Fire station and national space integrated layout decision support system and method

Abstract

The application discloses a fire station and national territory space integrated layout decision support system and method, relates to the layout decision support field, and comprehensively considers construction cost and a construction period, so that the built fire station can meet more requirements; the layout integer programming model of the fire station is solved, the places where the fire station needs to be built can be solved, the total construction period is minimum while the cost is within the budget; the road network graph between each fire station construction point and multiple fire station construction points is constructed; the shortest path length data between each fire station construction point and multiple fire accident occurrence points is determined according to the road network graph to perform the final screening on the fire station construction point again, so that the layout rationality and accuracy of the built fire station are further ensured.

Description

Technical Field

[0001] This invention belongs to the field of layout decision support, and more specifically, it relates to an integrated layout decision support system and method for fire stations and land space. Background Technology

[0002] Chinese patent CN113850426B discloses a method, device, terminal equipment, and storage medium for selecting fire station locations. The method constructs a first location selection model; under the condition that the first constraint corresponding to a first preset type of fire station is met, a location scheme for the first preset type of fire station is determined; a second location selection model is constructed with the objectives of minimizing the number of second preset type fire stations, minimizing the distance between the second preset type fire stations and the target demand point, and maximizing the average distance between adjacent second preset type fire stations; when the second constraint corresponding to the second preset type of fire station is met, a location scheme for the second preset type of fire station is determined according to the second location selection model.

[0003] If the construction period for a fire station is too long, it means that the new fire station cannot be put into use in a timely manner, which may result in longer arrival times for fire and rescue teams in emergencies such as fires. Summary of the Invention

[0004] In response to the problems in related technologies, this invention proposes a decision support system and method for the integrated layout of fire stations and land space, in order to overcome the aforementioned technical problems existing in the existing related technologies.

[0005] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0006] This invention provides a decision support method for the integrated layout of fire stations and land use, comprising the following steps:

[0007] S1. Set multiple types of fire station layout cost factors and fire station layout construction cycle factors to obtain a set of fire station layout cost factor types and a set of fire station layout construction cycle factors; collect cost factor data of multiple fire station construction sites based on the fire station layout cost factor type set to obtain a cost factor data matrix; evaluate the construction cycle factor data of multiple fire station construction sites based on the fire station layout construction cycle factor type set to obtain a construction cycle factor data matrix.

[0008] S2. Construct an integer planning model for fire station layout based on the cost factor data matrix and the construction cycle factor data matrix; solve the integer planning model for fire station layout to obtain a preliminary set of fire station construction points;

[0009] S3. Construct a road network map between each fire station construction site and multiple fire accident occurrence points in the initial selected fire station construction site set, and obtain a road network map matrix; calculate the shortest path length of each road network map in the road network map matrix, and obtain a shortest path length data matrix;

[0010] S4. Calculate the average shortest path length data for each fire station construction point in the shortest path length data matrix to obtain the average shortest path length dataset; perform final screening on the initial set of fire station construction points based on the average shortest path length dataset to obtain the final set of fire station construction points;

[0011] When constructing fire stations in a city, construction costs and construction periods are crucial factors to consider. Therefore, this scheme comprehensively considers both construction costs and construction periods during the initial screening of fire station construction sites, ensuring that the completed fire stations meet various requirements. Specifically, by collecting cost and construction period data from multiple fire station construction sites, data support is provided for the subsequent construction of an integer programming model for fire station layout. Solving this model determines the necessary locations for fire stations, minimizing both cost and overall construction period while keeping costs within budget. Furthermore, constructing a road network map between each selected fire station construction site and multiple fire accident points helps determine the shortest path length between each site and various fire accident locations. Excessively long shortest paths can lead to lower rescue efficiency. Therefore, this scheme performs a final screening of fire station construction sites based on the shortest path length data between each site and multiple fire accident locations, further ensuring the rationality and accuracy of the fire station layout.

[0012] Preferably, step S1 includes the following steps:

[0013] S11. Define the fire station construction area, and set several fire station construction points within the fire station construction area to obtain a set of fire station construction points. , a i Indicates the set number i A fire station construction site, This indicates the total number of designated fire station construction sites;

[0014] By defining multiple types of fire station layout cost factors and fire station layout construction cycle factors, a set of fire station layout cost factor types is obtained. and fire station layout and construction cycle factors type set ; , , , , These represent the types of land cost factors, construction cost factors, equipment cost factors, maintenance cost factors, and labor cost factors, respectively. Indicates the set number i Factors affecting the layout and construction cycle of fire stations b This indicates the total number of factors related to the construction cycle of the fire station layout.

[0015] S12. Collect cost factor data for each fire station construction site in the fire station construction site set according to the fire station layout cost factor type set, and obtain a cost factor data matrix. Then, based on the aforementioned fire station layout construction cycle factor type set, the construction cycle factor data of each fire station construction site in the fire station construction site set are evaluated to obtain the construction cycle factor data matrix. ; , They are as follows:

[0016] ; ;

[0017] in, , , , , These respectively represent the concentrated construction sites of the fire stations. i Data on land cost factors, construction cost factors, equipment cost factors, maintenance cost factors, and labor cost factors for each fire station construction site; This indicates that the fire station construction sites are concentrated at the first i The first fire station construction site j Data on various types of construction cycle factors;

[0018] The factors affecting the layout and construction cycle of fire stations include those related to the preliminary preparation stage, design stage, approval stage, bidding and procurement stage, construction stage, and acceptance and delivery stage.

