Method and device for analyzing geological structure characteristics of excavation working face of complex stratum

Abstract

The invention provides a geological structure feature analysis method and device for a mining working face of a complex stratum, and belongs to the technical field of mining engineering.The method comprises the steps that the mining working face is divided into a plurality of block sections, and geological hydrological data, block section labels and block section abnormal data of each block section are obtained and analyzed; determining a first region label, an abnormal level label and a sampling density of each block segment; determining mining physical data of the stratum rock core samples of each sample number of each block section and a plurality of sample clustering sets; determining a division label of each block segment, and determining each block segment or a fourth region label of the divided block segment of each block segment; and configuring a waterproof solid-fluid coupling similar material of each block section, acquiring pressure data of the block section, and performing a solid-liquid coupling simulation test on each block section. Similar materials can be configured in a targeted mode, a simulation test can be carried out by fusing measured pressure data, accurate characterization of complex stratum geologic structure features and stress environment replication are achieved, and analysis targeting and simulation authenticity are improved.

Description

Technical Field

[0001] This invention relates to the field of mining engineering technology, and in particular to a method and apparatus for analyzing the geological structural characteristics of mining faces in complex strata. Background Technology

[0002] As shallow mineral resources dwindle, mining operations are increasingly extending into deeper, more complex strata. The interweaving of fault fracture zones, water-rich zones, and other complex geological structures poses a severe challenge to mining safety. Traditional geological structure analysis often employs a broad, general assessment approach, lacking targeted sampling and being susceptible to data interference. Regional delineation relies on subjective experience, and modeling frequently suffers from over-smoothing, leading to distortion of geological features. Solid-liquid coupling simulations often use single similar materials without considering geological differences and anomalies, resulting in a disconnect between simulation and reality and difficulty in accurately identifying hidden geological risks. Existing technologies have conducted simulations using similar materials and solid-liquid coupling, but insufficient data fusion and integration with simulation experiments make it difficult to accurately replicate the characteristics and stress environments of complex strata, thus failing to provide adequate technical support for mining safety.

[0003] Therefore, the present invention provides a method and apparatus for analyzing the geological structural characteristics of mining faces in complex strata. Summary of the Invention

[0004] This invention provides a method and apparatus for analyzing the geological structural characteristics of mining faces in complex strata. By dividing the mining face, it acquires and analyzes the geological and hydrological data, segment labels, and segment anomaly data for each block. It determines the first region label, anomaly level label, and sampling density for each segment, determines the mining physical data of each sample core sample with a specific sample number for each segment, determines the sample cluster set of multiple sample cluster labels, determines the segmentation label for each segment, and determines the fourth region label for each segment or the segmentation of each segment. It configures a waterproof solid-fluid coupling similar material for each segment, acquires segment pressure data, and conducts solid-liquid coupling simulation tests on each segment. By selectively configuring similar materials and integrating measured pressure data to conduct simulation tests, it achieves accurate characterization of the geological structural characteristics of complex strata and replication of the stress environment, improving the targeting of the analysis and the realism of the simulation. This provides high-precision and high-reliability technical support for mining safety and support optimization.

[0005] In a first aspect, the present invention provides a method for analyzing the geological structural characteristics of mining faces in complex strata, comprising: Step 1: Divide the mining face into multiple segments, acquire and analyze the geological and hydrological data, segment labels, and segment anomaly data of each segment, and determine the first area label, anomaly level label, and sampling density of each segment; Step 2: Based on the sampling density, block label, and block anomaly data of each block, determine the mining physical data of the stratigraphic core sample of each sample number in each block, and determine multiple sample cluster sets and the sample cluster label of each sample cluster set; Step 3: Based on the block labels, first region labels, anomaly level labels, and sample cluster sets of all sample cluster labels of all blocks in the mining face, determine the partition label of each block, and determine the fourth region label of each block or the partition of each block. Step 4: Based on the segmentation label of each block, the fourth region label of each block or each segment of the segmentation, configure the waterproof solid-fluid coupling similar material for each block, obtain the block pressure data, and conduct solid-liquid coupling simulation test for each block.

[0006] According to the present invention, a method for analyzing the geological structural characteristics of a complex stratum mining face is provided, which divides the mining face into multiple segments, acquires and analyzes the geological and hydrological data, segment labels, and segment anomaly data of each segment of the mining face, and determines the first region label and sampling density of each segment of the mining face, including: The mining face is divided into multiple blocks. Based on geological sketches and roadway logging, geological and hydrological data of each block of the mining face are obtained. The geological and hydrological data includes geological and hydrological sub-data of multiple sub-segments. The geological and hydrological sub-data includes sub-segment labels, multiple geological parameters, geological parameter values ​​of each geological parameter, multiple hydrological parameters, and hydrological parameter values ​​of each hydrological parameter. Based on the roadway logging, the block labels and block anomaly data of each segment of the mining face are obtained. The block labels include normal and abnormal. If the block label is normal, the block anomaly data is empty. The block anomaly data includes the anomaly location and anomaly feature vector of multiple anomaly records. Obtain the regional division criteria, and based on the regional division criteria and the geological and hydrological data of each segment of the mining face, determine the first regional label of each segment of the mining face; The abnormal feature vectors of all abnormal records in the block abnormal data of each block labeled as abnormal are input into the abnormal detection model. Based on the output of the abnormal detection model, the abnormality level label of each block labeled as abnormal in the mining face is determined. The abnormality level label for each segment of the mining face is set to level 0 if the segment is labeled as normal. Based on the first region label and anomaly level label of each segment of the mining face, the sampling density of each segment of the mining face is determined.

[0007] According to the geological structural feature analysis method for complex strata mining faces provided by the present invention, based on the sampling density, block label, and block anomaly data of each block, the mining physical data of each sample core sample of each block are determined, including: Based on the sampling density of each block of the mining face, multiple stratum core samples and the sample number of each stratum core sample are collected from each block of the mining face. Based on the abnormal location of each abnormal record in the block anomaly data of each block with the block label as abnormal, identify the sample number of the core sample of the stratum to which each abnormal record in the block anomaly data of each block with the block label as abnormal belongs. Based on the sample number of the core sample of the formation to which all anomalous records belong in the anomalous data of each block labeled as anomalous, the anomalous sample data of each block labeled as anomalous is determined. Mechanical property tests were conducted on each sample core sample with a sample number in each block of the mining face. Based on the test results, mining mechanical data of each sample core sample with a sample number in each block was determined. The mining mechanical data includes multiple mechanical parameters and the mechanical parameter value of each mechanical parameter. X-ray diffraction experiments were conducted on each sample core of each block in the mining face to determine the mining mineral data of each sample core of each block. The mining mineral data includes multiple mineral names and the mineral content of each mineral name. Electron microscopy was performed on each sample core of each block in the mining face to determine the mining micro data of each sample core of each block. The mining micro data includes a variety of micro parameters and the micro parameter value of each micro parameter. Based on the mining mechanics data, mining mineral data, and mining microdata of the stratigraphic core samples of each sample number in each block of the mining face, the mining physical data of the stratigraphic core samples of each sample number in each block of the mining face are determined.

[0008] According to the method for analyzing the geological structural characteristics of a complex stratum mining face provided by the present invention, multiple sample cluster sets and sample cluster labels for each sample cluster set are determined, including: Based on all mechanical parameters in the mining mechanics data, all mineral names in the mining mineral data, and all micro parameters in the mining micro data of all sample core samples from all blocks of the mining face, the mining physical vector is determined. Based on the mining physical vector and the mining mechanics data, mining mineral data, and mining micro data in the core samples of each sample number of each block of the mining face, the mining physical value vector of the core samples of each sample number of each block of the mining face is determined. Based on the mining physical value vector of all sample numbers of the formation core samples in each block of the mining face, the block physical data of each block is determined. Based on the mining physical value vectors of all sample-numbered stratigraphic core samples in the block physical data of all blocks of the mining face, cluster analysis is performed on all sample-numbered stratigraphic core samples in all blocks of the mining face to determine multiple sample cluster sets and sample cluster labels for each sample cluster set. The sample cluster set includes the mining physical data and mining physical value vectors of multiple stratigraphic core samples from multiple blocks.

