Coal-rock interface advanced identification method and system based on image-spectrum-acoustic wave synergy

Abstract

The present invention provides a method and system for advanced recognition of coal-rock interface based on image-spectrum-acoustic wave collaboration, which relates to the technical field of coal-rock interface recognition, including obtaining borehole images and borehole wall acoustic waves at different positions in the drilling process; inputting the borehole images into a coal-rock boundary image recognition model to obtain a preliminary segmentation result of the coal-rock boundary; extracting mutation points of the borehole wall acoustic waves through stationary point analysis, obtaining mutation features of the wave velocity value based on the mutation points, and obtaining a preliminary recognition result of the coal-rock boundary through the mutation features; obtaining borehole wall spectral information, extracting elements and mineral components from the borehole wall spectral information to identify and verify the preliminary segmentation results and preliminary recognition results, and determining a fine coal-rock boundary; obtaining the mileage and strike information of the coal-rock boundary lines finally recognized in all different boreholes, connecting the coal-rock boundary lines in different boreholes, and determining the coal-rock interface in the spatial domain.

Description

Technical Field

[0001] The present disclosure relates to the technical field of coal-rock interface identification, and in particular to a method and system for advanced identification of coal-rock interface based on image-spectrum-acoustic wave collaboration. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art.

[0003] As the pillar of the energy industry, coal plays a vital role in urban development. Efficient coal mining is the key to ensuring energy utilization and improving economic benefits. In the process of coal mining, tunneling machines often collide with the coal-rock interface. Due to the different physical and mechanical properties of coal and rock, coal mining machinery is often damaged, such as the breakage of cutter teeth. In recent years, coal mine construction has gradually moved deeper into the ground, and there is an urgent need to promote the unmanned and intelligent construction of coal mines. Therefore, accurate identification of the coal-rock interface is one of the key factors to improve coal mining efficiency, and it is also an important part of promoting the unmanned and intelligent construction of coal mine shafts and tunnels.

[0004] Existing coal-rock identification technologies are mostly realized through manual experience, single-source information, and apparent information. Manual identification of coal and rock relies too much on expert experience, which can easily lead to misjudgment and omission of coal-rock interfaces, resulting in damage to coal mining machinery, poor coal quality, and other problems. In addition, the environment of deep underground tunnels is harsh, which causes great physiological and psychological damage to experts and does not meet the goal of unmanned and intelligent construction. Existing intelligent identification methods mostly use images or hyperspectral information, but the environment in coal mine tunnels is complex, and factors such as light and dust greatly affect the data quality of images, hyperspectral information, and complex heat sources hinder the application of infrared thermal imaging technology. In addition, existing technologies mostly perform apparent coal and rock identification on the mining surface, and cannot achieve advanced identification of the unmined coal and rock bodies in front. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and system for advanced recognition of coal-rock interface based on image-spectrum-acoustic wave collaboration. Through preliminary identification of images and acoustic waves and fine review of spectra, a coal-rock boundary image recognition model is established to perform preliminary segmentation of the boundary between coal and rock, and the mutation characteristics of acoustic wave velocity values ​​are extracted to perform fine recognition of the coal-rock interface, so as to accurately determine the coal-rock interface in the spatial domain.

[0006] According to some embodiments, the present disclosure adopts the following technical solutions:

[0007] The coal-rock interface advanced identification method based on image-spectrum-acoustic synergy includes:

[0008] Obtain borehole images and borehole wall sound waves at different positions during the drilling process;

[0009] Inputting the borehole image into a coal-rock boundary image recognition model to obtain a preliminary segmentation result of the coal-rock boundary line;

[0010] The mutation points of the borehole wall acoustic wave are extracted through stationary point analysis, the mutation characteristics of the wave velocity value are obtained based on the mutation points, and the preliminary recognition results of the coal-rock boundary are obtained through the mutation characteristics.

[0011] Obtain the spectral information of the hole wall, extract the elements and mineral components in the spectral information of the hole wall, verify the preliminary segmentation results and preliminary identification results, and determine the fine coal-rock boundary line;

[0012] The mileage and strike information of the coal-rock boundary lines finally identified in all different boreholes are obtained, the coal-rock boundary lines in different boreholes are connected, and the coal-rock interface in the spatial domain is determined.

