A mine pipeline flow analysis method based on digital twin model

Abstract

The present invention discloses a mine pipeline flow analysis method based on a digital twin model, which relates to the technical field of mine pipeline monitoring. By performing laser scanning on a target mine pipeline, point cloud data of the target mine pipeline is obtained, and a digital pipeline twin model corresponding to the target gold mine pipeline is constructed using the obtained point cloud data. Then, data acquisition terminals are arranged at various positions in the target mine pipeline to obtain flow data in real time, and the obtained flow data is updated to the digital pipeline twin model. The digital pipeline twin model performs simulation according to the obtained flow data, and determines whether there is an abnormality in the flow data in the target mine pipeline according to the simulation result. After the abnormality occurs, the abnormal location interval and the abnormal cause are determined, thereby realizing real-time monitoring of the inside of the target mine pipeline, and then timely arranging maintenance when an abnormality occurs to eliminate safety hazards.

Description

Technical Field

[0001] The present invention relates to the technical field of mine pipeline monitoring, and in particular to a mine pipeline flow analysis method based on a digital twin model. Background Art

[0002] In the process of underground mining, a large amount of water will be collected underground due to the outflow of water in the strata, the infiltration of rainwater and water in rivers, water-sand filling and underground water supply of hydraulic mining wells. If the accumulated water cannot be discharged in time, underground production may be hindered, underground safety cannot be guaranteed, and serious accidents may occur, posing a great threat to people's lives and national property. Therefore, underground drainage is extremely important. In the drainage process, dust, silt and other debris will be discharged with water, and will slowly accumulate at the bottom of the pipeline after a long time, causing the drainage capacity of the pipeline to decrease, posing serious safety hazards. Therefore, the water flow of the pipeline must be monitored in real time to determine whether the drainage is normal and whether the sediment in the pipeline exceeds the limit, so as to arrange maintenance in time and eliminate safety hazards; for this purpose, a mine pipeline flow analysis method based on a digital twin model is provided. Summary of the invention

[0003] The purpose of the present invention is to provide a mine pipeline flow analysis method based on a digital twin model.

[0004] The purpose of the present invention can be achieved by the following technical solution: A mine pipeline flow analysis method based on a digital twin model comprises the following steps:

[0005] Step S1: collecting mine pipeline data of the target mine pipeline, and building a corresponding digital pipeline twin model according to the collected mine pipeline data;

[0006] Step S2: Determine the corresponding data acquisition nodes according to the constructed digital pipeline twin model, and arrange the corresponding data acquisition terminals at the determined data acquisition nodes;

[0007] Step S3: Collect the flow data of each data collection node through the data collection terminal, integrate the collected flow data with the digital pipeline twin model, and synchronize the data of the digital pipeline twin model;

[0008] Step S4: Simulate the operating status of the digital pipeline twin model, and analyze whether the flow status at each location in the mine pipeline is normal based on the simulation results.

[0009] Furthermore, the target mine pipeline data is collected, and the process of constructing a corresponding digital pipeline twin model according to the collected mine pipeline data includes:

[0010] Use laser to scan the inside of the target mine pipeline to obtain corresponding point cloud data, import the obtained point cloud data into the point cloud processing software, and generate the corresponding pipeline point cloud model;

[0011] The generated pipeline point cloud model is divided into several point cloud regions, and the number of point clouds in each point cloud region is traversed to obtain the point cloud density of each point cloud region, which is recorded as D;

[0012] Set the point cloud density threshold range, recorded as (D1, D2);

[0013] Compare the point cloud density of each point cloud area with the set point cloud density threshold range, and optimize the pipeline point cloud model according to the comparison result;

[0014] When D∈(D1, D2), it means that the corresponding point cloud area does not need to be optimized;

[0015] When D≤D1, it means that the point cloud density in the corresponding point cloud area is too low, and the point cloud area is marked as a sparse area, and the sparse area needs to be filled and optimized;

[0016] When D≥D2, it means that the point cloud density in the corresponding point cloud area is too high, and the point cloud area is marked as a dense area, and redundancy optimization needs to be performed on the dense area;

[0017] After completing the optimization of the pipeline point cloud model, the corresponding structural labels are set in the pipeline point cloud model according to the layout of the target mine pipeline to obtain the corresponding digital pipeline twin model. The structural labels include connection point labels, valve body labels and pipeline direction labels.

