A coal geological exploration whole-process digital management integrated system

Abstract

The present application relates to the technical field of coal geological exploration digitization, and discloses a kind of coal geological exploration whole process digitization management integrated system.The system includes exploration perception module, data interpretation module, logic operation module, decision generation module and instruction execution module.System obtains multidimensional exploration perception flow by laying perception device in exploration whole process node, and is structured and analyzed into geological structure, engineering progress and environmental safety feature sequence by data interpretation module structure.Structure logic operation module generates geological data confidence mark and operation process coordination mark accordingly, and decision generation module generates control instruction accordingly, and finally by instruction execution module drives field equipment to complete adjustment.The scheme realizes real-time analysis and characterization of multi-source heterogeneous data on site, and establishes an intelligent closed-loop control mechanism based on data reliability and process coordination degree dual quantitative indicators, improving the overall synergy of exploration operation and the reliability of geological results.

Description

Technical Field

[0001] This invention relates to the field of digital technology for coal geological exploration, specifically to an integrated digital management system for the entire coal geological exploration process. Background Technology

[0002] Currently, on-site management in coal geological exploration relies primarily on manual recording and the decentralized operation of multiple independent systems. Data generated from different stages such as drilling, logging, and sampling are inconsistent in format, timing, and semantics, and are stored in mutually isolated databases. This results in the on-site status being fragmented into data segments that cannot be correlated in real time, making it difficult to form a coherent understanding of the overall operation.

[0003] Existing technical solutions typically process specific stages or single data types independently within the exploration process. These solutions lack a unified processing framework that spans the entire exploration process and integrates multi-source heterogeneous data. Raw sensing data cannot be parsed in real time into features with clear engineering significance, preventing the system from immediately assessing the quality and reliability of geological data acquisition, and from dynamically evaluating the coordination between project progress, safety, environmental factors, and geological objectives. Management decisions therefore rely on delayed and localized information.

[0004] This invention needs to meet the following core requirements: to realize real-time automated parsing of the continuous and mixed multidimensional raw data streams generated by each node, and to separate the structured feature sequences of different dimensions; to establish a decision mechanism that can simultaneously quantify the "intrinsic credibility of data" and "coordination of cross-link operations", and to drive the adaptive closed-loop control of the system based on this mechanism. Summary of the Invention

[0005] The purpose of this invention is to provide an integrated digital management system for the entire coal geological exploration process to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides an integrated digital management system for the entire coal geological exploration process, the system comprising: The exploration sensing module is used to deploy sensing devices at multiple physical nodes throughout the entire coal geological exploration process to continuously acquire multi-dimensional exploration sensing data reflecting the on-site operation status. The data interpretation module, connected to the exploration and perception module, performs structured analysis on the multidimensional exploration and perception flow, separating the geological structure feature sequence, the engineering progress feature sequence, and the environmental safety feature sequence. The logic operation module is connected to the data interpretation module, imports the geological structure feature sequence, performs compliance verification of the geological structure feature sequence, generates geological data confidence markers, and synchronously imports the project progress feature sequence and environmental safety feature sequence, performs synchronization fusion of the project progress feature sequence and environmental safety feature sequence, and generates work process coordination markers. The decision generation module is connected to the logic operation module, receives the geological data confidence marker and the operation process coordination marker, and generates exploration control parameter adjustment instructions and exploration operation path correction instructions according to the preset decision logic. The instruction execution module is connected to the decision generation module, parses the exploration control parameter adjustment instruction and the exploration operation path correction instruction, and drives the corresponding exploration execution mechanism to complete the parameter adjustment and path correction operations.

[0007] Preferably, the exploration sensing module continuously acquires a multi-dimensional exploration sensing stream reflecting the on-site operation status, including the following steps: Deploy core vision scanning devices at drilling sites to acquire images of the borehole inner wall at fixed time intervals, forming a drilling image stream; Distributed signal sensing devices are deployed along the well logging line to continuously collect electrical, acoustic, and radioactive physical field signals from the formation, forming a geophysical signal stream. A three-dimensional laser scanning device is deployed on the exploration engineering face to periodically scan the spatial contour point cloud of the tunnel and working face to form the point cloud flow of the engineering morphology. Gas concentration sensors and displacement monitoring sensors are deployed in the working environment to collect real-time values ​​of methane concentration, carbon monoxide concentration, roof displacement, and sidewall convergence, forming an environmental safety data stream.

[0008] Preferably, the data interpretation module performs structured analysis on the multidimensional exploration sensing flow, including the following steps: A feature extraction operation is performed on the drilling image stream to identify the location of lithological interfaces, the direction of fracture development, and the distribution density of rock cuttings in the images. The identification results are sorted according to the drilling depth to generate the core visual feature subsequence in the geological structure feature sequence. The geophysical signal stream is decomposed and reconstructed to separate the effective signal segments of the natural gamma logging curve, resistivity logging curve and sonic transit time logging curve. The mean amplitude, fluctuation period and abrupt change point location are extracted from each effective signal segment. The extraction results are sorted according to the detection depth to generate the geophysical feature subsequence in the geological structure feature sequence. Perform point cloud registration and comparison operations on the engineering topography point cloud flow, spatially compare the engineering topography point cloud obtained in the current cycle with the engineering topography point cloud of the previous cycle or design model, calculate the roadway cross-section shrinkage, working face advance distance and over- and under-excavation volume, and generate the engineering progress feature sequence. The environmental safety data stream is subjected to threshold comparison and trend analysis operations. The real-time collected gas concentration value, carbon monoxide concentration value, roof displacement value and two-sided convergence value are compared with their respective dynamic safety thresholds, and their slope over time is analyzed to generate the environmental safety feature sequence.

[0009] Preferably, the logic operation module performs compliance verification of the geological structure feature sequence and generates geological data confidence markers, including the following steps: Retrieve standard stratigraphic columns and typical geophysical response models of the target exploration area from the pre-set geological knowledge base; The positions of lithological interfaces sorted by depth in the core visual feature subsequence are compared layer by layer with the theoretical positions of the stratigraphic interfaces at the corresponding depths in the standard stratigraphic column, and the interface position deviation is calculated. The mean amplitudes of the natural gamma curves, resistivity curves, and acoustic transit time curves sorted by depth in the geophysical feature subsequence are compared with the theoretical response value range of the corresponding lithology in the typical geophysical response mode, and the percentage of data points exceeding the theoretical response value range is counted. Based on the interface position deviation and the proportion of data points exceeding the theoretical response value range, combined with the preset confidence calculation rules, the geological data confidence mark is calculated. The geological data confidence mark includes the overall confidence level and the index of abnormal data location.

