operations. At the same time, the newly generated residue removal efficiency feedback value is monitored in real time to perform dynamic iterative closed-loop optimization.

[0141] The better one combines reinforcement learning with real-time feedback optimization mechanism, can dynamically adapt to complex changes in geological conditions, effectively improve slag cleaning efficiency, and control equipment wear and energy consumption through multi-objective reward functions, thereby extending equipment life and reducing operating costs. Compared with the existing technology, traditional methods are mostly static slag cleaning path planning or manual intervention adjustment, which is difficult to optimize in real time during the slag cleaning process. The adoption of this method can realize dynamic adjustment of slag cleaning force, frequency and path, and has adaptability and high efficiency, which significantly improves the overall efficiency and reliability of slag cleaning operations, ensures refined and high-quality slag cleaning operations in complex geological environments, and solves the problems of reduced slag cleaning efficiency, excessive equipment wear and increased energy consumption due to imperfect slag cleaning path design in the existing technology.

[0142] This embodiment also provides a computer device, which is suitable for the slag cleaning method of the construction system based on the impact drill rig, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the slag cleaning method of the construction system based on the impact drill rig as proposed in the above embodiment.

[0143] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0144] The present embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the slag cleaning method for a construction system based on an impact drill rig as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage device, a flash memory, a magnetic disk or an optical disk.

[0145] In summary, the present invention realizes dynamic optimization of slag cleaning force, frequency and path through real-time geological data acquisition and application of adaptive algorithms, and significantly improves slag cleaning efficiency and construction quality; by real-time acquisition of geological data and combining fuzzy logic reasoning and Choquet integral to optimize slag cleaning parameters, the reinforcement learning algorithm is used to dynamically adjust the layered and segmented slag cleaning strategy according to complex geological conditions, and the slag cleaning path and parameters are corrected in real time through a multi-stage feedback method to ensure that the slag cleaning process is efficient and accurate, which significantly improves construction efficiency, equipment service life and slag cleaning intelligence level.

[0146] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A slag removal method for a construction system based on an impact drill rig, characterized in that: include, Collect real-time geological data of the drilling area; Based on real-time geological data, an adaptive algorithm is applied to calculate the slag removal intensity, frequency and path of each layer, and generate an optimized layered and segmented slag removal strategy. The specific steps are as follows: Through fuzzy logic, fuzzy reasoning is performed on the formation hardness coefficient, formation friction coefficient, formation structure data, fluid characteristics in the hole and hole geometry characteristics in real-time geological data; In fuzzy reasoning, the membership function is used to map the geological data of each layer to the membership function value and construct fuzzy rules; Dynamic fuzzy measurement and nonlinear Choquet integral are used to optimize the membership function value in fuzzy rules and generate the optimized value of each layer; Through reinforcement learning, the real-time geological data in each layer of optimization value is used as the state space, the combination of slag cleaning force, slag cleaning frequency and slag cleaning path is used as the action space, and the weighted sum of the target of slag cleaning efficiency, drill wear and energy consumption is used as the reward function; According to the geological characteristics of each layer and fuzzy reasoning, the optimized slag removal intensity, frequency and path of each layer are output to form a layered and segmented slag removal strategy; The multi-stage slag cleaning feedback method is used to dynamically optimize the slag cleaning path in the layered and segmented slag cleaning strategy; According to the optimized slag removal path, the drilling rig is controlled to perform slag removal operations; The residue removal efficiency during the slag cleaning operation is monitored in real time, and the monitoring parameters are fed back to the adaptive algorithm to adjust the layered and segmented slag cleaning strategy.

2. The slag removal method of the construction system based on the impact drill rig according to claim 1, characterized in that: The real-time geological data includes formation hardness coefficient , formation friction coefficient , stratigraphic structure data , fluid characteristics in the hole and pore geometry .

3. The slag removal method of the construction system based on the impact drill rig according to claim 2, characterized in that: The dynamic fuzzy measurement and nonlinear Choquet integral are used to optimize the membership function value in the fuzzy rule to generate the optimized value of each layer. The specific steps are as follows: For the membership function value in the fuzzy rule, the dynamic fuzzy measurement function is used to optimize the influence degree and mutual correlation of the target, and the expression is: ； ； in, represents the fuzzy measure function, Represents a collection of real-time geological data factors, An index variable representing real-time geological data, Indicates Real-time value of real-time geological data, Indicates The expected value of real-time geological data, is the square of the standard deviation, is an exponential function, Indicates The square difference between the actual value and the expected value of real-time geological data; Based on Choquet integral, the membership function value and the dynamic fuzzy measurement function are integrated, and the expression is: ； ； in, represents the calculation result of Choquet integral, represents the membership function value, Represents a single factor in a real-time geological data set, Representing fuzzy measure The incremental value of represents the mathematical definition of Choquet integral, represents the total number of slag cleaning related factors, Indicates the sorted The membership function value of real-time geological data, Before The fuzzy measurement value after the real-time geological data is sorted, Before The fuzzy measurement value after the real-time geological data is sorted, Indicates the sorted A collection of real-time geological data factors, Indicates the sorted A collection of real-time geological data factors; The mathematical definition of Choquet integral is applied to the cleaning intensity, cleaning frequency and cleaning path of each layer to generate the optimized value for each layer.

