An unmanned aerial vehicle emergency center site selection method and device under a complex roadway network

Abstract

A method and device for selecting an unmanned aerial vehicle emergency center in a complex roadway network, which measures the importance of nodes in the roadway by four indexes of the center degree, node betweenness, H index and core number in the complex network theory; candidate center nodes are selected by "digging holes", and the candidate nodes selected by "digging holes" are selected from a global perspective, which is suitable for various road network topological graphs, meets full coverage of all nodes, and determines the number of candidate site points from an objective point of view by measuring whether there are remaining nodes after "digging holes", thereby reducing the calculation amount in subsequent site selection operation; the number of node rescue equipment is determined according to the number of nodes controlled by the emergency center; according to different use scenarios, the weight of the objective function factor in the site selection model can be self-assigned, and the weight can be configured according to the underground station building capacity, the processing speed of emergency events and the demand for the highest cost performance, and users can select different site selection modes according to different environments or demands.

Description

Technical Field

[0001] This application belongs to the field of coal mine roadway inspection technology, specifically relating to a method and device for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex roadway network. Background Technology

[0002] With the development of 5G technology and the gradual emergence of underground drones, the application of drones in coal mine roadways to respond to emergencies will significantly upgrade mine safety. This has enormous economic and social benefits for promoting efficient coal mine production and ushering in the era of smart mines. Due to the requirements of maximum range and emergency response within a specific timeframe, drones necessitate the establishment of drone emergency site selection centers to ensure full-area coverage for emergency inspections of roadways.

[0003] However, in the methods for calculating candidate nodes in complex network analysis, the selection of candidate nodes by setting a certain value is often subjective, which leads to problems such as the inability to determine the number of candidate nodes, the over-concentration of candidate sites, and the inaccessibility of drones after adding constraints. This adds difficulty to the site selection problem. Summary of the Invention

[0004] In view of this, the purpose of this application is to propose a method and device for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex road network, so as to solve or partially solve the above-mentioned technical problems.

[0005] To achieve the above objectives, the first aspect of this application provides a method for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex tunnel network, comprising:

[0006] Obtain the tunnel topology map, extract the nodes of the line segments in the tunnel topology map, label the extracted nodes, map the tunnel topology map into an undirected graph, and construct a complex tunnel network model using the connectivity between the extracted nodes.

[0007] Using the relationship between the flow and topological location of nodes in the complex network model of the alleyway, the importance of nodes in the alleyway is measured and evaluated by preset indicators, including degree centrality, node betweenness, H-index and core number;

[0008] The weights of preset indicators were calculated using the analytic hierarchy process (AHP) to obtain the weights of degree centrality, node betweenness, H-index, and kernel number.

[0009] The indicator values ​​of each node are standardized, and a comprehensive indicator value is generated by combining the indicator weights. The comprehensive indicator values ​​are then sorted, and the node with the highest comprehensive indicator value is selected.

[0010] Draw a circle with the selected node as the center and the emergency flight distance converted from the emergency response time as the radius. Remove the nodes inside the circle from the tunnel topology map to complete the "hole digging". Calculate and sort the comprehensive index values ​​of the remaining nodes again, find the point with the highest importance and "dig holes" again until there are no more nodes to choose from in the tunnel topology map. Output the center of the circle as the candidate emergency center node.

[0011] A site selection planning model combining set coverage model and multi-objective decision-making is adopted to determine the number and location of emergency centers after comprehensively considering predetermined influencing factors.

[0012] As an optimal solution for selecting the location of UAV emergency response centers in complex tunnel networks, a complex tunnel network model is constructed using the extracted connectivity between nodes:

[0013] G = (N, E, W)

[0014] N = {n1, n2, ..., n} N}

[0015] In the formula, G is the tunnel topology graph, N represents the set of nodes in the tunnel topology graph, E is the set of edges in the tunnel topology graph, and e ij The edge between node i and node j represents the road in the alley; W ij For e ij The weight.

[0016] As an optimal solution for the location selection of UAV emergency centers in complex tunnel networks, the centrality of degree is represented as:

[0017]

[0018] In the formula, ND i The number of neighboring nodes of the specified node;

[0019] The number of cores is determined as follows:

[0020] Remove nodes with degree equal to k and the edges connecting them from the topology graph G to obtain subgraph G′. Delete nodes with degree less than or equal to k and the edges connecting them from subgraph G′ to obtain a new subgraph G″. Continue this process until there are no more nodes with degree less than or equal to k in the graph. k is the number of nodes removed.

[0021] As an optimal solution for the location selection of UAV emergency centers in complex tunnel networks, the node betweenness factor is expressed as:

[0022]

[0023] In the formula, α st Let α be the total number of shortest paths between node s and node t. st(i) represents the number of shortest paths between node s and node t that pass through node i:

[0024] The H-index is determined as follows:

[0025] Sort the degree values ​​of all neighboring nodes of node i in descending order. In a two-dimensional coordinate system, the horizontal axis is labeled with the node's index and the vertical axis is labeled with the node's degree value. Starting from the origin, draw a square with no nodes to the maximum extent possible in the first quadrant. The side length of the square is the H-index of node i.

[0026] As an optimal method for selecting the location of UAV emergency centers in complex tunnel networks, the Z-score standardization method is adopted to perform dimensionless processing on the scale values ​​of the preset indicators:

[0027]

[0028] In the formula, Z is the result after dimensionless processing, X is the original data, X′ is the average value of each indicator, and s is the standard deviation of each indicator.

[0029] The comprehensive index value is reflected by combining the weight ω with Z, using Z′. i =Z i ×ω is used to calculate the comprehensive index value to complete the comprehensive evaluation of the node.

[0030] As a preferred method for site selection of drone emergency centers in complex road network, the predetermined influencing factors include: site construction cost and drone purchase cost, emergency center operation cost, cost per unit distance of the shortest distance between the accident point and the emergency center, and cost per unit distance = energy consumption cost + battery maintenance cost + depreciation cost + cloud platform system usage cost.