[0018] Furthermore, the process of optimizing the filling of sparse areas includes:

[0019] Traverse the point clouds existing in the sparse area, and use the existing point clouds as reference points to generate the point cloud influence area;

[0020] Mark the areas in the sparse area that are not covered by the point cloud influence area as blank areas;

[0021] Divide the blank area into a plurality of blank sub-areas, wherein the size and the outline of the blank sub-areas are the same as the point cloud influence area;

[0022] Mark the point cloud influence area adjacent to the boundary of the blank sub-area, and obtain the point cloud value corresponding to the point cloud influence area;

[0023] Fill the mean value of each point cloud value into the blank sub-region, generate a corresponding point cloud, and mark the blank sub-region as a filled sub-region;

[0024] After all blank sub-regions adjacent to the point cloud influence region are filled, the remaining blank sub-regions not adjacent to the point cloud influence region are obtained;

[0025] Mark the filled sub-region adjacent to the boundary of the blank sub-region, and obtain the point cloud value corresponding to the filled sub-region;

[0026] The mean value of each point cloud value is filled into the blank sub-region, and a corresponding point cloud is generated. The blank sub-region is marked as a filled sub-region, and the filling of all blank sub-regions is completed by analogy.

[0027] Furthermore, the process of optimizing the redundancy removal in the dense area includes:

[0028] Construct a topological network for the dense area and mark the center points of each topological grid as topological points;

[0029] Get the point clouds existing in each topological grid and the corresponding point cloud values;

[0030] Obtain the point cloud discrete coefficient Dx of the topological grid;

[0031] Set the discrete coefficient threshold L;

[0032] When Dx≤L, it means that the discrete degree of the point cloud of the corresponding topological grid is low, and the point cloud of the topological grid is normalized to complete the redundancy optimization of the point cloud in the topological grid;

[0033] When Dx>L, it means that the point cloud of the corresponding topological grid is highly discrete. The maximum point cloud value and the minimum point cloud value in the topological grid are marked, and the corresponding topological sets are established respectively. The point clouds corresponding to the marked maximum point cloud value and the minimum point cloud value are mapped to the corresponding topological sets respectively.

[0034] After removing the point cloud mapped to the topological set, the point cloud discrete coefficient of the topological grid is recalculated and used to determine the degree of point cloud discreteness of the topological grid;

[0035] If the point cloud has a high degree of discreteness, the point clouds corresponding to the maximum and minimum point cloud values ​​in the topological grid are mapped to the corresponding topological set, and so on;

[0036] If the point cloud has a low degree of discreteness, the point cloud of the topological grid is normalized, and a point cloud influence area is generated for the point cloud in the topological set, and a sub-topological grid is generated in the topological grid according to the generated point cloud influence area.

[0037] Furthermore, according to the constructed digital pipeline twin model, the corresponding data acquisition nodes are determined, and the corresponding data acquisition terminals are arranged at the determined data acquisition nodes. The process includes:

[0038] Read each structural tag in the digital pipeline twin model, mark the location of each structural tag as the corresponding data acquisition node, and set the corresponding data acquisition terminal at the data acquisition node corresponding to the connection point tag and valve body tag in the target mine pipeline;

[0039] A corresponding data acquisition terminal group is set at a data acquisition node corresponding to the pipeline direction label in the target mine pipeline, and the data acquisition terminal group includes at least two data acquisition terminals;

[0040] Setting a sequence relationship for the data acquisition terminals in the data acquisition terminal group according to the pipeline direction labels;

[0041] According to the location of the data collection node of the pipeline where the connection point label is located, it is associated with at least one data collection terminal group, and the corresponding relative position relationship of the endpoints is set;

[0042] According to the position of the pipeline where the valve body label is located, it is associated with the two data acquisition terminals in the data acquisition terminal group that are closest to the valve body label, and the relative position relationship of the valve body is set.

[0043] Furthermore, the flow data of each data collection node is collected through the data collection terminal, and the process of fusing the collected flow data with the digital pipeline twin model includes:

[0044] Obtain the traffic data of the corresponding location in real time through the data collection terminal;

[0045] Set a data upload cycle, package the traffic data obtained in a data upload cycle, obtain the corresponding traffic data packet, and generate a time span label corresponding to the time span of the data upload cycle. Insert the generated time span label into the obtained traffic data packet and upload it to the digital pipeline twin model.

[0046] The digital pipeline twin model imports the received traffic data packet into the corresponding structure tag.

