Intelligent planning method and system for goaf drilling path

Abstract

The invention relates to the technical field of drilling planning, and discloses an intelligent planning method and system for a goaf drilling path, and the method comprises the steps: carrying out the continuous wavelet transformation of a goaf structure feature sequence, obtaining the time-frequency energy distribution, converting the spectrum dispersion feature into a stability index, and obtaining a stability index; and meanwhile, integrating the time-frequency energy distribution spectrum to obtain a signal energy sequence, and comparing the signal energy sequence with a calibration threshold to obtain gap distribution. The method comprises the following steps: mapping gap distribution and stability indexes to a three-dimensional space grid of a goaf to obtain grid data, fusing gap attributes and stability quantized values to generate a geological situation map, identifying a drilling risk area and a feasible path interval according to the geological situation map, and connecting adjacent nodes in the feasible interval to obtain an initial drilling path; and correcting the trajectory by combining the spatial relationship between the initial path and the real-time working condition path, and finally obtaining a goaf drilling planning path. According to the method, the precision of goaf drilling path planning and the efficiency of risk area judgment can be improved.

Description

Technical Field

[0001] This invention relates to the field of drilling planning technology, and in particular to an intelligent planning method and system for drilling paths in goaf areas. Background Technology

[0002] Existing technologies struggle to accurately and comprehensively characterize the geological features of goaf areas, resulting in a lack of reliable data support for path planning. They are unable to effectively transform the structural characteristics of goaf areas into quantifiable stability indicators, accurately identify the void distribution within goaf areas, or establish a risk information system covering the entire goaf space. Consequently, planned drilling paths are ill-suited to the complex geological conditions of goaf areas, and inaccurate assessments of geological risks can lead to insufficient path rationality.

[0003] Meanwhile, existing technologies have significant limitations in the dynamic adjustment of drilling paths, failing to achieve real-time path optimization. Current technologies typically rely solely on the initially planned path for drilling operations, lacking an effective mechanism for capturing and correcting deviations between real-time operating conditions and the initial path. This makes it difficult to cope with the impact of changes in the geological environment or equipment operating errors during drilling, easily leading to deviations from the planned drilling path. This not only reduces drilling efficiency but may also cause safety hazards due to the path deviating into risk areas. Summary of the Invention

[0004] This invention provides an intelligent planning method and system for drilling paths in goaf areas, the main purpose of which is to solve the problems of insufficient accuracy in drilling path planning and low efficiency in risk area identification.

[0005] To achieve the above objectives, the present invention provides an intelligent planning method for drilling paths in goaf areas, comprising:

[0006] A continuous wavelet transform is performed on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and the spectral dispersion characteristics in the time-frequency energy distribution are transformed into the stability index of the goaf.

[0007] The time-frequency energy distribution is integrated by energy spectrum to obtain the signal energy sequence of the goaf, and the signal energy sequence is compared with the calibrated energy threshold to obtain the void distribution of the goaf;

[0008] The void distribution and the stability index are mapped to the three-dimensional spatial grid of the goaf to obtain the grid data of the goaf.

[0009] By integrating the porosity attributes and stability quantification values ​​of the grid data, a geological situation map of the goaf is obtained, and the drilling risk areas and feasible path intervals of the goaf are identified based on the geological situation map.

[0010] Using the drilling risk area as a constraint boundary, connect adjacent path nodes within the feasible path interval, and use the connected path segment as the initial drilling path of the goaf.

[0011] Based on the spatial relationship between the initial drilling path and the real-time working condition path, the initial drilling path is corrected to obtain the drilling planning path for the goaf.

[0012] In a preferred embodiment, performing continuous wavelet transform on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and converting the spectral dispersion characteristics in the time-frequency energy distribution into a stability index of the goaf, includes:

[0013] The structural feature sequence of the goaf is decomposed at multiple scales to obtain the wavelet coefficient matrix of the goaf.

[0014] The modulus maxima of the wavelet coefficient matrix are normalized to obtain the time-frequency energy distribution of the goaf.

[0015] Extract the main oscillation frequency sequence from the time-frequency energy distribution, and map the distribution dispersion of the main oscillation frequency sequence to a preset stability level range to obtain the stability index of the goaf.

[0016] In a preferred embodiment, the step of performing energy spectrum integration on the time-frequency energy distribution to obtain the signal energy sequence of the goaf, and comparing the signal energy sequence with a calibrated energy threshold to obtain the void distribution of the goaf, includes:

[0017] Integrating the time-frequency energy distribution along the frequency axis yields the energy sequence of the goaf.

[0018] The energy sequence is smoothed to obtain the filtered energy sequence of the goaf.

[0019] The filtered energy sequence is compared with a preset energy threshold, and the segments obtained from the comparison that are lower than the preset energy threshold are taken as the void distribution of the goaf.

[0020] In a preferred embodiment, mapping the void distribution and the stability index to a three-dimensional spatial grid of the goaf to obtain grid data of the goaf includes:

[0021] Obtain a three-dimensional mesh model of the goaf;

[0022] The continuous low-energy sections in the void distribution are assigned to the grid cells of the three-dimensional grid model to obtain the void cells of the goaf.

[0023] The stability index is assigned to the non-void region in the grid cell to obtain the stability distribution grid of the goaf.

[0024] By integrating the void cells and the stability distribution grid, the grid data of the goaf is obtained.

[0025] In a preferred embodiment, the process of fusing the porosity attributes and stability quantification values ​​of the grid data to obtain a geological situation map of the goaf, and identifying drilling risk areas and feasible path intervals in the goaf based on the geological situation map, includes:

[0026] Based on the void attributes and stability quantification values ​​in the grid data, the three-dimensional spatial grid of the goaf is divided into risk areas to obtain the absolute risk area and stability risk level area of ​​the goaf.

[0027] By spatially overlaying the absolute risk area with the stability risk level area, a geological situation map of the goaf is obtained.

[0028] The high-risk areas in the geological situation map are identified as drilling risk areas in the goaf.

[0029] The low-risk and medium-risk stability areas in the geological situation map are identified as feasible path intervals for the goaf.

[0030] In a preferred embodiment, the step of dividing the three-dimensional spatial grid of the goaf into risk zones based on the void attributes and stability quantification values ​​in the grid data to obtain the absolute risk zone and stability risk level zone of the goaf includes:

[0031] Based on the void properties in the grid data, the void units are divided into absolute risk areas of the goaf.

[0032] The stability quantification value of the non-void region is divided into risk levels to obtain the risk category of the non-void region;

[0033] Based on the risk category, the non-void areas are spatially aggregated to obtain the stability risk level areas of the goaf.

[0034] In a preferred embodiment, the step of connecting adjacent path nodes within the feasible path interval, using the drilling risk area as a constraint boundary, and using the connected path segment as the initial drilling path for the goaf includes:

[0035] Within the feasible path interval, path nodes are deployed, and the shortest path between the path nodes is marked.

[0036] The drilling risk areas in the shortest path are filtered out, and the filtering result is used as the initial drilling path for the goaf.

[0037] In a preferred embodiment, the step of correcting the initial drilling path based on the spatial relationship between the initial drilling path and the real-time working condition path to obtain the drilling planning path for the goaf includes:

[0038] Acquire the real-time position and orientation data of the drilling equipment in the goaf area, and calculate the deviation vector between the position and orientation data and the initial path;

[0039] The drilling posture of the drilling equipment at the next moment is dynamically adjusted according to the deviation vector to obtain the drilling planning path of the goaf.