[0031] As the optimal site selection method for UAV emergency centers in complex tunnel networks, the objective function of the site selection planning model is:

[0032]

[0033] In the formula, CB j The construction cost of the emergency center includes fixed investment costs and the cost of purchasing drones; CR j For the operating costs of the emergency response center; CTD j The cost is the shortest distance between the accident site and the emergency center multiplied by the cost per unit distance; k CB k CR k CTD The corresponding weights;

[0034] The construction cost of the j-th emergency center is expressed as follows:

[0035] CB j =C cBuid +C uavp *UAVN j

[0036] In the formula, C cBuid C uavP The unit price of UAVN j The number of drones required for the j-th emergency center.

[0037] As the optimal site selection method for UAV emergency centers in complex road network environments, the constraints of the site selection planning model are as follows:

[0038]

[0039] In the formula, constraint (a) means that a demand point is served by only one rescue center;

[0040] Constraint (b) If an emergency facility center is built at point j, then x j It is 1 if it is true, otherwise it is 0.

[0041] Constraint (c) If node i is served by emergency center j, then y ij It is 1 if it is true, otherwise it is 0.

[0042] The constraint (d) node must be within the coverage area.

[0043] As a preferred method for selecting the location of UAV emergency centers in complex road network environments, the time penalty cost is transformed into a distance penalty cost. The penalty cost is set as the cost incurred when the UAV fails to arrive within the stipulated emergency rescue time, [0, t]. be [This is the optimal timeframe for emergency rescue, with the furthest flight time being (T)]. uav -t d ) / 2 minutes;

[0044] Based on the selection of candidate nodes, a genetic algorithm is used to solve for the optimal location point in a multi-objective process.

[0045] The second aspect of this application provides a device for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex tunnel network, employing the method for selecting the location of an UAV emergency center in a complex tunnel network as described in the first aspect or any possible implementation thereof, including:

[0046] The node extraction module is used to obtain the tunnel topology map and extract the nodes of the line segments in the tunnel topology map;

[0047] The node labeling module is used to label the extracted nodes and map the tunnel topology map into an undirected graph.

[0048] The tunnel complex network model construction module is used to construct a tunnel complex network model by utilizing the extracted connectivity between nodes;

[0049] The preset index selection module is used to measure and evaluate the importance of nodes in the alleyway by utilizing the flow and topological location relationship of nodes in the alleyway complex network model. The preset indexes include degree centrality, node betweenness, H-index, and core number.

[0050] The indicator weight calculation module is used to calculate the weights of preset indicators using the analytic hierarchy process (AHP) to obtain the indicator weights for degree centrality, node betweenness, H-index, and kernel number.

[0051] The indicator standardization module is used to standardize the indicator values ​​of each node and generate a comprehensive indicator value by combining the indicator weights.

[0052] The node sorting and selection module is used to sort the comprehensive index values ​​and select the node with the highest comprehensive index value.

[0053] The node "hole-drilling" processing module is used to draw a circle with the selected node as the center and the emergency flight distance converted from the emergency response time as the radius. The nodes inside the circle are removed from the roadway topology map to complete the "hole-drilling". The remaining nodes are recalculated and sorted according to the comprehensive index value. The point with the highest importance is found and "hole-drilled" again until there are no more nodes to choose from in the roadway topology map. The center of the drawn circle is output as the candidate emergency center node.

[0054] The site selection decision module is used to determine the number and location of emergency centers by adopting a site selection planning model that combines set coverage model and multi-objective decision-making, after comprehensively considering predetermined influencing factors.

[0055] A third aspect of this application proposes an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the method for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex tunnel network, as described in the first aspect or any possible implementation thereof.

[0056] The fourth aspect of this application proposes a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute a method for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex tunnel network, implementing the first aspect or any possible implementation thereof.

[0057] As can be seen from the above, the technical solution provided in this application solves the problem of emergency center site selection for applying drones to underground roadways. Considering the suitability for underground environments, the drone's endurance, and emergency response standards, an emergency center is established without increasing the workload of excavation in existing roadways. From the perspectives of flow and topological position relationships of nodes in complex networks, the importance of nodes in roadways is measured using four indicators from complex network theory: centrality, betweenness number, H-index, and core number. Candidate center nodes are screened through a "hole-drilling" method. Compared to the subjective approach of selecting a value to determine candidate nodes in complex network analysis, which makes complex network analysis more subjective and results in the inability to determine the number of candidate nodes and candidate site selection points, this method achieves a better result. To address issues such as overly concentrated locations and drone inaccessibility due to added constraints, the "hole-digging" method selects candidate nodes from a global perspective, adapting to various road network topologies and ensuring full coverage of all nodes. It also objectively determines the number of candidate sites by assessing whether any nodes remain after "hole-digging," reducing computational load in subsequent site selection calculations. The number of rescue devices per node is determined based on the number of nodes controlled by the emergency center. Furthermore, the weights of each factor in the objective function of the site selection model can be customized according to different usage scenarios. Users can configure weights based on their downhole construction capabilities, emergency response speed, and the need for the highest cost-effectiveness. Users can choose different site selection modes based on different environments or requirements. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a schematic diagram of the method for selecting the location of an unmanned aerial vehicle (UAV) emergency center under a complex road network, as described in this application embodiment.

[0060] Figure 2 This is a schematic diagram of the preset indicators in the method for selecting the location of an unmanned aerial vehicle emergency center under a complex tunnel network according to an embodiment of this application.

[0061] Figure 3 This is a schematic diagram illustrating the H-index solution in the method for selecting a drone emergency center location under a complex road network, as described in this application embodiment.

[0062] Figure 4 This is a schematic diagram illustrating the overall cost structure in the method for selecting a drone emergency center location under a complex road network, as described in this application embodiment.

[0063] Figure 5This is a schematic diagram of the genetic algorithm in the method for selecting the location of an unmanned aerial vehicle (UAV) emergency center under a complex road network, as described in this application embodiment.

[0064] Figure 6 Here is a roadway topology diagram in the UAV emergency center location method under a complex roadway network, as described in this application embodiment:

[0065] Figure 7 This is a schematic diagram of candidate emergency response centers in the UAV emergency center location method under complex roadway networks, as described in this application embodiment.