[0047] Furthermore, the process of synchronizing the data of the digital pipeline twin model includes:

[0048] Read the time span tag in the traffic data packet received by the digital pipeline twin model, and build the corresponding time axis according to the read time span tag;

[0049] Parsing the traffic data packet corresponding to the time span label, obtaining the traffic data corresponding to the time span label, and mapping the obtained traffic data to the time axis;

[0050] Constructing a multi-track timeline, wherein the multi-track timeline includes a plurality of blank tracks, and associating each blank track with a structure tag;

[0051] Traverse the timeline with the same structure tag as the blank track, and map the timeline to the corresponding blank track;

[0052] According to the time span corresponding to the time span label of the time axis, the flow data is aligned with the corresponding time period on the multi-track time axis, thereby completing the data synchronization of the flow data obtained by each data collection terminal.

[0053] Furthermore, the operation status of the digital pipeline twin model is simulated, and the process of analyzing whether the flow status at each location in the mine pipeline is normal according to the simulation results includes:

[0054] Traverse each mine pipeline in the digital pipeline twin model and divide the mine pipeline into corresponding pipeline segments according to the location of the connection point labels;

[0055] Sort the various data collection terminals in the pipeline section, and determine the starting point and the end point according to the sorting results;

[0056] Generate prediction values ​​for each data collection terminal based on the flow data at the starting point;

[0057] Compare the flow data obtained by each data collection terminal with the corresponding predicted value to obtain a deviation value;

[0058] Set the allowable deviation range;

[0059] If the deviation value is within the allowable deviation range, it means that the flow data of the corresponding data collection terminal is normal;

[0060] If the deviation value is not within the allowable deviation range, it means that the flow data at the location of the data collection terminal is abnormal.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] By performing laser scanning on the target mine pipeline, the point cloud data of the target mine pipeline is obtained, and the obtained point cloud data is used to build a digital pipeline twin model corresponding to the target mine pipeline. Then, by arranging data acquisition terminals at various locations in the target mine pipeline, the flow data is acquired in real time, and the obtained flow data is updated to the digital pipeline twin model. The digital pipeline twin model performs simulation based on the obtained flow data, and determines whether there is any abnormality in the flow data in the target mine pipeline based on the simulation results. When an abnormality occurs, the location interval of the abnormality and the cause of the abnormality are determined, thereby realizing real-time monitoring of the inside of the target mine pipeline, and then arranging maintenance in time when an abnormality occurs to eliminate safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0064] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0065] like Figure 1 As shown, a mine pipeline flow analysis method based on a digital twin model includes the following steps:

[0066] Step S1: collecting mine pipeline data of the target mine pipeline, and building a corresponding digital pipeline twin model according to the collected mine pipeline data;

[0067] Step S2: Determine the corresponding data acquisition nodes according to the constructed digital pipeline twin model, and arrange the corresponding data acquisition terminals at the determined data acquisition nodes;

[0068] Step S3: Collect the flow data of each data collection node through the data collection terminal, integrate the collected flow data with the digital pipeline twin model, and synchronize the data of the digital pipeline twin model;

[0069] Step S4: Simulate the operating status of the digital pipeline twin model, and analyze whether the flow status at each location in the mine pipeline is normal based on the simulation results.

[0070] It should be further explained that, in the specific implementation process, the process of collecting target mine pipeline data and building a corresponding digital pipeline twin model based on the collected mine pipeline data includes:

[0071] Use laser to scan the inside of the target mine pipeline to obtain corresponding point cloud data, import the obtained point cloud data into the point cloud processing software, and generate the corresponding pipeline point cloud model;

[0072] The generated pipeline point cloud model is divided into several point cloud regions, and the number of point clouds in each point cloud region is traversed to obtain the point cloud density of each point cloud region, which is recorded as D;

[0073] Set the point cloud density threshold range, recorded as (D1, D2);

[0074] Compare the point cloud density of each point cloud area with the set point cloud density threshold range, and optimize the pipeline point cloud model according to the comparison result;

[0075] When D∈(D1, D2), it means that the corresponding point cloud area does not need to be optimized;

[0076] When D≤D1, it means that the point cloud density in the corresponding point cloud area is too low, and the point cloud area is marked as a sparse area, and the sparse area needs to be filled and optimized;

[0077] When D≥D2, it means that the point cloud density in the corresponding point cloud area is too high, and the point cloud area is marked as a dense area, and redundancy optimization needs to be performed on the dense area;

[0078] After completing the optimization of the pipeline point cloud model, the corresponding structural labels are set in the pipeline point cloud model according to the layout of the target mine pipeline to obtain the corresponding digital pipeline twin model. The structural labels include connection point labels, valve body labels and pipeline direction labels.