[0040] In a preferred embodiment, the formula for calculating the deviation vector is:

[0041]

[0042] in: Let the deviation vector be... Let be the current spatial position vector of the device. Let the vector be the position vector of the nearest projected point on the initial drilling path. This is the attitude angle deviation vector. The weighting coefficients for the positions in the pose data. These are the pose weighting coefficients in the pose data. The weighting coefficient for the velocity deviation in the pose data. This is the velocity deviation vector.

[0043] To address the above problems, the present invention also provides an intelligent planning system for drilling paths in goaf areas, the system comprising:

[0044] The stability index module is used to perform continuous wavelet transform on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and to transform the spectral dispersion characteristics in the time-frequency energy distribution into the stability index of the goaf.

[0045] The void distribution module is used to perform energy spectrum integration on the time-frequency energy distribution to obtain the signal energy sequence of the goaf, and compare the signal energy sequence with the calibrated energy threshold to obtain the void distribution of the goaf.

[0046] The grid data module is used to map the void distribution and the stability index to the three-dimensional spatial grid of the goaf, so as to obtain the grid data of the goaf.

[0047] The path analysis module is used to fuse the void attributes and stability quantification values ​​of the grid data to obtain a geological situation map of the goaf, and to identify the drilling risk areas and feasible path intervals of the goaf based on the geological situation map.

[0048] The initial drilling path module is used to connect adjacent path nodes within the feasible path interval with the drilling risk area as the constraint boundary, and use the connected path segment as the initial drilling path of the goaf.

[0049] The drilling planning path module is used to correct the trajectory of the initial drilling path based on the spatial relationship between the initial drilling path and the real-time working condition path, so as to obtain the drilling planning path of the goaf.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. By performing continuous wavelet transform on the structural feature sequence of the goaf to obtain the time-frequency energy distribution, the spectral dispersion characteristics are transformed into stability indicators. At the same time, the void distribution is determined by comparing the energy spectrum integral with the threshold. Then, the two are mapped to a three-dimensional spatial grid and fused to generate a geological situation map. This can accurately identify drilling risk areas and feasible path intervals, so that the generation of the initial drilling path is based on comprehensive and quantitative geological data, effectively avoiding the blindness of path planning and improving the adaptability of the path to the actual geological conditions of the goaf.

[0052] 2. Based on the real-time position data of the drilling equipment, the deviation vector between the initial path and the actual position data is calculated. Then, the drilling position of the equipment is dynamically adjusted according to the deviation vector. The path deviation can be corrected in real time to ensure that the drilling path always conforms to the safety target, offset the impact of geological environment changes or equipment operation errors on the operation, reduce the probability of safety accidents caused by path deviation, improve the efficiency and quality of drilling operations, and ensure the stability and accuracy of the entire drilling process. Attached Figure Description

[0053] Figure 1 This is a flowchart illustrating an intelligent planning method for drilling paths in goaf areas, provided in an embodiment of the present invention.

[0054] Figure 2 A functional module diagram of an intelligent planning system for drilling paths in goaf areas provided in an embodiment of the present invention;

[0055] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0056] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0057] This application provides an intelligent planning method for drilling paths in goaf areas. The execution entity of this intelligent planning method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the intelligent planning method for drilling paths in goaf areas can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0058] Reference Figure 1 The diagram shown is a flowchart illustrating an intelligent planning method for drilling paths in goaf areas according to an embodiment of the present invention. In this embodiment, the intelligent planning method for drilling paths in goaf areas includes:

[0059] In this embodiment of the invention, when performing continuous wavelet transform on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and converting the spectral dispersion characteristics in the time-frequency energy distribution into a stability index of the goaf, the specific method is as follows:

[0060] The structural feature sequence of the goaf is decomposed at multiple scales to obtain the wavelet coefficient matrix of the goaf.

[0061] The modulus maxima of the wavelet coefficient matrix are normalized to obtain the time-frequency energy distribution of the goaf.

[0062] Extract the main oscillation frequency sequence from the time-frequency energy distribution, and map the distribution dispersion of the main oscillation frequency sequence to a preset stability level range to obtain the stability index of the goaf.

[0063] Specifically, the structural feature sequence of the goaf is convolved with the selected db4 wavelet basis function. During the operation, the structural feature sequence is decomposed step by step from low frequency to high frequency. Each decomposition yields approximation coefficients and detail coefficients at that scale. The approximation coefficients reflect the overall trend of the sequence, while the detail coefficients reflect the local fluctuations. The above convolution operation is repeated according to the preset decomposition scale (e.g., 5 layers). After each layer of decomposition, the corresponding approximation coefficients and detail coefficients are saved until all preset scales of decomposition are completed.

[0064] Specifically, the matrix containing non-negative moduli is traversed, and the magnitudes of all moduli in the matrix are compared. The largest moduli is identified and designated as the modulo maxima, which serves as a key reference for subsequent normalization. For each moduli in the matrix containing non-negative moduli, it is divided by the previously determined modulo maxima, ensuring precision in each division operation to obtain the normalized result for each moduli. At this point, the original moduli matrix is ​​converted into a normalized moduli matrix. Based on the multi-scale characteristics of wavelet transform, the elements in the normalized moduli matrix are rearranged according to the scale level at the time of decomposition and their corresponding time series positions, ensuring that the position of each element accurately corresponds to the information of the goaf structural feature sequence at a specific time and scale. Specifically, the frequency components corresponding to each time point in the time-frequency energy distribution are analyzed one by one, and the frequencies with the highest energy values ​​at each time point are selected. These highest energy frequencies selected at different time points are arranged in chronological order, forming the sequence of the main oscillation frequency sequence of the goaf. Determine the maximum and minimum values ​​in the master oscillation frequency sequence, and subtract the minimum value from the maximum value to obtain the range of the sequence. Then calculate the average value of all frequency values ​​in the sequence, and subtract the average value from each frequency value to obtain the deviation of each frequency value from the average value. Square each deviation, add up all the squared deviations, and divide by the number of frequency values ​​in the sequence to obtain the variance of the sequence. Finally, combine the range and variance to comprehensively reflect the degree to which each frequency value in the master oscillation frequency sequence deviates from the average level and the distribution range. This comprehensive result is the distribution dispersion of the master oscillation frequency sequence.

[0065] Furthermore, the approximate coefficients and detail coefficients obtained at all decomposition scales are arranged according to the decomposition order and scale level to form a two-dimensional matrix. This matrix is ​​the wavelet coefficient matrix of the goaf. Each element in the matrix corresponds to the decomposition information of the goaf structural feature sequence at a specific scale and specific location.

[0066] Furthermore, based on the rearranged normalized modulus matrix, a two-dimensional data chart is constructed with time as the horizontal axis, decomposition scale as the vertical axis, and normalized modulus as the numerical value. This two-dimensional data chart represents the time-frequency energy distribution of the goaf. Through this distribution, the energy changes of the goaf's structural characteristics at different times and scales can be clearly shown.

[0067] Furthermore, pre-defined stability level intervals are established. Based on geological data and drilling safety standards accumulated in goaf engineering practice, multiple different stability levels are defined, such as extremely high stability, high stability, medium stability, low stability, and extremely low stability. A corresponding distribution dispersion range is assigned to each stability level, and the dispersion range corresponding to each level constitutes a pre-defined stability level interval. The boundary values ​​of each interval are repeatedly verified to ensure accurate differentiation of different goaf stability states. Next, the distribution dispersion is mapped to the pre-defined stability level intervals to obtain the stability index. The distribution dispersion of the calculated master oscillation frequency sequence is compared with the boundary values ​​of each pre-defined stability level interval to determine which pre-defined stability level interval the distribution dispersion falls into. The stability level represented by that interval is the stability index of the goaf.