[0066] Figure 8 This is a diagram illustrating the scope of responsibility for an emergency response center under the integrated model in the method for selecting a location for an unmanned aerial vehicle (UAV) emergency response center in a complex road network, as described in this application embodiment.

[0067] Figure 9 This is a diagram illustrating the scope of responsibility of the emergency center under emergency mode in the method for selecting a location for an unmanned aerial vehicle (UAV) emergency center in a complex tunnel network, as described in this application embodiment.

[0068] Figure 10 This is a diagram illustrating the scope of responsibility for emergency facility centers under the minimum number of emergency centers mode in the method for selecting a location for an unmanned aerial vehicle (UAV) emergency center in a complex road network, as described in this application embodiment.

[0069] Figure 11 This is a schematic diagram of the drone emergency center location selection device under a complex tunnel network, as described in this application embodiment:

[0070] Figure 12 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with specific embodiments and the accompanying drawings.

[0072] It should be noted that, unless otherwise defined, the technical or scientific terms used in the embodiments of this application should have the ordinary meaning understood by a person skilled in the art to which this application pertains. The terms "comprising" or "including," or similar words used in the embodiments of this application, mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects.

[0073] Currently, most coal mining operations are still underground, relying heavily on manual inspections. This method is highly dependent on the experience of the workers, and is characterized by high workload, low efficiency, and excessive costs. Furthermore, the complex and relatively enclosed geographical environment of the mine tunnels makes it difficult to promptly locate faults in the event of incidents such as water inrushes, excessively high concentrations of toxic gases, or tunnel collapses. This not only results in a significant waste of emergency resources and manpower but also causes irreversible damage to mine equipment and the personal safety of workers.

[0074] Coal mine accidents have led to a very serious safety situation in production. In recent years, civilian drones have played a significant role in civilian fields such as power line inspection, emergency rescue, logistics distribution, and traffic information collection due to their stability, low power consumption, and networking capabilities. However, due to limitations such as the lack of GPS signals in coal mine tunnels, drones are currently only used for surveying in open-pit mines.

[0075] With the development of 5G technology and the gradual emergence of underground drones, the application of drones in coal mine roadways to respond to emergencies will significantly upgrade mine safety. This has enormous economic and social benefits for promoting efficient coal mine production and ushering in the era of smart mines. However, due to the requirements of drones' maximum range and the need to complete emergency response within a specific time frame, it is necessary to establish drone emergency site selection centers to meet the full-area coverage of emergency inspections in roadways.

[0076] Among related technologies, several methods for establishing emergency center locations have been disclosed. One method involves directly allocating demand points based on given center nodes, using a set coverage model for calculations. However, this is computationally complex for areas with a large number of nodes. Another method considers given node attributes such as distance and population density, employing clustering methods for emergency center location selection. Given the unique characteristics of underground tunnels, such as their location underground, complex geographical location, and the limitations imposed on drone flights by the road network, location selection in underground tunnels differs from the aforementioned problems and requires consideration of the suitability of underground site conditions. Tunnel location selection should be a discrete location within network location, applying complex network theory to the tunnel network to complete candidate node selection.

[0077] In methods for calculating candidate nodes in complex network analysis, candidate nodes are screened by setting a certain value. However, because the selection of the comprehensive value is often subjective, it leads to problems such as inability to determine the number of candidate nodes, over-concentration of candidate sites, and unreachability of drones after adding constraints, which increases the difficulty of site selection. In addition, most site selection models only consider emergency response time and cost, without taking into account the capacity of emergency equipment in each emergency center, or arbitrarily setting the capacity of emergency equipment in emergency centers to be the same.

[0078] In view of this, to solve the problem of emergency center site selection for applying drones in underground roadways, this application combines the idea of ​​matching pursuit algorithm with complex network analysis to propose a "hole-drilling" method for selecting candidate nodes. This involves finding the node with the highest comprehensive value and then eliminating nodes within a circle centered on that node and with the emergency response distance as the radius. This process is repeated multiple times until all nodes are under control, thus completing the candidate node selection. This application applies complex network theory to roadway networks to complete candidate node site selection. It proposes a method and device for drone emergency center site selection in complex roadway networks from multiple perspectives, including the maximum range limit of drones, the different capacities of inspection equipment included in the emergency center, and the total cost of the emergency center. This allows drones to be applied to emergency inspections in roadways, ensuring full coverage of all nodes and timely handling of emergencies. The following are the specific contents of the embodiments of this application.

[0079] See Figure 1 , Figure 2 , Figure 3 and Figure 4 This application provides a method for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex road network, comprising the following steps:

[0080] S1. Obtain the tunnel topology map, extract the nodes of the line segments in the tunnel topology map, label the extracted nodes, map the tunnel topology map into an undirected graph, and use the connectivity between the extracted nodes to construct a complex tunnel network model.

[0081] S2. Utilizing the relationship between flow and topological location of nodes in the aforementioned complex network model of the alleyway, the importance of nodes in the alleyway is evaluated using preset indicators, including degree centrality, node betweenness, H-index, and core number.

[0082] S3. The weights of the preset indicators are calculated using the analytic hierarchy process (AHP) to obtain the weights of degree centrality, node betweenness, H-index, and core number.

[0083] S4. Standardize the indicator values ​​of each node, generate a comprehensive indicator value by combining the indicator weights, sort the comprehensive indicator values, and select the node with the highest comprehensive indicator value.

[0084] S5. Draw a circle with the selected node as the center and the emergency flight distance converted from the emergency response time as the radius. Remove the nodes inside the circle from the tunnel topology map to complete the "hole digging". Calculate and sort the comprehensive index values ​​of the remaining nodes again, find the point with the highest importance and "dig holes" again until there are no more nodes to choose from in the tunnel topology map. Output the center of the circle as the candidate emergency center node.

[0085] S6. A site selection planning model combining set coverage model and multi-objective decision-making is adopted to determine the number and location of emergency centers after comprehensively considering predetermined influencing factors.

