A mine roadway design model training method, mine roadway design and device

Abstract

This application discloses a training method for a mine roadway design model, a mine roadway design, and an apparatus, relating to the fields of deep learning technology and intelligent mining technology. The method includes: acquiring graph structure data of the mine for model training, the graph structure data including non-roadway data and roadway data; inputting the non-roadway data into a graph neural network to be trained, obtaining roadway design data output by the graph neural network, the roadway design data including roadway design node data and roadway design edge data, the roadway design edge data representing the spatial relationship between each non-roadway node and each roadway design node; and adjusting the network parameters of the graph neural network based on the error between the roadway design data and the roadway data. This approach improves the design efficiency of mine roadway design.

Description

Technical Field

[0001] This application relates to the fields of deep learning technology and intelligent mining technology, and in particular to a method for training a mine roadway design model, and a mine roadway design and device. Background Technology

[0002] A smart mine is based on the digitalization and informatization of mines. It proactively senses, automatically analyzes, and rapidly processes information related to mine production, occupational health and safety, technical support, and logistical support. The ultimate goal of building a smart mine is to achieve safe, unmanned, efficient, and clean mines.

[0003] The smart mine system encompasses all aspects of a mine. According to the usual classification method, it can be divided into three aspects: smart production system, smart occupational health and safety system, and smart technical support and logistics support system construction.

[0004] More specifically, with the continuous advancement of smart mine construction, the way mine information is presented is gradually shifting from the traditional two-dimensional plane to three-dimensional space. Three-dimensional mine scenes can be built to showcase the overall picture of the mine and achieve mine transparency.

[0005] Digital twin technology integrates technologies such as sensors, the Internet of Things, virtual reality, and artificial intelligence to describe and model the characteristics, behaviors, operation processes, and performance of physical objects in the real world.

[0006] Applying digital twin technology to the mining industry enables the creation of digital twins of mines, thereby simulating and displaying underground mining scenarios. This allows operators to be aware of the real-time situation underground, leading to safer and more efficient mine management.

[0007] In mine digital twin technology, it is necessary to perform 3D modeling of the underground scene to generate a mine model, and then display the mine model in the application.

[0008] In the application of the above-mentioned smart mining technologies, it is necessary to design CAD drawings for underground mines and then construct a three-dimensional model of the mine. It can be seen that underground mine design is a prerequisite for the application of various smart mining technologies.

[0009] In underground mine design, the design of mine roadways is a primary focus. Currently, mine roadway design is still largely done manually based on experience, resulting in low design efficiency. Summary of the Invention

[0010] This application provides a method for training a mine roadway design model, a mine roadway design and apparatus, to solve the problem of low design efficiency in existing mine roadway design.

[0011] This application provides a method for training a mine roadway design model, including:

[0012] Obtain graph structure data from the mine for model training. The graph structure data includes: non-roadway data and roadway data. The non-roadway data includes non-roadway node data and non-roadway edge data. The roadway data includes roadway node data and roadway edge data. The non-roadway edge data represents the spatial relationship between each non-roadway node, and the roadway edge data represents the spatial relationship between each non-roadway node and each roadway node.

[0013] The non-lane data is input into the graph neural network to be trained to obtain the lane design data output by the graph neural network. The lane design data includes lane design node data and lane design edge data. The lane design edge data represents the spatial relationship between each non-lane node and each lane design node.

[0014] The network parameters of the graph neural network are adjusted based on the error between the tunnel design data and the tunnel data.

[0015] Furthermore, the graph structure data for model training is generated using the following steps:

[0016] Obtain CAD drawing data of the mine, wherein the CAD drawing data contains graphic information of the mine;

[0017] The CAD drawing data is converted into mine data in GIS exchange format, which includes non-tunnel mine data and tunnel mine data.

[0018] Based on the mining data in the GIS exchange format, graph structure data for model training is generated.

