Intelligent control method and system for grooving precision of sandy gravel geological underground diaphragm wall

Abstract

The invention relates to the technical field of coal low-carbon mining, and discloses a sandy gravel geological underground diaphragm wall grooving precision intelligent control method and system.The method comprises the steps that a purified surrounding rock density change curve and a gravel enrichment area three-dimensional map are subjected to coal mine stratum fusion treatment, and a shaft surrounding rock stability coefficient is formed; combining the shaft surrounding rock stability coefficient with the real-time working parameters of the drilling machine, and outputting a coal mine stratum dynamic response index; the basic regulation and control parameters are subjected to coal mine construction multi-objective optimization calculation, and an optimal operation parameter combination suitable for a coal mine shaft is obtained; and generating a coal mine construction carbon efficiency index by the real-time carbon emission equivalent and the material carbon emission contribution value through specific weighted calculation of the coal mine. The system comprises a shaft surrounding rock data fusion analysis module, a coal mine grooving self-adaptive regulation and control module and a coal mine construction carbon effect monitoring module. The construction efficiency and green building requirements are both considered, and a complete technical solution is provided for underground diaphragm wall construction under the sandy gravel stratum condition.

Description

Technical Field

[0001] This invention relates to the field of low-carbon coal mining technology, and in particular to an intelligent control method and system for trenching accuracy of underground continuous wall in sand and gravel geology. Background Technology

[0002] Gravel strata are characterized by loose structure, random gravel distribution, and poor cementation, making them prone to problems such as trench wall collapse and verticality deviation during diaphragm wall trenching. Against the backdrop of the coal industry's transition to green and low-carbon practices, underground engineering projects such as mine shaft construction and roadway support place higher demands on construction precision and environmental performance. Traditional trenching techniques lack sufficient precision control under complex geological conditions, easily leading to excessive concrete consumption, energy waste, and increased carbon emissions, contradicting the concept of low-carbon coal mining.

[0003] Existing technologies employ mechanical guidance control systems, using hydraulic servo mechanisms to adjust the attitude of the trenching machine, but lack geological adaptability; tilt sensor-based monitoring systems, which detect verticality through sensors installed on the trenching machine, suffer from data lag; pre-grouting reinforcement technology, which improves stratum stability through grouting, but increases cement consumption and carbon emissions; and manual measurement and correction methods, which rely on periodic total station checks and cannot achieve real-time control. These solutions have the following drawbacks: a conflict between control accuracy and efficiency, requiring multiple work stoppages for testing to ensure accuracy, extending the construction period and increasing energy consumption; poor stratum adaptability, with fixed-parameter control systems struggling to cope with the heterogeneity of gravel strata, leading to repetitive work; high carbon emissions, as grouting and reinforcement increase cement consumption, contradicting low-carbon mining requirements; insufficient intelligence, lacking real-time data fusion and analysis capabilities, and unable to establish a dynamic response relationship between construction parameters and stratum changes; and low energy utilization, with rework and repairs due to insufficient accuracy resulting in energy waste, failing to meet the requirements of green mine construction.

[0004] Current technologies lack real-time data fusion and analysis capabilities, making it impossible to establish a dynamic response relationship between construction parameters and geological changes. Therefore, this invention provides an intelligent control method and system for trenching accuracy of diaphragm walls in sand and gravel geology. Summary of the Invention

[0005] The main objective of this invention is to provide an intelligent control method and system for trenching accuracy of underground continuous walls in sand and gravel geology, in order to solve the problem that existing technologies lack real-time data fusion and analysis capabilities and cannot establish a dynamic response relationship between construction parameters and stratum changes.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A method for intelligent control of trenching accuracy in diaphragm wall construction in gravelly geological conditions, comprising the following steps: The dynamic response index of the coal mine formation is input into a prediction model trained with underground coal mine data to generate a prediction of the deformation trend of the surrounding rock of the coal mine shaft. The predicted deformation trend of the surrounding rock of the shaft is compared and analyzed with the drill string spatial attitude data of the current skew angle and azimuth angle to generate basic control parameters. The basic control parameters are then subjected to multi-objective optimization calculations for coal mine construction to obtain the optimal combination of operating parameters suitable for the coal mine shaft, including the thrust adjustment value and the rotation speed optimization value. The optimal combination of operating parameters is transmitted to the hydraulic control system to form the coal mine shaft control command, realizing precise adjustment of the trenching process.

[0007] As a further improvement of the present invention, the process of obtaining the optimal combination of operating parameters suitable for coal mine shafts includes the following steps: The dynamic response index of the coal mine strata is input into a prediction model trained with underground coal mine data; the time series features of the input dynamic response index are extracted to identify its short-term fluctuation patterns and intensity; the time series features are used by the state inference network inside the prediction model to calculate the most likely deformation displacement and deformation direction of the surrounding rock of the shaft in the future period based on the learned correlation rules, thus generating a prediction of the deformation trend of the surrounding rock of the coal mine shaft. Based on the predicted deformation trend of the surrounding rock in the coal mine shaft, a collaborative deviation analysis is performed with the drill string spatial attitude data of the current skew angle and azimuth angle. The deformation direction and displacement predicted in the surrounding rock deformation trend prediction are compared with the current trenching axis shown in the drill string spatial attitude data to calculate the physical quantity of the trajectory deviation estimate. The trajectory deviation estimate is output as a set of basic control parameters, including the initial value of the thrust correction and the initial value of the rotation speed correction, according to the preset deviation amount-control amount correspondence rule. The basic control parameters are subjected to multi-objective optimization calculations. The multi-objective optimization calculations include three objectives: the trenching accuracy objective determined by the basic control parameters, the energy consumption constraint objective represented by the carbon efficiency index of coal mine construction, and the drilling efficiency objective based on the requirements of coal mine shaft engineering. The multi-objective optimization calculations iteratively optimize among the three objectives to find the balance point that satisfies all constraints and output the optimal combination of operating parameters, including the final thrust adjustment value and rotation speed optimization value.

[0008] As a further improvement of the present invention, the process of outputting a set of basic control parameters includes the following steps: The deformation direction and displacement predicted in the surrounding rock deformation trend prediction are fused with the current trenching axis shown by the drill bit spatial attitude data through collaborative deviation analysis. The deformation trend, which includes the deformation direction and displacement, is projected in three-dimensional space onto a plane with the current trenching axis as the reference, and two independent prediction quantities are decomposed: the estimated value of the deviation angle of the deformation trend relative to the current trenching axis in the horizontal plane, and the estimated value of the dip angle in the vertical profile. The estimated deviation angle and the estimated tilt angle are combined according to their geometric relationship to obtain a trajectory deviation estimate that characterizes the overall degree of deviation. The trajectory deviation prediction value outputs basic control parameters based on the preset deviation amount-control amount correspondence rule.

[0009] As a further improvement of the present invention, a process for obtaining a trajectory deviation estimate characterizing the overall degree of deviation includes the following steps: The spatial baseline of the current trenching axis is used as the geometric composite baseline in three-dimensional space; The deflection angle estimate and the tilt angle estimate are regarded as the two legs of a right triangle. By calculating the length of the hypotenuse of the right triangle, the scalar values ​​of the two angular displacements in different directions are merged into a scalar value. The scalar value is defined as the comprehensive deviation, which represents the overall magnitude of the composite spatial offset composed of deviations in the horizontal and vertical directions. The comprehensive deviation is mapped to a trajectory deviation estimate with clear engineering risk warning significance based on the sensitivity and risk tolerance of different deviation amplitudes in coal mine shaft construction, thereby quantifying the risk of assembly channel path deviation that may be caused by future deformation.