[0009] According to the present invention, a method for analyzing the geological structural characteristics of a complex stratum mining face is provided. Based on the block labels, first region labels, anomaly level labels, and sample cluster sets of all sample cluster labels of the mining face, the method determines the division label of each block and determines the fourth region label of each block or the division block of each block, including: Based on the first area labels of all segments of the mining face, determine the first area label set of the mining face; Based on the sample cluster labels of all sample cluster sets of the mining face, determine the cluster label set of the mining face; Map all first region labels in the first region label set of the mining face to all sample cluster labels in the cluster label set to determine the mapping label set of the mining face. The mapping label set includes multiple mapping pairs, and each mapping pair includes a first region label and a sample cluster label. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, the anomaly level label of each block with the block label being anomaly, and the anomaly sample data, calculate the sample category label, the second region label, the block dispersion value of each block, and the division label of the stratigraphic core sample of each sample number in each block of the mining face, and calculate the fourth region label of each block with the division label being undivided. Based on the segment label for each segment, the sample category label for all sample numbered core samples, and the second region label, a fourth region label for each segment is determined.

[0010] According to the present invention, a method for analyzing the geological structural characteristics of a complex stratum mining face, based on the segment label for each segment, the sample category label for all sample-numbered stratum core samples, and the second region label, determines a fourth region label for each segment, including: If the block label of the mining face is abnormal, the block is divided based on the abnormality level label, abnormal sample data, and sample category label and second area label of all sample numbered stratigraphic core samples. This determines multiple subdivision blocks for each block and subdivision sample data for each subdivision block. The subdivision sample data includes multiple sample numbered stratigraphic core samples and mining physical data of each sample numbered stratigraphic core sample. Based on the sample number of the core sample of the stratum to which all the abnormal records in the block abnormal data of each block with the block label as abnormal, and the core sample of the stratum with all the sample numbers of each segment, the segmentation abnormal data of each segment of each block with the block label as abnormal is determined. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, the anomaly level label of each block with an anomaly block label, the partition sample data of each partitioned block of each block with an anomaly block label, and the partition anomaly data, iteratively calculate the partition dispersion value of each partitioned block of each block with an anomaly block label after partitioning, until the dispersion value of each partitioned block is less than the dispersion threshold, and determine the fourth region label of each partitioned block of each block. If the block label of the mining face is normal, the block is divided based on the sample category label and second area label of the stratigraphic core sample of all sample numbers of the block, and the multiple subdivision blocks and subdivision sample data of each subdivision block are determined. The subdivision sample data includes the stratigraphic core sample of multiple sample numbers and the mining physical data of the stratigraphic core sample of each sample number. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, and the partition sample data of each partitioned block of each block with normal block label, iteratively calculate the partition dispersion value of each partitioned block of each block with normal block label after partitioning, until the dispersion value of each partitioned block is less than the dispersion threshold, and determine the fourth region label of each partitioned block of each block.

[0011] According to the present invention, a method for analyzing the geological structural characteristics of a complex stratum mining face is provided. Based on the segmentation label of each block, the fourth region label of each block or the segmentation of each block, a waterproof solid-fluid coupling similar material is configured for each block, pressure data of the block is obtained, and a solid-liquid coupling simulation test is performed on each block, including: Based on the mining physical value vector of the core samples of the formation with the fourth region label of each undivided block and the physical data of all samples in the block, configure the waterproof solid-fluid coupling similar material of each undivided block of the mining face. Based on the mining physical value vector of all sample numbers in the physical data of each block segment with the division label, and the physical data of all sample numbers in the physical data of each segment of each block, the division physical data of each segment with the division label is determined. Based on the fourth region label of each segment of the division, the mining physical value vector of the stratum core sample with all sample numbers in the division physical data, the division label of the mining face is configured as the waterproof solid-fluid coupling similar sub-material of each segment of the division. Based on the waterproof solid-fluid coupling similar submaterials of all segments with the division label as each segment, the waterproof solid-fluid coupling similar material of the mining face with the division label as each segment is determined. Based on the sensor group buried in each segment of the mining face, the segment pressure data of each segment is acquired. The segment pressure data includes multiple pressure parameters and the pressure parameter value of each pressure parameter. Based on the block pressure data of each block and the waterproof solid-fluid coupling similar material, a solid-liquid coupling simulation test was conducted for each block.

[0012] Secondly, the present invention provides a geological structure feature analysis device for a complex stratum mining face, used to perform the geological structure feature analysis method for a complex stratum mining face described in the first aspect.

[0013] Thirdly, the present invention provides a device for analyzing the geological structural characteristics of complex strata mining faces, comprising: processor; Memory, used to store executable instructions; The processor is used to read executable instructions from memory and execute the executable instructions to implement the geological structure feature analysis method for complex strata mining faces as described in the first aspect.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the method for analyzing the geological structural features of a complex stratum mining face as described in the first aspect.

[0015] Compared with the prior art, the beneficial effects of this application are as follows: By dividing the mining face, geological and hydrological data, segment labels, and segment anomaly data for each block of the mining face are acquired and analyzed. This process determines the first region label, anomaly level label, and sampling density for each segment. It also determines the mining physical data of each core sample with a specific sample number for each segment, identifies sample cluster sets with multiple sample cluster labels, determines the segmentation label for each segment, and determines the fourth region label for each segment or its subdivided segments. Waterproof solid-fluid coupling similar materials are configured for each segment, and segment pressure data is acquired. Solid-liquid coupling simulation tests are then conducted for each segment. This allows for the targeted configuration of similar materials and the integration of measured pressure data to conduct simulation tests, achieving accurate characterization of complex geological structures and replication of the stress environment. This enhances the targeting of the analysis and the realism of the simulation, providing high-precision and high-reliability technical support for mining safety and support optimization. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a method for analyzing the geological structural features of a complex stratum mining face, as provided in an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of a geological structure feature analysis device for complex strata mining faces provided in an embodiment of the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0019] Example 1: This invention provides a method for analyzing the geological structural features of mining faces in complex strata, such as... Figure 1 As shown, it includes: Step 1: Divide the mining face into multiple segments, acquire and analyze the geological and hydrological data, segment labels, and segment anomaly data of each segment, and determine the first area label, anomaly level label, and sampling density of each segment; Step 2: Based on the sampling density, block label, and block anomaly data of each block, determine the mining physical data of the stratigraphic core sample of each sample number in each block, and determine multiple sample cluster sets and the sample cluster label of each sample cluster set; Step 3: Based on the block labels, first region labels, anomaly level labels, and sample cluster sets of all sample cluster labels of all blocks in the mining face, determine the partition label of each block, and determine the fourth region label of each block or the partition of each block. Step 4: Based on the segmentation label of each block, the fourth region label of each block or each segment of the segmentation, configure the waterproof solid-fluid coupling similar material for each block, obtain the block pressure data, and conduct solid-liquid coupling simulation test for each block.