[0010] Preferably, the logic operation module performs synchronization fusion of the project progress feature sequence and the environmental safety feature sequence to generate a work process coordination degree marker, including the following steps: Establish a synchronous analysis time window with time as the horizontal axis and project progress and safety indicators as the vertical axis; Within the synchronous analysis time window, the curve of the working face advance distance changing with time in the engineering progress characteristic sequence is superimposed and analyzed with the curve of the roof displacement value changing with time in the environmental safety characteristic sequence to identify whether the roof displacement value undergoes a sudden change that exceeds the normal fluctuation range near the time point when the advance distance changes abruptly. Within the synchronous analysis time window, the tunnel cross-section shrinkage in the engineering progress characteristic sequence is correlated with the two-side convergence value in the environmental safety characteristic sequence to determine whether the tunnel cross-section shrinkage is mainly caused by the two-side convergence. Based on the results of overlay analysis and correlation analysis, the temporal and causal correlation strength between changes in project progress and changes in safety indicators is assessed, and the work process coordination degree marker is generated accordingly. The work process coordination degree marker includes the coordination level and the time period identifier of non-coordination events.

[0011] Preferably, the decision generation module generates exploration control parameter adjustment instructions and exploration operation path correction instructions based on preset decision logic, including the following steps: Receive the confidence level marker of the geological data, determine whether its overall confidence level is lower than the preset acceptable threshold, and if it is lower, start the process of generating exploration control parameter adjustment instructions; In the process of generating exploration control parameter adjustment instructions, based on the abnormal data location index in the geological data confidence mark, the specific drilling depth or exploration depth is located, and the drilling parameters or logging parameters that are being used or planned to be used near the depth are retrieved to generate adjustment values ​​for drilling pressure, rotation speed, mud pump volume or logging instrument transmission power, which are then packaged into the exploration control parameter adjustment instructions. The system receives the coordination level marker of the operation process and determines whether its coordination level is lower than the preset coordination threshold. If it is lower, the system initiates the exploration operation path correction instruction generation process. In the process of generating exploration operation path correction instructions, based on the time period identifier of the non-cooperative event in the operation process coordination degree mark, the engineering progress characteristics within the corresponding time period are traced back, and combined with the three-dimensional geological model, the extension direction of the tunnel or the advancement sequence of the working face are replanned in areas with low safety risks, and the exploration operation path correction instructions containing new coordinate point sets and construction time sequences are generated.

[0012] Preferably, the instruction execution module parses the exploration control parameter adjustment instruction and drives the corresponding exploration execution mechanism, including the following steps: The exploration control parameter adjustment command is parsed to extract the drilling equipment number to be adjusted, the target adjustment parameter type, and the specific adjustment value contained therein; The control signal containing the target adjustment parameter type and adjustment value is sent to the corresponding intelligent drilling rig control system. The intelligent drilling rig control system, based on the received control signal, drives its hydraulic system or motor system to adjust the drilling pressure or rotation speed of the drill bit to the specified value, and then sends back an adjustment confirmation signal.

[0013] Preferably, the instruction execution module parses the exploration operation path correction instruction and drives the corresponding exploration execution mechanism, including the following steps: The exploration operation path correction instruction is analyzed to extract the new set of roadway centerline coordinate points and construction sequence contained therein; The new set of roadway centerline coordinate points and construction sequence are converted into a navigation path point sequence and work schedule that can be recognized by the tunneling equipment; The navigation path point sequence and work schedule are sent to the path planning controller of the automated tunneling machine; The path planning controller of the automated tunneling machine generates a motion trajectory to control the cutting head based on the received navigation path point sequence and work schedule, and drives the automated tunneling machine to perform tunneling operations along the new path and time sequence.

[0014] Preferably, the step of performing signal decomposition and reconstruction operations on the geophysical signal stream to separate the effective signal segments of the natural gamma logging curve, resistivity logging curve, and sonic transit time logging curve includes the following steps: The empirical mode decomposition algorithm is used to decompose the original geophysical signal stream at multiple scales to obtain a series of intrinsic mode function components. Calculate the sample entropy value of each intrinsic mode function component, and identify the components with sample entropy values ​​lower than a preset threshold as noise-dominant components and remove them; The remaining intrinsic mode function components are reconstructed to obtain the denoised geophysical signal; In the denoised geophysical signal, a bandpass filter is designed to separate the signal based on the inherent frequency characteristics of the natural gamma logging curve, resistivity logging curve and sonic transit time logging curve. Sliding window mean analysis is performed on the separated well logging curve signals to identify continuous segments with stable signal amplitudes and fluctuations within a preset range, which are then marked as valid signal segments. Align the effective signal segments of each logging curve according to the depth coordinates, and record the starting and ending depths of each effective signal segment.

[0015] Preferably, the step of assessing the temporal and causal correlation strength between changes in project progress and changes in safety indicators based on the results of overlay analysis and correlation analysis includes the following steps: Within the synchronous analysis time window, the rate of change of the working face advance distance and the rate of change of the top plate displacement are sampled at fixed time intervals to form the advance rate of change sequence and the displacement rate of change sequence. Calculate the cross-correlation coefficient between the propulsion rate change sequence and the displacement rate change sequence, and use the maximum value of the cross-correlation coefficient as the time correlation strength index; A Granger causality test model was constructed with project progress characteristics as independent variables and safety indicators as dependent variables, and causality tests were conducted with multiple lag periods. When the test statistic exceeds the critical value corresponding to the significance level, it is determined that the change in project progress is a Granger cause of the change in safety indicators, and the strength of causal relationship is recorded as the value of the test statistic. The time-related correlation strength index and the causal correlation strength index are weighted and fused to obtain the comprehensive correlation strength; Based on the numerical range of the comprehensive correlation strength, the correlation strength level between changes in project progress and changes in safety indicators is determined, and the correlation strength level is divided into three levels: strong correlation, medium correlation and weak correlation.

[0016] Compared with the prior art, the beneficial effects of the present invention are: By deploying sensing devices at each physical node throughout the entire exploration process, a multi-dimensional raw data stream constituting a panoramic view of the on-site operational status can be continuously collected. The data interpretation module analyzes this data stream, separating it into three parallel structured feature sequences: geological structure, project progress, and environmental safety. This process automates and real-time processing of mixed information on-site, transforming previously isolated data points into temporal features with clear engineering semantics. The status of each stage can be synchronously sensed and quantitatively represented, providing accurate and orderly input for real-time analysis based on the global status, thus changing the traditional reliance on manual post-event summarization and weak data correlation.