[0068] In summary, decomposing the original structural feature sequence into detailed information and overall trends at different scales provides core data for subsequent processing of wavelet coefficient matrices to obtain time-frequency energy distribution. This ensures that the subsequent time-frequency energy distribution can accurately reflect the subtle differences in the goaf structure, directly supporting the transformation of stability indicators and void distribution analysis. It is a key starting point for ensuring the accuracy of the entire drilling path planning data.

[0069] In summary, eliminating the magnitude differences of wavelet coefficients at different scales allows the obtained time-frequency energy distribution to more accurately reflect the energy change patterns of the goaf structure. This provides a reliable basis for extracting the stability index of the main oscillation frequency sequence and lays the foundation for obtaining the energy sequence by integrating along the frequency axis and identifying the void distribution, directly supporting the scientific nature of subsequent risk analysis and path planning.

[0070] In summary, transforming the abstract characteristics of time-frequency energy into stability quantification values ​​that can be directly used for risk assessment provides a precise basis for mapping stability indicators to three-dimensional grids and dividing areas into stability risk levels. This avoids potential safety hazards in path planning due to ambiguity in structural stability judgment and is a key risk quantification foundation supporting the construction of geological situation maps and drilling path safety planning.

[0071] In this embodiment of the invention, the step of performing energy spectrum integration on the time-frequency energy distribution to obtain the signal energy sequence of the goaf, and comparing the signal energy sequence with a calibrated energy threshold to obtain the void distribution of the goaf, is specifically used for:

[0072] Integrating the time-frequency energy distribution along the frequency axis yields the energy sequence of the goaf.

[0073] The energy sequence is smoothed to obtain the filtered energy sequence of the goaf.

[0074] The filtered energy sequence is compared with a preset energy threshold, and the segments obtained from the comparison that are lower than the preset energy threshold are taken as the void distribution of the goaf.

[0075] Specifically, starting from the initial frequency of the frequency range at that time point, the energy value corresponding to each frequency point is added to the energy value of the next frequency point in sequence until all frequency points at that time point are covered. After completing one accumulation, the total energy value corresponding to that time point is obtained.

[0076] Specifically, first determine the size of the sliding window used for smoothing. The window size needs to be set according to the density and fluctuation of data points in the energy sequence to ensure that the window can cover a sufficient number of data points to achieve a smoothing effect, while avoiding the loss of key features of the sequence due to an excessively large window. After selection, fix the window size for processing all subsequent data points.

[0077] Specifically, starting from the first data point in the filtered energy sequence, the energy value corresponding to each data point is extracted sequentially in chronological order. The extracted individual energy value is compared with a preset energy threshold. If the energy value is less than the preset energy threshold, the time position corresponding to the data point is marked as a potential gap point; if the energy value is greater than or equal to the preset energy threshold, the time position corresponding to the data point is marked as a non-gap point.

[0078] Furthermore, the total energy values ​​obtained from the above accumulation operation at each time point are arranged sequentially according to the time dimension. The arrangement process strictly follows the order from early to late time to ensure that each total energy value accurately corresponds to its corresponding time point. The final set of total energy values ​​arranged in chronological order is the energy sequence of the goaf.

[0079] Furthermore, starting from the first data point in the energy sequence, a sliding window covers the current data point and the number of adjacent data points corresponding to the window size. For example, if the window size is 3, the first window covers the 1st, 2nd, and 3rd data points, the second window covers the 2nd, 3rd, and 4th data points, and so on, until the window covers the last data point in the energy sequence. The values ​​of all energy data points contained within each sliding window are summed, and the sum is divided by the total number of data points in that window to obtain the average energy value corresponding to that window. This average energy value is used as the smoothed value for the data point at the middle position of the window. If the window starts at the beginning or end of the sequence and a middle point cannot be obtained, the starting or ending data point of the window is used as the position of the corresponding smoothed value. Following the original time order of the energy sequence, the average energy values ​​obtained after processing each sliding window are arranged sequentially to ensure that each smoothed value corresponds to the correct time position in the original sequence. The final set of average energy values ​​arranged in time order is the filtered energy sequence of the goaf.

[0080] Furthermore, after comparing each filtered energy sequence data point with the preset energy threshold, continuous segment identification is performed on the marking results. Adjacent time positions marked as potential void points are integrated into a continuous segment. Each such continuous segment represents the area within the goaf where voids may exist. Isolated potential void points that do not form continuous segments are excluded to avoid misjudgment. All identified continuous potential void segments are summarized, and the start and end time positions of each segment are determined. These summarized continuous segments together constitute a set reflecting the location and range of voids in the goaf; this set represents the void distribution within the goaf.

[0081] In summary, transforming dispersed energy information in the time and frequency domain into a one-dimensional energy sequence that can be directly used for analysis provides basic data for subsequent smoothing of the energy sequence and comparison with preset energy thresholds to determine the void distribution. This ensures that the void distribution identified later can accurately reflect the actual void situation in the goaf area and is an important data source to support subsequent risk area delineation and path planning.

[0082] In summary, eliminating noise interference in the original energy sequence and avoiding misjudging energy value fluctuations caused by noise as voids or non-void areas ensures that the void distribution obtained when comparing with the preset energy threshold can truly reflect the actual void range of the goaf. This provides accurate energy data support for subsequent grid data construction and risk area delineation, and directly affects the reliability of drilling path planning.

[0083] In summary, clearly defining the spatial range of cavities in the goaf from the denoised energy data provides a precise basis for mapping the void distribution to a three-dimensional grid and delineating absolute risk areas. This avoids drilling paths from entering dangerous areas due to fuzzy void identification and is a key data foundation for supporting the subsequent geological situation construction and safe path planning.

[0084] In this embodiment of the invention, the step of mapping the void distribution and the stability index to the three-dimensional spatial grid of the goaf to obtain the grid data of the goaf is specifically used for:

[0085] Obtain a three-dimensional mesh model of the goaf;

[0086] The continuous low-energy sections in the void distribution are assigned to the grid cells of the three-dimensional grid model to obtain the void cells of the goaf.

[0087] The stability index is assigned to the non-void region in the grid cell to obtain the stability distribution grid of the goaf.

[0088] By integrating the void cells and the stability distribution grid, the grid data of the goaf is obtained.

[0089] Specifically, a spatial coordinate system for the goaf is established, using the goaf boundary coordinates determined by field measurements as a reference. The origin, X-axis, Y-axis, and Z-axis directions of the coordinate system are set to ensure that the coordinate system accurately corresponds to the actual spatial location of the goaf. Based on the rock strata distribution information and goaf boundary parameters in the geological data, a complete three-dimensional model of the surrounding rock strata is first constructed. Then, based on the range of cavities inside the goaf determined by the mining engineering drawings and borehole core records, the cavity portion of the goaf is removed from the three-dimensional rock strata model, forming a preliminary three-dimensional model of the goaf.

[0090] Specifically, each continuous low-energy segment in the void distribution is extracted one by one. Based on the spatial coordinate range of the segment, grid cells whose spatial coordinate range is completely contained within the coordinate range of the continuous low-energy segment, as well as grid cells whose spatial coordinates partially overlap with the coordinate range of the continuous low-energy segment, are selected in the three-dimensional grid model. These selected grid cells are marked as cells to be assigned, ensuring that no grid cells associated with the continuous low-energy segment are missed.