[0020] In this embodiment, dividing the mining face into multiple segments aims to overcome the problem of local feature masking caused by overall analysis, allowing for precise focusing on the geological conditions of each area. Subsequently, geological and hydrological data are collected for each segment. This data encompasses core information reflecting the geological environment, such as lithology, coal seam thickness, and water permeability. The segment labels are also clearly defined as normal or abnormal; for abnormal segments, detailed abnormal data related to the anomalies are recorded. Through comprehensive analysis of this information, each segment is assigned a first-region label, and an anomaly level label is determined to quantify the degree of risk. Differential sampling densities are established based on geological complexity and anomaly level to ensure sufficient samples are obtained in key areas to support subsequent analysis.

[0021] In this embodiment, core samples are collected from each block based on the sampling density and assigned a unique sample number. Mechanical property tests, mineral composition analysis, and microstructure observations are performed on each sample. These results are integrated to form mining physical data, comprehensively reflecting the macroscopic mechanics, characteristic material composition, and microstructure of the rock mass. Subsequently, cluster analysis is used to group samples with similar physical properties into multiple sample cluster sets, each set corresponding to a sample cluster label.

[0022] In this embodiment, the block labels, first region labels, and anomaly level labels of all blocks are aggregated, and then combined with all sample cluster sets and their corresponding sample cluster labels to perform multi-dimensional information fusion analysis. Based on the analysis results, a partition label for each block is determined, and it is determined whether the block needs to be further split into smaller partitions. For blocks that do not need to be partitioned, the fourth region label is directly determined based on existing information; for blocks that need to be partitioned, a fourth region label is assigned to each partition after splitting, achieving label determination from preliminary qualitative to precise quantitative analysis.

[0023] In this embodiment, waterproof solid-fluid coupling similar materials are specifically configured based on the segmentation labels and fourth region labels of each block. For blocks that do not require segmentation, the entire material is directly configured. For blocks requiring segmentation, similar sub-materials are first configured for each segment, and then integrated into the material for the entire block according to spatial distribution, ensuring that the material's strength, porosity, and other properties closely match the actual rock mass. By embedding sensor groups in each block, block pressure data such as in-situ stress and seepage pressure are collected. These measured pressure data are used as load conditions, and solid-liquid coupling simulation tests are conducted in conjunction with the configured similar materials to replicate the deformation and failure patterns of the rock mass under the coupled action of stress and seepage during mining.

[0024] The beneficial effects of the above technical solution are as follows: By dividing the mining face, the geological and hydrological data, segment labels, and segment anomaly data of each segment of the mining face are acquired and analyzed. This allows for the determination of the first regional label, anomaly level label, and sampling density for each segment. It also allows for the determination of mining physical data for each sample core sample with each sample number within each segment, the determination of sample cluster sets with multiple sample cluster labels, the determination of the segmentation label for each segment, and the determination of the fourth regional label for each segment or segmentation of each segment. Furthermore, it allows for the configuration of waterproof solid-fluid coupling similar materials for each segment, the acquisition of segment pressure data, and the conduct of solid-liquid coupling simulation tests for each segment. By selectively configuring similar materials and integrating measured pressure data to conduct simulation tests, the solution achieves accurate characterization of complex geological structures and replication of the stress environment, improving the targeting of the analysis and the realism of the simulation. This provides high-precision and high-reliability technical support for mining safety and support optimization.

[0025] Example 2: This invention provides a method for analyzing the geological structural features of complex strata mining faces. The method divides the mining face into multiple segments, acquires and analyzes the geological and hydrological data, segment labels, and segment anomaly data for each segment, and determines the first region label and sampling density for each segment. The method includes: The mining face is divided into multiple blocks. Based on geological sketches and roadway logging, geological and hydrological data of each block of the mining face are obtained. The geological and hydrological data includes geological and hydrological sub-data of multiple sub-segments. The geological and hydrological sub-data includes sub-segment labels, multiple geological parameters, geological parameter values ​​of each geological parameter, multiple hydrological parameters, and hydrological parameter values ​​of each hydrological parameter. Based on the roadway logging, the block labels and block anomaly data of each segment of the mining face are obtained. The block labels include normal and abnormal. If the block label is normal, the block anomaly data is empty. The block anomaly data includes the anomaly location and anomaly feature vector of multiple anomaly records. Obtain the regional division criteria, and based on the regional division criteria and the geological and hydrological data of each segment of the mining face, determine the first regional label of each segment of the mining face; The abnormal feature vectors of all abnormal records in the block abnormal data of each block labeled as abnormal are input into the abnormal detection model. Based on the output of the abnormal detection model, the abnormality level label of each block labeled as abnormal in the mining face is determined. The abnormality level label for each segment of the mining face is set to level 0 if the segment is labeled as normal. Based on the first region label and anomaly level label of each segment of the mining face, the sampling density of each segment of the mining face is determined.

[0026] In this embodiment, the block division can be carried out every 5 meters along the roadway direction of the mining face. Each block is further subdivided into three sub-segments: top, middle, and bottom. If the roadway height exceeds 4 meters, a side sub-segment is added. The sub-segment labels include: roof, middle section, and side.

[0027] In this embodiment, geological sketching involves visually observing and recording information such as the attitude, structure, and morphology of rock strata at the mining face. Roadway logging, on the other hand, systematically records lithological changes, fracture development, and support deformation on the exposed roadway walls. These two methods are combined to collect geological and hydrological data for each block. The geological and hydrological data is further refined into multiple sub-segments, each corresponding to a small area within the block. Sub-segment labels are used to distinguish the basic attributes of the sub-segment. Multiple geological parameters cover core indicators such as coal seam dip angle, stratum thickness, and surrounding rock strength, each with a specific numerical value to quantify its characteristics. Multiple hydrological parameters include seepage volume, seepage form, and initial water level, each also equipped with a corresponding numerical value, allowing for precise description and quantification of the geological and hydrological conditions.

[0028] In this embodiment, block labels and block anomaly data for each segment are obtained through tunnel logging. During the tunnel logging process, the geological and engineering conditions of each segment are continuously tracked. If no anomalies such as rock wall seepage, blown-out cracking, or rock strata displacement occur within a segment, the segment label is marked as normal, and the segment anomaly data is empty. If any one or more of the above anomalies occur within a segment, the segment label is marked as anomaly. The segment anomaly data records the anomaly location and anomaly feature vector for each anomaly record in detail. The anomaly location clearly indicates the specific coordinates or range of the anomaly occurrence, while the anomaly feature vector provides a multi-dimensional quantitative description of the anomaly, such as the intensity of seepage or the amplitude of rock strata displacement.

[0029] In this embodiment, a pre-defined regional division standard is obtained. This standard is based on extensive engineering practice, industry-recommended specifications, manuals, guidelines, and geological theories, and covers the criteria for classifying different geological structural types. For example, different regional types are defined based on parameters such as rock strata assemblage, surrounding rock strength, and the degree of fracture development. The geological and hydrological data of each block are compared and analyzed with the regional division standard. Based on whether the data meets the characteristic requirements of various types of regions in the standard, each block is assigned a first regional label.

[0030] In this embodiment, the first region label includes fault fracture zone, weak interlayer, water-rich zone, high geostress zone, normal zone, etc.

[0031] In this embodiment, for each block labeled as abnormal, the abnormal feature vectors of all abnormal records in its block abnormal data are collected. These vectors contain multi-dimensional key information about the abnormality, which can comprehensively reflect the severity and scope of the abnormality. These abnormal feature vectors are input into a pre-trained abnormality detection model. This model can analyze and determine the input abnormal feature vectors by learning the features of a large amount of historical abnormal data, and output the corresponding abnormality level result. Based on the result, an abnormality level label is determined for each abnormal block, realizing the quantitative classification of the abnormality degree.

[0032] In this embodiment, for each block with a normal block label, since no abnormal phenomena have occurred, the geological and hydrological conditions are relatively stable, there is no abnormal risk or the abnormal risk is extremely low, so its abnormality level label is directly determined to be level 0.