[0010] As a further improvement of the present invention, the process of mapping a trajectory deviation prediction with clear engineering risk warning significance includes the following steps: Based on the coal mine shaft construction specifications and historical data, a risk level scale is pre-constructed. The risk level scale divides the comprehensive deviation value range into a corresponding relationship of different risk levels. Each level range corresponds to the sensitivity definition and risk tolerance limit of different deviations in the project. The overall deviation is located and matched on the established risk level scale and is assigned a discrete risk level index; the risk level index is an ordinal value, the magnitude of which represents the severity of the risk level it falls into. The risk level index, which represents the degree of abstract risk, is converted into a trajectory deviation estimate according to a predefined risk-physical quantity conversion rule.

[0011] As a further improvement to the present invention, the process of defining the risk-physical quantity conversion rule includes the following steps: Based on the design accuracy and trenching process requirements of coal mine shafts, predefine engineering benchmark values; the engineering benchmark value is a constant with the dimension of length, representing the acceptable or controllable benchmark path deviation in the current engineering context. The risk level index is converted into a risk amplification coefficient through the preset rules of the level-coefficient mapping table; there is a positive correlation between the value of the risk level index and the value of the risk amplification coefficient; that is, a low risk level index corresponds to a risk amplification coefficient close to 1, a medium risk level index corresponds to a moderate amplification coefficient greater than 1, and a high risk level index corresponds to a significant amplification coefficient much greater than 1. The final trajectory deviation estimate is generated by combining the established engineering benchmark values ​​with the generated risk amplification coefficient through quantitative synthesis calculation.

[0012] As a further improvement of the present invention, the process of quantitative synthesis calculation includes the following steps: A quantitative synthesis calculation benchmark is established. The calculation benchmark is a physical quantity fusion criterion established based on the principle of consistency of dimensions of coal mine shaft construction control. The final output estimate is a physical quantity with a clear length dimension, and its value needs to be determined by the benchmark quantity and the risk coefficient. The engineering baseline value is multiplied by the risk amplification factor to generate a preliminary uncalibrated estimate. The generated uncalibrated estimate is then processed by dimensional calibration to generate the final trajectory deviation estimate.

[0013] As a further improvement of the present invention, it also includes an acoustic strata detection device and a resistivity sensing device installed at the drill bit to simultaneously collect coal mine shaft surrounding rock density fluctuation data and pebble distribution characteristic data; the shaft surrounding rock density fluctuation data is filtered to obtain a purified surrounding rock density change curve; at the same time, the pebble distribution characteristic data is reconstructed through shaft space to generate a three-dimensional map of pebble enrichment area; the purified surrounding rock density change curve and the three-dimensional map of pebble enrichment area are fused with coal mine strata to form a shaft surrounding rock stability coefficient; the shaft surrounding rock stability coefficient is combined with the real-time working parameters of the drilling rig to output a coal mine strata dynamic response index, reflecting the real-time changes of the sand and pebble strata around the coal mine shaft.

[0014] As a further improvement of the present invention, it also includes the following: during the execution of coal mine shaft control commands, raw energy consumption data is collected by an electrical energy monitoring module and a hydraulic energy efficiency sensor installed on the drilling equipment, while simultaneously recording concrete consumption; the raw energy consumption data is processed by a coal mine carbon emission accounting program to output real-time carbon emission equivalents; the concrete consumption is calculated using the carbon conversion coefficient of building materials to obtain the carbon emission contribution value of the materials; the real-time carbon emission equivalent and the carbon emission contribution value of the materials are weighted using a coal mine-specific method to generate a coal mine construction carbon efficiency index; the coal mine construction carbon efficiency index is compared with the low-carbon standard value of the coal mining industry to form a coal mine construction energy efficiency assessment report, which is fed back to the coal mine trenching adaptive control system to optimize the energy consumption constraints in the calculation.

[0015] To achieve the above objectives, the present invention also provides the following technical solution: A smart control system for trenching accuracy of diaphragm walls in gravelly geological conditions is applied to the aforementioned smart control method for trenching accuracy of diaphragm walls in gravelly geological conditions. The smart control system for trenching accuracy of diaphragm walls in gravelly geological conditions includes: The wellbore surrounding rock data fusion and analysis module is used by the sonic formation detection device and resistivity sensor installed at the drill bit to simultaneously collect coal mine wellbore surrounding rock density fluctuation data and pebble distribution characteristic data. The wellbore surrounding rock density fluctuation data is filtered to obtain a purified surrounding rock density change curve. At the same time, the pebble distribution characteristic data is reconstructed through wellbore space to generate a three-dimensional map of pebble enrichment area. The purified surrounding rock density change curve and the three-dimensional map of pebble enrichment area are fused with coal mine formation data to form the wellbore surrounding rock stability coefficient. The wellbore surrounding rock stability coefficient is combined with the real-time working parameters of the drilling rig to output the coal mine formation dynamic response index, reflecting the real-time changes of the sand and pebble strata around the coal mine wellbore. The adaptive control module for coal mine trenching is used to input dynamic response indicators of coal mine formations into a prediction model trained with underground coal mine data to generate a prediction of the deformation trend of the surrounding rock in the coal mine shaft. The predicted deformation trend is then compared and analyzed with the drill string's spatial attitude data (current yaw and azimuth angles) to generate basic control parameters. These basic control parameters undergo multi-objective optimization calculations in coal mine construction to obtain the optimal combination of operating parameters suitable for the coal mine shaft, including thrust adjustment values ​​and rotation speed optimization values. This optimal combination of operating parameters is transmitted to the hydraulic control system to form coal mine shaft control commands, enabling precise adjustment of the trenching process. The coal mine construction carbon efficiency monitoring module is used during the execution of coal mine shaft control commands. It collects raw energy consumption data through an electrical energy monitoring module and hydraulic energy efficiency sensors installed on the drilling equipment, and records concrete consumption. The raw energy consumption data is processed by a coal mine carbon emission accounting program to output real-time carbon emission equivalents. The concrete consumption is calculated using the carbon conversion coefficient of building materials to obtain the carbon emission contribution value of the materials. The real-time carbon emission equivalent and the carbon emission contribution value of the materials are weighted using a coal mine-specific calculation to generate a coal mine construction carbon efficiency index. The coal mine construction carbon efficiency index is compared with the low-carbon standard value of the coal mining industry to form a coal mine construction energy efficiency assessment report, which is fed back to the coal mine trenching adaptive control system to optimize the energy consumption constraints in the calculation.