[0091] Specifically, the stability indices of the acquired goaf are extracted, and the spatial range corresponding to each stability index is determined. This spatial range must be consistent with the spatial coordinate system of the 3D mesh model. By comparing the spatial coordinates of the stability index with the spatial coordinate identifiers of the non-void region mesh cells, the specific value of the stability index corresponding to each non-void region mesh cell is determined, ensuring that each non-void region mesh cell can be matched with a unique corresponding stability index. The matched stability index values ​​are then assigned to the corresponding non-void region mesh cells one by one. In the database of the 3D mesh model, a "stability index" attribute field is added to each non-void region mesh cell, and the corresponding stability index value is entered into this field. During the entry process, the correspondence between the mesh cell identifier and the stability index value must be repeatedly checked to avoid incorrect value assignment.

[0092] Specifically, the unique identifiers and corresponding "is it a gap?" attributes of all grid cells are extracted from the gap cell database. Simultaneously, the unique identifiers and corresponding stability index attributes of all grid cells are extracted from the stability distribution grid database. These two sets of data are initially correlated based on the unique identifiers of the grid cells, forming a preliminary correlation data table containing both attributes for each grid cell. The grid cell attributes in the preliminary correlation data table are then validated for completeness. Each grid cell is checked to ensure it contains both the "is it a gap?" and "stability index" attributes. If a grid cell is found to be missing either attribute, its source data is traced to supplement the missing attribute information, ensuring that the attribute information of all grid cells is complete.

[0093] Furthermore, the preliminary three-dimensional model of the goaf is divided into grids. According to the preset grid size and density, the three-dimensional space of the goaf is evenly divided into multiple regular cubic grid units. Each grid unit has clear spatial coordinates and dimensions. At the same time, it is ensured that the grid unit can completely cover the cavity part of the goaf and the surrounding rock strata area, and finally a three-dimensional grid model of the goaf with complete structure and accurate coordinates is obtained.

[0094] Furthermore, the spatial affiliation of the grid cells marked as unassigned cells is confirmed. It is determined whether the core coordinates of each unassigned cell fall within the spatial coordinate range of the corresponding continuous low-energy segment. If the core coordinates are within the range, the unassigned cell is determined to belong to the grid cell corresponding to the continuous low-energy segment. If the core coordinates are not within the range, the unassigned cell is excluded to avoid misassigning irrelevant grid cells.

[0095] All confirmed grid units are aggregated and classified according to their corresponding continuous low-energy sections. The information of the continuous low-energy section corresponding to each grid unit is clarified. The set of grid units that have been classified and marked and confirmed to belong to continuous low-energy sections is the void unit of the goaf.

[0096] Furthermore, after assigning stability index values ​​to all grid cells in non-void regions, the attributes of the three-dimensional grid model are integrated to ensure that the attribute information of each grid cell is complete and searchable. At this point, the three-dimensional grid model containing the distribution information of stability indexes in non-void regions is the stability distribution grid of the goaf.

[0097] Furthermore, the verified grid cell data containing complete attribute information is rearranged according to the three-dimensional spatial coordinate order, and a spatial location index is added to the data so that the attribute information of each grid cell can accurately correspond to its position in three-dimensional space. The final complete dataset containing the spatial location of all grid cells, whether it is a void, and stability indicators is the grid data of the goaf.

[0098] In summary, providing a concrete three-dimensional spatial carrier for the void distribution and stability indicators of goaf areas allows the originally abstract void segments and stability quantification values ​​to be accurately assigned to corresponding grid cells. This supports subsequent key steps such as grid data integration, geological situation map construction, and path node layout, ensuring that the entire drilling path planning process is based on the real spatial structure of the goaf area and avoiding planning deviations caused by missing spatial information. This is the core foundation for ensuring the spatial accuracy of drilling path planning.

[0099] In summary, transforming the void distribution corresponding to the abstract low-energy signal into specific, locatable, and identifiable units in a three-dimensional grid provides accurate void spatial coordinates for subsequent delineation of absolute risk areas and generation of grid data by integrating stability indicators. This ensures that subsequent geological situation maps accurately reflect the spatial location of void-type risks and avoids misjudgment of drilling paths due to ambiguous void distribution. It is the core foundation supporting the spatial accuracy of risk area delineation and path planning.

[0100] In summary, specific stability quantification attributes are assigned to non-void regions within the 3D grid. Together with void units, these attributes form a complete grid data foundation that includes void risk and structural stability risk. This ensures that when subsequent geological situation maps are generated by fusing grid attributes, the risk gradient of non-void regions can be accurately reflected. This provides a basis for judging the stability of non-void regions for subsequent identification of drilling risk areas and feasible path intervals, directly supporting the scientific and accurate nature of path planning.

[0101] In summary, merging void cells reflecting cavity risk and stability distribution grids reflecting structural risk in non-void areas into a unified data volume provides a complete and interconnected three-dimensional spatial data foundation for the subsequent generation of geological situation maps by fusing grid attributes. This avoids analytical biases caused by the dispersion of the two types of risk data and directly supports the accurate identification of subsequent drilling risk areas and feasible path intervals. It is a key data carrier connecting geological data processing and path planning decisions.

[0102] In this embodiment of the invention, when fusing the porosity attributes and stability quantification values ​​of the grid data to obtain a geological situation map of the goaf, and identifying the drilling risk area and feasible path interval of the goaf based on the geological situation map, it is specifically used for:

[0103] Based on the void attributes and stability quantification values ​​in the grid data, the three-dimensional spatial grid of the goaf is divided into risk areas to obtain the absolute risk area and stability risk level area of ​​the goaf.

[0104] By spatially overlaying the absolute risk area with the stability risk level area, a geological situation map of the goaf is obtained.

[0105] The high-risk areas in the geological situation map are identified as drilling risk areas in the goaf.

[0106] The low-risk and medium-risk stability areas in the geological situation map are identified as feasible path intervals for the goaf.

[0107] Specifically, the spatial continuity of the initially screened risk area units to be classified is checked. Adjacent grid units that are all marked as risk area units to be classified are merged to form continuous blocks. At the same time, grid units that exist in isolation and are not adjacent to other risk area units to be classified are removed to avoid regional division errors caused by isolated units. The final continuous blocks formed by merging are the absolute risk areas of the goaf. The stability quantification values ​​of all non-void attribute grid units in the goaf grid data are extracted. According to the safety standards and geological stability requirements of the goaf drilling project, fixed risk level division boundaries are set. For example, the stability quantification values ​​are divided into three intervals: high stability, medium stability, and low stability. Each interval corresponds to a risk level. The high stability interval corresponds to the low risk level, the medium stability interval corresponds to the medium risk level, and the low stability interval corresponds to the high risk level.

[0108] Specifically, the spatial data of the absolute risk area is imported into a professional spatial overlay processing tool to generate a 3D spatial layer of the absolute risk area. This layer must clearly mark all grid cells belonging to the absolute risk area and distinguish them with specific visual identifiers, while retaining the spatial coordinate information of each grid cell to ensure that the layer accurately reflects the spatial distribution of the absolute risk area. Similarly, the spatial data of the stability risk level area is imported into the same spatial overlay processing tool to generate a 3D spatial layer of the stability risk level area. Different visual identifiers are assigned to the grid cells in this layer according to different risk levels, and the risk level information and spatial coordinates of each grid cell are associated to ensure that the layer can fully present the spatial differences in stability risk levels.