[0017] The logic operation module processes the structured feature sequences in parallel. It performs compliance verification on the geological structure feature sequences, generating markers to quantify their data quality and reliability. It also integrates and analyzes the project progress feature sequences and environmental safety feature sequences, generating markers to quantify the coordination between different stages of the operation. The decision generation module makes a comprehensive judgment based on these two markers and generates control commands. This transforms the two high-level management indicators—intrinsic data quality and operational process coordination—into calculable decision variables. The system's automated decision-making no longer relies solely on threshold judgments of a single parameter but comprehensively considers data reliability and process synergy. The driven parameter adjustments and path correction operations are closer to the global optimization goal, realizing a transformation from single-parameter control to intelligent closed-loop management based on multi-dimensional state fusion. Attached Figure Description

[0018] Figure 1 This is a sequence diagram of the integrated digital management system for the entire coal geological exploration process described in this invention. Figure 2 A flowchart for obtaining the multi-dimensional exploration sensing flow for the exploration sensing module; Figure 3 A flowchart for generating geological data confidence markers for the logic operation module; Figure 4 A confidence analysis chart of geological data for natural gamma logging curves; Figure 5 This is a curve showing the change in confidence level of geological data with depth. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Please see Figure 1 This invention provides an integrated digital management system for the entire coal geological exploration process. The system includes: an exploration sensing module that deploys various sensing devices at multiple physical nodes throughout the process to continuously collect and output multi-dimensional exploration sensing data; a data interpretation module that receives the sensing data, performs structured analysis, and separates geological structure feature sequences, engineering progress feature sequences, and environmental safety feature sequences; a logic operation module that imports the above sequences, first performs compliance verification on the geological structure feature sequences to generate geological data confidence markers, and simultaneously merges the engineering progress and safety feature sequences to generate operation process coordination markers; a decision generation module that, based on the two received markers and according to embedded preset decision logic, generates exploration control parameter adjustment instructions and exploration operation path correction instructions for optimizing operations; and an instruction execution module that parses these two types of instructions and converts them into executable control signals to drive the corresponding drilling, tunneling, and other exploration execution mechanisms to complete the actual parameter adjustment and path correction operations, thereby forming a closed-loop intelligent management process from sensing to execution.

[0021] In one embodiment of the present invention, see [reference] Figure 2In practical implementation, the exploration sensing module deploys sensing devices at multiple physical nodes throughout the entire coal geological exploration process to continuously acquire multi-dimensional exploration sensing data reflecting the on-site operational status. In a specific operational scenario within an exploration area, the implementation involves the spatial distribution and continuous temporal operation of various sensing devices. At drilling site ZK-301, the deployed core visual scanning device acquires annular images of the borehole wall at fixed time intervals of once per minute. As drilling progresses downwards from the ground, at a depth of 255 meters, the core visual scanning device acquires an image clearly showing the lithological interface between gray-black siltstone and light gray fine sandstone. During the drilling process to a depth of 260 meters, the core visual scanning device continues to acquire images, forming a stream of drilling images arranged in chronological and depth order. On the adjacent L2 logging line, the deployed distributed signal sensing device continuously collected the physical field signals of the formation at a density of 8 sampling points per meter. Within the depth range of 200 to 300 meters, the distributed signal sensing device recorded natural gamma readings fluctuating between 75 and 90 API, resistivity readings varying between 18 and 25 ohm-meters, and acoustic transit time readings ranging from 65 to 72 microseconds per foot. These signals together constitute the geophysical signal stream. Within the A3 transport roadway at a depth of -350 meters, a deployed 3D laser scanning device performs a full-station scan every four hours. The first scan yielded a point cloud data showing the roof center point coordinates as (X=1023.45, Y=887.12, Z=-350.05), and the second scan yielded the same coordinates. The spatial contour point cloud sequence from the two scans forms an engineering topography point cloud stream. Within the same operating environment of the A3 transport roadway, real-time monitoring data from deployed gas concentration sensors showed a methane concentration of 0.15% and a carbon monoxide concentration of 8 ppm. Simultaneously, data from deployed displacement monitoring sensors showed a roof displacement of 12 mm, a left side convergence of 5 mm, and a right side convergence of 4 mm. These real-time collected data converge to form an environmental safety data stream.

[0022] In some embodiments, the core scanning device is deployed close to the rear of the drill bit to ensure real-time imaging of the newly exposed borehole strata. Distributed signal sensors are arranged at equal intervals along the borehole cable, each responsible for collecting electrical, acoustic, and radioactive physical field signals at its depth point. The 3D laser scanning device is typically mounted on a movable support within the roadway and requires positioning calibration before each scan to ensure a unified spatial coordinate system for point cloud data from different periods. Gas concentration sensors and displacement monitoring sensors are deployed in a network across the roadway roof, sides, and working face, forming an environmental safety monitoring network covering the main working areas.

[0023] Optionally, the core scanning device employs a design combining a ring array light source and a high-resolution linear array camera to eliminate the effects of uneven illumination within the borehole and acquire clear images of the borehole wall. The distributed signal sensing device integrates micro-electrical measuring electrodes, a piezoelectric ceramic acoustic transducer, and a scintillation crystal gamma detector, enabling the simultaneous acquisition of multiple geophysical parameters. The 3D laser scanning device utilizes a pulsed laser ranging principle, with a scanning angle resolution set to 0.01 degrees, to acquire high-precision point cloud data of the tunnel surface. In the environmental safety data stream, the gas concentration sensor employs a catalytic combustion principle, the carbon monoxide concentration sensor employs an electrochemical principle, and the displacement monitoring sensor employs a laser ranging or wire displacement meter principle.

[0024] It is understandable that the formation of the drilling image stream depends on the continuity of the drilling process, and the image acquisition frequency must be matched with the drilling speed to prevent depth information misalignment. The continuity of the geophysical signal stream is related to the uniform hoisting speed of the logging cable; the stability of the hoisting speed determines the sampling uniformity of the signal in the depth domain. The periodic updates of the engineering topography point cloud stream depend on the setting of the scanning cycle; a shorter scanning cycle can reflect the dynamic changes of the engineering shape more promptly. The real-time performance of the environmental safety data stream is guaranteed by the sensor sampling frequency and the bandwidth of the data transmission link, enabling the uploading of monitoring data at the second or even millisecond level.

[0025] In one embodiment of the present invention, in a specific implementation, the data interpretation module is connected to the exploration perception module to perform structured analysis on the multi-dimensional exploration perception stream, separating the geological structure feature sequence, the project progress feature sequence, and the environmental safety feature sequence. The data interpretation module receives a drilling image stream from borehole ZK-301. The image stream contains sixteen borehole inner wall unfolded images acquired sequentially from a depth of 250 meters to 265 meters. The module performs feature extraction on the drilling image stream, identifying the location of lithological interfaces, fracture development orientation, and rock cuttings particle distribution density in each image. For example, a micro-fracture trending 35 degrees northeast is identified in the image at a depth of 255.3 meters, and a rock cuttings particle distribution density of 120 particles per square centimeter is identified in the image at a depth of 260.1 meters. All identified lithological interface depths, fracture parameters, and particle densities are sorted in ascending order of drilling depth to generate a core visual feature subsequence in the geological structure feature sequence. This subsequence is a structured list containing depth, lithological code, fracture parameter, and density value.