[0019] Furthermore, adjusting the network parameters of the graph neural network based on the error between the tunnel design data and the tunnel data includes:

[0020] The mean square error between the tunnel design data and the tunnel data is calculated and used as the value of the loss function of the graph neural network;

[0021] When the mean square error is not less than a preset error threshold, the network parameters of the graph neural network are adjusted.

[0022] Furthermore, the non-tunnel nodes include: ore body outline and ore pass;

[0023] The tunnel node is the tunnel centerline;

[0024] The tunnel design node is the tunnel design centerline.

[0025] This application also provides a method for designing mine roadways, including:

[0026] Obtain the non-tunnel map structure data of the mine to be designed. The non-tunnel map structure data includes: non-tunnel node data and non-tunnel edge data, wherein the non-tunnel edge data represents the spatial relationship between each non-tunnel node.

[0027] The non-lane map structure data is input into a graph neural network to obtain the lane design data output by the graph neural network. The lane design data serves as the lane map structure data. The lane design data includes lane design node data and lane design edge data. The lane design edge data represents the spatial relationship between each non-lane node and each lane design node.

[0028] Furthermore, it also includes:

[0029] The tunnel map structure data is converted into tunnel data in GIS exchange format;

[0030] The tunnel data in the GIS exchange format is converted into CAD drawing data of the tunnel.

[0031] Furthermore, the non-tunnel map structure data is generated using the following steps:

[0032] Obtain CAD drawing data of the non-tunnel sections of the mine, which includes graphic information of the non-tunnel sections of the mine;

[0033] Convert the CAD drawing data of non-lane roads into non-lane road data in GIS exchange format;

[0034] Based on the non-lane data in the GIS exchange format, non-lane map structure data is generated.

[0035] Furthermore, the non-tunnel nodes include: ore body outline and ore pass;

[0036] The tunnel design node is the tunnel design centerline.

[0037] This application embodiment also provides a mine roadway design model training device, including:

[0038] The training data acquisition module is used to acquire graph structure data of the mine for model training. The graph structure data includes: non-roadway data and roadway data. The non-roadway data includes non-roadway node data and non-roadway edge data. The roadway data includes roadway node data and roadway edge data. The non-roadway edge data represents the spatial relationship between each non-roadway node, and the roadway edge data represents the spatial relationship between each non-roadway node and each roadway node.

[0039] The training data input module is used to input the non-lane data into the graph neural network to be trained, and obtain the lane design data output by the graph neural network. The lane design data includes lane design node data and lane design edge data. The lane design edge data represents the spatial relationship between each non-lane node and each lane design node.

[0040] The model training module is used to adjust the network parameters of the graph neural network based on the error between the tunnel design data and the tunnel data.

[0041] Furthermore, the training data acquisition module is also used to generate the graph structure data for model training using the following steps:

[0042] Acquire CAD drawing data of the mine, the CAD drawing data containing graphic information of the mine; convert the CAD drawing data into mine data in GIS exchange format, the GIS exchange format mine data including non-tunnel mine data and tunnel mine data; generate graph structure data for model training based on the GIS exchange format mine data.

[0043] Furthermore, the model training module is specifically used to calculate the mean square error between the tunnel design data and the tunnel data, as the value of the loss function of the graph neural network; when the mean square error is not less than a preset error threshold, the network parameters of the graph neural network are adjusted.

[0044] Furthermore, the non-tunnel nodes include: ore body outline and ore pass;

[0045] The tunnel node is the tunnel centerline;

[0046] The tunnel design node is the tunnel design centerline.

[0047] This application also provides a mine roadway design device, including:

[0048] The non-tunnel data acquisition module is used to acquire the non-tunnel map structure data of the mine to be designed. The non-tunnel map structure data includes: non-tunnel node data and non-tunnel edge data, wherein the non-tunnel edge data represents the spatial relationship between each non-tunnel node.

[0049] The tunnel design module is used to input the non-tunnel graph structure data into a graph neural network to obtain tunnel design data output by the graph neural network. The tunnel design data serves as tunnel graph structure data and includes tunnel design node data and tunnel design edge data. The tunnel design edge data represents the spatial relationship between each non-tunnel node and each tunnel design node.