[0109] Specifically, the spatial boundaries of the selected high-risk areas are confirmed. The coordinate query function of the geological situation map is used to extract the starting X-axis, Y-axis, and Z-axis coordinates and the ending X-axis, Y-axis, and Z-axis coordinates of each high-risk area to determine the specific spatial range of each high-risk area. At the same time, it is checked whether these areas have spatial overlap. If there is overlap, they are merged into a continuous area. Finally, the spatial range and attribute information of all high-risk areas are summarized, and the resulting set of areas is the drilling risk area of ​​the goaf.

[0110] Furthermore, the stability quantification value of each non-void attribute grid cell is compared with the set risk level division boundary to determine which risk level range the stability quantification value of the grid cell falls into, thereby determining the risk level corresponding to the grid cell. Subsequently, grid cells with the same risk level are aggregated according to their spatial location, so that grid cells with the same risk level form a continuous area. These continuous areas with different risk levels together constitute the stability risk level area of ​​the goaf.

[0111] Furthermore, in the spatial overlay processing tool, the three-dimensional spatial layer of the absolute risk area and the three-dimensional spatial layer of the stability risk level area are overlaid to make the spatial coordinates of the two layers completely aligned. After overlay, the tool will automatically merge the information of the two layers. For grid cells with overlapping spatial positions, the visual identifiers and attributes of the absolute risk area are retained first. For non-overlapping grid cells, the visual identifiers and attributes of their original layers are retained. The final three-dimensional image containing the complete spatial distribution and attribute information of the absolute risk area and the stability risk level area is the geological situation map of the goaf.

[0112] Furthermore, the geological status map of the goaf is reviewed again to identify the visual identifiers for low-risk and medium-risk stability areas. Low-risk stability areas may be preset to a green hue or a green fill pattern, while medium-risk stability areas may be preset to a yellow hue or a yellow fill pattern. Based on these two visual identifiers, areas meeting the criteria are identified one by one on the geological status map to ensure that no low-risk or medium-risk stability areas are overlooked. The spatial extent of each identified low-risk and medium-risk stability area is extracted using coordinate lookup, confirming the spatial location and extent of each area. Then, the spatial extent and attribute information of the low-risk and medium-risk stability areas are integrated, removing any high-risk area segments that may be included, ensuring that the integrated area only contains low-risk and medium-risk stability areas. The final integrated area set represents the feasible path range of the goaf.

[0113] In summary, by deeply integrating two key types of information—absolute risk of undrillable cavities and stability gradient risk of non-cavity areas—a risk visualization carrier covering the entire goaf space is formed. This not only avoids decision-making blind spots caused by single risk data, but also provides a unique and reliable basis for accurate identification of drilling risk areas and definition of feasible path intervals through clear risk levels. It directly supports the scientific and safe generation of the initial drilling path and is a key link connecting geological data processing and path planning decisions.

[0114] In summary, by integrating panoramic geological information of absolute risk areas and stability risk level areas, dangerous areas that need to be strictly avoided are accurately extracted. This provides a clear prohibition range for subsequent path node layout and initial drilling path generation based on risk areas as constraints. It directly avoids safety accidents or path failures caused by accidentally entering high-risk areas during the drilling process, and is the core prerequisite for ensuring the scientific nature and safety of the entire drilling path planning.

[0115] In summary, by accurately delineating safe and drilling-ready areas from geological situation maps that integrate both types of risk information, the safety hazards of absolute and high-risk areas are eliminated. This provides clear options for subsequent deployment of path nodes and connection to form the initial drilling path within feasible limits. It directly supports the rationality and operability of the initial drilling path generation and is a key link in bridging geological risk analysis and actual path planning, ensuring the safety and efficiency of drilling path planning.

[0116] In this embodiment of the invention, when dividing the three-dimensional spatial grid of the goaf into risk areas based on the void attributes and stability quantification values ​​in the grid data to obtain the absolute risk area and stability risk level area of ​​the goaf, it is specifically used for:

[0117] Based on the void properties in the grid data, the void units are divided into absolute risk areas of the goaf.

[0118] The stability quantification value of the non-void region is divided into risk levels to obtain the risk category of the non-void region;

[0119] Based on the risk category, the non-void areas are spatially aggregated to obtain the stability risk level areas of the goaf.

[0120] Specifically, void units whose spatial locations have been verified are grouped according to their spatial adjacency. It is determined whether the spatial coordinate ranges of two void units overlap or are adjacent. If so, they are grouped into the same group until all void units are grouped, forming multiple continuous blocks composed of adjacent void units. Each block represents a concentrated void area in the goaf.

[0121] Specifically, based on the safety specifications and geological stability assessment standards for drilling projects in goaf areas, and combined with the range of arranged stability quantification values, fixed risk level division boundaries are set. For example, the stability quantification values ​​are divided into three intervals: high stability interval corresponding to low risk, medium stability interval corresponding to medium risk, and low stability interval corresponding to high risk. The boundary value of each interval needs to be determined with reference to the stability data of historical successful drilling cases to ensure that the division boundaries can accurately reflect the stability levels corresponding to different risk levels. The stability quantification value of each non-void area grid cell is compared one by one with the set risk level division boundaries. If the stability quantification value of a grid cell falls within the high stability interval, the risk category of the grid cell is determined to be low risk; if it falls within the medium stability interval, it is determined to be medium risk; and if it falls within the low stability interval, it is determined to be high risk. After each comparison of a grid cell is completed, its corresponding risk category is recorded to avoid confusion in the judgment results.

[0122] Specifically, the extracted low-risk grid cells are judged for adjacency based on their spatial location. If the spatial coordinates of two low-risk grid cells overlap or are adjacent in at least one of the three dimensions (X-axis, Y-axis, and Z-axis), these two grid cells are grouped together. This operation is repeated until all low-risk grid cells are grouped, forming multiple continuous spatial blocks composed of adjacent low-risk grid cells. These continuous spatial blocks are the basic units of the low-risk stability region. Following the same procedure, grid cells identified as medium-risk and high-risk in the non-gaps region are extracted separately. The complete three-dimensional spatial coordinates of each grid cell are recorded. Adjacency judgment is then used to group adjacent medium-risk grid cells together to form continuous spatial blocks of medium-risk grid cells; adjacent high-risk grid cells are grouped together to form continuous spatial blocks of high-risk grid cells. During this process, it is ensured that the grouping of medium-risk and high-risk grid cells does not overlap or become confused.

[0123] Furthermore, the spatial extent of each continuous area block is integrated to determine the overall starting and ending coordinates of each area block, clarifying its complete coverage in the three-dimensional space of the goaf. Then, the spatial extent of all continuous area blocks and the corresponding void unit information are summarized. The set of areas formed by these summarized continuous area blocks is the absolute risk area of ​​the goaf.

[0124] Furthermore, after completing the risk category determination of all non-gaps region grid cells, the determination results are classified and summarized, and the grid cells determined to be low-risk, medium-risk, and high-risk are respectively classified into three categories. At the same time, the number of grid cells in each category and the distribution of the corresponding stability quantification value are checked to ensure that the grid cells in each risk category meet the corresponding stability interval requirements. The final set of three risk cell categories is the risk category of the non-gaps region.

[0125] Furthermore, the continuous spatial blocks of low-risk, medium-risk, and high-risk are spatially integrated. After the continuous spatial blocks of each risk category are integrated, one or more complete spatial regions covering all grid units of that risk category are formed. The overall three-dimensional spatial coordinate range of each region is defined. Then, all the complete spatial regions of low-risk, medium-risk, and high-risk are summarized. The set of these spatial regions of different risk levels is the stability risk level region of the goaf.