[0079] It should be further explained that, in the specific implementation process, the process of filling optimization of sparse areas includes:

[0080] Traverse the point clouds existing in the sparse area. If there are point clouds in the sparse area, use the existing point clouds as reference points to generate the point cloud influence area.

[0081] Mark the areas in the sparse area that are not covered by the point cloud influence area as blank areas;

[0082] Divide the blank area into a plurality of blank sub-areas, wherein the size and the outline of the blank sub-areas are the same as the point cloud influence area;

[0083] Mark the point cloud influence area adjacent to the boundary of the blank sub-area, and obtain the point cloud value corresponding to the point cloud influence area;

[0084] Fill the mean value of each point cloud value into the blank sub-region, generate a corresponding point cloud, and mark the blank sub-region as a filled sub-region;

[0085] After all blank sub-regions adjacent to the point cloud influence region are filled, the remaining blank sub-regions not adjacent to the point cloud influence region are obtained;

[0086] Mark the filled sub-region adjacent to the boundary of the blank sub-region, and obtain the point cloud value corresponding to the filled sub-region;

[0087] Fill the mean value of each point cloud value into the blank sub-region, generate a corresponding point cloud, mark the blank sub-region as a filled sub-region, and complete the filling of all blank sub-regions in this way;

[0088] In another embodiment of the present invention, if there is no point cloud in the sparse area, the point cloud area adjacent to the sparse area is obtained, and the point cloud in the point cloud area adjacent to the sparse area is marked, and the point cloud influence area is generated with the marked point cloud as the reference point, and the point cloud filling of the blank area is completed by the above method.

[0089] It should be further explained that, in the specific implementation process, the process of optimizing the redundancy removal in the dense area includes:

[0090] Construct a topological network for the dense area and mark the center points of each topological grid as topological points;

[0091] Get the point clouds existing in each topological grid and the corresponding point cloud values;

[0092] Each point cloud in the topological grid is labeled as i, where i=1, 2, ..., n, n is an integer and n>0.

[0093] The point cloud value of the point cloud labeled i is recorded as K i ;

[0094] Then the point cloud discrete coefficient of the topological grid is obtained, denoted as Dx;

[0095] in, ;

[0096] Set the discrete coefficient threshold L;

[0097] When Dx≤L, it means that the discrete degree of the point cloud of the corresponding topological grid is low, and the point cloud of the topological grid is normalized to complete the redundancy optimization of the point cloud in the topological grid;

[0098] When Dx>L, it means that the point cloud of the corresponding topological grid is highly discrete. The maximum point cloud value and the minimum point cloud value in the topological grid are marked, and the corresponding topological sets are established respectively. The point clouds corresponding to the marked maximum point cloud value and the minimum point cloud value are mapped to the corresponding topological sets respectively.

[0099] After the point cloud mapped to the topological set is removed, the point cloud discrete coefficient of the topological grid is recalculated and used to determine the degree of point cloud discreteness of the topological grid. It should be further explained that in the specific implementation process, when the point cloud discrete coefficient of the topological grid is recalculated, the point cloud corresponding to the maximum point cloud value and the minimum point cloud value does not participate in the calculation;

[0100] If the point cloud has a high degree of discreteness, the point clouds corresponding to the maximum and minimum point cloud values ​​in the topological grid are mapped to the corresponding topological set, and so on;

[0101] If the point cloud has a low degree of discreteness, the point cloud of the topological grid is normalized, and a point cloud influence region is generated for the point cloud in the topological set, and a sub-topological grid is generated in the topological grid according to the generated point cloud influence region;

[0102] It should be further explained that, in the specific implementation process, the point cloud in the topological grid is normalized to obtain the corresponding point cloud mean according to the point cloud value of each point cloud in the topological grid, and the corresponding point cloud is generated according to the obtained point cloud mean, and the generated point cloud is set to the topological point of the corresponding topological grid.