[0050] Furthermore, the tunnel design module is also used to convert the tunnel map structure data into tunnel data in GIS exchange format; and to convert the tunnel data in GIS exchange format into CAD drawing data of the tunnel.

[0051] Furthermore, the non-lane data acquisition module is also used to generate the non-lane map structure data using the following steps:

[0052] Obtain CAD drawing data of non-tunnel areas in the mine, which contains graphic information of the non-tunnel areas; convert the CAD drawing data of non-tunnel areas into non-tunnel data in GIS exchange format; and generate non-tunnel map structure data based on the non-tunnel data in GIS exchange format.

[0053] Furthermore, the non-tunnel nodes include: ore body outline and ore pass;

[0054] The tunnel design node is the tunnel design centerline.

[0055] This application also provides an electronic device, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to: implement any of the above-described mine roadway design model training methods, or implement any of the above-described mine roadway design methods.

[0056] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements any of the above-described mine roadway design model training methods, or implements any of the above-described mine roadway design methods.

[0057] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to execute any of the above-described mine roadway design model training methods, or to execute any of the above-described mine roadway design methods.

[0058] The beneficial effects of this application include:

[0059] The method provided in this application involves acquiring graph structure data of the mine for model training, inputting non-tunnel data from the graph structure data into a graph neural network to be trained, obtaining tunnel design data output by the graph neural network, and adjusting the network parameters of the graph neural network based on the error between the obtained tunnel design data and the tunnel data in the graph structure data, thereby achieving effective training of the graph neural network. Based on the trained graph neural network, when mine tunnel design is required, non-tunnel graph structure data of the mine to be designed can be acquired, and this non-tunnel graph structure data can be input into the graph neural network to obtain the output tunnel design data, which improves design efficiency compared to manual design in the prior art.

[0060] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0061] The accompanying drawings are provided to further illustrate the present application and form part of the specification. They are used together with the embodiments of the present application to explain the application and do not constitute a limitation thereof. In the drawings:

[0062] Figure 1 A flowchart of the mine roadway design model training method provided in the embodiments of this application;

[0063] Figure 2 A flowchart illustrating the generation of graph structure data for model training in the mine roadway design model training method provided in this application embodiment;

[0064] Figure 3 A flowchart illustrating the adjustment of network parameters in a graph neural network within a mine roadway design model training method provided in this application embodiment;

[0065] Figure 4 A flowchart of a mine roadway design method provided in the embodiments of this application;

[0066] Figure 5 A schematic diagram of the structure of the mine roadway design model training device provided in the embodiments of this application;

[0067] Figure 6 A schematic diagram of the structure of the mine roadway design device provided in the embodiments of this application;

[0068] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0069] To provide a solution for improving the design efficiency of mine roadway design, this application provides a mine roadway design model training method, mine roadway design, and apparatus. The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustrative and explanatory purposes only and are not intended to limit the scope of this application. Furthermore, the embodiments and features described herein can be combined with each other unless otherwise specified.

[0070] This application provides a method for training a mine roadway design model, such as... Figure 1 As shown, it includes:

[0071] Step 11: Obtain graph structure data from the mine for model training. The graph structure data includes: non-roadway data and roadway data. Non-roadway data includes non-roadway node data and non-roadway edge data. Roadway data includes roadway node data and roadway edge data. Non-roadway edge data represents the spatial relationship between each non-roadway node, and roadway edge data represents the spatial relationship between each non-roadway node and each roadway node.

[0072] Step 12: Input the non-lane data into the graph neural network to be trained to obtain the lane design data output by the graph neural network. The lane design data includes lane design node data and lane design edge data. The lane design edge data represents the spatial relationship between each non-lane node and each lane design node.

[0073] Step 13: Adjust the network parameters of the graph neural network based on the error between the tunnel design data and the tunnel data.

[0074] The above-described mine roadway design model training method provided in this application embodiment obtains graph structure data of the mine for model training, inputs non-roadway data in the graph structure data into the graph neural network to be trained, obtains roadway design data output by the graph neural network, and adjusts the network parameters of the graph neural network based on the error between the obtained roadway design data and the roadway data in the graph structure data, thereby achieving effective training of the graph neural network.