[0126] In summary, by focusing on the void properties in the grid data, the safety level of each void cell is accurately determined, and cells that meet the absolute risk criteria are clearly classified as absolute risk areas. This classification process transforms abstract geological data into concrete spatial identifiers, providing a clear and actionable basis for subsequent filtering of drilling risk areas in the shortest path.

[0127] In summary, this division provides a precise priority basis for subsequent path planning. When setting up feasible path intervals, low-risk non-gap areas can be prioritized, while high-risk non-gap areas can be avoided. Medium-risk areas can be used cautiously based on actual working conditions, avoiding safety hazards or resource waste caused by indiscriminate planning.

[0128] In summary, the geological situation map serves as the foundation for subsequent identification of drilling risk areas and feasible path intervals. The generated stability risk level areas are overlaid with absolute risk areas to jointly constitute the risk stratification structure of the geological situation map. This accurately delineates the range of feasible paths, and the aggregated stability risk level areas directly define the drilling priorities for different regions: low-risk areas can be considered as priority path intervals, medium-risk areas require careful evaluation, and high-risk areas must be avoided. This provides clear constraints for subsequent connection of path nodes and generation of initial drilling paths.

[0129] In this embodiment of the invention, when the drilling risk area is used as a constraint boundary, adjacent path nodes within the feasible path interval are connected, and the resulting path segment is used as the initial drilling path for the goaf, the specific usage is as follows:

[0130] Within the feasible path interval, path nodes are deployed, and the shortest path between the path nodes is marked.

[0131] The drilling risk areas in the shortest path are filtered out, and the filtering result is used as the initial drilling path for the goaf.

[0132] Specifically, according to the set distribution interval, path nodes are laid out one by one in the three-dimensional space of the feasible path interval. Each path node is assigned a unique identification number and the precise three-dimensional coordinates of each node are recorded. From the laid-out path nodes, one node is selected as the starting reference node. Then, the spatial straight-line distance between the starting reference node and all other nodes is calculated in turn. The calculation is based on the three-dimensional coordinates of the two nodes. Through intuitive comparison of spatial distance, the node with the shortest distance to the starting reference node is determined. The line connecting these two nodes is marked as the candidate shortest path segment, and the length of the path segment and the identification numbers of the two nodes are recorded.

[0133] Specifically, each segment of the shortest path is spatially compared with the drilling risk area. Each segment's spatial extent overlaps with the risk area. Specifically, the coordinates of any point on the segment are checked against the boundary coordinates of the risk area. If part or all of a segment's spatial extent falls within the risk area, it is marked as a risky segment requiring filtering. If a segment does not enter the risk area at all, it is marked as a retained segment. The risky segments are further processed by checking if their start and end nodes are outside the risk area. If both nodes are outside the risk area, and only the middle part of the segment crosses it, the overlapping portion is deleted, and the start and end nodes are reconnected to form a new risk-free segment. If either the start or end node is within the risk area, the segment is deleted, and the reason for deletion and the corresponding node information are recorded.

[0134] Furthermore, using the endpoint node of the marked candidate shortest path segment as the new reference node, the above calculation and marking process is repeated, that is, the spatial straight-line distance between the new reference node and the remaining unassociated nodes is calculated, the node corresponding to the shortest distance is determined, and the new candidate shortest path segment is marked, until all path nodes are included in the association range of the candidate shortest path segments. At this time, all marked candidate shortest path segments together constitute the shortest path between path nodes.

[0135] Furthermore, all path segments marked as reserved and regenerated risk-free path segments are collected. Following the node connection order of the original shortest path, these path segments are connected sequentially to ensure that the node coordinates of adjacent path segments can be accurately connected to form a complete continuous path. At the same time, it is checked whether the entire continuous path completely avoids the drilling risk area and covers the key nodes within the feasible path interval. The final complete continuous path is the initial drilling path of the goaf.

[0136] In general, during actual drilling, equipment may deviate from its path due to changes in geological conditions in the goaf and equipment vibration. Obtaining real-time position and orientation data of drilling equipment in the goaf can capture the core status of the equipment, such as position, attitude, and speed, in real time. This provides real and continuous field data support for subsequent judgment on whether the path has deviated, and avoids the accumulation of drilling errors caused by relying on static initial paths.

[0137] In summary, by accurately identifying and removing portions of the shortest path that overlap with drilling risk areas, the pre-planned shortest path is purified. This provides a reliable initial basis for subsequent real-time monitoring of drilling equipment posture, dynamic adjustment of drilling posture, and generation of the final drilling planning path. It ensures that the entire drilling operation proceeds within a safe framework, balancing drilling efficiency and safety risks. This guarantees that the invention can be effectively applied to drilling practices in goaf areas, improving the success rate and safety of related projects such as goaf resource development or geological exploration.

[0138] In this embodiment of the invention, when the initial drilling path is corrected based on the spatial relationship between the initial drilling path and the real-time working condition path to obtain the drilling planning path for the goaf, it is specifically used for:

[0139] Acquire the real-time position and orientation data of the drilling equipment in the goaf area, and calculate the deviation vector between the position and orientation data and the initial path;

[0140] The drilling posture of the drilling equipment at the next moment is dynamically adjusted according to the deviation vector to obtain the drilling planning path of the goaf.

[0141] Specifically, the system captures the position and attitude information of the equipment in three-dimensional space in real time. Position information includes the X, Y, and Z axis coordinates of the equipment's core components, while attitude information includes the angle between the equipment's drilling direction and a preset reference direction. This real-time captured position and attitude information is integrated to form the real-time position and attitude data of the drilling equipment in the goaf. From the acquired initial drilling path data of the goaf, the system extracts the complete three-dimensional coordinate sequence of the path, clarifying the X, Y, and Z axis coordinates of each point on the initial drilling path, as well as the overall trend of the path. Simultaneously, it determines the preset attitude reference of the initial drilling path, i.e., the standard drilling direction corresponding to each point on the path.

[0142] Specifically, the calculated deviation vector is first analyzed to separate position deviation data, attitude angle deviation data, and velocity deviation data. The specific dimensional deviation value corresponding to each data point is then determined. For example, the deviation magnitudes of the X, Y, and Z axes in the position deviation data; the angle deviation value between the drilling direction and the standard direction in the attitude angle deviation data; and the difference between the actual velocity and the preset velocity in the velocity deviation data. Based on the analyzed position deviation data, the adjustment direction and magnitude of the drilling equipment's spatial position at the next moment are determined. If there is a positive deviation in the X-axis direction, the equipment is controlled to move a corresponding distance in the negative X-axis direction to offset the deviation. If there is a deviation in the Y-axis or Z-axis, the position in the corresponding axis direction is adjusted according to the same logic to ensure that the equipment's position at the next moment is closer to the nearest projection point of the initial path, reducing position deviation.

[0143] Furthermore, the position information in the real-time drilling equipment's pose data is compared with the three-dimensional coordinate sequence of the initial drilling path to find the point on the initial drilling path closest to the equipment's current position. This point is the closest projection point of the equipment's current position on the initial drilling path. The three-dimensional coordinates of this projection point are recorded, and the differences between the equipment's current position coordinates and the projection point coordinates in the X, Y, and Z axes are calculated. These differences together constitute the position deviation data. Next, the attitude information in the real-time drilling equipment's pose data is compared with the preset attitude reference of the initial drilling path to calculate the angle difference between the equipment's current drilling direction and the standard drilling direction at the corresponding projection point. This difference is the attitude angle deviation data. At the same time, the difference between the equipment's current drilling speed and the preset speed of the initial drilling path is obtained as the speed deviation data. Then, the position deviation data, attitude angle deviation data, and speed deviation data are combined in a fixed order to form a comprehensive deviation data set, which is the deviation vector between the pose data and the initial path.