[0026] In some embodiments, the data interpretation module performs signal decomposition and reconstruction operations on the geophysical signal stream, separating the effective signal segments of the natural gamma ray logging curve, resistivity logging curve, and sonic transit time logging curve. The data interpretation module processes the raw geophysical signal stream from the L2 logging line, which is a mixed signal recording depth and various physical quantities. An empirical mode decomposition (EMD) algorithm is used to perform multi-scale decomposition on the raw geophysical signal stream in the depth range of 200 to 300 meters. The EMD algorithm decomposes the signal into seven intrinsic mode function (EMF) components and one residual component. The sample entropy value of each EMF component is calculated, and a sample entropy threshold of 0.5 is set. The third and fifth EMF components, with sample entropy values ​​below 0.5, are identified as noise-dominant components and removed from the signal composition. The remaining first, second, fourth, sixth, and seventh EMF components and the residual component are reconstructed to obtain the denoised geophysical signal. In the denoised geophysical signals, based on the typical frequency range of natural gamma logging signals (0-10 Hz), resistivity logging signals (1-50 Hz), and sonic transit-time logging signals (5-200 Hz), Butterworth bandpass filters were designed for the corresponding frequency ranges to separate the signals, resulting in three independent logging curves. A sliding window mean analysis with a window length of 0.5 meters was performed on the separated natural gamma logging curve signals to identify continuous segments with stable amplitudes between 80 and 85 API and fluctuations within ±3 API, such as the segment from depth 230.5 m to 278.2 m. This segment was marked as the effective signal segment of the natural gamma logging curve. The same operation was performed on the resistivity logging curve and the sonic transit-time logging curve, marking the effective signal segments respectively. The effective signal segments of the three logging curves were aligned according to depth coordinates, and the start and end depths of each effective signal segment were recorded. For example, the effective signal segment for natural gamma logging was from 230.5 m to 278.2 m, and the effective signal segment for resistivity logging was from 228.1 m to 280.0 m. The mean amplitude, fluctuation period, and abrupt change location were extracted from each effective signal segment. An abrupt change location was identified at a depth of 255 m for the natural gamma logging curve. All extracted results were sorted according to the exploration depth to generate a geophysical feature subsequence in the geological structure feature sequence.

[0027] Optionally, point cloud registration and comparison operations are performed on the engineering topography point cloud stream. The data interpretation module receives the engineering topography point cloud streams acquired during two scan cycles, T1 and T2, of the A3 roadway. Spatially, the engineering topography point cloud acquired during the T2 scan is spatially registered with the one acquired during the T1 scan, aligning the point clouds based on the coordinates of three fixed anchor points within the roadway. The two registered point clouds are then spatially compared to calculate the cross-sectional shrinkage of the roadway at the monitoring station. For example, if the Z-coordinate of the roof center point changes from -350.05 meters to -350.12 meters, the calculated roof subsidence is 0.07 meters, the working face advance distance is 4.5 meters, and the over- and under-excavation volume of the roadway sidewalls is 1.2 cubic meters in the positive direction. The calculated cross-sectional shrinkage, advance distance, and over- and under-excavation volume data are used to generate an engineering progress feature sequence.

[0028] It is understandable that threshold comparison and trend analysis operations are performed on the environmental safety data stream. The data interpretation module receives the environmental safety data stream from the A3 roadway in real time. The real-time collected methane concentration value of 0.15% is compared with the preset dynamic safety threshold of 0.8%, the carbon monoxide concentration value of 8 ppm is compared with the dynamic safety threshold of 24 ppm, the roof displacement value of 12 mm is compared with the dynamic safety threshold of 25 mm, and the sidewall convergence value of 9 mm is compared with the dynamic safety threshold of 15 mm. The slope of the methane concentration value change over the past ten minutes is analyzed as an increase of 0.01% per hour, and the slope of the roof displacement value change is analyzed as an increase of 0.5 mm per hour. The threshold comparison results and the slope analysis results are combined to generate an environmental safety feature sequence, which includes the real-time values ​​of each parameter, the over-limit status indicator, and their changing trends.

[0029] In some embodiments, the data interpretation module processes the geophysical signal stream following a sequence of signal preprocessing and effective information extraction. Empirical Mode Decomposition (EMD) algorithms are used to process non-stationary signals, and sample entropy calculation is used to quantitatively assess the randomness of components to distinguish noise. Point cloud registration relies on physical markers with absolute coordinates pre-deployed at the scanning site to ensure accurate alignment of point cloud data from different times. Threshold comparison of the environmental safety data stream employs a dynamic safety threshold, which is dynamically calculated by the system based on the surrounding rock conditions of the tunnel and the mining stage, and is not a fixed value.

[0030] In one embodiment of the present invention, see [reference] Figure 3In practical implementation, the logic operation module connects to the data interpretation module, imports geological structure feature sequences, performs compliance checks on the geological structure feature sequences, and generates geological data confidence markers. In an exploration project targeting Block X of the Qinshui Coalfield, the logic operation module retrieves the standard stratigraphic column and typical geophysical response model of the target exploration area from a pre-set geological knowledge base. The standard stratigraphic column contains theoretical lithology, thickness, and interface depth information of all strata within the depth range from the surface to the target coal seam. For example, it records that the theoretical depth of the top boundary sandstone of the No. 3 coal seam of the Permian Shanxi Formation is 258.0 meters. The typical geophysical response model stores the theoretical response value ranges of natural gamma, resistivity, and sonic transit time corresponding to different lithologies in the area.

[0031] The logic operation module compares the locations of lithological interfaces sorted by depth in the core visual feature subsequence with the theoretical locations of the corresponding stratigraphic interfaces at the same depth in the standard stratigraphic column. One important lithological interface identified in the core visual feature subsequence is the interface between siltstone and fine sandstone, observed at a depth of 255.3 meters, while the theoretical depth of the corresponding stratigraphic interface recorded in the standard stratigraphic column is 258.0 meters. The calculated deviation at this interface location is 2.7 meters. The logic operation module performs the same calculation on all five identified lithological interfaces in the sequence, obtaining a set of interface location deviations.