[0019] Preferably, step S2 includes the following steps:

[0020] S21. Set the total budget for each fire station layout cost factor type in the fire station layout cost factor type set when constructing the fire station, and obtain the fire station layout total budget dataset. , , , , , These represent the total budget data for land cost factors, construction cost factors, equipment cost factors, maintenance cost factors, and labor cost factors, respectively.

[0021] S22. Construct an integer programming model for the fire station layout based on the total budget dataset, construction cycle factor data matrix, and cost factor data matrix. The objective function of the integer programming model for the fire station layout is as follows:

[0022] ;

[0023] In the formula, This indicates the total construction period of the fire station under construction; Indicates the set number i One undetermined coefficient The constraint set for the integer programming model of the fire station layout is as follows.

[0024] ;

[0025] S23. Solve the integer programming model for the fire station layout to obtain the preliminary set of fire station construction points. , c 1i This represents the result of solving the integer programming model for the fire station layout. i A fire station construction site, This represents the total number of fire station construction sites obtained by solving the integer programming model for the fire station layout;

[0026] Since construction plans often include budgets for construction investment, setting total budget data for land cost factors, construction cost factors, equipment cost factors, maintenance cost factors, and labor cost factors provides constraint data for the subsequent construction of the integer programming model for fire station layout, making the integer programming model for fire station layout solvable.

[0027] Preferably, step S23 includes the following steps:

[0028] S231, Constructing the first slime mold population , Indicates the first slime mold population i slime mold, This represents the size of the first slime mold population; the maximum number of iterations for the first slime mold population is set to... d 1. The current iteration number is d2, denoted as the first maximum iteration number and the first current iteration number, respectively; the search space dimension of the first slime mold population is... ;

[0029] S232. Based on the objective function of the integer programming model for the fire station layout, randomly generate the initial position of each slime mold in the first slime mold population, and obtain the first initial position matrix. ;

[0030] ;

[0031] in, Indicates the first slime mold population in the first group. i The initial position of slime mold is at the first j Components in each search space dimension; ;

[0032] S233. The objective function of the integer programming model for the fire station layout is used as the fitness function of the first slime mold population.

[0033] S234. Start the iteration. Before the iteration, set the first current iteration number. d 2 is set to 1; during the first iteration, the fitness value of each initial position in the first initial position matrix is ​​calculated using the fitness function of the first slime mold population, resulting in a first fitness value set; the maximum fitness value in the first fitness value set and the corresponding initial position of the slime mold are taken as the first global optimal fitness and the first global optimal position, respectively; each initial position in the first initial position matrix is ​​updated based on the first global optimal fitness and the first global optimal position, in conjunction with the constraint conditions of the fire station layout integer programming model; after the update is completed, the first current iteration number is set to 1. d 2 plus 1 and proceed to the next iteration;

[0034] In each iteration, the fitness function of the first slime mold population is used to calculate the fitness value of each slime mold's position obtained in the previous iteration, resulting in a second fitness value set. The maximum fitness value in the second fitness value set and the corresponding initial position of the slime mold are taken as the second global optimal fitness and the second global optimal position, respectively. Based on the second global optimal fitness and the second global optimal position, and in conjunction with the constraint set of the fire station layout integer programming model, the position of each slime mold obtained in the previous iteration is updated again. After the update is completed, the first current iteration number is... d 2 plus 1 and proceed to the next iteration;

[0035] S235, when If the first optimal position is found, stop iterating and obtain the first final global optimal position; otherwise, continue iterating until... Until then; remove the fire station construction points in the fire station construction point set corresponding to the position components that are 0 in the first final global best position, and obtain the preliminary set of fire station construction points;

[0036] The slime mold optimization algorithm can quickly find the optimal or near-optimal solution by simulating the biological oscillator and cytoplasmic flow of slime molds. It is relatively insensitive to the quality of the initial solution and the selection of algorithm parameters, and combines an exploration and development search strategy, which helps to escape local optima and improve global search capabilities. Based on the above advantages, this scheme uses the slime mold optimization algorithm to iteratively optimize multiple 0-1 undetermined coefficients of the integer programming model for fire station layout, and directly uses the objective function as the fitness function. Therefore, as the iteration proceeds, it maximizes its objective function while satisfying the corresponding set of constraints.