[0016] This invention achieves precise perception and adaptive control of complex geological conditions through multi-source data fusion and a dynamic response mechanism. The collaborative operation of acoustic strata detection and resistivity sensing establishes a spatial coupling relationship between surrounding rock stability and pebble distribution, providing a reliable geological basis for the trenching process. Closed-loop control of the predictive model and real-time drill bit attitude effectively suppresses deviation risks, and parameter optimization of the hydraulic system significantly improves the accuracy of the trenching axis. The introduction of energy efficiency monitoring and carbon emission accounting forms a sustainability assessment system for the construction process. Through dynamic comparison of the carbon efficiency index with industry standards, process parameters are further optimized under energy consumption constraints. The entire method ensures trenching quality while also considering construction efficiency and green building requirements, providing a complete technical solution for diaphragm wall construction in sandy and gravelly geological conditions. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the steps of an embodiment of the intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to the present invention. Figure 2 This is a schematic diagram illustrating the steps of an embodiment of the intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology of the present invention, which outputs dynamic response indicators of coal mine strata. Figure 3 This is a schematic diagram illustrating the steps of obtaining the optimal combination of operating parameters suitable for coal mine shafts in an embodiment of the intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to the present invention. Figure 4 This is a schematic diagram illustrating the steps of generating the carbon efficiency index for coal mine construction in an embodiment of the intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to the present invention. Figure 5 This is a schematic diagram of the functional modules of an embodiment of the intelligent control system for trenching accuracy of underground continuous wall in sand and gravel geology of the present invention; Figure 6 This is a schematic diagram of the structure of an embodiment of the electronic device of the present invention; Figure 7 This is a schematic diagram of the structure of one embodiment of the storage medium of the present invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0019] The terms "first," "second," and "third" used in this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified. All directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this invention are only used to explain the relative positional relationships and movements between components in a specific orientation (as shown in the accompanying drawings). If the specific orientation changes, the directional indications also change accordingly. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0020] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0021] like Figure 1 As shown, this embodiment provides an example of an intelligent control method for trenching accuracy of diaphragm walls in sandy and gravelly geological conditions. In this embodiment, the intelligent control method for trenching accuracy of diaphragm walls in sandy and gravelly geological conditions specifically includes the following steps: Step S1: The acoustic strata detection device and resistivity sensor installed at the drill bit simultaneously collect data on the density fluctuation of the surrounding rock in the coal mine shaft and the distribution characteristics of pebbles; the density fluctuation data of the surrounding rock in the shaft is filtered to obtain a purified density change curve; at the same time, the pebble distribution characteristics data are reconstructed through the shaft space to generate a three-dimensional map of the pebble enrichment area; the purified density change curve of the surrounding rock and the three-dimensional map of the pebble enrichment area are fused with the coal mine strata to form the stability coefficient of the surrounding rock in the shaft; the stability coefficient of the surrounding rock in the shaft is combined with the real-time working parameters of the drilling rig to output the dynamic response index of the coal mine strata, reflecting the real-time changes of the sand and pebble strata around the coal mine shaft; Step S2: The dynamic response index of the coal mine formation is input into the prediction model trained with coal mine underground data to generate a prediction of the deformation trend of the surrounding rock of the coal mine shaft. The deformation trend prediction of the surrounding rock of the shaft is compared and analyzed with the drill bit spatial attitude data of the current skew angle and azimuth angle to generate basic control parameters. The basic control parameters are optimized through multi-objective optimization calculations for coal mine construction to obtain the optimal combination of operating parameters suitable for the coal mine shaft, including the thrust adjustment value and the rotation speed optimization value. The optimal combination of operating parameters is transmitted to the hydraulic control system to form the coal mine shaft control command, so as to realize the precise adjustment of the trenching process. Step S3: During the execution of coal mine shaft control commands, raw energy consumption data is collected through the power monitoring module and hydraulic energy efficiency sensor installed on the drilling equipment, and the amount of concrete consumed is recorded simultaneously. The raw energy consumption data is processed by the coal mine carbon emission accounting program to output real-time carbon emission equivalents. The amount of concrete consumed is calculated using the carbon conversion coefficient of building materials to obtain the carbon emission contribution value of the materials. The real-time carbon emission equivalent and the carbon emission contribution value of the materials are weighted using a coal mine-specific calculation to generate the coal mine construction carbon efficiency index. The coal mine construction carbon efficiency index is compared with the low-carbon standard value of the coal mining industry to form a coal mine construction energy efficiency assessment report, which is fed back to the coal mine trenching adaptive control system to optimize the energy consumption constraints in the calculation.

[0022] Preferably, the intelligent control method for trenching accuracy of diaphragm walls in gravelly geological formations in this embodiment achieves precise perception and adaptive control of complex geological conditions through multi-source data fusion and a dynamic response mechanism. The collaborative operation of acoustic strata detection and resistivity sensing establishes a spatial coupling relationship between surrounding rock stability and gravel distribution, providing a reliable geological basis for the trenching process. Closed-loop control of the predictive model and real-time drill bit attitude effectively suppresses the risk of deviation, and parameter optimization of the hydraulic system significantly improves the accuracy of the trenching axis. The introduction of energy efficiency monitoring and carbon emission accounting forms a sustainability assessment system for the construction process. Through dynamic comparison of the carbon efficiency index with industry standards, the process parameters under energy consumption constraints are further optimized. The entire method ensures trenching quality while also considering construction efficiency and green building requirements, providing a complete technical solution for diaphragm wall construction in gravelly geological conditions.

[0023] Furthermore, such as Figure 2 As shown, the process of outputting the dynamic response index of the coal mine strata in step S1 specifically includes the following steps: Step S11: Map the surrounding rock density change curve to the corresponding depth position of the three-dimensional map of the pebble enrichment area, and dynamically correct the density fluctuation value of the surrounding rock density change curve along the depth direction of the coal mine shaft according to the degree of pebble enrichment. Step S12: The corrected density fluctuation value and pebble distribution characteristic data are calculated using a stability integral function. The fluctuation value and pebble influence at each depth point are weighted and integrated to generate a stable value sequence along the wellbore depth, which ultimately forms the wellbore surrounding rock stability coefficient. The wellbore surrounding rock stability coefficient comprehensively expresses the surrounding rock stability state under the combined action of density fluctuation and pebble distribution. The corrected density fluctuation value and pebble distribution characteristics are calculated using a stability integral function, a mathematical processing procedure designed to integrate multi-source stratigraphic features. First, a composite stability unit is defined for each depth point, composed of the corrected density fluctuation value and the corresponding spatial distribution characteristics of pebbles, such as pebble enrichment intensity and geometric morphology. Then, the stability integral function performs a dual-weighting factor integration operation on each composite stability unit: one weighting factor allocates the contribution of the density fluctuation value to the overall stiffness of the surrounding rock, while the other weighting factor allocates the strengthening or weakening effect of the interlocking structure within the surrounding rock based on the pebble distribution characteristics. The two weighting factors are coupled at each depth point to generate a transient stability value characterizing the overall stability of that point. Finally, all transient stability values ​​are sequentially concatenated and smoothed along the wellbore depth direction to form a complete stability value sequence. This stability value sequence is the wellbore surrounding rock stability coefficient, quantifying the continuous change in the surrounding rock stability state determined by the rock mass density and pebble distribution along the wellbore depth direction. The procedure for calculating the stability integral function: Input: For a specific depth point in the wellbore Its input data is defined as: The density fluctuation value after correction at this point; : The spatial distribution feature set of pebbles corresponding to this point (including enrichment intensity and geometric shape); deal with: Calculate density stiffness weight : rule: The value is from It is uniquely determined by the "density-stiffness mapping table"; the core rule of this mapping table is: The higher the value, the better. The value assigned to it increases accordingly, reflecting its increased contribution to the stiffness of the surrounding rock; Calculate the weight of the pebble structure : rule: The value is from It is uniquely determined through the "pebble structure effect mapping table"; the core rule of this mapping table is: firstly, according to... The enrichment intensity and geometric morphology are used to determine whether the overall effect is "enhancing" or "weakening". If it is "enhancing", then... It is assigned a positive value; if it is "weakened", then It is assigned a negative value. The magnitude of its absolute value is determined by the degree of strengthening or weakening.

[0024] Perform coupling operations to generate transient stable values. : Rule: This depth point transient stability value The two weighting factors mentioned above and Through stability coupling function The calculation yields the result. Its standard operational form is:

[0025] Among them, the function One specific implementation rule is to perform weighted product operations, that is:

[0026] In this rule, the baseline stability constant is a pre-defined positive constant used to convert the density contribution into a basic stability value in the absence of pebble structure effects. The strengthening effect of pebble structures (…) (Positive) will increase Weakening effect ( If it is negative, it will decrease. ; Output: A scalar value That is, the depth point The transient stability value; Final sequence formation: For the entire depth profile of the wellbore, from the starting point to the ending point, the above procedure is repeated for each depth point; all calculated... Arrange them according to their corresponding depth order to generate the final output—the wellbore surrounding rock stability coefficient sequence. ; Step S13: Using the stability coefficient of the surrounding rock of the shaft as input through dynamic response mapping, perform real-time correlation analysis with the real-time working parameters of the drilling rig; calculate a comprehensive quantitative index, namely the dynamic response index of the coal mine formation, based on the changing trend of the stability coefficient of the surrounding rock of the shaft and the current value of the drilling rig parameters; the dynamic response index of the coal mine formation reflects the real-time response of the sand and gravel formation around the current coal mine shaft to the drilling rig operation.