[0032] The logic operation module calculates the geological data confidence level based on the interface position deviation and the proportion of data points exceeding the theoretical response value range, combined with preset confidence level calculation rules. The preset confidence level calculation rules are centered on a quantitative formula used to comprehensively assess the impact of position deviation and data anomalies on the overall data reliability. This formula is: ; in: This represents the overall confidence score calculated. This represents the total number of lithological interfaces being compared. Representing the The observation depth of each interface, Representing the The theoretical depth of each interface This represents the percentage of data points that exceed the theoretical response value range. The normalized weighting coefficient representing the deviation of the interface position is set to 0.4. The normalized weighting coefficient, representing the proportion of outliers in the data, is set to 0.3. Substituting the example data above, the average relative deviation of the interface position deviation is calculated to be 0.023. The overall confidence score is calculated to be 0.18. It is 0.905.

[0033] Optionally, when retrieving standard stratigraphic columns and typical geophysical response models from the geological knowledge base, the logic operation module needs to intelligently match the geographical coordinates of the current exploration point with the designed target area stratigraphy to ensure that the retrieved benchmark is comparable to the actual drilled strata. The calculation of interface position deviation uses relative deviation rather than absolute deviation to eliminate evaluation bias caused by differences in the thickness of different strata. When calculating the proportion of data points exceeding the theoretical response value range, the logic operation module independently judges three parameters: natural gamma, resistivity, and acoustic transit time. If any parameter exceeds the range, the data point is counted as an outlier.

[0034] It is understandable that the generation of confidence markers for geological data is a quantitative, multi-factor comprehensive evaluation process, with an overall confidence score. The value range is defined between 0 and 1; a higher score indicates a higher degree of agreement between the data and prior geological knowledge, and more reliable data quality. The weighting coefficients in the confidence score calculation rules... and The system management interface allows for adjustments based on different exploration stages or geological complexity. For example, in the early stages of exploration, the requirements for interface position deviation can be appropriately relaxed, i.e., the deviation can be lowered. The generation of anomaly data location indexes not only serves the overall evaluation but also provides clear and in-depth guidance for subsequent targeted data review or supplementary testing.

[0035] In one embodiment of the present invention, in a specific implementation, the logic operation module is connected to the data interpretation module, synchronously imports the project progress feature sequence and the environmental safety feature sequence, performs synchronization fusion of the project progress feature sequence and the environmental safety feature sequence, and generates a work process coordination degree mark. The logic operation module establishes a synchronous analysis time window with time as the horizontal axis and project progress and safety indicators as the vertical axis, and the length of the synchronous analysis time window is set to the work period of the most recent 8 hours. Within the synchronous analysis time window, the logic operation module overlays the curve of the working face advance distance over time in the engineering progress characteristic sequence with the curve of the roof displacement value over time in the environmental safety characteristic sequence. The working face advance distance is 150 meters at time point T3:20 (i.e., 20:00 on the third day) and 158 meters at time point T4:04 (i.e., 4:00 on the fourth day). It is identified that near the time point where the advance distance jumps by 8 meters, the roof displacement value increases from 15 mm at time point T3:20 to 28 mm at time point T4:04. The increase of 13 mm in the roof displacement value exceeds the normal fluctuation range of no more than 1 mm per hour under the surrounding rock conditions of this roadway and is judged as a sudden change. Within the same synchronous analysis time window, the logic operation module correlates the tunnel cross-sectional shrinkage in the engineering progress feature sequence with the convergence values ​​of the two sides in the environmental safety feature sequence. The tunnel cross-sectional shrinkage measured at time point T4:00 is 120 square centimeters, while the left side convergence value recorded in the environmental safety feature sequence at the same time point is 7 mm and the right side convergence value is 8 mm. The total theoretical cross-sectional shrinkage is approximately 105 square centimeters. The logic operation module determines that the tunnel cross-sectional shrinkage is mainly caused by the convergence of the two sides.

[0036] In some embodiments, based on the results of overlay analysis and correlation analysis, the temporal and causal correlation strength between changes in project progress and changes in safety indicators is assessed. Within the synchronous analysis time window, the logic operation module samples the rate of change of the working face advance distance and the rate of change of the top plate displacement value at fixed time intervals of half an hour, forming the advance rate of change sequence and the displacement rate of change sequence. Refer to Table 1; the sequence data is shown in Table 1.

[0037] Table 1: Sampling Table of Propulsion Change Rate and Displacement Change Rate within the Synchronous Analysis Time Window The cross-correlation coefficient between the rate of change in propulsion and the rate of change in displacement is calculated. The maximum value of the cross-correlation coefficient occurs at zero lag, and is 0.92. The logic operation module uses 0.92 as the time correlation strength index. The logic operation module constructs a Granger causality test model with project progress characteristics as the independent variable and safety indicators as the dependent variable, and performs a causality test with a two-lag period. The test statistic F-value calculated by the Granger causality test model is 6.5. With a significance level of 0.05 and a corresponding critical value of 5.2, the test statistic 6.5 exceeds the critical value of 5.2. The logic operation module determines that the change in project progress within this time window is a Granger cause of the change in safety indicators and records the causal correlation strength as 6.5. The logic operation module weights and fuses the time correlation strength index and the causal correlation strength to obtain the comprehensive correlation strength. The weighted fusion formula is as follows: ; in: Represents the overall correlation strength. Represents the strength of time-related correlation indicators. This represents the Granger causality test statistic. The normalization coefficient is set to 10. and We set the weights to 0.6 and 0.4 respectively. Substitute the data to calculate: Based on the numerical range definition of comprehensive correlation strength, 0.8 to 1.0 indicates strong correlation, 0.5 to 0.8 indicates moderate correlation, and 0 to 0.5 indicates weak correlation. The calculated result of 0.812 falls into the strong correlation category. The logic operation module generates a work process coordination level marker accordingly. This marker includes the coordination level "non-cooperative" and the time period identifier of the non-cooperative event, "T4:00 to T5:00". The logic for determining the coordination level is: although the correlation strength is strong, the top plate displacement experienced a sudden change exceeding the safety threshold; therefore, the process and safety status do not match, and it is marked as non-cooperative.

[0038] Optionally, the length of the synchronous analysis time window can be adaptively adjusted according to the stability of the surrounding rock and the intensity of operations. In sections with fractured rock strata and high operational intensity, the synchronous analysis time window can be automatically shortened to 2-4 hours to improve analysis sensitivity. Overlay analysis not only compares the magnitude of changes but also analyzes the phase difference of the changing trends, such as whether the acceleration of advance always leads the acceleration of displacement. In the correlation analysis, when calculating whether the tunnel cross-sectional shrinkage is mainly caused by the convergence of the two sidewalls, the logic operation module calls the design cross-sectional shape and size formula of the tunnel, converts the convergence value of the two sidewalls into the theoretical shrinkage area, and then compares it with the actual measured full-section shrinkage.