[0033] In this embodiment, the first region label and anomaly level label of each block are considered comprehensively. The first region label reflects the basic geological structure type of the block. Different types of regions have different geological complexities and analysis requirements. The anomaly level label quantifies the degree of anomaly risk of the block. The higher the risk, the higher the requirement for the amount and accuracy of sampling data. By combining these two labels, differentiated sampling density standards are formulated. For example, for blocks with complex geological structures and high anomaly levels, a higher sampling density is set to obtain enough data to support detailed analysis. For blocks with simple geological structures and anomaly level 0, a lower sampling density is set to save sampling resources and engineering costs, achieving a precise match between sampling density and the geological characteristics and risk level of the block.

[0034] The beneficial effects of the above technical solution are as follows: by dividing the mining face into multiple segments, acquiring and analyzing the geological and hydrological data, segment labels, and segment anomaly data of each segment of the mining face, and determining the first area label and sampling density of each segment of the mining face, it is possible to overcome the limitations of uniform sampling, achieve a balance between targeted and intensive sampling in high-risk areas and economical sampling in normal areas, improve the data relevance and resource utilization efficiency of geological structure analysis, and reduce the cost of ineffective sampling.

[0035] Example 3: This invention provides a method for analyzing the geological structural characteristics of mining faces in complex formations. Based on the sampling density, block label, and block anomaly data of each block, it determines the mining physical data of each sample core sample with each sample number in each block, including: Based on the sampling density of each block of the mining face, multiple stratum core samples and the sample number of each stratum core sample are collected from each block of the mining face. Based on the abnormal location of each abnormal record in the block anomaly data of each block with the block label as abnormal, identify the sample number of the core sample of the stratum to which each abnormal record in the block anomaly data of each block with the block label as abnormal belongs. Based on the sample number of the core sample of the formation to which all anomalous records belong in the anomalous data of each block labeled as anomalous, the anomalous sample data of each block labeled as anomalous is determined. Mechanical property tests were conducted on each sample core sample with a sample number in each block of the mining face. Based on the test results, mining mechanical data of each sample core sample with a sample number in each block was determined. The mining mechanical data includes multiple mechanical parameters and the mechanical parameter value of each mechanical parameter. X-ray diffraction experiments were conducted on each sample core of each block in the mining face to determine the mining mineral data of each sample core of each block. The mining mineral data includes multiple mineral names and the mineral content of each mineral name. Electron microscopy was performed on each sample core of each block in the mining face to determine the mining micro data of each sample core of each block. The mining micro data includes a variety of micro parameters and the micro parameter value of each micro parameter. Based on the mining mechanics data, mining mineral data, and mining microdata of the stratigraphic core samples of each sample number in each block of the mining face, the mining physical data of the stratigraphic core samples of each sample number in each block of the mining face are determined.

[0036] In this embodiment, stratigraphic core samples are collected based on the determined sampling density of each block. The sampling density determines the number of samples collected from different blocks. Blocks with complex geological structures or high anomaly levels have higher sampling densities and more samples collected, while blocks with simple geological conditions and low anomaly levels have lower sampling densities and fewer samples collected. Each collected stratigraphic core sample is assigned a unique sample number, which serves as an identifier to distinguish different samples.

[0037] In this embodiment, for each block labeled as anomalous, the anomalous location of each anomalous record is recorded in detail in its block anomalous data. By comparing and matching the anomalous location with the sampling location of the formation core sample, the formation core sample corresponding to each anomalous record is identified, and then the sample number of the formation core sample to which the anomalous record belongs is determined.

[0038] In this embodiment, after identifying the sample numbers of the core samples to which all anomalous records belong in each block labeled as anomalous, these sample numbers are systematically aggregated to form the anomalous sample data for that anomalous block. The anomalous sample data centralizes the information of all core samples related to the anomalous phenomena within that block.

[0039] In this embodiment, rigorous mechanical property tests were conducted on each sample core sample from each block, following relevant rock mechanics testing standards to ensure the accuracy and reliability of the results. The mechanical property tests covered several key mechanical parameters, including compressive strength, tensile strength, elastic modulus, cohesion, and internal friction angle. These parameters quantify the macroscopic mechanical properties of the core samples, reflecting the rock mass's resistance to deformation and failure. Specific numerical values ​​were obtained for each mechanical parameter.

[0040] In this embodiment, X-ray diffraction experiments were performed on core samples of each sample number in each block. X-ray diffraction technology can accurately detect the names of various minerals contained in the core samples, such as clay minerals, quartz, feldspar, montmorillonite, illite, etc. At the same time, the experimental analysis can also determine the content of each mineral. The amount of mineral content directly affects the physical and mechanical properties of the rock mass. For example, too high a clay mineral content will lead to reduced rock mass strength and susceptibility to mudification.

[0041] In this embodiment, electron microscopy (EMS) is used to observe core samples from each block with specific sample numbers. EMS can clearly reveal the microstructure of the core samples and obtain various key micro parameters, such as porosity, fracture density, intergranular cementation, and fracture width. Each micro parameter yields a specific value, quantifying the microstructural characteristics of the rock mass and reflecting its internal density and fracture development.

[0042] In this embodiment, after acquiring the mining mechanics data, mining mineral data, and mining microscopic data of each core sample with each sample number in each block, these three types of data are comprehensively integrated and summarized to form the mining physical data of the sample. The mining physical data integrates the macroscopic mechanical properties, mineral composition, and microstructural characteristics of the rock mass, realizing a multi-dimensional and comprehensive characterization of the core sample.

[0043] The beneficial effects of the above technical solution are as follows: Based on the sampling density, block label, and block anomaly data of each block, the mining physical data of the stratigraphic core sample of each sample number in each block can be determined, which can enhance the support of the data for geological structure analysis and provide a high-quality and targeted data foundation for subsequent clustering and regional division.

[0044] Example 4: This invention provides a method for analyzing the geological structural features of mining faces in complex strata, determining multiple sample cluster sets and sample cluster labels for each sample cluster set, including: Based on all mechanical parameters in the mining mechanics data, all mineral names in the mining mineral data, and all micro parameters in the mining micro data of all sample core samples from all blocks of the mining face, the mining physical vector is determined. Based on the mining physical vector and the mining mechanics data, mining mineral data, and mining micro data in the core samples of each sample number of each block of the mining face, the mining physical value vector of the core samples of each sample number of each block of the mining face is determined. Based on the mining physical value vector of all sample numbers of the formation core samples in each block of the mining face, the block physical data of each block is determined. Based on the mining physical value vectors of all sample-numbered stratigraphic core samples in the block physical data of all blocks of the mining face, cluster analysis is performed on all sample-numbered stratigraphic core samples in all blocks of the mining face to determine multiple sample cluster sets and sample cluster labels for each sample cluster set. The sample cluster set includes the mining physical data and mining physical value vectors of multiple stratigraphic core samples from multiple blocks.

[0045] In this embodiment, mining physical data from all core samples with all sample numbers across all blocks of the mining face are aggregated. All mechanical parameters are extracted from the mining mechanical data, all mineral names are extracted from the mining mineral data, and all micro-parameters are extracted from the mining micro-data. These extracted parameters and mineral names are then integrated into a unified set of indicators, which constitutes the mining physical vector. The core function of the mining physical vector is to establish a unified standard framework covering all analytical dimensions, ensuring that data from all subsequent samples can be processed based on the same indicator system.