[0086] In this embodiment, step S1 involves using the original method to read and model the topological graph of the tunnel, extracting each node from each line segment in the tunnel topological graph, labeling the nodes in the tunnel topological graph, mapping the tunnel topological graph to an undirected graph G, and constructing a topological adjacency matrix based on the connectivity between nodes as a complex network model of the tunnel. The constructed complex network model of the tunnel is as follows:

[0087] G = (N, E, W)

[0088] N = {n l n2, ..., n N}

[0089] In the formula, G is the tunnel topology graph, N represents the set of nodes in the tunnel topology graph, E is the set of edges in the tunnel topology graph, and e ij The edge between node i and node j represents the road in the alley; W ij For e ij The weight.

[0090] Support Figure 2 In this embodiment, since the roadway topology is a complex network, this application starts from the two perspectives of the flow and topological position relationship of nodes in the complex network, and uses four indicators, namely degree centrality, node betweenness, H index and core number, to measure and evaluate the importance of nodes in the roadway.

[0091] The degree centrality is represented as:

[0092]

[0093] In the formula, ND i ND represents the number of neighboring nodes of a specified node; i The larger the DC i The higher the value, the more routes pass through that node, and the higher the probability that node i is a hub station compared to other nodes in the road network topology.

[0094] Among them, coreness i Represented as:

[0095] coreness i =k

[0096] By removing nodes with degree equal to k and their connecting edges from the roadway topology graph G, a subgraph G′ is obtained. Then, nodes with degree less than or equal to k and their connecting edges are deleted from subgraph G′, resulting in a new subgraph G″. This process continues until no nodes with degree less than or equal to k remain in the graph. The removed nodes all have a core number of k. Next, nodes with degree equal to k+1 are removed, and this process is repeated until all nodes in the roadway topology graph are removed.

[0097] The node betweenness is represented as:

[0098]

[0099] In the formula, α st Let α be the total number of shortest paths between node s and node t. st (i) represents the number of shortest paths between nodes s and t via node i.

[0100] Support Figure 3 The H-index is determined as follows:

[0101] Taking node i in the roadway topology diagram as an example, the degree values ​​of all neighboring nodes of node i are sorted in descending order. In the two-dimensional coordinate system, the horizontal axis is labeled with the corresponding index of the node, and the vertical axis is labeled with the degree value of the node. Starting from the origin, a square without any nodes is drawn to the maximum extent in the first quadrant. The side length of the square is the H exponent of node i.

[0102] In this embodiment, four indicators—degree centrality, node betweenness, H-index, and core number—are used as indicators to measure the importance of nodes in the evaluation roadway, and the analytic hierarchy process (AHP) is employed for weight calculation. Here, a, b, c, d, e, and f are the quantified values ​​of pairwise importance comparisons among the above four indicators:

[0103]

[0104] Using the arithmetic mean method:

[0105]

[0106]

[0107]

[0108] ω T =[ω DD ω BC ω H-index ω coreness [ ] is the transpose matrix of the weights of each indicator;

[0109] The eigenvector D is:

[0110] D=C×ω

[0111] Therefore, the largest eigenvalue is:

[0112]

[0113] The consistency index (CI) is:

[0114] CI=(λ-n) / (n-1)=(λ-4) / (4-1)

[0115] The random consistency index RI is obtained from the table:

[0116] RI = 0.89

[0117] Furthermore, because the consistency ratio (CR) is:

[0118] CR = CI / RI

[0119] If CR≤0.1, the indicator weights are considered to meet the consistency evaluation.

[0120] In this embodiment, Z-score normalization is used to perform dimensionless processing on the scale values ​​of the preset index:

[0121]

[0122] In the formula, Z is the result after dimensionless processing, X is the original data, X′ is the average value of each indicator, and s is the standard deviation of each indicator.

[0123]

[0124] In this embodiment, the weight ω is combined with Z, using Z′ i =Z i The comprehensive evaluation is completed by calculating ×ω, that is, using an index value Z′. i This reflects the topological and traffic characteristics of the network topology graph: then the comprehensive index value Z′ of the coordinate points is analyzed. i Sort in descending order.

[0125] In this embodiment, step S5 combines the idea of ​​a matching pursuit algorithm to find candidate nodes that satisfy full node coverage. First, the node with the highest overall importance is found, and a circle is drawn with this node as the center and the emergency flight distance converted from the emergency response time as the radius. All nodes within the circle are removed from the tunnel topology map, completing the "hole-digging". The remaining nodes are then recalculated and sorted for overall importance, and the point with the highest importance is "hole-digging" again. This process is iterated until no more nodes are available in the complex tunnel map. The center of the circle drawn in each step is used as the candidate emergency center node to narrow down the range of site selection schemes and simplify the solution process of the multi-emergency center site selection model.

[0126] In this embodiment, since accidents in complex networks are characterized by multiple occurrences, irregular outbreak points, and high timeliness requirements for accident handling, step S6 adopts a location planning model that combines the Location Set Covering problem (LSCP) and multi-objective decision-making to determine the optimal location of the emergency rescue station after comprehensively considering various influencing factors.

[0127] The basic assumptions are as follows:

[0128] 1. All the underground rescue equipment and drones are of the same model;

[0129] 2. During the rescue operation, the drone adopted an autonomous obstacle avoidance mode and could only fly along the road network routes. The drone flew at its maximum speed V. uavMax The flight speed is constant at m / s, and the default endurance time for each mission is the maximum endurance time T. uavMax minute;

[0130] 3. Emergency rescue missions have high requirements for response time. The time standard from the emergency center to the fault location is set as: t be The optimal response time should be 1 minute. Ignoring drone monitoring time, the default is to complete scene detection and photo transmission at the fault location within td minutes.

[0131] 4. Emergency centers are located only at intersections within the alleyways. Each emergency center covers multiple sites, and each site is monitored and handled by only one emergency center.