[0027] Preferably, in this embodiment, the density variation curve of the surrounding rock is mapped to the corresponding depth position of the three-dimensional map of the gravel enrichment area. The density fluctuation value is corrected by the degree of gravel enrichment, which can enhance the spatial matching accuracy between the density data and the actual formation structure. After the corrected density fluctuation value and the gravel distribution characteristics are weighted by the stability integral function, the stability state of the surrounding rock at different depths affected by gravel can be quantified, forming a continuously distributed sequence of wellbore surrounding rock stability coefficients. This coefficient is analyzed by dynamic response mapping and correlation with real-time drilling rig parameters. The resulting coal mine formation dynamic response index can characterize the mechanical feedback intensity of sand and gravel formations to drilling operations in real time, providing a quantitative basis for adaptive control of drilling rig parameters, thereby improving the response capability and stability control level of the wellbore construction process to complex formation changes.

[0028] Furthermore, the process of calculating a comprehensive quantitative index in step S13 specifically includes the following steps: Step S131: The instantaneous rate of change and direction of change of the wellbore surrounding rock stability coefficient sequence are converted into a quantified trend vector; at the same time, the current values ​​of drilling rig parameters, including thrust and rotation speed, are normalized into a machine state vector. Step S132: The trend vector and the machine state vector are dynamically coupled and calculated. Based on the deterioration or improvement trend of the surrounding rock stability indicated by the trend vector, the current machine state vector is evaluated in real time to exacerbate or inhibit the trend. Step S133: Through the preset response intensity mapping relationship, the intensity of the interaction that aggravates or inhibits the effect is converted into a scalar value; the scalar value is a dynamic response index of the coal mine strata, reflecting the real-time intensity and nature of the interaction between the current drilling operation and the dynamically changing sand and gravel strata.

[0029] Preferably, in this embodiment, the instantaneous rate and direction of change of the surrounding rock stability coefficient sequence are quantified into a trend vector, which can accurately capture the dynamic evolution characteristics of the formation. The drilling rig thrust and rotation speed are normalized to form a machine state vector, realizing multi-parameter collaborative characterization. By analyzing the interaction between the trend vector and the machine state vector through dynamic coupling operations, the enhancement or weakening effect of drilling rig operation on the evolution trend of surrounding rock stability can be determined in real time. Based on the preset response intensity mapping relationship, the degree of interaction is transformed into a scalar index, ultimately forming a quantitative criterion that can characterize the real-time interaction intensity of the drilling rig-formation system, providing data support for optimizing drilling parameters.

[0030] Furthermore, the process of dynamically coupling the trend vector and the machine state vector in step S132 specifically includes the following steps: Step S1321: Convert the velocity intensity information in the trend vector into a field strength parameter to define the strength of the coupling field force; at the same time, convert the directionality information in the trend vector into a field direction parameter to define the properties of the coupling field; using the field strength parameter and the field direction parameter, construct a dynamic coupling field through a specific rule called the field generation function. Step S1322: In the dynamic coupling field, the machine state vector interacts with the current dynamic coupling field to generate an intervention effect vector. It is determined whether the propulsion and rotational velocity components in the machine state vector constitute a positive inhibition or a negative amplification relationship with the trend representing the deterioration or improvement of stability in the dynamic coupling field. For example, in a dynamic coupling field where stability tends to deteriorate, a high-value propulsion component will be judged as a negative amplification, thus generating a negative component in the intervention effect vector; conversely, a moderately optimized rotational velocity component may be judged as a positive inhibition, thus generating a positive component. Step S1323: The obtained intervention effect vector is aggregated through a preset response intensity mapping relationship to synthesize the effect intensity of all components in the intervention effect vector and obtain the magnitude of the intervention effect vector in the mapping space. The magnitude is a scalar value, which is defined as the dynamic response index of coal mine strata.

[0031] Preferably, this embodiment employs a technique for dynamically coupling the trend vector and the machine state vector. Through a field generation function, the rate intensity and direction information of the trend vector are transformed into a dynamic coupling field with specific intensity and properties. The machine state vector generates an intervention effect vector within this field, whose components are assigned positive or negative values ​​based on their interaction with the stability trend. The intervention effect vector is aggregated into a scalar-form coal mine formation dynamic response index through a response intensity mapping relationship. This achieves a quantitative characterization of the interaction between the machine's operating state and the formation's dynamic characteristics, providing a calculable basis for stability assessment.

[0032] Furthermore, such as Figure 4 As shown, step S2, which involves obtaining the optimal combination of operating parameters suitable for coal mine shafts, specifically includes the following steps: Step S21: The dynamic response index of the coal mine strata is input into a prediction model trained with underground coal mine data; the time series features of the input dynamic response index are extracted to identify its short-term fluctuation patterns and intensity; the time series features are used by the state inference network inside the prediction model to calculate the most likely deformation displacement and deformation direction of the surrounding rock of the shaft in the future period based on the learned correlation rules, thus generating a prediction of the deformation trend of the surrounding rock of the coal mine shaft. The construction process of the prediction model is as follows: A coal mine underground time-series training library was constructed by collecting two sets of key data in the underground coal mine environment over a long period of time and synchronously. One set is the historical time-series data of the dynamic response indicators of the coal mine strata, and the other set is the historical time-series data of the actual deformation of the surrounding rock of the shaft recorded by a high-precision inclinometer. The two sets of data aligned on the time axis together constitute a coal mine underground time-series training library.

[0033] A formation behavior memory kernel is formed by inputting a constructed underground coal mine time-series training library into a parameterized network framework with self-learning capabilities. First, deep pattern mining is performed on the dynamic response index sequences in the underground coal mine time-series training library to identify the hidden and complex correspondences between various fluctuation patterns and subsequent actual deformation of the surrounding rock. The identified correspondences are then abstracted and solidified into a series of association weights and trigger thresholds. The set of weights and thresholds ultimately forms a stable formation behavior memory kernel. The formation behavior memory kernel encapsulates the causal laws between formation response and surrounding rock deformation under specific geological conditions in underground coal mines. The generated state extrapolation network, consisting of a formed formation behavior memory kernel, is configured into a predictive computation structure. It possesses the capability to receive the current dynamic response index sequence and invoke the memory kernel for forward computation. This predictive computation structure, equipped with the formation behavior memory kernel, is defined as the state extrapolation network. It is the final, completed model core that can be used for practical prediction. Step S22: Based on the obtained deformation trend prediction of the surrounding rock in the coal mine shaft, perform a collaborative deviation analysis with the drill string spatial attitude data of the current skew angle and azimuth angle; compare the deformation direction and displacement predicted in the surrounding rock deformation trend prediction with the current trenching axis shown in the drill string spatial attitude data to calculate a physical quantity called trajectory deviation prediction; the trajectory deviation prediction outputs a set of basic control parameters, including the initial value of thrust correction and the initial value of rotation speed correction, according to the preset deviation amount-control amount correspondence rule; Step S23: Perform multi-objective optimization calculations on the basic control parameters; the multi-objective optimization calculations include three objectives: the trenching accuracy objective determined by the basic control parameters, the energy consumption constraint objective represented by the carbon efficiency index of coal mine construction, and the drilling efficiency objective based on the requirements of coal mine shaft engineering; the multi-objective optimization calculations iteratively optimize among the three objectives to find the balance point that satisfies all constraints, and output the optimal combination of operating parameters, including the final thrust adjustment value and rotation speed optimization value.