[0046] In this embodiment, after determining a unified mining physical vector, the corresponding mining physical data is retrieved for each sample core sample with a specific sample number in each segment of the mining face. The specific values ​​of each mechanical parameter are obtained from the mining mechanics data, the content values ​​corresponding to each mineral name are obtained from the mining mineral data, and the specific values ​​of each micro-parameter are obtained from the mining micro-data. Then, according to the order of the indicators in the mining physical vector, these specific values ​​are sequentially filled in to form the mining physical value vector for that sample. Each value corresponds one-to-one with a specific indicator in the mining physical vector.

[0047] In this embodiment, for each block, the mining physical value vectors of all core samples corresponding to all sample numbers within that block have been obtained. These vectors are systematically collected and organized to form the block physical data. The block physical data is a concentrated representation of the characteristics of all samples within that block.

[0048] In this embodiment, cluster analysis is performed based on the mining physical value vectors of all sample core samples with different sample numbers in the block physical data of all blocks. The core logic of the cluster analysis is to group vectors according to the degree of similarity between them, grouping vectors with high feature similarity into the same set and vectors with large feature differences into different sets, ultimately forming multiple sample cluster sets. Each sample cluster set represents a type of rock mass with similar physical properties, and each set is assigned a sample cluster label to quickly distinguish different types of rock mass features. Each sample cluster set may contain sample vectors from multiple different blocks and their corresponding mining physical data.

[0049] In this embodiment, the sample clustering labels include stable regions, gradual transition regions, and collapsing regions. The physical vectors collected for sample clusters labeled as stable regions include high compressive strength, high elastic modulus, low Poisson's ratio, low fracture density, and low porosity. The physical vectors collected for sample clusters labeled as gradual transition regions include moderate compressive strength, moderate elastic modulus, moderate Poisson's ratio, moderate fracture density, and moderate porosity. The physical vectors collected for sample clusters labeled as collapsing regions include low compressive strength, low elastic modulus, high Poisson's ratio, high fracture density, and high porosity.

[0050] The beneficial effects of the above technical solution are: determining multiple sample cluster sets and sample cluster labels for each sample cluster set can improve the uniformity and objectivity of classification, and provide standardized and comparable quantitative basis for region label determination and quantitative partitioning.

[0051] Example 5: This invention provides a method for analyzing the geological structural features of mining faces in complex strata. Based on the block labels, first region labels, anomaly level labels, and sample cluster sets of all sample cluster labels for all blocks of the mining face, the method determines the partition label of each block and determines the fourth region label of each block or the partitioned block of each block, including: Based on the first area labels of all segments of the mining face, determine the first area label set of the mining face; Based on the sample cluster labels of all sample cluster sets of the mining face, determine the cluster label set of the mining face; Map all first region labels in the first region label set of the mining face to all sample cluster labels in the cluster label set to determine the mapping label set of the mining face. The mapping label set includes multiple mapping pairs, and each mapping pair includes a first region label and a sample cluster label. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, the anomaly level label of each block with the block label being anomaly, and the anomaly sample data, calculate the sample category label, the second region label, the block dispersion value of each block, and the division label of the stratigraphic core sample of each sample number in each block of the mining face, and calculate the fourth region label of each block with the division label being undivided. Based on the segment label for each segment, the sample category label for all sample numbered core samples, and the second region label, a fourth region label for each segment is determined.

[0052] In this embodiment, the first area labels of all blocks in the mining face are summarized, and all different first area labels are collected and organized to form a first area label set.

[0053] In this embodiment, sample clustering labels of all sample cluster sets of the mining face are collected, and these sample clustering labels are summarized to form a clustering label set.

[0054] In this embodiment, the first region label is a qualitative geological structure label pre-defined based on geological sketching, well logging, and tunnel logging methods, covering fault fracture zones, weak interlayers, water-rich zones, high geostress zones, and normal areas, each corresponding to different geological structures or environmental characteristics of the mining face. The sample cluster label is a quantitative rock mass stability label obtained by clustering the mining physical data of all strata core samples, including stable regions, gradual transition regions, and collapse regions, each representing different stability states of the rock mass. The mapping process involves performing correlation analysis between each label in the first region label set and each label in the cluster label set. Based on the inherent relationship between geological structural characteristics and rock mass stability, matching combinations are determined. For example, fault fracture zones usually correspond to collapse areas, normal areas usually correspond to stable areas, and weak interlayers, water-rich zones, and high geostress zones may correspond to gradual change areas or collapse areas. These matching combinations form mapping pairs, and all mapping pairs together constitute the mapping label set. Its core is to establish the correspondence between qualitative geological structural labels and quantitative stability labels, allowing the two different dimensions of labels to form a mutually reinforcing correlation system.

[0055] In this embodiment, based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, the anomaly level label of each block with an anomaly block label, and the anomaly sample data, the sample category label, the second region label, the block dispersion value of each block, and the division label of the stratigraphic core sample of each sample number in each block of the mining face are calculated. Furthermore, the fourth region label of each block with an undivided division label is calculated. The calculation formula is as follows: ; ; ; ; ; ; ; ; ; in, This represents the label of the first region of the i-th block segment. This represents the stratigraphic core sample with the j-th sample number in the i-th block. This represents the sample cluster set whose cluster label is the k-th sample. This represents the cluster label of the k-th sample. This represents the sample category label of the stratigraphic core sample with the j-th sample number in the i-th block. This represents the m-th mapping pair in the set of mapping labels. N1 represents the number of mapping pairs in the mapping label set. This represents the label of the first region within the m-th mapping pair in the set of mapping labels. The second region label represents the core sample with the j-th sample number in the i-th block. This represents the set of labels for the third region of the i-th block segment. This represents the nth third region label in the set of third region labels for the i-th block segment. This represents the number of stratigraphic core samples collected within the i-th block, and iN3 represents the number of third region labels in the third region label set of the i-th block. The second region label represents the core sample with the j-th sample number in the i-th block, and the first indicator function is based on the n-th third region label in the third region label set. This represents the sample number of the core sample to which the p-th anomalous record in the block anomaly data of the i-th block belongs, and iN4 represents the number of anomalous records in the block anomaly data of the i-th block. This represents the anomaly level label of the i-th block segment. This represents the anomaly weight of the core sample with the j-th sample number in the i-th block. This represents the clustering label weight of the core sample with the j-th sample number in the i-th block. The block dispersion value of the second region label for all sample numbers of the stratigraphic core samples in the i-th block represents the block dispersion value. Indicates the dispersion threshold. This represents the label of the fourth region in the i-th block segment. This represents the partition label of the i-th block segment. This represents the number of core samples from all sample numbers in the i-th block where the second region label is the nth third region label in the set of third region labels. This indicates the position of the third region label corresponding to the largest second region label in the third region label set among all sample numbers of the stratigraphic core samples of the i-th block. The third region label represents the largest number of second region labels among all sample numbers of the stratigraphic core samples in the i-th block, and the corresponding third region label in the third region label set.

[0056] In this embodiment, the dispersion threshold Based on the mining experience and conservative approach of the project, a dispersion threshold of 0.60-0.30 indicates that the distribution of labels in the second area has begun to disperse, but there are still labels with obvious advantages. A dispersion threshold of 0.30-0.90 indicates that the labels in the second area are moderately mixed. If the project is conservative, it can be directly processed according to the label category with the largest number of labels in the second area. A dispersion threshold of 0.90-1.10 indicates that the distribution of labels in the second area is highly mixed and cannot be forcibly normalized. A dispersion threshold of 0.35 can be taken as the value.

[0057] The beneficial effects of the above technical solution are as follows: Based on the block labels, first region labels, anomaly level labels, and sample cluster sets of all sample cluster labels of the mining face, the division label of each block is determined, and the fourth region label of each block or the division block of each block is determined. This can greatly improve the consistency of region labels and the scientific nature of block division, and lay a precise classification foundation for subsequent material configuration and simulation tests.