4. The slag removal method of the construction system based on the impact drill rig according to claim 3, characterized in that: The multi-stage slag cleaning feedback method is used to dynamically optimize the slag cleaning path in the layered and segmented slag cleaning strategy. The specific steps are as follows: Real-time collection of the residue rate, slag cleaning path deviation, drilling rig vibration amplitude, energy consumption and slag cleaning efficiency during the slag cleaning process as slag cleaning feedback data ; Utilizing slag removal feedback data A dynamic optimization model is constructed, and the recursive Bayesian estimation is used to adjust the slag removal path. The expression is: ； in, represents the optimized slag removal path, Represents the predicted value of the current slag removal path, represents the Kalman gain, Represents the mapping matrix between feedback data and slag removal path, For the slag removal path, Indicates a point in time; In the slag removal path When adjusting the slag removal path, the correction value of the slag removal path is calculated with the goal of minimizing the residual slag rate and the slag removal path deviation. ; Correction value based on slag removal path and optimized slag removal path , update the slag removal path for the next stage in real time; In the process of updating the slag removal path for the next stage, cubic spline interpolation is applied to smooth the slag removal path; The smoothed slag cleaning path is divided into several small sections, and the initial length of each slag cleaning path is adaptively adjusted through fuzzy logic reasoning, and the slag cleaning path is optimized and corrected at the same time; After each stage of slag removal is completed, the residual rate and the slag removal path deviation are calculated in real time, and the slag removal path for the next stage is adjusted through fuzzy reasoning and recursive Bayesian estimation. , the expression is: ； in, is the feedback gain coefficient, The difference between the current stage residue rate and the expected value.

5. The slag removal method of the construction system based on the impact drill rig according to claim 4, characterized in that: According to the optimized slag removal path, the drilling rig is controlled to perform slag removal operation, and the specific steps are as follows: Obtain the optimized slag removal path and parse it into control instructions; Calibrate the initial position of the drill, check the equipment status, and load the parsed slag removal path instructions into the drill controller; Start the drill to move along the planned slag removal path through the drill controller, dynamically adjust the tool movement speed and angle, and correct the deviation in real time; Collect the slag cleaning process data, adjust the slag cleaning path through comparative feedback, and optimize the slag cleaning intensity and frequency; After each section of the slag cleaning path is completed, the drill rig is calibrated to the starting point of the next section of the slag cleaning path, and the slag cleaning force, frequency and path are adjusted to adapt to the new geological conditions. The slag cleaning path smoothing algorithm is used to optimize the connection process.

6. The slag removal method of the construction system based on the impact drill rig according to claim 5, characterized in that: The specific steps of real-time monitoring of the residue removal efficiency during the slag removal operation are as follows: The sensors are used to collect the residue concentration, flow rate and image data of the slag cleaning area during the slag cleaning operation; The collected residue concentration, flow rate and residue cleaning area image data are used to dynamically calculate the residue concentration change rate and the residue cleaning efficiency through the optical transmission method to obtain the residue cleaning efficiency index; Mark the residue accumulation area based on the slag removal efficiency index; Evaluate the cleaning coverage in the residue accumulation area through image processing algorithms; The slag removal coverage is used to dynamically quantify the real-time efficiency of the slag removal operation process and generate a feedback value of the residue removal efficiency.

7. The slag removal method of the construction system based on the impact drill rig according to claim 6, characterized in that: The monitoring parameters are fed back to the adaptive algorithm to adjust the layered and segmented slag removal strategy. The specific steps are as follows: The feedback value of residue removal efficiency is used as a monitoring parameter; Compare the monitored parameters with the expected efficiency values ​​after optimization at each layer and calculate the residuals; According to the residual, the current slag removal path is adjusted through recursive Bayesian estimation; The modified slag removal path is optimized using dynamic fuzzy measurement, the feedback value of residue removal efficiency is associated with the slag removal force, slag removal frequency and slag removal path, the weight distribution is recalculated, and a new optimization strategy value is generated; The updated slag removal path is used as the state input of reinforcement learning, and the residue removal efficiency, equipment wear and energy consumption are used as the reward function to dynamically adjust the slag removal intensity, frequency and path, and generate an adjusted hierarchical and segmented optimized slag removal strategy. The adjusted slag removal strategy is loaded into the drilling rig controller to execute a new round of slag removal operations. At the same time, the newly generated residue removal efficiency feedback value is monitored in real time as a monitoring parameter to perform dynamic iterative closed-loop optimization.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the slag cleaning method of the construction system based on the impact drill rig are implemented as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the slag cleaning method of the construction system based on the impact drill rig according to any one of claims 1 to 7 are implemented.

Images