[0013] According to some embodiments, the present disclosure adopts the following technical solutions:

[0014] The coal-rock interface advanced identification system based on image-spectrum-acoustic wave synergy includes:

[0015] A data acquisition module, used to acquire drilling images and hole wall sound waves at different positions during the drilling process;

[0016] The module for preliminary identification of the boundary line is used to input the borehole image into the coal-rock boundary image identification model to obtain the preliminary segmentation result of the coal-rock boundary line; extract the mutation point of the borehole wall sound wave through stationary point analysis, obtain the mutation feature of the wave velocity value based on the mutation point, and obtain the preliminary identification result of the coal-rock boundary line through the mutation feature;

[0017] The boundary line review module is used to obtain the hole wall spectrum information, extract the elements and mineral components in the hole wall spectrum information, and review the preliminary segmentation results and preliminary identification results to determine the fine coal-rock boundary line;

[0018] The coal-rock interface acquisition module is used to obtain the mileage and strike information of the coal-rock boundary lines finally identified in all different boreholes, connect the coal-rock boundary lines in different boreholes, and determine the coal-rock interface in the spatial domain.

[0019] According to some embodiments, the present disclosure adopts the following technical solutions:

[0020] A non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave collaboration is implemented.

[0021] According to some embodiments, the present disclosure adopts the following technical solutions:

[0022] An electronic device comprises: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the coal-rock interface advance identification method based on image-spectrum-acoustic wave synergy.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] The disclosed method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave collaboration, the method for advanced identification of coal-rock interface by collaborative image, spectrum and acoustic wave, performs preliminary identification of coal-rock boundary through the established coal-rock boundary image recognition model and acoustic wave velocity anomaly characteristics, adopts spectral technology to identify the geochemical composition of the hole wall to verify the identification result, makes full use of image, spectrum, acoustic wave and other technologies, integrates multi-source information of appearance, composition and physical mechanics of coal and rock, and after preliminary identification of image and acoustic wave and detailed review of spectrum, breaks the drawback of identifying coal and rock only through single-source information, eliminates the theoretical blind spot of coal-rock identification, ensures the detailed identification of coal-rock interface, and guides the formulation of plans for on-site cutting machinery.

[0025] The disclosed method for advance identification of coal-rock interface based on image-spectrum-acoustic wave collaboration performs advance identification of the coal seam rock mass in front of the mining face through cross-advance drilling, thereby overcoming the drawback of the prior art of only identifying the excavated face. The cross-arrangement of drilling holes also avoids geological blind spots caused by the consistency of the coal-rock interface and the drilling direction.

[0026] The disclosed coal-rock interface advance identification method based on image-spectrum-acoustic wave synergy is highly automated and intelligent. The work process in the mine and tunnel does not require manpower and can be directly applied only through the intelligent control of mechanical devices, thus ensuring the construction safety in the mine and tunnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings constituting a part of the present disclosure are used to provide a further understanding of the present disclosure. The illustrative embodiments of the present disclosure and their descriptions are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0028] Figure 1 This is a flow chart of a method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave synergy according to an embodiment of the present disclosure;

[0029] Figure 2 A schematic diagram of annotating a data set of a coal-rock boundary image recognition model according to an embodiment of the present disclosure;

[0030] Figure 3 This is a diagram of the arrangement of drilling holes in an embodiment of the present disclosure (taking some drilling holes as an example);

[0031] Figure 4 A schematic diagram of the coal-rock interface in an embodiment of the present disclosure (taking eight boreholes as an example);

[0032] Figure 5 This is a diagram of an automatic telescopic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0033] The present disclosure is further described below in conjunction with the accompanying drawings and embodiments.

[0034] It should be noted that the following detailed descriptions are all illustrative and are intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present disclosure belongs.

[0035] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present disclosure. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0036] Example 1

[0037] In one embodiment of the present disclosure, a method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave synergy is provided, wherein the coal-rock boundary is initially identified by using an established coal-rock boundary image recognition model and acoustic wave velocity anomaly characteristics, and the geochemical composition of the hole wall is identified by using spectral technology to review the identification results, including:

[0038] Step 1: Acquire drilling images and hole wall sound waves at different positions during the drilling process;

[0039] Step 2: input the borehole image into a coal-rock boundary image recognition model to obtain a preliminary segmentation result of the coal-rock boundary line;

[0040] The mutation points of the borehole wall acoustic wave are extracted through stationary point analysis, the mutation characteristics of the wave velocity value are obtained based on the mutation points, and the preliminary recognition results of the coal-rock boundary are obtained through the mutation characteristics.