[0075] In one embodiment of this application, graph structure data for model training can be generated using the following steps, such as... Figure 2 As shown, it includes:

[0076] Step 21: Obtain the CAD drawing data of the mine. The CAD drawing data contains the graphic information of the mine.

[0077] The CAD drawing data obtained in this step is the underground mine design data for a certain horizontal line in the mine. It is the CAD drawing data of the completed design, which contains graphic information of the mine, such as layers and lines.

[0078] The file format is .dwg, stored in text or binary form, and contains geometric information and attributes of the graphics, which reflect the design for some scenarios in underground mines, including the design for tunnels.

[0079] Step 22: Convert the CAD drawing data into GIS exchange format mine data. GIS exchange format mine data includes non-tunnel mine data and tunnel mine data.

[0080] In this step, the converted mine data in GIS exchange format can be Geojson data, and the data types can include points, lines, multilines, polygons, etc. The format structure can be represented as follows:

[0081]

[0082] In this embodiment of the application, the mining data in the GIS exchange format may include non-tunnel mining data and tunnel mining data. The non-tunnel mining data may include ore body outline data and ore pass data. The GIS data structure of ore body outline, ore pass, and tunnel is illustrated below:

[0083] Ore body outline:

[0084] Unique identifier (ID) for ore bodies;

[0085] Ore body coordinates: A series of coordinate points (XYZ form) that constitute the boundary of the ore body, where the ore body data type is a closed line (LineString) or a polygon (Polygon);

[0086] Ore body related attributes: MineType ore body type (rock, ore, etc.), mining area number, etc.

[0087] Well chute:

[0088] The unique identifier (ID) for the chute;

[0089] Catch coordinates: A series of coordinate points (XYZ form) that constitute the boundary of the chute, where the chute data type is a polygon;

[0090] Ore pass related attributes: orePassType (hoisting shaft, ventilation shaft, cutting shaft, cable shaft, elevator shaft, etc.), mine area number, etc.

[0091] Alleyway:

[0092] Unique identifier for alleyway (ID);

[0093] Tunnel coordinates: A series of coordinate points (XYZ form) that form the centerline of the tunnel, where the tunnel data type is line (LineString);

[0094] Tunnel-related attributes: TunnelType (along the vein, through the vein, external vein connecting tunnel, return air shaft connecting tunnel, ore pass connecting tunnel, etc.), mine area number, etc.

[0095] Step 23: Generate graph structure data for model training based on the mine data in GIS exchange format.

[0096] Graph data consists of a finite non-empty set of nodes and a set of edges between nodes, usually represented as: G = (V, E), where G represents a graph, V represents the set of nodes in G, and E represents the set of edges between nodes in G.

[0097] In this step, geopandas and networkx (Python library) can be used to read and construct GIS data of ore body outlines, ore passes, and tunnels into a graph data structure.

[0098] Specifically, the node data and edge data include:

[0099] Node data:

[0100] It includes non-tunnel node data and tunnel node data. Correspondingly, non-tunnel nodes include the ore body outline and ore pass, while tunnel nodes are the tunnel centerlines.

[0101] Type: Identifies whether the node is the centerline of a roadway, a ore pass, or the outline of a ore body;

[0102] Geometry coordinates: The coordinates of a node, which can be a series of coordinates representing a node;

[0103] Tunnel Types: Along-the-vein tunnels, through-the-vein tunnels, external connecting tunnels, return air shaft connecting tunnels, chute connecting tunnels, etc.

[0104] orePassType: hoisting shaft, ventilation shaft, cutting shaft, cable shaft, elevator shaft, etc.;

[0105] MineType: Rock, Ore; MineType can represent the outline type of ore body.

[0106] Edge data:

[0107] The edge data includes non-lane edge data and lane edge data. Non-lane edge data represents the spatial relationship between non-lane nodes, while lane edge data represents the spatial relationship between non-lane nodes and lane nodes.