[0132] 5. Considering the frequent occurrence of faults and the different number of controlled nodes allocated by the emergency center, the number of drones equipped for each node varies in order to avoid wasting resources;

[0133] 6. The construction of emergency centers requires a large investment of funds. Therefore, while ensuring that all sites are covered, the number of emergency centers should be minimized to keep the total cost to a minimum.

[0134] Specifically, in constructing the site selection planning model, the influencing factors of emergency center site selection are considered. The maximum coverage radius of the emergency center is set based on the limitation of the drone's own battery's maximum endurance. From multiple perspectives, such as the different capacities of the inspection equipment included in the emergency center and the total construction and operation costs of the emergency center, the goal is to minimize the total cost while ensuring full coverage. Users can configure weights according to their own economic capabilities, the speed of emergency response, and the need for the highest cost-effectiveness.

[0135] Support Figure 4The site selection of emergency rescue stations in underground tunnels needs to consider the impact of multiple objectives, namely, the comprehensive cost (CAll), which is the sum of the construction cost and the cost of purchasing drones (CB); the operating cost (CR) of the emergency center; the cost per unit distance of the shortest distance between the accident point and the emergency center (CTD); and the cost per unit distance (ECTD) = energy consumption cost + battery maintenance cost + depreciation cost + cloud platform system usage cost.

[0136] The objective function of the site selection planning model is:

[0137]

[0138] In the formula, CB j The construction cost of the emergency center includes fixed investment costs and the cost of purchasing drones; CR j For the operating costs of the emergency response center; CTD j The cost is the shortest distance between the accident site and the emergency center multiplied by the cost per unit distance; k CB k CR k CTD The corresponding weights;

[0139] The construction cost of the j-th emergency center is expressed as follows:

[0140] CB j =C cBuid +C uavp *UAVN j

[0141] In the formula, C cBuid C uavP The unit price of UAVN j The number of drones required for the j-th emergency center.

[0142] in:

[0143] UAVN i min ≥1

[0144] numUAV = N / M

[0145] UAVN j =conPoint j / numUAV

[0146] UAVN j min≥1 means that each center has at least one drone; numUAV = N / M represents the ideal state of even distribution of nodes, the number of controlled nodes numUAV that an emergency center can accommodate, which is the total number of nodes N divided by the number of emergency centers M; UAVN j =conPoint j / numUAV means the number of nodes controlled by the j-th emergency center divided by numUAV, and the result is the number of UAVs required for the j-th emergency center. j Taiwanese drone.

[0147] Specifically, the constraints of the site selection planning model are:

[0148]

[0149] In the formula, constraint (a) means that a demand point is served by only one rescue center;

[0150] Constraint (b) If an emergency facility center is built at point j, then x j It is 1 if it is true, otherwise it is 0;

[0151] Constraint (c) If node i is served by emergency center j, then y jj It is 1 if it is true, otherwise it is 0;

[0152] The constraint (d) node must be within the coverage area.

[0153] Since the time factor (also known as time satisfaction) cannot be scientifically quantified, and the drone travels at a constant speed, the optimal emergency time for the drone is transformed into the optimal emergency distance: D = V * t; that is, the time penalty cost is transformed into a distance penalty cost, and the penalty cost is set as the cost incurred when the drone fails to arrive within the stipulated emergency rescue time, [0, t]. be [This is the optimal timeframe for emergency rescue, with the furthest flight time being (T)]. uav -t d ) / 2 minutes.

[0154] The penalty function is defined as follows:

[0155]

[0156] When the emergency rescue time t is exceeded be At that time, C D The value is infinity. If the drone can reach the target within the emergency rescue time, the penalty function is 0 and has no effect.

[0157] Support Figure 5 Based on the selection of candidate nodes, a genetic algorithm is used to solve for the optimal location point for multiple objectives.

[0158] Taking the roadways of a coal mine in a certain region as an example, this study examines the site selection of a drone emergency center under a complex roadway network. The roadway topology is shown below. Figure 6 As shown, it includes the following steps:

[0159] Step 1: First, the original method is used to read and model the topology of the lanes in a certain area, extracting each node from each line segment in the lane map, and then labeling the nodes. The lane topology map used in this application has a total of 1174 nodes and 1285 line segments. Based on the connectivity between nodes, a topological adjacency matrix is ​​constructed.

[0160] Step 2: The tunnel topology is a complex network. The importance of nodes in the tunnel is evaluated from four aspects: the relationship between the flow and topological position of nodes in the complex network, the centrality of adoption degree, the betweenness of nodes, the H index, and the number of cores.

[0161] Step 3: Standardize the data of each indicator, calculate the weight of each indicator using the analytic hierarchy process (AHP), and rank the importance of each node after a comprehensive evaluation of its importance.

[0162] In this embodiment, a judgment matrix C is constructed. ij :

[0163]

[0164] The transpose matrix of the weights of each indicator is then:

[0165] ω T =[ω DC ω BC ω H-index ω corenes s]=[0.05437,0.24683,0.24683,0.45198]

[0166] Because of the consistency ratio

[0167] CR = CI / RI = 0.006 ≤ 0.1

[0168] Therefore ω T The consistency check is satisfied.

[0169] The data for each indicator were standardized, and the overall importance of each node was calculated based on its weight. Table 1 shows the overall importance of each node in the roadway before site selection began.

[0170] Table 1. Comprehensive Evaluation Results of Node Importance

[0171]

[0172] Step 4: Using point number 403, which has the highest comprehensive index value, as the center, and within the specified emergency response time t...be The process involves converting the data to a radius 'd' and drawing a circle. All nodes within this circle are then removed from the tunnel map, completing the "hole-digging" process. The remaining nodes are then recalculated and sorted based on their overall importance, with the highest-importance point being used for "hole-digging." This iterative process continues until no more nodes are available in the complex tunnel map. The center of each circle is used as a candidate emergency center node to narrow down the range of site selection options and simplify the solution process for the multi-emergency center site selection model.

[0173] like Figure 7 The diagram shows site selection based on emergency response times of 15 minutes and 8 minutes, respectively. Figure 7 A total of 17 candidate center points were selected in the middle left section, with an emergency response time limit of 15 minutes. Figure 7 A total of 37 candidate center points were selected in the middle and right sections, with an emergency response time limit of 8 minutes.