[0039] It is understandable that the time correlation strength index, calculated using the cross-correlation coefficient, reflects the similarity in waveform between the rate of change in project schedule and the rate of change in safety indicators, but it cannot indicate the direction of causality. The Granger causality test model is used to statistically determine whether a change in one time series can be used to predict a change in another time series. Its test result, "change in project schedule is a Granger cause of change in safety indicators," indicates that acceleration or deceleration of project schedule statistically significantly leads deterioration or improvement in safety indicators. The weights in the weighted fusion formula... and Adjustments can be made based on the management strategy's focus; if more emphasis is placed on real-time synchronization, improvements can be made. If more attention is paid to causal early warning, it can improve The time period identifier for non-coordinated events is determined based on the intersection interval of correlation strength analysis and safety threshold exceeding events on the time axis.

[0040] See Figure 4 In the geological data confidence analysis, the correlation between the mean natural gamma (API, left vertical axis) and the confidence score (0-1, right vertical axis) is simultaneously displayed with the exploration depth as the horizontal axis. The theoretical response range of the natural gamma at corresponding depths is marked with light-colored areas. Specifically, the blue line in the figure represents the trend of the measured mean natural gamma with depth: the mean is 65 API at a depth of 100m, peaking at 90 API at 400m, and then gradually decreasing to 62 API at 800m. The red line represents the confidence score, calculated based on the matching degree between the measured value and the theoretical response range. At a depth of 400m, although the measured mean natural gamma (90 API) is within the theoretical response range, the confidence score drops sharply to 0.78, marking it as an anomaly. The cause of this anomaly needs further verification using typical geophysical response patterns of the corresponding strata in the geological knowledge base, such as the presence of local radioactive mineral enrichment or interference from logging instrument signals. In terms of parameter correlation logic, the confidence score is positively correlated with the fluctuation range of the measured value: when the measured value is in the central region of the theoretical response value range (such as 300m depth), the confidence score remains above 0.85; when the measured value is close to the boundary of the theoretical range (such as 600m depth), the confidence score decreases synchronously.

[0041] In one embodiment of the present invention, in a specific implementation, the decision generation module is connected to the logic operation module, receives geological data confidence level markers and operation process coordination level markers, and generates exploration control parameter adjustment instructions and exploration operation path correction instructions according to preset decision logic. The geological data confidence level markers received by the decision generation module include an overall confidence level of "Level B" and anomaly data location indexes [255.1m, 256.5m, 257.8m]. The acceptable threshold for the overall confidence level set in the preset decision logic is "Level A". The decision generation module determines that "Level B" is lower than "Level A", and the determination result is lower than the acceptable threshold, and then starts the exploration control parameter adjustment instruction generation process. In the process of generating adjustment instructions for exploration control parameters, the decision generation module locates the specific drilling depths of 255.1 m, 256.5 m, and 257.8 m based on the anomaly data location index [255.1 m, 256.5 m, 257.8 m] in the geological data confidence level markers. It then retrieves the drilling parameters currently in use near the 255.1 m to 257.8 m depth range: drill pressure 12 tons, rotation speed 75 rpm, and mud pump flow rate 32 liters / second. Based on the confidence level and depth corresponding to the anomaly data location, the decision generation module generates adjustment values ​​for drill pressure and rotation speed. The parameter adjustment amounts are calculated using a mapping function, with the following formula: ; in: This represents the adjustment amount for a specific drilling parameter. The numerical value represents the confidence level required by the pre-defined decision-making logic. This represents the numerical value corresponding to the overall confidence level in the confidence level markers of the actually received geological data. This represents the adjustment coefficient for different parameters. The drill pressure adjustment amount is calculated. Tons, speed adjustment amount The decision generation module encapsulates the adjustment values ​​into exploration control parameter adjustment instructions. The instructions include: equipment number "Drill Rig-07", target parameter "Drill Pressure" adjusted to 12.4 tons, and target parameter "Rotation Speed" adjusted to 77 revolutions per minute. Simultaneously, the decision generation module receives operation process coordination markers containing a coordination level of "Non-coordination" and the time period identifier of the non-coordination event "T4:00 to T5:00". The preset coordination level threshold in the decision logic is "Basic Coordination". The decision generation module determines that "Non-coordination" is lower than "Basic Coordination", and the result is below the coordination threshold, thus initiating the exploration operation path correction instruction generation process. In the exploration operation path correction instruction generation process, the decision generation module, based on the time period identifier of the non-coordination event "T4:00 to T5:00" in the operation process coordination markers, traces back the project progress characteristics within the corresponding time period T4:00 to T5:00. Records show that the working face advanced 5 meters in the Y direction during this period, but the roof displacement increased significantly. The decision generation module, combined with the 3D geological model of the area, determined that a small fault structure existed 15 meters ahead of the planned advance direction. Based on this, the module identified a high-risk original path and searched for and planned a new path in the 3D geological model that bypassed the area with lower safety risk. The module then generated a path correction instruction for the exploration operation, including a new set of coordinate points and a new construction sequence. The new set of coordinate points is [(X1000,Y1500,Z-350),(X1005,Y1508,Z-350),(X1012,Y1510,Z-350)], and the new construction sequence is: "Delay the original T5:00 start of tunneling; after the roof displacement stabilizes, begin tunneling at T6:00 according to the new coordinate point set."

[0042] In some embodiments, the preset decision logic of the decision generation module includes multi-level judgment rules. The first level judges whether the overall confidence level or the coordination level is lower than a threshold. The second level judges the specific nature of the time period identifier of the abnormal data location index or the non-coordination event, such as judging whether the anomaly is a systematic shift or a local mutation, to decide whether to generate an adjustment command or an alarm command. When retrieving drilling parameters or logging parameters that are being used or planned to be used near the depth of the abnormal data location index, the decision generation module needs to access the drilling rig monitoring system or logging plan database in real time to obtain accurate current parameter values ​​or predetermined parameter values. In the exploration control parameter adjustment command generation process, the adjustment of the logging instrument transmission power is usually related to the degree of decrease in the signal-to-noise ratio. The greater the decrease in the signal-to-noise ratio, the greater the power increase.

[0043] Optionally, in the exploration operation path correction instruction generation process, when replanning the extension direction of the tunnel or the advancement sequence of the working face, the decision generation module will call the path planning algorithm. The algorithm performs optimization calculations with multiple objectives, including avoiding known geological anomalies and stress concentration areas, and minimizing efficiency losses caused by path changes. When generating exploration operation path correction instructions containing a new set of coordinate points and construction sequence, the new set of coordinate points needs to be converted into a three-dimensional coordinate sequence in an absolute coordinate system that can be recognized by the tunneling equipment control system. The construction sequence needs to be coordinated with the overall exploration operation plan to avoid resource conflicts. After generating exploration control parameter adjustment instructions and exploration operation path correction instructions, the decision generation module will attach a unique instruction identifier and generation timestamp to each instruction and send the instruction to the instruction execution module.