[0144] Furthermore, based on the attitude angle deviation data, the drilling direction of the drilling equipment is adjusted. If there is an angular deviation between the current drilling direction and the preset attitude reference of the initial path, the attitude adjustment mechanism of the equipment is activated, and the drilling components of the equipment are rotated to deflect the drilling direction toward the preset attitude reference direction until the deviation angle is reduced to meet the drilling accuracy requirements, ensuring that the drilling direction of the equipment at the next moment is consistent with the direction of the initial path. Combining the speed deviation data, the drilling speed of the drilling equipment is adjusted. If the current speed is higher than the preset speed, the power output of the equipment is reduced to slow down the drilling speed; if the current speed is lower than the preset speed, the power output is increased to increase the drilling speed, so that the equipment speed matches the preset speed requirements of the initial path. Then, the equipment state after the position, attitude, and speed adjustment is recorded as the drilling posture at the next moment. In the above manner, the real-time posture data of the drilling equipment is continuously acquired, the deviation vector is calculated, and the drilling posture at the next moment is dynamically adjusted. The spatial coordinates corresponding to the adjusted drilling posture at each moment are connected sequentially in time to form a continuous path trajectory, which is the drilling planning path of the goaf.

[0145] In summary, real-time capture of the deviation between the actual drilling trajectory and the initial planned path provides data for adjusting the drilling posture of the equipment at the next moment based on the deviation vector, and obtaining a precise drilling planning path. This avoids safety risks caused by path deviation due to changes in the geological environment or equipment errors, and is a key dynamic control basis for ensuring the accuracy and safety of the drilling process.

[0146] In summary, real-time correction of deviations between the initial drilling path and actual working conditions offsets the impact of geological environment changes or equipment operation errors on the path, ensuring that the final drilling path always aligns with the planning objectives of safety and efficiency, and avoiding drilling accidents or mission failures due to path deviations.

[0147] In this embodiment of the invention, when the initial drilling path is corrected based on the spatial relationship between the initial drilling path and the real-time working condition path to obtain the drilling planning path for the goaf, it is specifically used for:

[0148] In this embodiment of the invention, the formula for calculating the deviation vector is specifically used for:

[0149]

[0150] in: Let the deviation vector be... Let be the current spatial position vector of the device. Let the vector be the position vector of the nearest projected point on the initial drilling path. This is the attitude angle deviation vector. The weighting coefficients for the positions in the pose data. These are the pose weighting coefficients in the pose data. The weighting coefficient for the velocity deviation in the pose data. This is the velocity deviation vector.

[0151] Specifically, the deviation vector is obtained by calculating the current spatial position vector of the equipment, the position vector of the nearest projection point of the current point on the initial drilling path, the attitude angle deviation vector, and the velocity deviation vector, and then combining the weighting coefficients of position, attitude, and velocity deviation according to a specific calculation method. The current spatial position vector of the equipment is obtained by the pose acquisition device on the drilling equipment capturing the equipment's position information in three-dimensional space in real time, including the X-axis, Y-axis, and Z-axis coordinates of the equipment's core components, and then integrating this information into a vector. The position vector of the nearest projection point of the current point on the initial drilling path is obtained by comparing the current spatial position vector of the equipment with the three-dimensional coordinate sequence of the initial drilling path, finding the point on the initial drilling path closest to the current position of the equipment, and recording the three-dimensional coordinates of that point to form a vector. The attitude angle deviation vector is obtained by comparing the current attitude information of the equipment with the preset attitude reference of the initial drilling path, calculating the angle difference between the current drilling direction of the equipment and the standard drilling direction at the corresponding projection point, and forming a vector based on this difference. The position weighting coefficient is derived from the position accuracy requirements of goaf drilling projects, combined with the analysis of the impact of position deviation on drilling results in historical drilling data, and is a pre-set fixed value used to measure the importance of position deviation in the total deviation. The attitude weighting coefficient is derived from the influence of the drilling equipment's drilling direction on the accuracy of the drilling path, referring to past cases of attitude deviation leading to path deviation in drilling operations, and is a pre-set fixed value used to measure the importance of attitude deviation in the total deviation. The speed deviation weighting coefficient is derived from the impact of drilling speed on drilling efficiency and path stability, by analyzing the changes in the drilling path under different speed deviations, and is a pre-set fixed value used to measure the importance of speed deviation in the total deviation. The speed deviation vector is derived from the difference between the current drilling speed of the equipment and the preset speed of the initial drilling path, and is a vector formed based on this difference.

[0152] Furthermore, the formula comprehensively considers the deviation between the current spatial position of the drilling equipment and the position of the nearest projection point on the initial drilling path, the deviation between the current attitude of the equipment and the preset attitude, and the deviation between the current speed of the equipment and the preset speed. By assigning corresponding weight coefficients to different deviations, a deviation vector that can comprehensively reflect the degree of deviation between the current state of the equipment and the initial drilling path is calculated. This provides accurate data for the subsequent dynamic adjustment of the drilling posture of the drilling equipment, ensuring that the adjusted posture of the equipment can better fit the initial drilling path and guaranteeing that the drilling operation is carried out in the planned direction.

[0153] In summary, with fixed weighting coefficients for position, attitude, and velocity deviation, if the difference between the current spatial position vector of the equipment and the position vector of the nearest projection point on the initial drilling path increases (i.e., the actual position of the equipment deviates further from the initial path projection point), the value of the deviation vector will increase; conversely, if this difference decreases, the value of the deviation vector will decrease. When the attitude angle deviation vector increases—that is, the angle deviation between the equipment's drilling direction and the standard direction increases—the value of the deviation vector will increase accordingly, assuming the attitude weighting coefficient remains unchanged; conversely, if the attitude angle deviation vector decreases, the value of the deviation vector will also decrease. If the velocity deviation vector increases—that is, the difference between the actual drilling speed and the preset speed increases—the value of the deviation vector will increase, assuming the velocity deviation weighting coefficient remains fixed; conversely, if the velocity deviation vector decreases, the value of the deviation vector will decrease. When a certain weight coefficient increases, the influence of the corresponding deviation factor on the deviation vector will increase. If the deviation value of the deviation factor remains unchanged, the value of the deviation vector will increase with the increase of the weight coefficient. Conversely, when the weight coefficient decreases, the influence of the corresponding deviation factor on the deviation vector will weaken, and the value of the deviation vector will decrease accordingly.

[0154] like Figure 2 The diagram shown is a functional block diagram of an intelligent planning system for drilling paths in goaf areas provided in an embodiment of the present invention.

[0155] The intelligent planning system 100 for drilling paths in goaf areas described in this invention can be installed in an electronic device. Depending on the functions implemented, the intelligent planning system 100 may include a stability index module 101, a void distribution module 102, a grid data module 103, a path analysis module 104, an initial drilling path module 105, and a drilling planning path module 106. The modules described in this invention can also be called units, referring to a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0156] In this embodiment, the functions of each module / unit are as follows:

[0157] The stability index module is used to perform continuous wavelet transform on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and to transform the spectral dispersion characteristics in the time-frequency energy distribution into the stability index of the goaf.

[0158] The void distribution module is used to perform energy spectrum integration on the time-frequency energy distribution to obtain the signal energy sequence of the goaf, and compare the signal energy sequence with the calibrated energy threshold to obtain the void distribution of the goaf.

[0159] The grid data module is used to map the void distribution and the stability index to the three-dimensional spatial grid of the goaf, so as to obtain the grid data of the goaf.