[0058] Example 6: This invention provides a method for analyzing the geological structural features of complex strata mining faces. Based on the segment labels of each divided block, the sample category labels of all sample-numbered stratigraphic core samples, and the second region label, a fourth region label is determined for each divided block, including: If the block label of the mining face is abnormal, the block is divided based on the abnormality level label, abnormal sample data, and sample category label and second area label of all sample numbered stratigraphic core samples. This determines multiple subdivision blocks for each block and subdivision sample data for each subdivision block. The subdivision sample data includes multiple sample numbered stratigraphic core samples and mining physical data of each sample numbered stratigraphic core sample. Based on the sample number of the core sample of the stratum to which all the abnormal records in the block abnormal data of each block with the block label as abnormal, and the core sample of the stratum with all the sample numbers of each segment, the segmentation abnormal data of each segment of each block with the block label as abnormal is determined. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, the anomaly level label of each block with an anomaly block label, the partition sample data of each partitioned block of each block with an anomaly block label, and the partition anomaly data, iteratively calculate the partition dispersion value of each partitioned block of each block with an anomaly block label after partitioning, until the dispersion value of each partitioned block is less than the dispersion threshold, and determine the fourth region label of each partitioned block of each block. If the block label of the mining face is normal, the block is divided based on the sample category label and second area label of the stratigraphic core sample of all sample numbers of the block, and the multiple subdivision blocks and subdivision sample data of each subdivision block are determined. The subdivision sample data includes the stratigraphic core sample of multiple sample numbers and the mining physical data of the stratigraphic core sample of each sample number. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, and the partition sample data of each partitioned block of each block with normal block label, iteratively calculate the partition dispersion value of each partitioned block of each block with normal block label after partitioning, until the dispersion value of each partitioned block is less than the dispersion threshold, and determine the fourth region label of each partitioned block of each block.

[0059] In this embodiment, when a segment of the mining face is labeled as anomalous, the segmentation process requires the integration of multiple key information aspects to ensure accuracy. The anomaly level label quantifies the severity of the anomaly in that segment; different levels correspond to different impact ranges and risk levels, making them key risk factors to consider during segmentation. Anomaly sample data identifies core samples directly related to the anomaly within the segment. These samples collectively reflect the rock mass characteristics of the anomalous area, and the segmentation process must rationally define the segmentation range around these samples. The sample category labels for all numbered stratigraphic core samples are derived from previous cluster analysis. By integrating this information, the anomalous segment is split into multiple smaller segments, each with higher similarity in rock mass characteristics. Simultaneously, segmentation sample data is generated for each segment, containing all numbered stratigraphic core samples within the segment and the mining physical data for each sample.

[0060] In this embodiment, for each block labeled as anomalous, its block anomalous data records the sample numbers of the core samples from the formation to which all anomalous records belong. These numbers clearly identify which samples are related to the anomalous phenomenon. These sample numbers are compared with all sample numbers in each segment to filter out the anomalous sample numbers and their corresponding anomalous records contained in each segment, thereby forming the segmented anomalous data for each segment.

[0061] In this embodiment, based on multi-dimensional information, the dispersion value of each segment is iteratively calculated. The dispersion value measures the degree of dispersion of sample features within a segment; the smaller the value, the higher the consistency of the second region label of the samples within the segment. During the iteration process, the boundaries of the segments are continuously adjusted according to the magnitude of the dispersion value until the dispersion value of each segment is less than a preset dispersion threshold. At this point, the rock mass features within the segment are considered to have reached sufficient consistency. Based on the final segmentation result and various other information, a fourth region label is assigned to each segment.

[0062] In this embodiment, when the block label of the mining face is normal, it indicates that there are no abnormalities within the block and the geological conditions are relatively stable, but fine-grained subdivision is required to ensure the accuracy of geological structure analysis. The main basis for subdivision is the sample category label and second region label of all sample-numbered stratigraphic core samples within the block. Combining these two labels, the normal block is split into multiple subdivision blocks, and the sample characteristics within each subdivision block have high similarity. At the same time, each subdivision block generates corresponding subdivision sample data, which includes all sample-numbered stratigraphic core samples within the block and the mining physical data of each sample.

[0063] In this embodiment, for each block segment with a normal segment label, determining its fourth region label also requires relying on multiple information sources. The dispersion value of each segment is iteratively calculated based on multidimensional information. By continuously adjusting the boundaries of the segment segments, the dispersion value is gradually reduced until the dispersion value of each segment is less than the dispersion threshold. Based on the final segmentation result and relevant information, a fourth region label is assigned to each segment.

[0064] In this embodiment, the calculation process of the segment dispersion value is similar to the calculation process of the segment dispersion value, and the determination process of the fourth region label of the segment is similar to the determination process of the fourth region label of the segment.

[0065] The beneficial effects of the above technical solution are as follows: Based on the segment label of each segment, the sample category label of all sample numbered stratigraphic core samples, and the second region label, the fourth region label of each segment is determined as the segment label of each segment. This can ensure the consistency of samples within the segment or within the segment, break through the limitations of fixed division, realize the refined and objective definition of geological structural regions, improve the fit between the fourth region label and the actual geological characteristics, and further provide accurate zoning basis for subsequent simulation experiments.

[0066] Example 7: This invention provides a method for analyzing the geological structural characteristics of mining faces in complex strata. Based on the segmentation labels of each block, and the fourth region label of each block or each block segment, a waterproof solid-fluid coupling similar material is configured for each block. Block pressure data is obtained, and solid-liquid coupling simulation tests are conducted on each block, including: Based on the mining physical value vector of the core samples of the formation with the fourth region label of each undivided block and the physical data of all samples in the block, configure the waterproof solid-fluid coupling similar material of each undivided block of the mining face. Based on the mining physical value vector of all sample numbers in the physical data of each block segment with the division label, and the physical data of all sample numbers in the physical data of each segment of each block, the division physical data of each segment with the division label is determined. Based on the fourth region label of each segment of the division, the mining physical value vector of the stratum core sample with all sample numbers in the division physical data, the division label of the mining face is configured as the waterproof solid-fluid coupling similar sub-material of each segment of the division. Based on the waterproof solid-fluid coupling similar submaterials of all segments with the division label as each segment, the waterproof solid-fluid coupling similar material of the mining face with the division label as each segment is determined. Based on the sensor group buried in each segment of the mining face, the segment pressure data of each segment is acquired. The segment pressure data includes multiple pressure parameters and the pressure parameter value of each pressure parameter. Based on the block pressure data of each block and the waterproof solid-fluid coupling similar material, a solid-liquid coupling simulation test was conducted for each block.

[0067] In this embodiment, for each block labeled as unclassified, a fourth region label clarifies the geological structure of that block. This fourth region label includes fault fracture zones, weak interlayers, water-rich zones, high-stress zones, and normal zones. The physical value vectors of all sample-numbered stratigraphic core samples in the block's physical data comprehensively quantify the combined mechanical, mineral, and microscopic characteristics of the rock mass within that block. Based on these two key pieces of information, a waterproof solid-fluid coupling similar material is specifically configured for that block, ensuring that the similar material's strength, porosity, mineral content, and other characteristics closely match the actual rock mass of the block.

[0068] In this embodiment, for each segment labeled as "divided," the original segment's physical data includes the mining physical value vectors of all samples from the entire segment, while the sub-segment's sample data focuses on the samples within that sub-segment and their corresponding mining physical data. Integrating and analyzing these two sets of data extracts the unique rock mass characteristic parameters for each sub-segment, forming the sub-segment's physical data. This sub-segment physical data eliminates interference from other sub-segment data within the original segment, more accurately reflecting the comprehensive rock mass characteristics of a single sub-segment.