[0034] Preferably, in this embodiment, dynamic response indicators are input into the prediction model for time-series feature extraction and state extrapolation, which can accurately predict the deformation displacement and direction of the surrounding rock, providing forward-looking data support for wellbore stability control. Through collaborative deviation analysis of the surrounding rock deformation trend and the drill string's spatial attitude, trajectory deviation estimates are generated and basic control parameters are derived, achieving dynamic matching between the drilling trajectory and geological changes. Based on a multi-objective optimization algorithm, trenching accuracy, carbon efficiency index, and drilling efficiency are collaboratively optimized, ultimately outputting an optimized combination of thrust and rotation speed. While ensuring the accuracy of the wellbore axis, this significantly improves energy utilization efficiency and construction progress, forming an intelligent drilling control closed loop with adaptive characteristics.

[0035] Furthermore, the process of outputting a set of basic control parameters in step S22 specifically includes the following steps: Step S221: The deformation direction and displacement predicted in the surrounding rock deformation trend prediction are fused with the current trenching axis shown by the drill bit spatial attitude data through collaborative deviation analysis; the deformation trend containing the deformation direction and displacement is projected in three-dimensional space onto a plane with the current trenching axis as the reference, and two independent prediction quantities are decomposed: the predicted angle of the deformation trend relative to the current trenching axis in the horizontal plane, and the predicted angle of inclination in the vertical profile; the two prediction values ​​are jointly encapsulated into a composite data volume called spatial difference vector; Step S222: Combine the deflection angle prediction and the tilt angle prediction according to their geometric relationship to obtain a single value that represents the overall deviation, namely the trajectory deviation prediction, which quantifies the risk of assembly groove path deviation that may be caused by future deformation. Step S223: The trajectory deviation prediction value is output as a basic control parameter according to the preset deviation-control value correspondence rule. The deviation-control value correspondence rule is a dual-channel control mechanism: In the first channel, the trajectory deviation prediction value is directly converted into the initial value of the propulsion correction according to the linear correction rule. Its core principle is that when the deviation prediction value increases, the initial value of the propulsion correction is adjusted downward accordingly. In the second channel, the same trajectory deviation prediction value is converted into the initial value of the rotation speed correction according to a set of nonlinear response rules. Its core principle is to determine whether the rotation speed is slightly increased or significantly decreased based on whether the deviation prediction value exceeds a specific critical point.

[0036] The first channel: the process of generating the initial value of thrust correction, establishing a deterministic mapping from the trajectory deviation estimate to the initial value of thrust correction; its core is a benchmark of pressure gradient scale; 1. Establish a pressure gradient scale: First, predefine a pressure gradient scale; this scale is a numerical correspondence, specifying the ideal thrust level corresponding to each trajectory deviation from the predicted value within a set maximum allowable deviation range from zero. The ideal thrust level is expressed as a percentage of a baseline thrust. 2. Perform linear mapping query: When a specific trajectory deviates from the predicted input, the system queries this pressure gradient scale; the design of this scale follows a core principle: as the deviation from the predicted value increases, the corresponding percentage of propulsion decreases linearly; 3. Calculate the initial value of thrust correction: The system multiplies the percentage obtained from the query with the benchmark thrust set by the current drilling rig system; the result is the initial value of thrust correction. Therefore, the greater the deviation from the expected value, the smaller the percentage obtained through the scale query, and the lower the final calculated initial value of thrust correction, thus achieving the purpose of downward adjustment. The second channel: the process of generating the initial value of rotational speed correction, aims to establish a nonlinear mapping from the trajectory deviation prediction to the initial value of rotational speed correction; its core is a decision mechanism based on rotational speed mode switching; 1. Set the speed response critical point: First, preset a key speed response critical point; this critical point is a specific trajectory deviation estimate value, dividing the entire deviation range into two different intervals: a low deviation zone and a high deviation zone. 2. Low Deviation Zone Mode - Slag Removal Optimization: When the input trajectory deviation is lower than or equal to the critical point of rotational speed response, the system enters the low deviation zone mode. In this mode, the system will add a fixed, pre-set speed increment to the baseline rotational speed set by the drilling rig system according to a small increase rule. This aims to slightly increase the rotational speed to enhance the slag removal capability of the drill bit and optimize construction efficiency using relatively stable working conditions. 3. High Deviation Zone Mode - Execution Risk Avoidance: When the input trajectory deviates from the predicted value by more than the speed response critical point, the system immediately switches to the high deviation zone mode. In this mode, based on a significant reduction rule, the baseline rotational speed is multiplied by a fixed discount factor less than 1 (e.g., 70%) to obtain a significantly reduced speed value; this aims to rapidly reduce the rotational speed to decrease the drill string torque load and effectively avoid the risk of stuck drill in the event of significant formation deformation. Through the above process, the first channel uses the pressure gradient scale to achieve linear reduction of propulsion; the second channel uses the speed response critical point to achieve nonlinear switching response of rotational speed between different risk areas; the two channels process the same trajectory deviation prediction in parallel, and finally output a complete set of basic control parameters in a coordinated manner.

[0037] Preferably, in this embodiment, the process of outputting basic control parameters involves collaborative analysis of surrounding rock deformation trends and drill bit spatial attitude data. The deformation trend is projected onto the current trenching axis plane in three-dimensional space, decomposed into a deviation angle prediction and an inclination angle prediction, and encapsulated as a spatial difference vector. Subsequently, the deviation from the predicted trajectory of these two parameters is synthesized to quantify the overall deviation risk of the trenching path. This prediction is converted into initial values ​​for thrust correction and rotational speed correction based on a dual-channel control mechanism: the initial thrust correction follows a linear correction rule, decreasing accordingly as the deviation from the predicted value increases; the initial rotational speed correction uses a nonlinear response rule, slightly increasing or significantly decreasing based on whether the deviation from the predicted value exceeds a critical point. The overall technical effect is to achieve precise quantification and dynamic control of the trenching axis deviation risk. Through a correction mechanism combining linear and nonlinear methods, it suppresses trajectory deviation while maintaining equipment operational stability, improving trenching accuracy and control efficiency.

[0038] Furthermore, the process of obtaining a single numerical value representing the overall degree of deviation in step S222 specifically includes the following steps: Step S2221: Use the spatial reference line of the current trenching axis as the geometric synthesis reference in three-dimensional space; Step S2222: Treat the deflection angle estimate and the tilt angle estimate as the two legs of a right triangle, and merge the angular displacement scalars in two different directions into a scalar value by calculating the length of the hypotenuse of the right triangle; the scalar value is defined as the comprehensive deviation, which represents the overall magnitude of the composite spatial offset composed of deviations in the horizontal and vertical directions. Step S2223: The comprehensive deviation is mapped to a trajectory deviation estimate with clear engineering risk warning significance based on the sensitivity and risk tolerance of different deviation amplitudes in coal mine shaft construction, thereby quantifying the risk of assembly channel path deviation that may be caused by future deformation.

[0039] Preferably, in this embodiment, the process of combining the deflection angle estimate and the tilt angle estimate into a single value is achieved by treating the two estimates as the two legs of a right triangle and calculating the length of the hypotenuse to obtain the comprehensive deviation. This scalar value integrates angular displacement information in both the horizontal and vertical directions, characterizing the overall magnitude of the spatial offset. Subsequently, based on the sensitivity and risk tolerance of coal mine shaft construction to deviations, the comprehensive deviation is mapped to a trajectory deviation estimate with engineering risk warning significance.