[0160] The path analysis module is used to fuse the void attributes and stability quantification values ​​of the grid data to obtain a geological situation map of the goaf, and to identify the drilling risk areas and feasible path intervals of the goaf based on the geological situation map.

[0161] The initial drilling path module is used to connect adjacent path nodes within the feasible path interval with the drilling risk area as the constraint boundary, and use the connected path segment as the initial drilling path of the goaf.

[0162] The drilling planning path module is used to correct the trajectory of the initial drilling path based on the spatial relationship between the initial drilling path and the real-time working condition path, so as to obtain the drilling planning path of the goaf.

[0163] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0164] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0165] Furthermore, the functional modules 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 unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0166] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0167] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0168] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. An intelligent planning method for drilling paths in goaf areas, characterized in that, The method includes: A continuous wavelet transform is performed on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and the spectral dispersion characteristics in the time-frequency energy distribution are transformed into the stability index of the goaf. The time-frequency energy distribution is integrated by energy spectrum to obtain the signal energy sequence of the goaf, and the signal energy sequence is compared with the calibrated energy threshold to obtain the void distribution of the goaf; The void distribution and the stability index are mapped to the three-dimensional spatial grid of the goaf to obtain the grid data of the goaf. By integrating the porosity attributes and stability quantification values ​​of the grid data, a geological situation map of the goaf is obtained, and the drilling risk areas and feasible path intervals of the goaf are identified based on the geological situation map. Using the drilling risk area as a constraint boundary, connect adjacent path nodes within the feasible path interval, and use the connected path segment as the initial drilling path of the goaf. Based on the spatial relationship between the initial drilling path and the real-time working condition path, the initial drilling path is corrected to obtain the drilling planning path for the goaf.

2. The intelligent planning method for drilling paths in goaf areas as described in claim 1, characterized in that, The step of performing continuous wavelet transform on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and converting the spectral dispersion characteristics in the time-frequency energy distribution into a stability index of the goaf, includes: The structural feature sequence of the goaf is decomposed at multiple scales to obtain the wavelet coefficient matrix of the goaf. The modulus maxima of the wavelet coefficient matrix are normalized to obtain the time-frequency energy distribution of the goaf. Extract the main oscillation frequency sequence from the time-frequency energy distribution, and map the distribution dispersion of the main oscillation frequency sequence to a preset stability level range to obtain the stability index of the goaf.

3. The intelligent planning method for drilling paths in goaf areas as described in claim 1, characterized in that, The step of performing energy spectrum integration on the time-frequency energy distribution to obtain the signal energy sequence of the goaf, and comparing the signal energy sequence with a calibrated energy threshold to obtain the void distribution of the goaf, includes: Integrating the time-frequency energy distribution along the frequency axis yields the energy sequence of the goaf. The energy sequence is smoothed to obtain the filtered energy sequence of the goaf. The filtered energy sequence is compared with a preset energy threshold, and the segments obtained from the comparison that are lower than the preset energy threshold are taken as the void distribution of the goaf.

4. The intelligent planning method for drilling paths in goaf areas as described in claim 1, characterized in that, The process of mapping the void distribution and the stability index to a three-dimensional spatial grid of the goaf to obtain the grid data of the goaf includes: Obtain a three-dimensional mesh model of the goaf; The continuous low-energy sections in the void distribution are assigned to the grid cells of the three-dimensional grid model to obtain the void cells of the goaf. The stability index is assigned to the non-void region in the grid cell to obtain the stability distribution grid of the goaf. By integrating the void cells and the stability distribution grid, the grid data of the goaf is obtained.

5. The intelligent planning method for drilling paths in goaf areas as described in claim 1, characterized in that, The process of fusing the porosity attributes and stability quantification values ​​of the grid data yields a geological situation map of the goaf. Based on this geological situation map, drilling risk areas and feasible path intervals within the goaf are identified, including: Based on the void attributes and stability quantification values ​​in the grid data, the three-dimensional spatial grid of the goaf is divided into risk areas to obtain the absolute risk area and stability risk level area of ​​the goaf. By spatially overlaying the absolute risk area with the stability risk level area, a geological situation map of the goaf is obtained. The high-risk areas in the geological situation map are identified as drilling risk areas in the goaf. The low-risk and medium-risk stability areas in the geological situation map are identified as feasible path intervals for the goaf.

6. The intelligent planning method for drilling paths in goaf areas as described in claim 4, characterized in that, Based on the porosity attributes and stability quantification values ​​in the grid data, the three-dimensional spatial grid of the goaf is divided into risk areas to obtain the absolute risk area and stability risk level area of ​​the goaf, including: Based on the void properties in the grid data, the void units are divided into absolute risk areas of the goaf. The stability quantification value of the non-void region is divided into risk levels to obtain the risk category of the non-void region; Based on the risk category, the non-void areas are spatially aggregated to obtain the stability risk level areas of the goaf.

7. The intelligent planning method for drilling paths in goaf areas as described in claim 1, characterized in that, The step of using the drilling risk area as a constraint boundary, connecting adjacent path nodes within the feasible path interval, and using the connected path segment as the initial drilling path for the goaf includes: Within the feasible path interval, path nodes are deployed, and the shortest path between the path nodes is marked. The drilling risk areas in the shortest path are filtered out, and the filtering result is used as the initial drilling path for the goaf.

8. The intelligent planning method for drilling paths in goaf areas as described in claim 1, characterized in that, The step of correcting the initial drilling path based on the spatial relationship between the initial drilling path and the real-time working condition path to obtain the drilling planning path for the goaf includes: Acquire the real-time position and orientation data of the drilling equipment in the goaf area, and calculate the deviation vector between the position and orientation data and the initial path; The drilling posture of the drilling equipment at the next moment is dynamically adjusted according to the deviation vector to obtain the drilling planning path of the goaf.

9. The intelligent planning method for drilling paths in goaf areas as described in claim 8, characterized in that, The formula for calculating the deviation vector is as follows: in: Let the deviation vector be... Let be the current spatial position vector of the device. Let the vector be the position vector of the nearest projected point on the initial drilling path. This is the attitude angle deviation vector. The weighting coefficients for the positions in the pose data. These are the pose weighting coefficients in the pose data. The weighting coefficient for the velocity deviation in the pose data. This is the velocity deviation vector.

10. An intelligent planning system for drilling paths in goaf areas, characterized in that, The system includes: The stability index module is used to perform continuous wavelet transform on the structural feature sequence of the goaf to obtain the time-frequency energy distribution of the goaf, and to transform the spectral dispersion characteristics in the time-frequency energy distribution into the stability index of the goaf. The void distribution module is used to perform energy spectrum integration on the time-frequency energy distribution to obtain the signal energy sequence of the goaf, and compare the signal energy sequence with the calibrated energy threshold to obtain the void distribution of the goaf. The grid data module is used to map the void distribution and the stability index to the three-dimensional spatial grid of the goaf, so as to obtain the grid data of the goaf. The path analysis module is used to fuse the void attributes and stability quantification values ​​of the grid data to obtain a geological situation map of the goaf, and to identify the drilling risk areas and feasible path intervals of the goaf based on the geological situation map. The initial drilling path module is used to connect adjacent path nodes within the feasible path interval with the drilling risk area as the constraint boundary, and use the connected path segment as the initial drilling path of the goaf. The drilling planning path module is used to correct the trajectory of the initial drilling path based on the spatial relationship between the initial drilling path and the real-time working condition path, so as to obtain the drilling planning path of the goaf.

Images