[0041] Step 3: Obtain the spectral information of the hole wall, extract the elements and mineral components in the spectral information of the hole wall, identify and review the preliminary segmentation results and preliminary identification results, and determine the fine coal-rock boundary line;

[0042] Step 4: Obtain the mileage and strike information of the coal-rock boundary lines finally identified in all different boreholes, connect the coal-rock boundary lines in different boreholes, and determine the coal-rock interface in the spatial domain.

[0043] As an embodiment, the specific implementation process of the coal-rock interface advance identification method based on image-spectrum-acoustic wave synergy disclosed in the present invention is as follows:

[0044] Step 1: Collect coal samples, rock samples and coal-rock mixture samples along the mines and tunnels through geological surveys, mineral exploration and other means to establish a coal-rock sample library;

[0045] Step 2: With reference to the actual coal-rock interface in the established coal-rock sample library, the coal and rock samples contained in the sample library are processed and spliced ​​to establish coal-rock splicing plates of different splicing types;

[0046] Step 3: Obtain a large amount of image data of the established coal-rock splicing plate and use it as a data set to train a coal-rock boundary image recognition model;

[0047] Step 4: After the preliminary preparations for the actual engineering application of steps 1-3 are completed, during the actual construction of the shaft and tunnel, cross-advance drilling is performed on the mining face, and the dust, rock slag and coal slag inside the borehole are blown out by circulating air;

[0048] Step 5: Mount the high-definition camera, acoustic wave detector and spectral probe on the top of the automatic telescopic device and move them into the borehole at a constant speed;

[0049] Step 6: During the in-depth drilling process, the borehole wall is monitored and tested in real time through images and sound waves. The coal-rock boundary is preliminarily segmented through the coal-rock boundary image recognition model. The sudden change characteristics of the sound wave velocity value are extracted to identify the coal-rock interface. The coal-rock boundary line recognition results of the image and sound waves are recorded.

[0050] Step 7: During the withdrawal of the automatic telescopic device, the elements and mineral compositions of the hole wall are obtained by spectroscopy to review the coal-rock interface recognition results detected by image and acoustic wave detection, and the correct coal-rock boundary is retained;

[0051] Step 8: Collect the mileage and strike information of the coal-rock boundary lines in all boreholes, connect the boundary lines in different boreholes, and determine the coal-rock interface in the spatial domain.

[0052] Furthermore, in step 1, by means of geological survey, mineral exploration and other means, coal samples, rock samples and coal-rock mixture samples stored along the mines and tunnels are collected to establish a coal-rock sample library;

[0053] Specifically, geological survey and mineral exploration methods mainly include surface exploration, geological mapping, drilling and geological sketching inside tunnels;

[0054] The coal and rock sample library established includes rocks that have not experienced weathering or alteration, rocks that have experienced weathering or alteration, different types of coal blocks, and mixtures of the above rocks and coal that are common in the area along the target roadway;

[0055] In this embodiment, after preliminary surface exploration and collection of shaft and tunnel samples, it was found that the rocks along the shaft and tunnel were mainly mudstone, and the type of coal produced was mainly bituminous coal. At the same time, blocks where bituminous coal and mudstone coexisted were collected to establish a coal and rock sample library for the shaft and tunnel engineering.

[0056] Furthermore, in step 2, the actual coal-rock interface in the established coal-rock sample library is used as a reference to process and splice the coal and rock samples contained in the sample library to establish coal-rock splicing plates of different splicing types;

[0057] Specifically, with the actual coal-rock interface in the established coal-rock sample library as a reference, the processing and splicing of coal and rock samples refers to cutting and grinding coal blocks and rocks of uneven thickness to process the above samples into plates, and then bonding them to form coal-rock splicing plates with different splicing methods and splicing line directions;

[0058] In this embodiment, information such as the splicing angles and the direction of the splicing lines of the coexisting blocks of bituminous coal and rock in the coal-rock sample library is collected by means of manual sketching and photographing, and a corresponding test plan is formulated based on this information. The bituminous coal and shale in the sample library are processed into circular plates with a diameter of 20 cm and a thickness of 3 cm to establish a coal-rock splicing plate sample library.