[0108] Specifically, edge data can include the spatial relationships between the ore body outline, the ore pass, and the roadway centerline (a complete roadway includes the roadway centerline, the left waistline, and the right waistline, which are derived from the roadway centerline by offsetting Width / 2 to the left and right based on the roadway width Width). These relationships include intersection and inclusion (e.g., the ore body outline includes the roadway, the ore body outline includes the ore pass, the ore body outline intersects with the roadway, and the ore pass intersects with the roadway).

[0109] In this embodiment of the application, the tunnel node is the tunnel centerline. Correspondingly, the tunnel design node in the tunnel design data output by the graph neural network is the tunnel design centerline, which can be understood as the tunnel centerline designed based on the input non-tunnel data.

[0110] In one embodiment of this application, regarding step 13 above, the network parameters of the graph neural network are adjusted based on the error between the tunnel design data and the tunnel data, such as... Figure 3 As shown, it can specifically include:

[0111] Step 31: Calculate the mean square error between the tunnel design data and the tunnel data, and use it as the value of the loss function of the graph neural network.

[0112] In this embodiment, the mean square error between the tunnel design data and the tunnel data is used as the loss function of the graph neural network, and can be calculated using the following formula:

[0113] MSE = 1 / n * ∑(y_pred - y_true) 2 ;

[0114] Where n is the number of training iterations, which can also be understood as the number of samples (one set of samples is used for one training iteration), y_pred is the predicted tunnel design data, y_true is the tunnel data used for training, and Z(y_pred-y_true) is the total tunnel data. 2 This is the summation of the training results that have been completed.

[0115] Step 32: When the mean square error is not less than the preset error threshold, adjust the network parameters of the graph neural network and start the next training.

[0116] In this embodiment, the preset error threshold MSEValue can be flexibly set according to the needs of actual application. The smaller the value, the more training times need to be completed, and the better the performance of the obtained graph neural network. For example, it can be 0.1.

[0117] In this embodiment of the application, the graph neural network can adopt various known feasible graph neural networks. For example, multiple layers of graph convolutional layers can be used as the graph neural network. The more layers there are, the better the performance of the graph neural network obtained by training, but the more computing resources are consumed. The specific settings can be flexibly configured based on the actual application. For example, two layers of graph convolutional layers can be used.

[0118] In this embodiment of the application, after the above model training is completed, self-test sample data can be used to predict the map data structure of the roadway centerline based on the trained model. When the deviation between the position of a roadway centerline in the prediction result and the position of the roadway centerline in the corresponding self-test sample is within a preset range, it can be determined that the prediction result of this roadway centerline is correct. When the prediction result exceeds the preset range, the number of training times of the same level data can be increased to retrain the model.

[0119] Based on the mine roadway design model trained using the above-mentioned mine roadway design model training method, this application embodiment also provides a mine roadway design method, such as... Figure 4 As shown, it includes:

[0120] Step 41: Obtain the non-roadway diagram structure data of the mine to be designed. The non-roadway diagram structure data includes: non-roadway node data and non-roadway edge data. Among them, the non-roadway edge data represents the spatial relationship between each non-roadway node.

[0121] Step 42: Input the non-lane graph structure data into the graph neural network to obtain the lane design data output by the graph neural network. The lane design data serves as the lane graph structure data. The lane design data includes lane design node data and lane design edge data. The lane design edge data represents the spatial relationship between each non-lane node and each lane design node.

[0122] The mine roadway design method provided in this application, based on the trained graph neural network, can obtain the non-roadway diagram structure data of the mine to be designed when mine roadway design is required. The non-roadway diagram structure data is input into the graph neural network to obtain the output roadway design data. Compared with the manual design in the prior art, the design efficiency is improved.

[0123] Furthermore, since the quality of mine roadway design is dependent on the experience of the designers, there is a possibility that the designed mine roadways may not be reasonable enough. However, the mine roadway design method provided in the embodiments of this application can ensure that the designed mine roadways meet certain design rationality requirements. Moreover, the designers can further revise the design based on the design results output by the graph neural network to obtain the final mine roadway design results for practical application. Thus, while taking into account the design rationality, the design efficiency is significantly improved.