[0103] It should be further explained that, in the specific implementation process, the process of determining the corresponding data acquisition nodes according to the constructed digital pipeline twin model and arranging the corresponding data acquisition terminals at the determined data acquisition nodes includes:

[0104] Read each structural tag in the digital pipeline twin model, mark the location of each structural tag as the corresponding data acquisition node, and set the corresponding data acquisition terminal at the data acquisition node corresponding to the connection point tag and valve body tag in the target mine pipeline;

[0105] A corresponding data acquisition terminal group is set at a data acquisition node corresponding to the pipeline direction label in the target mine pipeline, and the data acquisition terminal group includes at least two data acquisition terminals;

[0106] Setting a sequence relationship for the data acquisition terminals in the data acquisition terminal group according to the pipeline direction labels;

[0107] According to the location of the data collection node of the pipeline where the connection point label is located, it is associated with at least one data collection terminal group, and the corresponding relative position relationship of the endpoints is set;

[0108] According to the position of the pipeline where the valve body label is located, it is associated with the two data acquisition terminals in the data acquisition terminal group that are closest to the valve body label, and the relative position relationship of the valve body is set.

[0109] It should be further explained that, in the specific implementation process, the flow data of each data collection node is collected through the data collection terminal, and the process of fusing the collected flow data with the digital pipeline twin model includes:

[0110] Obtain the traffic data of the corresponding location in real time through the data collection terminal;

[0111] Set a data upload cycle, package the traffic data obtained in a data upload cycle, obtain the corresponding traffic data packet, and generate a time span label corresponding to the time span of the data upload cycle. Insert the generated time span label into the obtained traffic data packet and upload it to the digital pipeline twin model.

[0112] The digital pipeline twin model imports the received traffic data packet into the corresponding structure tag.

[0113] It should be further explained that, in the specific implementation process, the process of data synchronization of the digital pipeline twin model includes:

[0114] Read the time span tag in the traffic data packet received by the digital pipeline twin model, and build the corresponding time axis according to the read time span tag;

[0115] Parsing the traffic data packet corresponding to the time span label, obtaining the traffic data corresponding to the time span label, and mapping the obtained traffic data to the time axis;

[0116] Constructing a multi-track timeline, wherein the multi-track timeline includes a plurality of blank tracks, and associating each blank track with a structure tag;

[0117] Traverse the timeline with the same structure tag as the blank track, and map the timeline to the corresponding blank track;

[0118] According to the time span corresponding to the time span label of the time axis, the flow data is aligned with the corresponding time period on the multi-track time axis, thereby completing the data synchronization of the flow data obtained by each data collection terminal.

[0119] It should be further explained that, in the specific implementation process, the operation status of the digital pipeline twin model is simulated, and the process of analyzing whether the flow status at various locations in the mine pipeline is normal based on the simulation results includes:

[0120] Traverse each mine pipeline in the digital pipeline twin model and divide the mine pipeline into corresponding pipeline segments according to the location of the connection point labels;

[0121] Get whether each pipeline segment is connected to the valve body tag. If so, mark the pipeline segment as the main pipeline segment; otherwise, mark it as the secondary pipeline segment.

[0122] For the main pipeline section, the relative position relationship between the pipeline direction label, connection point label, and valve body label in the main pipeline section is obtained, each data collection terminal in the main pipeline section is sorted, and the starting point and the end point are determined according to the sorting result;

[0123] Generate prediction values ​​for each data collection terminal based on the flow data at the starting point;

[0124] Compare the flow data obtained by each data collection terminal with the corresponding predicted value to obtain a deviation value;

[0125] Set the allowable deviation range;

[0126] If the deviation value is within the allowable deviation range, it means that the flow data of the corresponding data collection terminal is normal;

[0127] If the deviation value is lower than the lower limit of the allowable deviation range, it means that the flow data at the location of the data collection terminal is abnormal;

[0128] Taking the data collection terminal as the reference point, if all subsequent data collection terminals are abnormal, it means that there is a leak in the mine pipeline between the data collection terminal and the previous data collection terminal; if there is no abnormality in the subsequent data collection terminal, it means that the data collection terminal itself is faulty;

[0129] If the deviation value is higher than the upper limit of the allowable deviation range, it means that the flow data at the location of the data collection terminal is abnormal;

[0130] Taking the data collection terminal as the reference point, if all subsequent data collection terminals have abnormalities, it means that there is a blockage in the mine pipeline between the data collection terminal and the previous data collection terminal. If there is no abnormality in the subsequent data collection terminal, it means that the data collection terminal itself has a fault.