[0040] Furthermore, step S2223, which maps a trajectory deviation from the estimated value to a clearly defined engineering risk warning, specifically includes the following steps: Step S22231: Based on the coal mine shaft construction specifications and historical data, a risk level scale is pre-constructed. The risk level scale divides the comprehensive deviation value range into a corresponding relationship of different risk levels, such as a slight deviation zone, a moderate warning zone, and a severe intervention zone. Each level range corresponds to the sensitivity definition and risk tolerance limit of different deviation magnitudes in engineering. Step S22232: The overall deviation is located and matched on the established risk level scale and assigned a discrete risk level index; the risk level index is an ordinal value, the magnitude of which represents the severity of the risk level it falls into; for example, when the overall deviation falls into the "slight deviation zone", it is assigned a low risk level index; when it falls into the "heavy intervention zone", it is assigned a high risk level index. Step S22233: Convert the risk level index, which represents the degree of abstract risk, into a trajectory deviation estimate according to a predefined risk-physical quantity conversion rule.

[0041] Preferably, the mapping process in this embodiment establishes a correspondence between the comprehensive deviation and the engineering risk level through a risk level scale, realizing the conversion from continuous numerical values ​​to discrete risk indices. Subsequently, based on the risk-physical quantity conversion rule, the abstract risk index is transformed into a specific trajectory deviation estimate. This achieves a systematic conversion from three-dimensional spatial deviation information to quantitative evaluation of engineering risks. Through pre-established grading standards, the comprehensive deviation obtained from geometric calculations is combined with engineering practice experience to form a risk assessment result with clear operational guidance. The final output trajectory deviation estimate reflects both the geometric characteristics of spatial location deviation and includes professional judgment on the engineering risk level, providing a comprehensive evaluation basis for construction decisions that takes into account both theoretical calculations and engineering practice.

[0042] Furthermore, the process of defining the risk-physical quantity conversion rule in step S22233 specifically includes the following steps: Step S222331: Based on the design accuracy and trenching process requirements of the coal mine shaft, predefine the engineering benchmark value; the engineering benchmark value is a constant with the dimension of length, representing the acceptable or controllable benchmark path deviation in the current engineering context. Step S222332: The risk level index is converted into a risk amplification coefficient through the preset rules of the level-coefficient mapping table; there is a positive correlation between the value of the risk level index and the value of the risk amplification coefficient; that is, a low risk level index corresponds to a risk amplification coefficient close to 1, a medium risk level index corresponds to a moderate amplification coefficient greater than 1, and a high risk level index corresponds to a significant amplification coefficient much greater than 1. Step S222333: Based on the established engineering benchmark values ​​and the generated risk amplification coefficient, the final trajectory deviation estimate is generated through quantitative synthesis calculation.

[0043] Preferably, the risk-physical quantity conversion rule establishment process in this embodiment defines the benchmark scale of path deviation through engineering benchmark values, and then combines it with the amplification coefficient corresponding to the risk level index for quantitative synthesis, ultimately generating the trajectory deviation estimate. This achieves a precise mapping from abstract risk assessment to specific engineering physical quantities. The engineering benchmark values ​​provide a benchmark reference that meets the requirements of construction accuracy, while the risk amplification coefficient reflects the amplification effect of different risk levels on deviation. The trajectory deviation estimate formed by combining the two retains the geometric characteristics of the original deviation data while incorporating professional considerations for engineering risk judgment, providing a quantitative basis for trenching trajectory control that is both theoretically rigorous and engineering-applicable. This conversion mechanism ensures that the risk assessment results can be directly applied to construction decisions and deviation control operations.

[0044] Furthermore, the process of quantization synthesis calculation in step S222333 specifically includes the following steps: Step S2223331: Determine the quantitative synthesis calculation benchmark. The calculation benchmark is a physical quantity fusion criterion established based on the principle of consistency of the dimensions of coal mine shaft construction control. The final output estimate is a physical quantity with a clear length dimension, and its value needs to be determined by the benchmark quantity and the risk coefficient. Step S2223332: Multiply the engineering baseline value with the risk amplification factor to generate a preliminary uncalibrated estimate; Step S2223333: The generated uncalibrated estimate is processed by engineering dimension calibration to generate the final trajectory deviation estimate.

[0045] Preferably, the quantitative synthesis calculation process in this embodiment ensures the consistency of physical dimensions by establishing a computational benchmark, uses multiplication to achieve the initial fusion of the benchmark quantity and the risk coefficient, and then ensures the engineering applicability of the output value through calibration. This transforms the abstract risk assessment into a trajectory deviation prediction value with clear physical meaning. The establishment of the computational benchmark ensures that the output results are consistent with engineering control requirements in terms of dimensions; multiplication allows for a reasonable amplification of the benchmark deviation by the risk level; and calibration further optimizes the accuracy and engineering practicality of the prediction value. Through this series of calculation steps, the final generated trajectory deviation prediction value not only reflects the quantitative relationship between the risk level and the deviation but also meets the accuracy requirements of practical engineering applications, providing a reliable basis for the calculation of control parameters.

[0046] Furthermore, such as Figure 4 As shown, the process of generating the coal mine construction carbon efficiency index in step S3 specifically includes the following steps: Step S31: The electricity sequence data is processed by the coal mine power grid carbon intensity factor to generate the electricity carbon emission component; the coal mine power grid carbon intensity factor is a dynamic parameter pre-set based on the energy structure of the power grid in the coal mine area. The processing involves multiplying the electricity consumption by the factor to convert the physical electricity consumption into equivalent carbon emissions. Meanwhile, the hydraulic oil consumption sequence data is processed by the fuel carbon emission coefficient to generate the hydraulic carbon emission component. This coefficient is a constant predetermined based on the thermochemical characteristics of hydraulic oil and the complete combustion model. The processing involves multiplying the hydraulic oil consumption by this coefficient to convert the fuel consumption into an equivalent carbon emission. Subsequently, the carbon emission components from electricity and hydraulic systems are superimposed through carbon emission stream aggregation calculation. This calculation accumulates the values ​​of the two components over a unified time step, forming a real-time carbon emission equivalent data stream that continuously changes with the construction progress. Step S32: The amount of concrete consumed is processed by the carbon conversion coefficient of building materials to generate the carbon emission contribution value of the materials. The carbon conversion coefficient of building materials is a constant predetermined based on the carbon emission inventory analysis of the entire process of concrete from raw material production to transportation. The processing method is to multiply the total amount of concrete consumed by the coefficient to convert the amount of materials used into a corresponding one-time cumulative carbon emission contribution value.

[0047] Preferably, the process of generating the carbon efficiency index for coal mine construction in this embodiment converts electricity consumption and hydraulic oil consumption into carbon emission components and aggregates them, while converting concrete consumption into a material carbon emission contribution value. This achieves a comprehensive quantification of carbon emissions generated by energy consumption and material use during construction. A precise mapping relationship from construction operations to carbon emissions is established. Electricity and hydraulic oil consumption are converted into time-series carbon emission components through corresponding carbon conversion factors, and their aggregation forms a real-time carbon emission data stream reflecting dynamic energy consumption during construction. Concrete consumption is converted into a cumulative carbon emission contribution value through a material carbon conversion coefficient, characterizing the carbon footprint of material use. These calculations together construct a complete carbon emission accounting system, providing an accurate data foundation for carbon efficiency assessment of the construction process, enabling quantitative monitoring of the environmental impact of energy consumption and material use, and supporting subsequent energy efficiency optimization and low-carbon control decisions.

[0048] like Figure 5As shown, this embodiment also provides an embodiment of an intelligent control system for trenching accuracy of diaphragm walls in gravel geology. In this embodiment, the intelligent control system for trenching accuracy of diaphragm walls in gravel geology is applied to the intelligent control method for trenching accuracy of diaphragm walls in gravel geology as described in the above embodiment. The intelligent control system for trenching accuracy of diaphragm walls in gravel geology includes a wellbore surrounding rock data fusion analysis module 1, a coal mine trenching adaptive control module 2, and a coal mine construction carbon efficiency monitoring module 3, which are connected in sequence.