[0044] The instruction execution module connects to the decision generation module, parses the exploration control parameter adjustment instructions, and drives the corresponding exploration execution mechanism. The instruction execution module receives and parses the exploration control parameter adjustment instructions, extracting from them the drilling equipment number to be adjusted ("Drill Rig-07"), the target adjustment parameter type ("Drill Pressure") and its specific adjustment value ("12.4 tons"), and the target adjustment parameter type ("Rotation Speed") and its specific adjustment value ("77 rpm"). The instruction execution module then sends the control signal containing the target adjustment parameter type "Drill Pressure" and its adjustment value ("12.4 tons") and the target adjustment parameter type "Rotation Speed" and its adjustment value ("77 rpm") to the corresponding intelligent drilling rig control system via the industrial network. Based on the received control signals, the intelligent drilling rig control system drives its hydraulic system to adjust the drilling pressure servo valve, adjusting the drilling pressure of the drill bit from 12 tons to 12.4 tons, and drives its motor system to adjust the speed controller, adjusting the speed of the drill bit from 75 rpm to 77 rpm. After the adjustment is completed, the intelligent drilling rig control system sends an adjustment confirmation signal to the command execution module, which includes "drilling pressure has been adjusted to 12.4 tons and speed has been adjusted to 77 rpm".

[0045] See Figure 5During the data verification phase of coal geological exploration, the variation pattern of geological data confidence level with drilling depth was observed. Specifically, the blue curve in the figure represents the geological data confidence level, which remained stable at around 0.9 in the depth range of 250m to 255m. When the drilling depth entered the abnormal depth range of 255.1m-257.8m (marked by the pink area in the figure), the confidence level experienced several local decreases, with the lowest value falling below the confidence threshold (Level A, indicated by the orange dashed line in the figure, corresponding to around 0.85). Subsequently, it recovered to a stable level of 0.9 outside the abnormal range. This abnormal depth range corresponds to the abnormal data location index [255.1m, 256.5m, 257.8m] in the geological data confidence level markers, reflecting a reduced match between the geological structural feature sequence at this depth and the standard stratigraphic column and typical geophysical response model. Therefore, data quality needs to be optimized by adjusting exploration control parameters.

[0046] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0047] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A fully digital management integrated system for the entire coal geological exploration process, characterized in that, The system includes: The exploration sensing module is used to deploy sensing devices at multiple physical nodes throughout the entire coal geological exploration process to continuously acquire multi-dimensional exploration sensing data reflecting the on-site operation status. The data interpretation module, connected to the exploration and perception module, performs structured analysis on the multidimensional exploration and perception flow, separating the geological structure feature sequence, the engineering progress feature sequence, and the environmental safety feature sequence. The logic operation module is connected to the data interpretation module, imports the geological structure feature sequence, performs compliance verification of the geological structure feature sequence, generates geological data confidence markers, and synchronously imports the project progress feature sequence and environmental safety feature sequence, performs synchronization fusion of the project progress feature sequence and environmental safety feature sequence, and generates work process coordination markers. The decision generation module is connected to the logic operation module, receives the geological data confidence marker and the operation process coordination marker, and generates exploration control parameter adjustment instructions and exploration operation path correction instructions according to the preset decision logic. The instruction execution module is connected to the decision generation module, parses the exploration control parameter adjustment instruction and the exploration operation path correction instruction, and drives the corresponding exploration execution mechanism to complete the parameter adjustment and path correction operations.

2. The integrated digital management system for the entire coal geological exploration process according to claim 1, characterized in that, The exploration sensing module continuously acquires a multi-dimensional exploration sensing stream reflecting the on-site operation status, including the following steps: Deploy core vision scanning devices at drilling sites to acquire images of the borehole inner wall at fixed time intervals, forming a drilling image stream; Distributed signal sensing devices are deployed along the well logging line to continuously collect electrical, acoustic, and radioactive physical field signals from the formation, forming a geophysical signal stream. A three-dimensional laser scanning device is deployed on the exploration engineering face to periodically scan the spatial contour point cloud of the tunnel and working face to form the point cloud flow of the engineering morphology. Gas concentration sensors and displacement monitoring sensors are deployed in the working environment to collect real-time values ​​of methane concentration, carbon monoxide concentration, roof displacement, and sidewall convergence, forming an environmental safety data stream.

3. The integrated digital management system for the entire coal geological exploration process according to claim 2, characterized in that, The data interpretation module performs structured analysis on the multidimensional exploration sensing flow, including the following steps: A feature extraction operation is performed on the drilling image stream to identify the location of lithological interfaces, the direction of fracture development, and the distribution density of rock cuttings in the images. The identification results are sorted according to the drilling depth to generate the core visual feature subsequence in the geological structure feature sequence. The geophysical signal stream is decomposed and reconstructed to separate the effective signal segments of the natural gamma logging curve, resistivity logging curve and sonic transit time logging curve. The mean amplitude, fluctuation period and abrupt change point location are extracted from each effective signal segment. The extraction results are sorted according to the detection depth to generate the geophysical feature subsequence in the geological structure feature sequence. Perform point cloud registration and comparison operations on the engineering topography point cloud flow, spatially compare the engineering topography point cloud obtained in the current cycle with the engineering topography point cloud of the previous cycle or design model, calculate the roadway cross-section shrinkage, working face advance distance and over- and under-excavation volume, and generate the engineering progress feature sequence. The environmental safety data stream is subjected to threshold comparison and trend analysis operations. The real-time collected gas concentration value, carbon monoxide concentration value, roof displacement value and two-sided convergence value are compared with their respective dynamic safety thresholds, and their slope over time is analyzed to generate the environmental safety feature sequence.

4. The integrated digital management system for the entire coal geological exploration process according to claim 1, characterized in that, The logic operation module performs compliance verification of the geological structure feature sequence and generates geological data confidence labels, including the following steps: Retrieve standard stratigraphic columns and typical geophysical response models of the target exploration area from the pre-set geological knowledge base; The positions of lithological interfaces sorted by depth in the core visual feature subsequence are compared layer by layer with the theoretical positions of the stratigraphic interfaces at the corresponding depths in the standard stratigraphic column, and the interface position deviation is calculated. The mean amplitudes of the natural gamma curves, resistivity curves, and acoustic transit time curves sorted by depth in the geophysical feature subsequence are compared with the theoretical response value range of the corresponding lithology in the typical geophysical response mode, and the percentage of data points exceeding the theoretical response value range is counted. Based on the interface position deviation and the proportion of data points exceeding the theoretical response value range, combined with the preset confidence calculation rules, the geological data confidence mark is calculated. The geological data confidence mark includes the overall confidence level and the index of abnormal data location.