[0131] For the secondary pipeline section, the pipeline direction label in the main pipeline section and the relative position relationship of the connection point label are obtained, and the flow data obtained by the data acquisition terminal at the location of the connection point label are used to obtain the predicted values ​​of other data acquisition terminals, and then it is determined whether there are abnormalities in the flow data obtained by each data acquisition terminal. The judgment method is the same as that of the main pipeline section and will not be repeated here.

[0132] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments with equivalent changes without departing from the scope of the technical solution of the present invention. However, any modification or equivalent replacement of the above embodiments made according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A mine pipeline flow analysis method based on a digital twin model, characterized in that: The following steps are involved: Step S1: collecting mine pipeline data of the target mine pipeline, and constructing a corresponding digital pipeline twin model according to the collected mine pipeline data; Step S2: Determine the corresponding data acquisition nodes according to the constructed digital pipeline twin model, and arrange the corresponding data acquisition terminals at the determined data acquisition nodes; Step S3: Collect the flow data of each data collection node through the data collection terminal, integrate the collected flow data with the digital pipeline twin model, and synchronize the data of the digital pipeline twin model; Step S4: simulating the operating status of the digital pipeline twin model, and analyzing whether the flow status at each location in the mine pipeline is normal according to the simulation results; The process of collecting target mine pipeline data and building a corresponding digital pipeline twin model based on the collected mine pipeline data includes: Use laser to scan the inside of the target mine pipeline to obtain corresponding point cloud data, import the obtained point cloud data into the point cloud processing software, and generate the corresponding pipeline point cloud model; The generated pipeline point cloud model is divided into several point cloud regions, and the number of point clouds in each point cloud region is traversed to obtain the point cloud density of each point cloud region, which is recorded as D; Set the point cloud density threshold range, recorded as (D1, D2); Compare the point cloud density of each point cloud area with the set point cloud density threshold range, and optimize the pipeline point cloud model according to the comparison result; When D∈(D1, D2), it means that the corresponding point cloud area does not need to be optimized; When D≤D1, it means that the point cloud density in the corresponding point cloud area is too low, and the point cloud area is marked as a sparse area, and the sparse area needs to be filled and optimized; When D≥D2, it means that the point cloud density in the corresponding point cloud area is too high, and the point cloud area is marked as a dense area, and redundancy optimization needs to be performed on the dense area; After completing the optimization of the pipeline point cloud model, the corresponding structural labels are set in the pipeline point cloud model according to the layout of the target mine pipeline to obtain the corresponding digital pipeline twin model. The structural labels include connection point labels, valve body labels and pipeline direction labels.

2. According to a method for analyzing mine pipeline flow based on a digital twin model according to claim 1, it is characterized in that: The process of optimizing the filling of sparse areas includes: Traverse the point clouds existing in the sparse area, and use the existing point clouds as reference points to generate the point cloud influence area; Mark the areas in the sparse area that are not covered by the point cloud influence area as blank areas; Divide the blank area into a plurality of blank sub-areas, wherein the size and the outline of the blank sub-areas are the same as the point cloud influence area; Mark the point cloud influence area adjacent to the boundary of the blank sub-area, and obtain the point cloud value corresponding to the point cloud influence area; Fill the mean value of each point cloud value into the blank sub-region, generate a corresponding point cloud, and mark the blank sub-region as a filled sub-region; After all blank sub-regions adjacent to the point cloud influence region are filled, the remaining blank sub-regions not adjacent to the point cloud influence region are obtained; Mark the filled sub-region adjacent to the boundary of the blank sub-region, and obtain the point cloud value corresponding to the filled sub-region; The mean value of each point cloud value is filled into the blank sub-region, and a corresponding point cloud is generated. The blank sub-region is marked as a filled sub-region, and the filling of all blank sub-regions is completed by analogy.