[0174] Step 5: Consider the factors influencing emergency center site selection. Establish a site selection planning model, and set the maximum coverage radius of the emergency center based on the limitation of the drone's own battery's maximum flight time. Consider various factors such as the different numbers of inspection equipment included in the emergency center, and the total construction and operation costs of the emergency center, to achieve the minimum total cost while ensuring full coverage. Obtain the drone's operating speed, battery life, and price per drone.

[0175] Table 2. Relevant parameters of UAVs

[0176]

[0177] The relevant parameters in the site selection planning model are shown in Table 3: It is assumed that the construction cost is 30,000 yuan / site and the operating cost is 1,500 yuan / site; the cost per unit distance (ECTD) is set to 0.87 yuan / km;

[0178] Table 3. Parameters related to the site selection model

[0179]

[0180] The parameters of the genetic algorithm are shown in Table 4:

[0181] Table 4. Parameters related to the genetic algorithm

[0182]

[0183] To address the different needs and applicable scopes of underground emergency rescue modes, three options are proposed: a comprehensive mode (with high cost-effectiveness) site selection, a rapid response mode site selection, and a mode with the fewest emergency centers.

[0184] Among these factors, a multi-factor (cost-effectiveness high) site selection scheme was adopted, taking into account factors such as construction, operation, daily wear and tear costs, and shortest distance. Based on the 15-minute candidate nodes planned in step 4, the construction method with the highest cost-effectiveness was selected while achieving full node coverage. An evaluation system was constructed considering accident response time and various costs to conduct a suitability evaluation of the alleyway emergency center.

[0185] The rapid response mode site selection scheme prioritizes response time, disregarding the additional costs associated with building, operating, and maintaining the emergency center compared to the first method. For more urgent situations, it's necessary to shorten the response time, such as changing the optimal response time to within 8 minutes. Candidate nodes are selected based on the 8-minute candidate nodes chosen in step four to complete the site selection.

[0186] Among them, the site selection scheme with the fewest emergency centers is constrained by conditions such as underground tunnel safety and excavation difficulties. It prioritizes the number of emergency centers, disregarding costs such as purchasing drones and flight distance consumption, and only requires minimizing the number of stations. The site selection is completed under the premise of achieving full node coverage and completing emergency response within 15 minutes.

[0187] Step 6: Solve the model using a combination of genetic algorithm and Dijkstra's algorithm. Dijkstra's algorithm is used to calculate the shortest distance between any two nodes in the roadway topology map, and the genetic algorithm is used to calculate the site selection results.

[0188] Among them, the site selection scheme that takes into account multiple factors (high cost performance) is as follows:

[0189] For the multi-factor integrated objective function, the coefficients of each factor are k. CB =0.24, k CR =0.08, k CTD =0.68. The objective function is:

[0190]

[0191] The site selection and allocation results are shown in Table 5. There are a total of 17 emergency center sites. In this model, the calculated numUAV is 69, and the number of drones is 17.

[0192] Table 5. Site Selection Results of the Integrated Model

[0193]

[0194] See Figure 8 This is a diagram showing the scope of responsibility for the emergency center under the integrated model.

[0195] Among them, the rapid response mode location scheme:

[0196] The site selection and allocation results are shown in Table 6. There are a total of 37 emergency center sites and 37 drones.

[0197] Table 6. Location Selection Results for Rapid Response Mode

[0198]

[0199] See Figure 9 This is a diagram showing the scope of rescue responsibilities for each emergency center under the emergency response model.

[0200] Among them, the site selection scheme with the fewest emergency centers is as follows:

[0201] The objective function is: The site selection and allocation results are shown in Table 7. There are a total of 14 emergency center sites and 14 drones.

[0202] Table 7. Site Selection Results for the Minimum Number of Emergency Centers

[0203]

[0204] See Figure 10 This is a diagram showing the scope of responsibility for emergency facility centers under the model with the fewest number of emergency centers.

[0205] The site selection schemes and applicable scopes under different modes are shown in Tables 8 and 9.

[0206] Table 8. Site selection schemes under different modes

[0207]

[0208] Table 9 Scope of Application for Different Modes

[0209]

[0210]

[0211] In summary, this application obtains a tunnel topology map, extracts nodes from line segments in the tunnel topology map, labels the extracted nodes, maps the tunnel topology map to an undirected graph, and constructs a complex tunnel network model using the connectivity between the extracted nodes. It then uses the relationship between the flow and topological location of nodes in the complex tunnel network model to measure and evaluate the importance of nodes in the tunnel using preset indicators, including degree centrality, node betweenness, H-index, and core number. The analytic hierarchy process (AHP) is used to calculate the weights of the preset indicators, obtaining the weights of degree centrality, node betweenness, H-index, and core number. Finally, the indicator values ​​of each node are standardized and combined with... The system generates a comprehensive index value based on index weights, sorts these values, and selects the node with the highest comprehensive index value. A circle is drawn with the selected node as the center and the emergency flight distance converted from the emergency response time as the radius. Nodes within this circle are removed from the tunnel topology map, completing the "hole excavation." The remaining nodes are then recalculated and sorted for their comprehensive index values. The point with the highest importance is then "excavated" again until no more nodes are available in the tunnel topology map. The center of the drawn circle is then output as the candidate emergency center node. A site selection planning model combining ensemble coverage and multi-objective decision-making is used to determine the number and location of emergency centers after considering predetermined influencing factors. This application addresses the problem of emergency center site selection for underground mine roadways using drones. Considering the suitability for underground environments, drone endurance, and emergency response standards, an emergency center is established without increasing excavation or other workload in existing roadways. From the perspectives of flow and topological location relationships of nodes in complex networks, four indicators from complex network theory—centrality, betweenness number, H-index, and core number—are used to measure the importance of nodes in the roadway. Candidate center nodes are selected through a "hole-drilling" method. Compared to the subjective selection of a value in complex network analysis, which leads to uncertainties in determining the number of candidate nodes, overly concentrated candidate sites, and increased constraints, this method avoids the more subjective nature of complex network analysis. To address issues such as unreachable drones after a disaster, the "hole-digging" method selects candidate nodes from a global perspective, adapting to various road network topologies and ensuring full coverage of all nodes. It also objectively determines the number of candidate sites by assessing whether any nodes remain after "hole-digging," reducing computational load in subsequent site selection calculations. The number of rescue devices per node is determined based on the number of nodes controlled by the emergency center. Depending on the emphasis of the usage scenario, the weights of each factor in the objective function of the site selection model can be customized. Users can configure weights based on their downhole construction capabilities, emergency response speed, and the need for the highest cost-effectiveness. Users can choose different site selection modes according to different environments or needs.