[0069] In this embodiment, based on the fourth region label of each segment of each block and the mining physical value vector of the core samples of the strata with all sample numbers in the segmentation physical data, a waterproof solid-fluid coupling similar sub-material is configured for each segment. Each similar sub-material is designed with a ratio based on the rock mass characteristics of the corresponding segment to ensure that the sub-material is highly consistent with the actual rock mass of the segment in terms of mechanical properties, mineral composition, and microstructure. This allows the simulation of each sub-block to realistically reproduce its own rock mass behavior and avoids the problem that a single material cannot simulate the complex rock mass distribution within the segment.

[0070] In this embodiment, each segment, categorized by label, consists of multiple segments, and each segment has a corresponding similar sub-material. These similar sub-materials are integrated according to the spatial distribution and proportion of each segment within the original segment to form a waterproof solid-fluid coupling similar material for the entire segment. The integrated similar material fully preserves the differences in rock mass characteristics of each segment, realistically simulating the distribution and characteristic differences of rock masses in different areas within the original segment, making the solid-liquid coupling simulation of the entire segment more closely resemble actual geological conditions.

[0071] In this embodiment, sensor arrays are pre-embedded in each segment of the mining face. These arrays contain various types of pressure sensors, enabling real-time acquisition of various pressure data experienced by the segment during actual mining. The segment pressure data covers multiple key pressure parameters, such as ground stress, seepage pressure, and support reaction force. Each pressure parameter has a specific numerical record. This data directly reflects the actual stress environment and load conditions of the segment, providing realistic boundary conditions and load input for subsequent solid-liquid coupling simulation tests, ensuring a high degree of consistency between the stress environment of the simulation test and the actual field conditions.

[0072] In this embodiment, the pressure data of each block is used as the load input and boundary condition for the simulation test. Combined with the previously configured waterproof solid-fluid coupling similar material, a solid-liquid coupling simulation test is carried out for that block. The similar material restores the physical and mechanical properties of the rock mass, and the pressure data restores the actual stress environment. The combination of the two enables the simulation test to accurately replicate the deformation law and failure mechanism of the rock mass under the coupled action of stress and seepage during the mining process. The test results can truly reflect the actual situation on site, providing high-precision and high-reliability data support for subsequent geological structure stability analysis, support scheme optimization, and other work, avoiding the problem of test result distortion caused by discrepancies between materials or loads and reality.

[0073] The beneficial effects of the above technical solution are as follows: Based on the division label of each block, the fourth area label of each block or the division of each block, the waterproof solid-fluid coupling similar material of each block is configured, the block pressure data is obtained, and the solid-liquid coupling simulation test is carried out on each block. This can achieve accurate replication of the characteristics of complex strata rock mass and stress environment, improve the authenticity and reliability of the simulation test, and provide high-precision data support for the optimization of support scheme.

[0074] Example 8: This invention provides a device for analyzing the geological structural features of a complex stratum mining face, used to execute any one of the geological structural feature analysis methods for complex stratum mining faces in embodiments 1 to 7 above.

[0075] Example 9: This invention provides a device for analyzing the geological structural features of complex strata mining faces, such as... Figure 2 As shown, the device may include a processor and a memory, the memory of which can be used to store executable instructions. The processor can read the executable instructions from the memory and execute them to implement a method for analyzing the geological structural features of a complex stratum mining face, as described in the above embodiments.

[0076] The geological structure feature analysis device 200 for complex strata mining faces in this embodiment of the invention can be an electronic device. This electronic device can include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (e.g., vehicle navigation terminals), wearable devices, etc., as well as fixed terminals such as digital TVs, desktop computers, smart home devices, etc.

[0077] It should be noted that, Figure 2 The geological structure feature analysis device 200 shown for complex strata mining faces is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0078] like Figure 2 As shown, the geological structure feature analysis device 200 for complex strata mining faces may include a processing unit (e.g., a central processing unit, a graphics processing unit, etc.) 201, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 202 or a program loaded from a storage device 208 into a random access memory (RAM) 203. The RAM 203 also stores various programs and data required for the operation of the geological structure feature analysis device 200 for complex strata mining faces. The processing unit 201, ROM 202, and RAM 203 are interconnected via a bus 204. An input / output (I / O) interface 205 is also connected to the bus 204.

[0079] Typically, the following devices can be connected to the I / O interface 205: input devices 206 including, for example, a touchscreen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 203 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 208 including, for example, magnetic tape, hard disk, etc.; and communication devices 209. The communication device 209 allows a geological structure feature analysis device 200 for complex strata mining faces to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 2A geological structure feature analysis device 200 for complex strata mining faces is shown, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0080] Example 10: This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, enables the processor to implement any one of the geological structural feature analysis methods for complex strata mining faces described in embodiments 1 to 7.

[0081] For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication device 209, or installed from storage device 208, or installed from ROM 202. When the computer program is executed by processing device 201, it performs any of the geological structural feature analysis methods for complex strata mining faces in embodiments 1 to 7 of the present invention.

[0082] It should be noted that the computer-readable medium described above in this invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this invention, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0083] In some implementations, clients and servers can communicate using any currently known or future-developed network protocol such as HTTP, and can interconnect with digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (“LANs”), wide area networks (“WANs”), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future-developed networks.

[0084] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units 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. Those skilled in the art can understand and implement this without any creative effort.

[0085] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing the geological structural characteristics of mining faces in complex strata, characterized in that, include: Step 1: Divide the mining face into multiple segments, acquire and analyze the geological and hydrological data, segment labels, and segment anomaly data of each segment, and determine the first area label, anomaly level label, and sampling density of each segment; Step 2: Based on the sampling density, block label, and block anomaly data of each block, determine the mining physical data of the stratigraphic core sample of each sample number in each block, and determine multiple sample cluster sets and the sample cluster label of each sample cluster set; Step 3: Based on the block labels, first region labels, anomaly level labels, and sample cluster sets of all sample cluster labels of all blocks in the mining face, determine the partition label of each block, and determine the fourth region label of each block or the partition of each block. Step 4: Based on the segmentation label of each block, the fourth region label of each block or each segment of the segmentation, configure the waterproof solid-fluid coupling similar material for each block, obtain the block pressure data, and conduct solid-liquid coupling simulation test for each block.

2. The method for analyzing the geological structural characteristics of a complex stratum mining face according to claim 1, characterized in that, The mining face is divided into multiple segments. Geological and hydrological data, segment labels, and segment anomaly data for each segment are acquired and analyzed to determine the first area label and sampling density for each segment, including: The mining face is divided into multiple blocks. Based on geological sketches and roadway logging, geological and hydrological data of each block of the mining face are obtained. The geological and hydrological data includes geological and hydrological sub-data of multiple sub-segments. The geological and hydrological sub-data includes sub-segment labels, multiple geological parameters, geological parameter values ​​of each geological parameter, multiple hydrological parameters, and hydrological parameter values ​​of each hydrological parameter. Based on the roadway logging, the block labels and block anomaly data of each segment of the mining face are obtained. The block labels include normal and abnormal. If the block label is normal, the block anomaly data is empty. The block anomaly data includes the anomaly location and anomaly feature vector of multiple anomaly records. Obtain the regional division criteria, and based on the regional division criteria and the geological and hydrological data of each segment of the mining face, determine the first regional label of each segment of the mining face; The abnormal feature vectors of all abnormal records in the block abnormal data of each block labeled as abnormal are input into the abnormal detection model. Based on the output of the abnormal detection model, the abnormality level label of each block labeled as abnormal in the mining face is determined. The abnormality level label for each segment of the mining face is set to level 0 if the segment is labeled as normal. Based on the first region label and anomaly level label of each segment of the mining face, the sampling density of each segment of the mining face is determined.