[0059] Furthermore, in step 3, a large amount of image data of the established coal-rock splicing plate is obtained and used as a data set for training to obtain a coal-rock boundary image recognition model;

[0060] Specifically, obtaining massive image data of the coal-rock splicing plate includes: in an indoor environment, by simulating the lighting conditions in the tunnel borehole, using a high-definition camera to shoot the coal-rock splicing plate to obtain massive image data thereof.

[0061] The coal-rock boundary image recognition model can generally be a supervised model or an unsupervised model. The supervised model uses semantic segmentation to first mark the boundary lines of the training data and input them into models such as Deeplabv3+ for training.

[0062] In this embodiment, a high-definition camera is used to take photos of samples in the coal-rock splicing plate sample library, with a data volume of more than 1,000 photos, and each photo data is manually annotated, such as Figure 2As shown in the figure, the annotation content includes the coal-rock boundary, coal, and rock, and the data is divided into a training set and a test set in a ratio of 2:1. The Deeplabv3+ semantic segmentation model is used for supervised training. The model is divided into two parts: encoder and decoder. The encoder part includes backbone and aspp.

[0063] The specific process is as follows: the labeled image is input into the backbone part of the encoder to obtain the output feature map, which is divided into two parts: one part is the feature map output by the last layer of convolution, and the other part is the feature map of the intermediate low-level features; the first part of the backbone output is sent to the ASPP module, and the second part is sent to the Decoder module. The ASPP module accepts the first part of the backbone output as input, and uses four different dilation rate hollow convolution blocks (including convolution, BN, activation layer) and a global average pooling block (including pooling, convolution, BN, activation layer) to obtain a total of five sets of feature maps. After concat, they pass through a 1*1 convolution block (including convolution, BN, activation, dropout layer), and finally sent to the Decoder module.

[0064] Processing of the decoder part: Receive the low-level feature maps from the backbone middle layer and the output from the ASPP module as input. First, use 1*1 convolution to reduce the channel dimension of the low-level feature maps from 256 to 48; then, interpolate and upsample the feature maps from ASPP to obtain feature maps of the same size as the low-level feature maps;

[0065] Next, the low-level feature maps of channel dimensionality reduction and the feature maps obtained by linear interpolation upsampling are concatenated using concat and sent to a set of 3*3 convolution blocks for processing; finally, linear interpolation upsampling is performed again to obtain a predicted image with the same resolution as the original image.

[0066] Through the above steps, the separation of different coal areas and rock areas can be achieved, thereby obtaining a coal-rock boundary image recognition model with a recognition accuracy rate exceeding 95%.

[0067] Further, in step 4, after the preliminary preparation work for the actual engineering application of steps 1-3 is completed, during the actual construction of the shaft and tunnel, the mining face is cross-drilled in advance, and the dust, rock slag and coal slag inside the borehole are blown out by circulating air;

[0068] Specifically, after the preliminary preparation work is completed, during the actual construction of the shafts and tunnels, cross-advance drilling is carried out on the mining face, and the dust, rock slag, coal slag, etc. inside the boreholes are blown out by circulating air.

[0069] Cross advance drilling refers to drilling from the left and right sides of the mining face at the same angle as the mining face, to prevent the interface from being missed due to the coincidence of the coal-rock interface and the drilling angle, and to eliminate the geological blind spots of advance drilling;

[0070] The dust, rock slag and coal slag inside the borehole are blown out by the reverse wind pressure generated by the drilling rig to blow out the waste generated by the drilling;

[0071] In this embodiment, the mining surface of the shaft and tunnel is drilled at certain points, and the drilling plan is as follows: Figure 3 As shown, with the center line as the dividing line, the left hole is drilled to the right, and the right hole is drilled to the left, while maintaining an angle of 45° with the mining surface. The drilling is carried out using a pneumatic drill with a drilling depth of 10m. During the drilling process, the waste generated during drilling is blown out.

[0072] Further, in step 5, a high-definition camera, an acoustic wave detector, and a spectral probe are mounted on the top of the automatic telescopic device and extended into the borehole at a uniform speed;

[0073] Specifically, the overall diameter of the automatic telescopic device is smaller than the diameter of the drilled hole. The top is provided with mounting holes for a high-definition camera, an acoustic wave detector, and a spectral probe. The power supply lines and data lines of the relevant equipment are hidden inside the device through the corresponding wire holes on the telescopic device to prevent damage caused by water seepage in the hole. Figure 5 shown.