[0212] It should be noted that the method in this embodiment can be executed by a single device, such as a computer or server. The method can also be applied in a distributed scenario, where multiple devices cooperate to complete the task. In such a distributed scenario, one of these devices may execute only one or more steps of the method in this embodiment, and the multiple devices will interact with each other to complete the method described.

[0213] It should be noted that the above description describes some embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in a different order than that shown in the above embodiments and still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0214] See Figure 11 Based on the same inventive concept, and corresponding to any of the above embodiments, this application also provides a device for selecting the location of an unmanned aerial vehicle (UAV) emergency center in a complex tunnel network, comprising:

[0215] Node extraction module 1 is used to obtain the tunnel topology map and extract the nodes of the line segments in the tunnel topology map;

[0216] Node labeling module 2 is used to label the extracted nodes and map the tunnel topology map into an undirected graph;

[0217] The tunnel complex network model construction module 3 is used to construct a tunnel complex network model by utilizing the extracted connectivity between nodes;

[0218] The preset index selection module 4 is used to measure and evaluate the importance of nodes in the alleyway by utilizing the flow and topological location relationship of nodes in the alleyway complex network model. The preset indexes include degree centrality, node betweenness, H-index and core number.

[0219] The indicator weight calculation module 5 is used to calculate the weights of preset indicators using the analytic hierarchy process (AHP) to obtain the indicator weights of degree centrality, node betweenness, H-index, and kernel number.

[0220] The indicator standardization module 6 is used to standardize the indicator values ​​of each node and generate a comprehensive indicator value by combining the indicator weights.

[0221] The node sorting and selection module 7 is used to sort the comprehensive index values ​​and select the node with the highest comprehensive index value.

[0222] The node "hole-digging" processing module 8 is used to draw a circle with the selected node as the center and the emergency flight distance converted from the emergency response time as the radius, remove the nodes inside the circle from the roadway topology map, and complete the "hole-digging"; the remaining nodes are recalculated and sorted according to the comprehensive index value, and the point with the highest importance is found to "dig" again until there are no more nodes to choose from in the roadway topology map, and the center of the drawn circle is output as the candidate emergency center node;

[0223] The site selection decision module 9 is used to determine the number and location of emergency centers by adopting a site selection planning model that combines set coverage model and multi-objective decision-making, after comprehensively considering predetermined influencing factors.

[0224] The device described above is used to implement the method for selecting the location of an unmanned aerial vehicle (UAV) emergency center under a complex road network as described in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0225] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method for selecting the location of an unmanned aerial vehicle emergency center in a complex tunnel network as described in any of the above embodiments.

[0226] Figure 12 This embodiment illustrates a more specific hardware structure of an electronic device, which may include a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, memory 1020, input / output interface 1030, and communication interface 1040 are interconnected internally via the bus 1050.

[0227] The processor 1010 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0228] The memory 1020 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program code is stored in the memory 1020 and is called and executed by the processor 1010.

[0229] The input / output interface 1030 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components within the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touchscreens, microphones, various sensors, etc., while output devices may include displays, speakers, vibrators, indicator lights, etc.

[0230] The communication interface 1040 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0231] Bus 1050 includes a pathway for transmitting information between various components of the device, such as processor 1010, memory 1020, input / output interface 1030, and communication interface 1040.

[0232] It should be noted that although the above-described device only shows the processor 1010, memory 1020, input / output interface 1030, communication interface 1040, and bus 1050, in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0233] The electronic devices described above are used to implement the corresponding method for selecting the location of an unmanned aerial vehicle (UAV) emergency center under a complex road network in any of the foregoing embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0234] Based on the same inventive concept, corresponding to the methods of any of the above embodiments, this application also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the UAV emergency center location method under complex tunnel networks as described in any of the above embodiments.

[0235] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0236] The computer instructions stored in the storage medium of the above embodiments are used to cause the computer to execute the UAV emergency center location method under complex road network as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0237] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of this application (including the claims) is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of the embodiments of this application as described above, which are not provided in the details for the sake of brevity.

[0238] Additionally, to simplify the description and discussion, and to avoid obscuring the embodiments of this application, the well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Furthermore, the apparatus may be shown in block diagram form to avoid obscuring the embodiments of this application, and this also takes into account the fact that the details of the implementation of these block diagram apparatuses are highly dependent on the platform on which the embodiments of this application will be implemented (i.e., these details should be fully understood by those skilled in the art). While specific details (e.g., circuits) have been set forth to describe exemplary embodiments of this application, it will be apparent to those skilled in the art that the embodiments of this application can be implemented without these specific details or with variations thereof. Therefore, these descriptions should be considered illustrative rather than restrictive.

[0239] Although this application has been described in conjunction with specific embodiments thereof, many substitutions, modifications, and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0240] The embodiments of this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of this application should be included within the protection scope of this application.