3. The method for analyzing the geological structural characteristics of a complex stratum mining face according to claim 2, characterized in that, Based on the sampling density, block label, and block anomaly data of each block, the mining physical data of the formation core samples for each sample number in each block are determined, including: Based on the sampling density of each block of the mining face, multiple stratigraphic core samples and the sample number of each stratigraphic core sample are collected from each block of the mining face. Based on the abnormal location of each abnormal record in the block anomaly data of each block with the block label as abnormal, identify the sample number of the core sample of the stratum to which each abnormal record in the block anomaly data of each block with the block label as abnormal belongs. Based on the sample number of the core sample of the formation to which all anomalous records belong in the anomalous data of each block labeled as anomalous, the anomalous sample data of each block labeled as anomalous is determined. Mechanical property tests were conducted on each sample core sample with a sample number in each block of the mining face. Based on the test results, mining mechanical data of each sample core sample with a sample number in each block was determined. The mining mechanical data includes multiple mechanical parameters and the mechanical parameter value of each mechanical parameter. X-ray diffraction experiments were conducted on each sample core of each block in the mining face to determine the mining mineral data of each sample core of each block. The mining mineral data includes multiple mineral names and the mineral content of each mineral name. Electron microscopy was performed on each sample core of each block in the mining face to determine the mining micro data of each sample core of each block. The mining micro data includes a variety of micro parameters and the micro parameter value of each micro parameter. Based on the mining mechanics data, mining mineral data, and mining microdata of the stratigraphic core samples of each sample number in each block of the mining face, the mining physical data of the stratigraphic core samples of each sample number in each block of the mining face are determined.

4. The method for analyzing the geological structural characteristics of a complex stratum mining face according to claim 3, characterized in that, Determine multiple sample cluster sets and the sample cluster labels for each sample cluster set, including: Based on all mechanical parameters in the mining mechanics data, all mineral names in the mining mineral data, and all micro parameters in the mining micro data of all sample core samples from all blocks of the mining face, the mining physical vector is determined. Based on the mining physical vector and the mining mechanics data, mining mineral data, and mining micro data in the core samples of each sample number of each block of the mining face, the mining physical value vector of the core samples of each sample number of each block of the mining face is determined. Based on the mining physical value vector of all sample numbers of the formation core samples in each block of the mining face, the block physical data of each block is determined. Based on the mining physical value vectors of all sample-numbered stratigraphic core samples in the block physical data of all blocks of the mining face, cluster analysis is performed on all sample-numbered stratigraphic core samples in all blocks of the mining face to determine multiple sample cluster sets and sample cluster labels for each sample cluster set. The sample cluster set includes the mining physical data and mining physical value vectors of multiple stratigraphic core samples from multiple blocks.

5. The method for analyzing the geological structural characteristics of a complex stratum mining face according to claim 4, characterized in that, Based on the segment labels, first region labels, anomaly level labels, and sample cluster sets of all sample cluster labels for the mining face, the partition label for each segment is determined, and the fourth region label for each segment or each segment's partitioned segment is determined, including: Based on the first area labels of all segments of the mining face, determine the first area label set of the mining face; Based on the sample cluster labels of all sample cluster sets of the mining face, determine the cluster label set of the mining face; Map all first region labels in the first region label set of the mining face to all sample cluster labels in the cluster label set to determine the mapping label set of the mining face. The mapping label set includes multiple mapping pairs, and each mapping pair includes a first region label and a sample cluster label. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, the anomaly level label of each block with the block label being anomaly, and the anomaly sample data, calculate the sample category label, the second region label, the block dispersion value of each block, and the division label of the stratigraphic core sample of each sample number in each block of the mining face, and calculate the fourth region label of each block with the division label being undivided. Based on the segment label for each segment, the sample category label for all sample numbered core samples, and the second region label, a fourth region label for each segment is determined.

6. The method for analyzing the geological structural characteristics of a complex stratum mining face according to claim 5, characterized in that, Based on the segment label for each segment of the division, the sample category label for all sample-numbered stratigraphic core samples, and the second region label, a fourth region label for each segment of the division is determined, including: If the block label of the mining face is abnormal, the block is divided based on the abnormality level label, abnormal sample data, and sample category label and second area label of all sample numbered stratigraphic core samples. This determines multiple subdivision blocks for each block and subdivision sample data for each subdivision block. The subdivision sample data includes multiple sample numbered stratigraphic core samples and mining physical data of each sample numbered stratigraphic core sample. Based on the sample number of the core sample of the stratum to which all the abnormal records in the block abnormal data of each block with the block label as abnormal, and the core sample of the stratum with all the sample numbers of each segment, the segmentation abnormal data of each segment of each block with the block label as abnormal is determined. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, the anomaly level label of each block with an anomaly block label, the partition sample data of each partitioned block of each block with an anomaly block label, and the partition anomaly data, iteratively calculate the partition dispersion value of each partitioned block of each block with an anomaly block label after partitioning, until the dispersion value of each partitioned block is less than the dispersion threshold, and determine the fourth region label of each partitioned block of each block. If the block label of the mining face is normal, the block is divided based on the sample category label and second area label of the stratigraphic core sample of all sample numbers of the block, and the multiple subdivision blocks and subdivision sample data of each subdivision block are determined. The subdivision sample data includes the stratigraphic core sample of multiple sample numbers and the mining physical data of the stratigraphic core sample of each sample number. Based on all mapping pairs in the mapping label set of the mining face, the sample cluster set of each sample cluster label, the first region label of each block, the block label, and the partition sample data of each partitioned block of each block with normal block label, iteratively calculate the partition dispersion value of each partitioned block of each block with normal block label after partitioning, until the dispersion value of each partitioned block is less than the dispersion threshold, and determine the fourth region label of each partitioned block of each block.

7. The method for analyzing the geological structural characteristics of a complex stratum mining face according to claim 6, characterized in that, Based on the segmentation label of each block, and the fourth region label of each block or each segment's segmentation, a waterproof solid-fluid coupling similar material is configured for each block. Segment pressure data is obtained, and solid-liquid coupling simulation tests are conducted on each block, including: Based on the mining physical value vector of the core samples of the formation with the fourth region label of each undivided block and the physical data of all samples in the block, configure the waterproof solid-fluid coupling similar material of each undivided block of the mining face. Based on the mining physical value vector of all sample numbers in the physical data of each block segment with the division label, and the physical data of all sample numbers in the physical data of each segment of each block, the division physical data of each segment with the division label is determined. Based on the fourth region label of each segment of the division, the mining physical value vector of the stratum core sample with all sample numbers in the division physical data, the division label of the mining face is configured as the waterproof solid-fluid coupling similar sub-material of each segment of the division. Based on the waterproof solid-fluid coupling similar submaterials of all segments with the division label as each segment, the waterproof solid-fluid coupling similar material of the mining face with the division label as each segment is determined. Based on the sensor group buried in each segment of the mining face, the segment pressure data of each segment is acquired. The segment pressure data includes multiple pressure parameters and the pressure parameter value of each pressure parameter. Based on the block pressure data of each block and the waterproof solid-fluid coupling similar material, a solid-liquid coupling simulation test was conducted for each block.

8. A device for analyzing the geological structural characteristics of a complex stratum mining face, characterized in that, This method is used to perform the geological structural feature analysis method for complex strata mining faces as described in any one of claims 1 to 7.

9. A device for analyzing the geological structural characteristics of a complex stratum mining face, characterized in that, include: processor; Memory, used to store executable instructions; The processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the geological structure feature analysis method for complex strata mining faces as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, causes the processor to implement the geological structural feature analysis method for complex strata mining faces as described in any one of claims 1-7.

Images