[0074] The acoustic wave detector includes an acoustic wave transmitter and an acoustic wave receiver, and the spectrum probe is an infrared spectrum probe, a Raman spectrum probe, an X-ray diffraction spectrum probe, a laser induced breakdown spectrometer probe, an X-ray fluorescence spectrum probe, etc.

[0075] In this embodiment, a high-definition camera, an acoustic wave transmitter, an acoustic wave receiver, an infrared spectrum probe, and a laser induced breakdown spectrometer probe are mounted on the top of the automatic telescopic device and extended at a uniform speed of 1 m / min.

[0076] Furthermore, in step 6, during the deep drilling process, the borehole wall is monitored and tested in real time by using images and sound waves, the coal-rock boundary is preliminarily segmented by using the coal-rock boundary image recognition model, the mutation characteristics of the acoustic wave velocity value are extracted to identify the coal-rock interface, the mutation point is extracted by the stationary point analysis method, the location of the mutation point is the location of the interface, and the coal-rock boundary line recognition results of the image and sound waves are recorded;

[0077] Specifically, the monitoring and testing of the borehole wall by images and sound waves means that the camera and sound wave detector continue to work during the deep drilling process of the automatic telescopic device. The principle of image recognition is that there is a clear boundary between the two colors of materials, and the coal-rock boundary is identified by identifying this boundary; the principle of sound wave recognition is that the propagation speed of sound waves is inconsistent between materials with different physical properties, so the boundary between coal and rock will cause a sudden change in wave speed, and the coal-rock boundary is identified by this wave speed mutation feature;

[0078] Recording the coal-rock boundary line identification results of images and acoustic waves is to record in detail the mileage, position in the hole and extension direction of the coal-rock boundary identified by image and acoustic wave technical means;

[0079] However, the coal-rock boundary recognition results of images and acoustic waves are not necessarily all correct. In image recognition, weathering, alteration and other effects will cause the rock color to change, and image recognition is prone to recognize the boundary between the color abnormal area and the normal surrounding rock area caused by the above effects as the coal-rock boundary, and the cracks inside the hole wall are also likely to be recognized as the coal-rock boundary; in acoustic wave recognition, if the rock and coal seam are intact, the acoustic wave test can effectively identify the boundary between the two substances, but if the rock or coal seam is disturbed by geological effects, construction disturbances and other factors and is broken, the acoustic wave test cannot accurately identify the mutation point of the transition between the two substances, resulting in misjudgment. Therefore, it is necessary to review the recognition results through the component information belonging to the essence of the material to ensure the accuracy of the results.

[0080] In this embodiment, during the process of the automatic telescopic device entering at a uniform speed, the high-definition camera and the acoustic wave detector continue to work, and the collected information is returned to the computer through the wireless / Bluetooth device. The image information is identified in real time through the established coal-rock boundary image recognition model, and the mutation point of the acoustic wave information is extracted through stationary point analysis. The direction information and mileage position of each identification boundary line are recorded, including:

[0081] 1) Data preprocessing

[0082] First, the data is cleaned to remove noise, then the data is converted to convert the sequence data into a continuous difference sequence, and finally the continuous difference sequence is smoothed through a filter to reduce the impact of noise on the analysis results.

[0083] 2) Stationary point detection

[0084] Perform stationary point detection on the continuous difference sequence to find the stationary point in the continuous difference sequence, that is, the mutation point. The position of the mutation point is the position of the interface.

[0085] Furthermore, in step 7, during the withdrawal of the automatic telescopic device, the elements and mineral compositions of the hole wall are obtained by the spectral probe to review the coal-rock interface recognition results detected by the image and the acoustic wave, and the correct coal-rock boundary line is retained;

[0086] Specifically, identifying the elements and mineral components of the hole wall by spectroscopy includes obtaining the element information of the hole wall by means of laser induced breakdown spectroscopy, X-ray fluorescence spectroscopy, etc., and obtaining the mineral information of the hole wall by means of infrared spectroscopy, Raman spectroscopy, and X-ray diffraction spectroscopy;

[0087] Reviewing the coal-rock boundary line identification results of images and sound waves means that during the retraction of the telescopic device, the element and mineral composition of the materials on both sides of the boundary line are identified in a targeted manner through the recorded information such as the position of the coal-rock boundary line identification results. Taking Si and C elements as examples, the Si element in coal is far less than that in rock, while the C element is much higher than that in rock; taking sulfides as an example, the sulfides in coal are much higher than those in rock.