5. The integrated digital management system for the entire coal geological exploration process according to claim 1, characterized in that, The logic operation module performs synchronization fusion of the project progress feature sequence and the environmental safety feature sequence to generate a work process coordination degree marker, including the following steps: Establish a synchronous analysis time window with time as the horizontal axis and project progress and safety indicators as the vertical axis; Within the synchronous analysis time window, the curve of the working face advance distance changing with time in the engineering progress characteristic sequence is superimposed and analyzed with the curve of the roof displacement value changing with time in the environmental safety characteristic sequence to identify whether the roof displacement value undergoes a sudden change that exceeds the normal fluctuation range near the time point when the advance distance changes abruptly. Within the synchronous analysis time window, the tunnel cross-section shrinkage in the engineering progress characteristic sequence is correlated with the two-side convergence value in the environmental safety characteristic sequence to determine whether the tunnel cross-section shrinkage is mainly caused by the two-side convergence. Based on the results of overlay analysis and correlation analysis, the temporal and causal correlation strength between changes in project progress and changes in safety indicators is assessed, and the work process coordination degree marker is generated accordingly. The work process coordination degree marker includes the coordination level and the time period identifier of non-coordination events.

6. The integrated digital management system for the entire coal geological exploration process according to claim 1, characterized in that, The decision generation module generates exploration control parameter adjustment instructions and exploration operation path correction instructions based on preset decision logic, including the following steps: Receive the confidence level marker of the geological data, determine whether its overall confidence level is lower than the preset acceptable threshold, and if it is lower, start the process of generating exploration control parameter adjustment instructions; In the process of generating exploration control parameter adjustment instructions, based on the abnormal data location index in the geological data confidence mark, the specific drilling depth or exploration depth is located, and the drilling parameters or logging parameters that are being used or planned to be used near the depth are retrieved to generate adjustment values ​​for drilling pressure, rotation speed, mud pump volume or logging instrument transmission power, which are then packaged into the exploration control parameter adjustment instructions. The system receives the coordination level marker of the operation process and determines whether its coordination level is lower than the preset coordination threshold. If it is lower, the system initiates the exploration operation path correction instruction generation process. In the process of generating exploration operation path correction instructions, based on the time period identifier of the non-cooperative event in the operation process coordination degree mark, the engineering progress characteristics within the corresponding time period are traced back, and combined with the three-dimensional geological model, the extension direction of the tunnel or the advancement sequence of the working face are replanned in areas with low safety risks, and the exploration operation path correction instructions containing new coordinate point sets and construction time sequences are generated.

7. The integrated digital management system for the entire coal geological exploration process according to claim 6, characterized in that, The instruction execution module parses the exploration control parameter adjustment instruction and drives the corresponding exploration execution mechanism, including the following steps: The exploration control parameter adjustment command is parsed to extract the drilling equipment number to be adjusted, the target adjustment parameter type, and the specific adjustment value contained therein; The control signal containing the target adjustment parameter type and adjustment value is sent to the corresponding intelligent drilling rig control system. The intelligent drilling rig control system, based on the received control signal, drives its hydraulic system or motor system to adjust the drilling pressure or rotation speed of the drill bit to the specified value, and then sends back an adjustment confirmation signal.

8. The integrated digital management system for the entire coal geological exploration process according to claim 6, characterized in that, The instruction execution module parses the exploration operation path correction instruction and drives the corresponding exploration execution mechanism, including the following steps: The exploration operation path correction instruction is analyzed to extract the new set of roadway centerline coordinate points and construction sequence contained therein; The new set of centerline coordinate points and construction sequence of the tunnel are converted into a navigation path point sequence and work schedule that can be recognized by the tunneling equipment; The navigation path point sequence and work schedule are sent to the path planning controller of the automated tunneling machine; The path planning controller of the automated tunneling machine generates a motion trajectory to control the cutting head based on the received navigation path point sequence and work schedule, and drives the automated tunneling machine to perform tunneling operations along the new path and time sequence.

9. The integrated digital management system for the entire coal geological exploration process according to claim 3, characterized in that, The step of performing signal decomposition and reconstruction on the geophysical signal stream to separate the effective signal segments of the natural gamma logging curve, resistivity logging curve, and sonic transit time logging curve includes the following steps: The empirical mode decomposition algorithm is used to decompose the original geophysical signal stream at multiple scales to obtain a series of intrinsic mode function components. Calculate the sample entropy value of each intrinsic mode function component, and identify the components with sample entropy values ​​lower than a preset threshold as noise-dominant components and remove them; The remaining intrinsic mode function components are reconstructed to obtain the denoised geophysical signal; In the denoised geophysical signal, a bandpass filter is designed to separate the signal based on the inherent frequency characteristics of the natural gamma logging curve, resistivity logging curve and sonic transit time logging curve. Sliding window mean analysis is performed on the separated well logging curve signals to identify continuous segments with stable signal amplitudes and fluctuations within a preset range, which are then marked as valid signal segments. Align the effective signal segments of each logging curve according to the depth coordinates, and record the starting and ending depths of each effective signal segment.

10. The integrated digital management system for the entire coal geological exploration process according to claim 5, characterized in that, Based on the results of overlay analysis and correlation analysis, the assessment of the temporal and causal correlation between changes in project progress and changes in safety indicators includes the following steps: Within the synchronous analysis time window, the rate of change of the working face advance distance and the rate of change of the top plate displacement are sampled at fixed time intervals to form the advance rate of change sequence and the displacement rate of change sequence. Calculate the cross-correlation coefficient between the propulsion rate change sequence and the displacement rate change sequence, and use the maximum value of the cross-correlation coefficient as the time correlation strength index; A Granger causality test model was constructed with project progress characteristics as independent variables and safety indicators as dependent variables, and causality tests were conducted with multiple lag periods. When the test statistic exceeds the critical value corresponding to the significance level, it is determined that the change in project progress is a Granger cause of the change in safety indicators, and the strength of causal relationship is recorded as the value of the test statistic. The time-related correlation strength index and the causal correlation strength index are weighted and fused to obtain the comprehensive correlation strength; Based on the numerical range of the comprehensive correlation strength, the correlation strength level between changes in project progress and changes in safety indicators is determined, and the correlation strength level is divided into three levels: strong correlation, medium correlation and weak correlation.

Images