[0124] In this embodiment, the tunnel design data output by the graph neural network is graph structure data. Furthermore, the tunnel design data can be transformed to obtain CAD drawing data that can be directly used by designers, specifically including:

[0125] Convert the tunnel map structure data into tunnel data in GIS exchange format;

[0126] Convert the tunnel data in GIS exchange format into CAD drawing data of the tunnel.

[0127] Converting map structure data to GIS exchange format, and converting GIS exchange format data to CAD drawing data, are related to the above. Figure 2 The reverse operation of the data format conversion shown will not be described in detail here.

[0128] In one embodiment of this application, non-tunnel map structure data can be generated using the following steps:

[0129] Obtain CAD drawing data of non-tunnel areas in the mine. The CAD drawing data of non-tunnel areas contains graphic information of non-tunnel areas in the mine.

[0130] Convert the CAD drawing data of non-lane roads into non-lane road data in GIS exchange format;

[0131] Generate non-lane map structure data based on non-lane data in GIS exchange format.

[0132] In the steps described above for generating non-tunnel map structure data, converting CAD drawing data into GIS exchange format data, and generating map structure data based on the GIS exchange format data, are consistent with the above. Figure 2 The data format conversion operations shown are similar and will not be described in detail here.

[0133] In the mine roadway design method provided in this application embodiment, non-roadway nodes may include: ore body outline and ore pass;

[0134] The tunnel design node is the tunnel design centerline, which is the designed tunnel centerline. Based on this, designers can continue to add other attribute information of the tunnel, such as tunnel type, tunnel width, and other attribute information.

[0135] The mine roadway design model training method and mine roadway design method provided in the embodiments of this application can automatically design the roadway centerline based on known CAD drawing data other than roadways, such as ore body outlines and ore passes. This improves the design efficiency of mine roadway excavation design plan drawings, allowing mine designers to draw the left waistline, right waistline and other annotation information of the roadway based on the automatically designed roadway centerline drawing data, only needing to offset left and right according to the roadway width, without having to consider the collaborative design of geological exploration data, engineering survey data, etc., which improves the drawing efficiency of mine roadway excavation design plan drawings to a certain extent.

[0136] Furthermore, it enables the application of AI algorithms in the intelligent design of mine roadways, accelerating the intelligent upgrading of mines.

[0137] Based on the same inventive concept, and according to the mine roadway design model training method provided in the above embodiments of this application, another embodiment of this application also provides a mine roadway design model training device, the structural schematic diagram of which is shown below. Figure 5 As shown, it specifically includes:

[0138] The training data acquisition module 51 is used to acquire graph structure data of the mine for model training. The graph structure data includes: non-roadway data and roadway data. The non-roadway data includes non-roadway node data and non-roadway edge data. The roadway data includes roadway node data and roadway edge data. The non-roadway edge data represents the spatial relationship between each non-roadway node, and the roadway edge data represents the spatial relationship between each non-roadway node and each roadway node.

[0139] The training data input module 52 is used to input the non-lane data into the graph neural network to be trained, and obtain the lane design data output by the graph neural network. The lane design data includes lane design node data and lane design edge data. The lane design edge data represents the spatial relationship between each non-lane node and each lane design node.

[0140] The model training module 53 is used to adjust the network parameters of the graph neural network based on the error between the tunnel design data and the tunnel data.

[0141] Furthermore, the training data acquisition module 51 is also used to generate the graph structure data for model training using the following steps:

[0142] Acquire CAD drawing data of the mine, the CAD drawing data containing graphic information of the mine; convert the CAD drawing data into mine data in GIS exchange format, the GIS exchange format mine data including non-tunnel mine data and tunnel mine data; generate graph structure data for model training based on the GIS exchange format mine data.