Claims

1. A method for locating an unmanned aerial vehicle emergency center in a complex tunnel network, comprising: obtaining a tunnel topology map, extracting nodes of line segments in the tunnel topology map, labeling the extracted nodes, mapping the tunnel topology map into an undirected graph, and constructing a tunnel complex network model using the connectivity between the extracted nodes; using the traffic and topological position relationship of the nodes in the tunnel complex network model, adopting a preset index to measure and evaluate the importance of the nodes in the tunnel, the preset index including the degree centrality, node betweenness, H index, and core number; calculating the weights of the preset index to obtain the index weights of the degree centrality, node betweenness, H index, and core number; standardizing the index values of each node, combining the index weights to generate a comprehensive index value, sorting the comprehensive index values, and selecting the node with the highest comprehensive index value; drawing a circle with the selected node as the center and the emergency flight distance converted from the emergency response time as the radius, removing the nodes within the circle from the tunnel topology map to complete the "digging", calculating and sorting the comprehensive index values of the remaining nodes again, finding the node with the highest importance to perform "digging" again, until there is no node left to select in the tunnel topology map, and outputting the center of the drawn circle as the candidate emergency center node; adopting a location planning model combining a set covering model and multi-objective decision-making, and after comprehensively considering predetermined influencing factors, deciding the number and location of the emergency center.

2. The method of claim 1, wherein, The tunnel complex network model constructed using the connectivity between the extracted nodes is: G = (N, E, W) N = {n1, n2,..., n N} In the formula, G is a roadway topology graph, N represents a node set in the roadway topology graph, E is an edge set in the roadway topology graph, e ij is an edge between node i and node j, and represents a road in the roadway; W ij is a weight of e ij .

3. The method of claim 1, wherein, The degree centrality is represented as: In the formula, ND i is the number of neighbor nodes of the designated node; The core number is determined as: Remove the nodes with degree equal to k and the edges connected to the nodes in the tunnel topology graph G to obtain a subgraph G', remove the nodes with degree less than or equal to k and the edges connected to the nodes in the subgraph G' to obtain a new subgraph G'', until there is no node with degree less than or equal to k in the graph, and k is the core number of the removed node.

4. The method of claim 3, wherein, The node betweenness is represented as: wherein α st is the total number of shortest paths between node s and node t, α st (i) is the number of shortest paths between node s and node t that pass through node i; The H index is determined as: Arrange the degree values of all neighbor nodes of node i in descending order, label the horizontal coordinate with the serial number of the node and the vertical coordinate with the degree value of the node in a two-dimensional coordinate system, start from the origin, and draw a square without any nodes in the first quadrant to the maximum extent, and the side length of the square is the H index of node i.

5. The method of claim 4, wherein, The scale values of the preset index are processed dimensionlessly using the Z-score standardization method: In the formula, Z is the result of dimensionless processing, X is the original data, X' is the average value of the data of each index value, and s is the standard deviation of the data of each index value; The reflection mode of the comprehensive index value is: combining the weight ω with Z, adopting Z' i = Z i × ω to calculate the comprehensive index value to complete the comprehensive evaluation of the node.

6. The method of claim 5, wherein, The predetermined influencing factors include: station construction cost and unmanned aerial vehicle purchase cost, emergency center operation cost, shortest distance between accident point and emergency center x unit distance consumption cost, and unit distance length consumption cost = energy consumption cost + battery maintenance cost + depreciation cost + cloud platform system usage cost.

7. The method of claim 6, wherein, The objective function of the location planning model is: CB j is the stationing cost of the emergency center, including fixed investment cost and unmanned aerial vehicle purchase cost; CR j is the operation cost of the emergency center; CTD j is the cost of the shortest distance between the accident emergency point and the emergency center multiplied by the cost per unit distance; k CB , k CR , k CTD is the corresponding weight; The construction cost of the jth emergency center is represented as: CB j = C cBuid + C uavp * UAVN j where C cBuid is the cost of building each emergency center, C uavP is the unit price of a UAV, UAVN j is the number of UAVs needed for the jth emergency center.

8. The method of claim 7, wherein, The constraint conditions of the location planning model are: In the formula, constraint condition (a) represents that a demand point is served by only one rescue center; Constraint (b) is 1 if an emergency facility center is built at j, otherwise 0. j is 1 if an emergency facility center is built at j, otherwise 0. Constraint (c) y ij is 1 if node i is served by emergency center j, otherwise 0; Constraint condition (d) requires that the node be within the coverage range.

9. The method of claim 8, wherein, The time penalty cost is converted into distance penalty cost, the penalty cost is set as the cost generated by the unmanned aerial vehicle not arriving at the emergency rescue within the specified time, [0, t be ] is the optimal time period of the emergency rescue time, the flight farthest time is (T uay -t d ) / 2 minutes; On the basis of the completion of candidate node selection, a genetic algorithm is used to solve the multi-objective optimal site selection.

10. A device for locating an emergency center of unmanned aerial vehicles under complex tunnel network, adopting the method for locating an emergency center of unmanned aerial vehicles under complex tunnel network according to any one of claims 1 to 9, wherein, The method comprises the following steps: a node extraction module is configured to acquire a roadway topology graph and extract nodes of line segments in the roadway topology graph; a node labeling module is configured to label the extracted nodes and map the roadway topology graph into an undirected graph; a roadway complex network model construction module is configured to construct a roadway complex network model by using connectivity between the extracted nodes; a preset index selection module is configured to use a preset index to measure and evaluate the importance of nodes in the roadway by using a relationship between traffic and topological positions of the nodes in the roadway complex network model, the preset index comprising a degree centrality, a node betweenness, an H index, and a core number; an index weight calculation module is configured to calculate weights of the preset index to obtain index weights of the degree centrality, the node betweenness, the H index, and the core number; an index standardization module is configured to standardize index values of each node and generate a comprehensive index value in combination with the index weights; a node sorting selection module is configured to sort the comprehensive index value and select a node with the highest comprehensive index value; a node "hole digging" processing module is configured to draw a circle with the selected node as the center and an emergency flight distance converted from an emergency response time as a radius, remove nodes in the circle from the roadway topology graph to complete "hole digging", calculate and sort the comprehensive index value of the remaining nodes again, find a node with the highest importance again to perform "hole digging", and output a center of the drawn circle as a candidate emergency center node until no node is available in the roadway topology graph; and a site selection decision module is configured to use a site selection planning model combining a set covering model and a multi-objective decision to determine the number and positions of the emergency centers after comprehensively considering predetermined influencing factors.

Images