[0088] In this embodiment, when the automatic telescopic device reaches the top of the borehole and finishes collecting the interface information, the recorded position is used as the withdrawal pause point, and each is checked one by one in the order from the inside to the outside. When the target position is reached, mineral and element tests are carried out by infrared spectroscopy and laser induced breakdown spectroscopy respectively, with Si, S, C elements and sulfide content as indicators. There should be significant differences on both sides of the dividing line, and data without significant differences will be eliminated.

[0089] Specifically, for the infrared spectrum: different minerals contain specific molecular groups. When receiving light radiation, these groups will absorb part of the radiation, so that the reflectivity information received by the instrument will have absorption valleys. Different minerals are different in the shape and position of the absorption valleys. The present invention identifies the type of minerals through spectral angle matching and uses the fully constrained least squares decomposition method to obtain the mineral content.

[0090] Laser-induced breakdown spectroscopy: The type and content of elements can be directly output during testing without the need for subsequent interpretation.

[0091] In step 8, the mileage and strike information of the coal-rock boundary lines in all boreholes are collected, the boundary lines in different boreholes are connected, and the coal-rock interface in the spatial domain is determined.

[0092] Specifically, collecting the mileage and strike information of the coal-rock boundary line inside the borehole includes collecting the mileage and strike information of the correct coal-rock boundary line after spectral verification.

[0093] Connecting the boundary lines in different boreholes to determine the coal-rock interface means linking the 0° and 180° positions of the coal-rock boundary line at each borehole identification with the corresponding positions of other boreholes to form a coal-rock interface.

[0094] In this embodiment, after checking the coal-rock boundary line through the above steps, the boundary line information in each borehole is collected, and each borehole is connected according to the 0° and 180° of the circular borehole as the beginning and the end, and finally a coal-rock interface is formed, and a three-dimensional visualization is performed, such as Figure 4 shown.

[0095] Example 2

[0096] In one embodiment of the present disclosure, a coal-rock interface advance recognition system based on image-spectrum-acoustic wave synergy is provided, comprising:

[0097] A data acquisition module, used to acquire drilling images and hole wall sound waves at different positions during the drilling process;

[0098] The module for preliminary identification of the boundary line is used to input the borehole image into the coal-rock boundary image identification model to obtain the preliminary segmentation result of the coal-rock boundary line; extract the mutation point of the borehole wall sound wave through stationary point analysis, obtain the mutation feature of the wave velocity value based on the mutation point, and obtain the preliminary identification result of the coal-rock boundary line through the mutation feature;

[0099] The boundary line review module is used to obtain the hole wall spectrum information, extract the elements and mineral components in the hole wall spectrum information, and review the preliminary segmentation results and preliminary identification results to determine the fine coal-rock boundary line;

[0100] The coal-rock interface acquisition module is used to obtain the mileage and strike information of the coal-rock boundary lines finally identified in all different boreholes, connect the coal-rock boundary lines in different boreholes, and determine the coal-rock interface in the spatial domain.

[0101] Example 3

[0102] In one embodiment of the present disclosure, a non-transitory computer-readable storage medium is provided, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave synergy is implemented.

[0103] Example 4

[0104] An electronic device is provided in an embodiment of the present disclosure, characterized in that it includes: a processor, a memory and a computer program; wherein the processor is connected to the memory, and the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes the method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave synergy.

[0105] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0106] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0107] Although the above describes the specific implementation methods of the present disclosure in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present disclosure. Technical personnel in the relevant field should understand that on the basis of the technical solution of the present disclosure, various modifications or variations that can be made by those skilled in the art without creative work are still within the scope of protection of the present disclosure.

Claims

1. A coal-rock interface advanced identification method based on image-spectrum-acoustic wave synergy, characterized in that: include: Obtain borehole images and borehole wall sound waves at different positions during the drilling process; Obtaining borehole images and borehole wall sound waves at different positions during the drilling process, including: drilling by cross-advance drilling, drilling holes at points on the mining surface of the shaft and tunnel, drilling from the left and right sides of the mining surface at the same angle as the mining surface, blowing out dust, rock slag and coal slag inside the borehole through the reverse wind pressure generated by the drilling rig, carrying a high-definition camera, an acoustic wave detector and a spectrum probe to the top of the automatic telescopic device, and extending them into the borehole at a uniform speed for data collection; Inputting the borehole image into a coal-rock boundary image recognition model to obtain a preliminary segmentation result of the coal-rock boundary line; The mutation points of the borehole wall acoustic wave are extracted through stationary point analysis, the mutation characteristics of the wave velocity value are obtained based on the mutation points, and the preliminary recognition results of the coal-rock boundary are obtained through the mutation characteristics. Obtain the spectral information of the hole wall, extract the elements and mineral components in the spectral information of the hole wall, verify the preliminary segmentation results and preliminary identification results, and determine the fine coal-rock boundary line; The mileage and strike information of the coal-rock boundary lines finally identified in all different boreholes are obtained, the coal-rock boundary lines in different boreholes are connected, and the coal-rock interface in the spatial domain is determined.