[0049] The wellbore surrounding rock data fusion analysis module 1 is used by the sonic formation detection device and resistivity sensor installed at the drill bit to simultaneously collect coal mine wellbore surrounding rock density fluctuation data and pebble distribution characteristic data. The wellbore surrounding rock density fluctuation data is filtered to obtain a purified surrounding rock density change curve. Simultaneously, the pebble distribution characteristic data is used to generate a three-dimensional map of pebble-rich areas through wellbore spatial reconstruction. The purified surrounding rock density change curve and the three-dimensional map of pebble-rich areas are then fused with the coal mine formation to form a wellbore surrounding rock stability coefficient. This stability coefficient is combined with the drilling rig's real-time operating parameters to output a coal mine formation dynamic response index, reflecting the real-time changes in the sand and pebble strata surrounding the coal mine wellbore. The coal mine trenching adaptive control module 2 is used to input the coal mine formation dynamic response index into a prediction model trained with coal mine underground data to generate a coal mine wellbore surrounding rock deformation trend prediction. The wellbore surrounding rock deformation trend prediction is compared and analyzed with the current drill bit spatial attitude data for skew angle and azimuth angle to generate basic control parameters. The basic control parameters are optimized through multi-objective optimization calculations for coal mine construction to obtain the optimal combination of operating parameters suitable for coal mine shafts, including the adjustment value of propulsion force and the optimization value of rotation speed. The optimal combination of operating parameters is transmitted to the hydraulic control system to form coal mine shaft control commands, realizing precise adjustment of the trenching process. The coal mine construction carbon efficiency monitoring module 3 is used to collect raw energy consumption data through the power monitoring module and hydraulic energy efficiency sensor installed on the drilling equipment during the execution of coal mine shaft control commands, and simultaneously records the amount of concrete consumed. The raw energy consumption data is processed by the coal mine carbon emission accounting program to output the real-time carbon emission equivalent. The amount of concrete consumed is calculated through the carbon conversion coefficient of building materials to obtain the carbon emission contribution value of the materials. The real-time carbon emission equivalent and the carbon emission contribution value of the materials are weighted and calculated using coal mine-specific methods to generate the coal mine construction carbon efficiency index. The coal mine construction carbon efficiency index is compared with the low-carbon standard value of the coal mining industry to form a coal mine construction energy efficiency assessment report, which is fed back to the coal mine trenching adaptive control to optimize the energy consumption constraints in the calculation.

[0050] Preferably, this embodiment constructs a complete closed-loop control system of perception-decision-execution-evaluation. Accurate perception of the surrounding rock condition is achieved through the fusion analysis of multi-source geological data. An adaptive control mechanism is formed based on predictive models and multi-objective optimization algorithms. An energy efficiency evaluation feedback loop is established in conjunction with a carbon efficiency monitoring module. The collaborative work of each module enables the system to maintain trenching accuracy in complex sand and gravel strata, while simultaneously considering construction efficiency and carbon emission control, ultimately achieving safe, precise, and green downhole continuous wall construction.

[0051] like Figure 6 As shown, this embodiment provides an embodiment of an electronic device 4, which includes a processor 41 and a memory 42 coupled to the processor 41.

[0052] The memory 42 stores program instructions for implementing the intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to any of the above embodiments.

[0053] The processor 41 is used to execute program instructions stored in the memory 42 to perform intelligent control of trenching accuracy for underground continuous walls in sand and gravel geology.

[0054] The processor 41 can also be referred to as a CPU (Central Processing Unit). The processor 41 may be an integrated circuit chip with signal processing capabilities. The processor 41 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor can be a microprocessor or any conventional processor.

[0055] Furthermore, Figure 7 This is a schematic diagram of the structure of a storage medium according to an embodiment of this application. The storage medium 5 of this embodiment stores program instructions 51 capable of implementing all the methods described above. These program instructions 51 can be stored in the storage medium in the form of a software product, including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks, or terminal devices such as computers, servers, mobile phones, and tablets.

[0056] In the several embodiments provided by this invention, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0057] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated units described above can be implemented in hardware or as software functional units. The above are merely embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

[0058] The specific embodiments of the invention have been described in detail above, but these are merely examples, and the invention is not limited to the specific embodiments described above. For those skilled in the art, any equivalent modifications or substitutions to the invention are also within the scope of this invention. Therefore, all equivalent transformations, modifications, and improvements made without departing from the spirit and principles of this invention should be included within the scope of this invention.

Claims

1. A method for intelligent control of trenching accuracy in diaphragm wall construction in gravel and pebble geology, characterized in that, The intelligent control method for trenching accuracy of underground diaphragm walls in gravel and pebble geological conditions includes the following steps: The dynamic response index of the coal mine formation is input into a prediction model trained with underground coal mine data to generate a prediction of the deformation trend of the surrounding rock of the coal mine shaft. The predicted deformation trend of the surrounding rock of the shaft is compared and analyzed with the drill string spatial attitude data of the current skew angle and azimuth angle to generate basic control parameters. The basic control parameters are then subjected to multi-objective optimization calculations for coal mine construction to obtain the optimal combination of operating parameters suitable for the coal mine shaft, including the thrust adjustment value and the rotation speed optimization value. The optimal combination of operating parameters is transmitted to the hydraulic control system to form the coal mine shaft control command, realizing precise adjustment of the trenching process.

2. The intelligent control method for trenching accuracy of diaphragm wall in sand and gravel geology according to claim 1, characterized in that, The process of obtaining the optimal combination of operating parameters for coal mine shafts includes the following steps: The dynamic response index of the coal mine strata is input into a prediction model trained with underground coal mine data; the time series features of the input dynamic response index are extracted to identify its short-term fluctuation patterns and intensity; the time series features are used by the state inference network inside the prediction model to calculate the most likely deformation displacement and deformation direction of the surrounding rock of the shaft in the future period based on the learned correlation rules, thus generating a prediction of the deformation trend of the surrounding rock of the coal mine shaft. Based on the predicted deformation trend of the surrounding rock in the coal mine shaft, a collaborative deviation analysis is performed with the drill string spatial attitude data of the current skew angle and azimuth angle. The deformation direction and displacement predicted in the surrounding rock deformation trend prediction are compared with the current trenching axis shown in the drill string spatial attitude data to calculate the physical quantity of the trajectory deviation estimate. The trajectory deviation estimate is output as a set of basic control parameters, including the initial value of the thrust correction and the initial value of the rotation speed correction, according to the preset deviation amount-control amount correspondence rule. The basic control parameters are subjected to multi-objective optimization calculations. The multi-objective optimization calculations include three objectives: the trenching accuracy objective determined by the basic control parameters, the energy consumption constraint objective represented by the carbon efficiency index of coal mine construction, and the drilling efficiency objective based on the requirements of coal mine shaft engineering. The multi-objective optimization calculations iteratively optimize among the three objectives to find the balance point that satisfies all constraints and output the optimal combination of operating parameters, including the final thrust adjustment value and rotation speed optimization value.

3. The intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to claim 2, characterized in that, The process of outputting a set of basic control parameters includes the following steps: The deformation direction and displacement predicted in the surrounding rock deformation trend prediction are fused with the current trenching axis shown by the drill bit spatial attitude data through collaborative deviation analysis. The deformation trend, which includes the deformation direction and displacement, is projected in three-dimensional space onto a plane with the current trenching axis as the reference, and two independent prediction quantities are decomposed: the estimated value of the deviation angle of the deformation trend relative to the current trenching axis in the horizontal plane, and the estimated value of the dip angle in the vertical profile. The estimated deviation angle and the estimated tilt angle are combined according to their geometric relationship to obtain a trajectory deviation estimate that characterizes the overall degree of deviation. The trajectory deviation prediction value outputs basic control parameters based on the preset deviation amount-control amount correspondence rule.