[0143] Furthermore, the model training module 53 is specifically used to calculate the mean square error between the tunnel design data and the tunnel data, as the value of the loss function of the graph neural network; when the mean square error is not less than a preset error threshold, the network parameters of the graph neural network are adjusted.

[0144] Furthermore, the non-tunnel nodes include: ore body outline and ore pass;

[0145] The tunnel node is the tunnel centerline;

[0146] The tunnel design node is the tunnel design centerline.

[0147] Based on the same inventive concept, and according to the mine roadway design method provided in the above embodiments of this application, another embodiment of this application also provides a mine roadway design device, the structural schematic diagram of which is shown below. Figure 6 As shown, it specifically includes:

[0148] The non-tunnel data acquisition module 61 is used to acquire the non-tunnel map structure data of the mine to be designed. The non-tunnel map structure data includes: non-tunnel node data and non-tunnel edge data, wherein the non-tunnel edge data represents the spatial relationship between each non-tunnel node.

[0149] The tunnel design module 62 is used to input the non-tunnel graph structure data into the graph neural network to obtain the tunnel design data output by the graph neural network. The tunnel design data serves as the tunnel graph structure data. The tunnel design data includes tunnel design node data and tunnel design edge data. The tunnel design edge data represents the spatial relationship between each non-tunnel node and each tunnel design node.

[0150] Furthermore, the tunnel design module 62 is also used to convert the tunnel map structure data into tunnel data in GIS exchange format; and to convert the tunnel data in GIS exchange format into CAD drawing data of the tunnel.

[0151] Furthermore, the non-lane data acquisition module 61 is also used to generate the non-lane map structure data using the following steps:

[0152] Obtain CAD drawing data of non-tunnel areas in the mine, which contains graphic information of the non-tunnel areas; convert the CAD drawing data of non-tunnel areas into non-tunnel data in GIS exchange format; and generate non-tunnel map structure data based on the non-tunnel data in GIS exchange format.

[0153] Furthermore, the non-tunnel nodes include: ore body outline and ore pass;

[0154] The tunnel design node is the tunnel design centerline.

[0155] The functions of the above modules can be corresponding to Figures 1 to 4 The corresponding processing steps in the process shown will not be repeated here.

[0156] The mine roadway design model training device and mine roadway design device provided in the embodiments of this application can be implemented by computer programs. Those skilled in the art should understand that the above-described module division method is only one of many module division methods. Whether divided into other modules or not divided into modules, as long as the mine roadway design model training device and mine roadway design device have the above-described functions, they should all be within the protection scope of this application.

[0157] This application also provides an electronic device, such as... Figure 7 As shown, it includes a processor 71 and a machine-readable storage medium 72, the machine-readable storage medium 72 storing machine-executable instructions that can be executed by the processor 71, the processor 71 being prompted by the machine-executable instructions to: implement any of the above-described mine roadway design model training methods, or implement any of the above-described mine roadway design methods.

[0158] This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements any of the above-described mine roadway design model training methods, or implements any of the above-described mine roadway design methods.

[0159] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to execute any of the above-described mine roadway design model training methods, or to execute any of the above-described mine roadway design methods.

[0160] The machine-readable storage medium in the aforementioned electronic device may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0161] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0162] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of devices, electronic devices, computer-readable storage media, and computer program products are basically similar to the method embodiments, and therefore the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0163] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0164] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0165] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0166] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0167] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A mine roadway design model training method, characterized in that, The method comprises the following steps: obtaining graph structure data of a mine for model training, the graph structure data comprising non-roadway data and roadway data, the non-roadway data comprising non-roadway node data and non-roadway edge data, and the roadway data comprising roadway node data and roadway edge data, wherein the non-roadway edge data represents spatial relationships between non-roadway nodes, and the roadway edge data represents spatial relationships between non-roadway nodes and roadway nodes; inputting the non-roadway data into a graph neural network to be trained to obtain roadway design data output by the graph neural network, the roadway design data comprising roadway design node data and roadway design edge data, and the roadway design edge data representing spatial relationships between non-roadway nodes and roadway design nodes; adjusting network parameters of the graph neural network based on errors between the roadway design data and the roadway data.