2. The coal-rock interface advance identification method based on image-spectrum-acoustic wave synergy according to claim 1 is characterized in that: The coal-rock boundary image recognition model includes a supervised model and an unsupervised model. The supervised model first labels the boundary lines of the training data through semantic segmentation and inputs them into the Deeplabv3+ model for training; the unsupervised learning model directly learns the unlabeled data through the K-means and ICCV21 algorithms, and performs unsupervised classification by identifying the pixel change features of the image.

3. The coal-rock interface advanced identification method based on image-spectrum-acoustic wave synergy according to claim 1 is characterized in that: During the process of deep drilling by the automatic telescopic device, the high-definition camera and acoustic wave detector continue to work. The propagation speed of acoustic waves is inconsistent between materials with different physical properties, which will cause a sudden change in wave velocity at the boundary between coal and rock. The coal-rock boundary can be identified by the sudden change in wave velocity value.

4. The coal-rock interface advanced identification method based on image-spectrum-acoustic wave synergy according to claim 1 is characterized in that: During the retraction process of the automatic telescopic device, the elements and mineral composition of the hole wall are obtained through the spectral probe to review the coal-rock interface identification results detected by image and acoustic wave detection to retain the correct coal-rock boundary line; the elements and mineral composition include the use of laser induced breakdown spectroscopy and X-ray fluorescence spectroscopy to obtain the element information of the hole wall, and the use of infrared spectroscopy, Raman spectroscopy, and X-ray diffraction spectroscopy to obtain the mineral information of the hole wall.

5. The coal-rock interface advance identification method based on image-spectrum-acoustic wave synergy according to claim 1 is characterized in that: The 0° and 180° positions of the coal-rock boundary line at each borehole identification are linked to the corresponding positions of other boreholes to form a coal-rock interface.

6. The coal-rock interface advanced identification method based on image-spectrum-acoustic wave synergy according to claim 1 is characterized in that: The training data for the coal-rock boundary image recognition model is obtained in the following way: coal samples, rock samples and coal-rock mixture samples stored along the mines and tunnels are collected to establish a coal-rock sample library; with the actual coal-rock interface in the coal-rock sample library as a reference, the coal and rock samples contained in the sample library are processed and spliced ​​to establish coal-rock splicing plates of different splicing types; massive image data of the coal-rock splicing plates are obtained and used as a data set to train the coal-rock boundary image recognition model.

7. A coal-rock interface advance identification system based on image-spectrum-acoustic wave synergy, which executes a coal-rock interface advance identification method based on image-spectrum-acoustic wave synergy as claimed in any one of claims 1 to 6, characterized in that: include: A data acquisition module, used to acquire drilling images and hole wall sound waves at different positions during the drilling process; The module for preliminary identification of the boundary line is used to input the borehole image into the coal-rock boundary image identification model to obtain the preliminary segmentation result of the coal-rock boundary line; extract the mutation point of the borehole wall sound wave through stationary point analysis, obtain the mutation feature of the wave velocity value based on the mutation point, and obtain the preliminary identification result of the coal-rock boundary line through the mutation feature; The boundary line review module is used to obtain the hole wall spectrum information, extract the elements and mineral components in the hole wall spectrum information, and review the preliminary segmentation results and preliminary identification results to determine the fine coal-rock boundary line; The coal-rock interface acquisition module is used to obtain the mileage and strike information of the coal-rock boundary lines finally identified in all different boreholes, connect the coal-rock boundary lines in different boreholes, and determine the coal-rock interface in the spatial domain.

8. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave synergy as described in any one of claims 1-6 is implemented.

9. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes the method for advanced identification of coal-rock interface based on image-spectrum-acoustic wave synergy as described in any one of claims 1-6.

Images