4. The intelligent control method for trenching accuracy of diaphragm wall in gravel geology according to claim 3, characterized in that, The process of obtaining a trajectory deviation estimate that characterizes the overall degree of deviation includes the following steps: The spatial baseline of the current trenching axis is used as the geometric composite baseline in three-dimensional space; The deflection angle estimate and the tilt angle estimate are regarded as the two legs of a right triangle. By calculating the length of the hypotenuse of the right triangle, the scalar values ​​of the two angular displacements in different directions are merged into a scalar value. The scalar value is defined as the comprehensive deviation, which represents the overall magnitude of the composite spatial offset composed of deviations in the horizontal and vertical directions. The comprehensive deviation is mapped to a trajectory deviation estimate with clear engineering risk warning significance based on the sensitivity and risk tolerance of different deviation amplitudes in coal mine shaft construction, thereby quantifying the risk of assembly channel path deviation that may be caused by future deformation.

5. The intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to claim 4, characterized in that, The process of mapping a deviation from the projected trajectory to a value with clear engineering risk warning significance includes the following steps: Based on the coal mine shaft construction specifications and historical data, a risk level scale is pre-constructed. The risk level scale divides the comprehensive deviation value range into a corresponding relationship of different risk levels. Each level range corresponds to the sensitivity definition and risk tolerance limit of different deviations in the project. The overall deviation is located and matched on the established risk level scale and is assigned a discrete risk level index; the risk level index is an ordinal value, the magnitude of which represents the severity of the risk level it falls into. The risk level index, which represents the degree of abstract risk, is converted into a trajectory deviation estimate according to a predefined risk-physical quantity conversion rule.

6. The intelligent control method for trenching accuracy of underground continuous wall in gravel geology according to claim 5, characterized in that, The process of defining risk-physical quantity conversion rules includes the following steps: Based on the design accuracy and trenching process requirements of coal mine shafts, predefine engineering benchmark values; the engineering benchmark value is a constant with the dimension of length, representing the acceptable or controllable benchmark path deviation in the current engineering context. The risk level index is converted into a risk amplification coefficient through the preset rules of the level-coefficient mapping table; there is a positive correlation between the value of the risk level index and the value of the risk amplification coefficient; that is, a low risk level index corresponds to a risk amplification coefficient close to 1, a medium risk level index corresponds to a moderate amplification coefficient greater than 1, and a high risk level index corresponds to a significant amplification coefficient much greater than 1. The final trajectory deviation estimate is generated by combining the established engineering benchmark values ​​with the generated risk amplification coefficient through quantitative synthesis calculation.

7. The intelligent control method for trenching accuracy of diaphragm wall in gravel geology according to claim 6, characterized in that, The process of quantitative synthesis calculation includes the following steps: A quantitative synthesis calculation benchmark is established. The calculation benchmark is a physical quantity fusion criterion established based on the principle of consistency of the dimensions of coal mine shaft construction control. The final output estimate is a physical quantity with a clear length dimension, and its value needs to be determined by the benchmark quantity and the risk coefficient. The engineering baseline value is multiplied by the risk amplification factor to generate a preliminary uncalibrated estimate. The generated uncalibrated estimate is then processed by dimensional calibration to generate the final trajectory deviation estimate.

8. The intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to claim 1, characterized in that, It also includes an acoustic strata detection device and a resistivity sensor installed at the drill bit to simultaneously collect data on the density fluctuation of the surrounding rock in the coal mine shaft and the distribution characteristics of pebbles; the density fluctuation data of the surrounding rock in the shaft is filtered to obtain a purified density change curve of the surrounding rock; at the same time, the pebble distribution characteristics data are reconstructed through the shaft space to generate a three-dimensional map of the pebble enrichment area; the purified density change curve of the surrounding rock and the three-dimensional map of the pebble enrichment area are fused with the coal mine strata to form the stability coefficient of the surrounding rock in the shaft; the stability coefficient of the surrounding rock in the shaft is combined with the real-time working parameters of the drilling rig to output the dynamic response index of the coal mine strata, reflecting the real-time changes of the sand and pebble strata around the coal mine shaft.

9. The intelligent control method for trenching accuracy of underground continuous wall in sand and gravel geology according to claim 1, characterized in that, It also includes the following: during the execution of coal mine shaft control commands, raw energy consumption data is collected through power monitoring modules and hydraulic energy efficiency sensors installed on drilling equipment, while simultaneously recording concrete consumption; the raw energy consumption data is processed by a coal mine carbon emission accounting program to output real-time carbon emission equivalents; the concrete consumption is calculated using the carbon conversion coefficient of building materials to obtain the carbon emission contribution value of the materials; the real-time carbon emission equivalent and the carbon emission contribution value of the materials are weighted using a coal mine-specific method to generate a coal mine construction carbon efficiency index; the coal mine construction carbon efficiency index is compared with the low-carbon standard value of the coal mining industry to form a coal mine construction energy efficiency assessment report, which is fed back to the coal mine trenching adaptive control system to optimize the energy consumption constraints in the calculation.

10. An intelligent control system for trenching accuracy of diaphragm walls in sandy and gravelly geological conditions, applied to the intelligent control method for trenching accuracy of diaphragm walls in sandy and gravelly geological conditions as described in any one of claims 1 to 9, characterized in that... The intelligent control system for trenching accuracy of the underground diaphragm wall in gravel geology includes: The wellbore surrounding rock data fusion and analysis module is used by the sonic formation detection device and resistivity sensor installed at the drill bit to simultaneously collect coal mine wellbore surrounding rock density fluctuation data and pebble distribution characteristic data. The wellbore surrounding rock density fluctuation data is filtered to obtain a purified surrounding rock density change curve. At the same time, the pebble distribution characteristic data is reconstructed through wellbore space to generate a three-dimensional map of pebble enrichment area. The purified surrounding rock density change curve and the three-dimensional map of pebble enrichment area are fused with coal mine formation data to form the wellbore surrounding rock stability coefficient. The wellbore surrounding rock stability coefficient is combined with the real-time working parameters of the drilling rig to output the coal mine formation dynamic response index, reflecting the real-time changes of the sand and pebble strata around the coal mine wellbore. The adaptive control module for coal mine trenching is used to input dynamic response indicators of coal mine formations into a prediction model trained with underground coal mine data to generate a prediction of the deformation trend of the surrounding rock in the coal mine shaft. The predicted deformation trend is then compared and analyzed with the drill string's spatial attitude data (current yaw and azimuth angles) to generate basic control parameters. These basic control parameters undergo multi-objective optimization calculations in coal mine construction to obtain the optimal combination of operating parameters suitable for the coal mine shaft, including thrust adjustment values ​​and rotation speed optimization values. This optimal combination of operating parameters is transmitted to the hydraulic control system to form coal mine shaft control commands, enabling precise adjustment of the trenching process. The coal mine construction carbon efficiency monitoring module is used during the execution of coal mine shaft control commands. It collects raw energy consumption data through an electrical energy monitoring module and hydraulic energy efficiency sensors installed on the drilling equipment, and records concrete consumption. The raw energy consumption data is processed by a coal mine carbon emission accounting program to output real-time carbon emission equivalents. The concrete consumption is calculated using the carbon conversion coefficient of building materials to obtain the carbon emission contribution value of the materials. The real-time carbon emission equivalent and the carbon emission contribution value of the materials are weighted using a coal mine-specific calculation to generate a coal mine construction carbon efficiency index. The coal mine construction carbon efficiency index is compared with the low-carbon standard value of the coal mining industry to form a coal mine construction energy efficiency assessment report, which is fed back to the coal mine trenching adaptive control system to optimize the energy consumption constraints in the calculation.

Images