2. The method of claim 1, wherein, The graph structure data for model training is generated by the following steps: obtaining CAD drawing data of a mine, the CAD drawing data containing graphic information of the mine; converting the CAD drawing data into mine data in GIS exchange format, the mine data in GIS exchange format comprising non-roadway mine data and roadway mine data; generating graph structure data for model training based on the mine data in GIS exchange format.

3. The method of claim 1, wherein, The adjusting of the network parameters of the graph neural network based on errors between the roadway design data and the roadway data comprises: calculating mean square errors between the roadway design data and the roadway data as values of a loss function of the graph neural network; adjusting the network parameters of the graph neural network when the mean square errors are not less than a preset error threshold.

4. The method according to any one of claims 1 to 3, characterized in that, The non-roadway nodes comprise ore body contour lines and ore pass; the roadway nodes are roadway center lines; the roadway design nodes are roadway design center lines.

5. A method of mine roadway design, characterised by, The method comprises the following steps: obtaining non-roadway graph structure data of a mine to be designed, the non-roadway graph structure data comprising non-roadway node data and non-roadway edge data, wherein the non-roadway edge data represents spatial relationships between non-roadway nodes; inputting the non-roadway graph structure data into a graph neural network trained by the method of any one of claims 1-4 to obtain roadway design data output by the graph neural network, the roadway design data serving as roadway graph structure data, the roadway design data comprising roadway design node data and roadway design edge data, and the roadway design edge data representing spatial relationships between non-roadway nodes and roadway design nodes.

6. The method of claim 5, wherein, The method further comprises the following steps: converting the roadway graph structure data into roadway data in GIS exchange format; converting the roadway data in GIS exchange format into CAD drawing data of the roadway.

7. The method of claim 5, wherein, The non-roadway graph structure data is generated by the following steps: obtaining non-roadway CAD drawing data of a mine, the non-roadway CAD drawing data containing graphic information of non-roadways of the mine; converting the non-roadway CAD drawing data into non-roadway data in GIS exchange format; generating non-roadway graph structure data based on the non-roadway data in GIS exchange format.

8. The method according to any one of claims 5 to 7, wherein, The non-roadway node comprises: a ore body contour line and a draw shaft; The roadway design node is a center line in roadway design.

9. A mine roadway design model training apparatus, characterized by, The method comprises the following steps: The training data acquisition module is configured to acquire graph structure data of the mine for model training, the graph structure data comprising non-roadway data and roadway data, the non-roadway data comprising non-roadway node data and non-roadway edge data, and the roadway data comprising roadway node data and roadway edge data, wherein the non-roadway edge data represents spatial relationships between non-roadway nodes, and the roadway edge data represents spatial relationships between non-roadway nodes and roadway nodes. The training data input module is configured to input the non-roadway data into a graph neural network to be trained to obtain roadway design data output by the graph neural network, the roadway design data comprising roadway design node data and roadway design edge data, and the roadway design edge data representing spatial relationships between non-roadway nodes and roadway design nodes. The model training module is configured to adjust network parameters of the graph neural network based on errors between the roadway design data and the roadway data.

10. A mine roadway design apparatus, characterised by, The method comprises the following steps: The non-roadway data acquisition module is configured to acquire non-roadway graph structure data of a mine to be designed, the non-roadway graph structure data comprising non-roadway node data and non-roadway edge data, wherein the non-roadway edge data represents spatial relationships between non-roadway nodes. The roadway design module is configured to input the non-roadway graph structure data into a graph neural network trained by the device of claim 9 to obtain roadway design data output by the graph neural network, the roadway design data serving as roadway graph structure data, the roadway design data comprising roadway design node data and roadway design edge data, and the roadway design edge data representing spatial relationships between non-roadway nodes and roadway design nodes.

11. An electronic device, comprising: The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method of any one of claims 1-4 or the method of any one of claims 5-8.

12. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method of any one of claims 1-4 or the method of any one of claims 5-8.

Images