3. The method for analyzing mine pipeline flow based on a digital twin model according to claim 2 is characterized in that: The process of optimizing the dense area for redundancy removal includes: Construct a topological network for the dense area and mark the center points of each topological grid as topological points; Get the point clouds existing in each topological grid and the corresponding point cloud values; Obtain the point cloud discrete coefficient Dx of the topological grid; Set the discrete coefficient threshold L; When Dx≤L, it means that the discrete degree of the point cloud of the corresponding topological grid is low, and the point cloud of the topological grid is normalized to complete the redundancy optimization of the point cloud in the topological grid; When Dx>L, it means that the point cloud of the corresponding topological grid is highly discrete. The maximum point cloud value and the minimum point cloud value in the topological grid are marked, and the corresponding topological sets are established respectively. The point clouds corresponding to the marked maximum point cloud value and the minimum point cloud value are mapped to the corresponding topological sets respectively. After removing the point cloud mapped to the topological set, the point cloud discrete coefficient of the topological grid is recalculated and used to determine the degree of point cloud discreteness of the topological grid; If the point cloud has a high degree of discreteness, the point clouds corresponding to the maximum and minimum point cloud values ​​in the topological grid are mapped to the corresponding topological set, and so on; If the point cloud has a low degree of discreteness, the point cloud of the topological grid is normalized, and a point cloud influence area is generated for the point cloud in the topological set, and a sub-topological grid is generated in the topological grid according to the generated point cloud influence area.

4. The method for analyzing mine pipeline flow based on a digital twin model according to claim 3 is characterized in that: The process of determining the corresponding data acquisition nodes according to the constructed digital pipeline twin model and arranging the corresponding data acquisition terminals at the determined data acquisition nodes includes: Read each structural tag in the digital pipeline twin model, mark the location of each structural tag as the corresponding data acquisition node, and set the corresponding data acquisition terminal at the data acquisition node corresponding to the connection point tag and valve body tag in the target mine pipeline; A corresponding data acquisition terminal group is set at a data acquisition node corresponding to the pipeline direction label in the target mine pipeline, and the data acquisition terminal group includes at least two data acquisition terminals; Setting a sequence relationship for the data acquisition terminals in the data acquisition terminal group according to the pipeline direction labels; According to the location of the data collection node of the pipeline where the connection point label is located, it is associated with at least one data collection terminal group, and the corresponding relative position relationship of the endpoints is set; According to the position of the pipeline where the valve body label is located, it is associated with the two data acquisition terminals in the data acquisition terminal group that are closest to the valve body label, and the relative position relationship of the valve body is set.

5. The method for analyzing mine pipeline flow based on a digital twin model according to claim 4 is characterized in that: The process of collecting the flow data of each data collection node through the data collection terminal and fusing the collected flow data with the digital pipeline twin model includes: Obtain the traffic data of the corresponding location in real time through the data collection terminal; Set a data upload cycle, package the traffic data obtained in a data upload cycle, obtain the corresponding traffic data packet, and generate a time span label corresponding to the time span of the data upload cycle. Insert the generated time span label into the obtained traffic data packet and upload it to the digital pipeline twin model. The digital pipeline twin model imports the received traffic data packet into the corresponding structure tag.

6. The method for analyzing mine pipeline flow based on a digital twin model according to claim 5 is characterized in that: The process of synchronizing data for the digital pipeline twin model includes: Read the time span tag in the traffic data packet received by the digital pipeline twin model, and build the corresponding time axis according to the read time span tag; Parsing the traffic data packet corresponding to the time span label, obtaining the traffic data corresponding to the time span label, and mapping the obtained traffic data to the time axis; Constructing a multi-track timeline, wherein the multi-track timeline includes a plurality of blank tracks, and associating each blank track with a structure tag; Traverse the timeline with the same structure tag as the blank track, and map the timeline to the corresponding blank track; According to the time span corresponding to the time span label of the time axis, the flow data is aligned with the corresponding time period on the multi-track time axis, thereby completing the data synchronization of the flow data obtained by each data collection terminal.

7. The method for analyzing mine pipeline flow based on a digital twin model according to claim 6 is characterized in that: The process of simulating the operating status of the digital pipeline twin model and analyzing whether the flow status at various locations in the mine pipeline is normal based on the simulation results includes: Traverse each mine pipeline in the digital pipeline twin model and divide the mine pipeline into corresponding pipeline segments according to the location of the connection point labels; Sort the data collection terminals in the pipeline section and determine the starting point and the end point according to the sorting results; Generate prediction values ​​for each data collection terminal based on the flow data at the starting point; Compare the flow data obtained by each data collection terminal with the corresponding predicted value to obtain a deviation value; Set the allowable deviation range; If the deviation value is within the allowable deviation range, it means that the flow data of the corresponding data collection terminal is normal; If the deviation value is not within the allowable deviation range, it means that the flow data at the location of the data collection terminal is abnormal.

Images