[0037] Preferably, step S3 includes the following steps:

[0038] S31. Statistically analyze multiple fire accident locations within the fire station construction area to obtain a set of fire accident locations. , This indicates the statistical result of the first... i The location of the fire accident This represents the total number of fire incident locations obtained from statistics; a road network map is constructed between each fire incident location in the fire incident location set and each fire station construction location in the initial selected fire station construction location set, resulting in a road network map matrix. e ;as follows,

[0039] ;

[0040] in, e ij This indicates that the initial selection of fire station construction sites is concentrated in the first... i The fire station construction site is located at the fire location. j Road network diagram between the fire locations;

[0041] S32. Calculate the shortest path length in each network graph of the road network graph matrix to obtain the shortest path length data matrix. ;as follows,

[0042] ;

[0043] in, This indicates that the initial selection of fire station construction sites is concentrated in the first... i The fire station construction site is located at the fire location. j Shortest path length data in the road network diagram between fire locations;

[0044] Because urban roads are complex and dense, and fire stations need to reach the scene of a fire in a timely manner when carrying out firefighting operations, the shorter the path between the fire station and the fire location, the better. Therefore, this solution uses a graph data structure to simulate urban roads, and then uses graph theory to solve for the shortest path of each road network graph, that is, to solve for the shortest path between each fire station construction point and each fire location, providing a basis for the final selection of fire station construction points.

[0045] Preferably, the step S31, which involves statistically analyzing multiple fire incident locations within the fire station construction area to obtain a set of fire incident locations, includes the following steps:

[0046] S311. Define the set of influencing factors for fire accidents. , Indicates the set number i Types of factors influencing the occurrence of fire accidents This indicates the total number of types of factors that influence the occurrence of fire accidents.

[0047] Based on the aforementioned set of fire accident influencing factors, data on fire accident influencing factors for multiple locations where fires have occurred in the past and locations where no fires have occurred were collected to obtain a historical fire accident influencing factor data matrix. g 1 and historical fire accident label dataset ，g 2i Indicates the number of collections i Fire incident label data corresponding to each location Indicates the total number of locations where data was collected; g 1. As follows,

[0048] ;

[0049] in, g 1ij Indicates the number of collections i The location of the first j Data on factors influencing the occurrence of various types of fire accidents;

[0050] S312. Construct an initial SVM classification model; train and test the initial SVM classification model using the fire accident occurrence label dataset and the fire accident occurrence influencing factor data matrix; after training and testing are completed, obtain the final SVM classification model.

[0051] S313. Select several locations within the fire station construction area to collect data on factors influencing the occurrence of fire accidents, and obtain a data matrix of current factors influencing the occurrence of fire accidents. g 3; as follows,

[0052] ;

[0053] in, g 3ij Indicates the first selected area in the fire station construction area i The location of the first j Data on factors influencing the occurrence of various types of fire accidents. This indicates the total number of locations selected within the fire station construction area;

[0054] Each row of data in the current fire accident influencing factor data matrix is ​​input into the final SVM classification model for classification, resulting in the current fire accident occurrence label dataset. , g 4i This indicates the first selected area from the fire station construction region. i Fire accident occurrence label data is obtained by classifying the data on factors influencing the occurrence of fire accidents at various locations;

[0055] S314. Select the fire accident occurrence tag data corresponding to the fire accidents that have occurred in the current fire accident occurrence tag dataset, and merge the selected locations in the corresponding fire station construction area to obtain the fire occurrence point set;

[0056] The types of factors influencing fire accidents include human factors, such as stoves not being turned off in time during cooking and prolonged overloading of electrical equipment; natural factors, such as high temperatures, drought, and windy weather conditions that increase the risk of fire; and facility and equipment factors, such as aging cables, circuit overload, and short circuits, all of which can cause fires. By collecting data on the influencing factors of fire accidents from multiple locations that have experienced fire accidents in the past and those that have not, data support is provided for the subsequent construction of a final SVM classification model that can map the data on the influencing factors of fire accidents to the corresponding fire accidents. By constructing the final SVM classification model, a model tool is provided for classifying and mapping the data on the influencing factors of fire accidents in multiple current locations, and multiple locations with the potential for fires are selected.

[0057] Preferably, step S32 includes the following steps:

[0058] S321. Traverse each road network graph in the road network graph matrix, and construct the adjacency matrix corresponding to the currently traversed road network graph, denoted as the current adjacency matrix. ;as follows,

[0059] ;

[0060] in, This indicates the current traversal of the road network graph. i The node and the first j The path length value between nodes, when When =0, it indicates that the current traversal of the road network graph is at the 0th position. i The node and the first j There are no road connections between the nodes;

[0061] S322, Constructing a second slime mold population , Indicates the second slime mold population. i slime mold, This indicates the size of the second slime mold population; the maximum number of iterations for the second slime mold population is set to... d 3. The current iteration number is d 4, denoted as the second maximum iteration number and the second current iteration number respectively; the search space dimension of the second slime mold population is... ;

[0062] S323. Set the starting point and ending point of the currently traversed road network graph, denoted as the current starting point and the current ending point, respectively; set the initial position of each slime mold in the second slime mold population according to the current starting point and the current ending point, and obtain the second initial position matrix. ;as follows,

[0063] ;

[0064] in, Indicates the second slime mold population of the first i The initial position of slime mold is in the first place. j Components in each search space dimension ;when When =0, it means that the currently generated path does not include the path in the currently traversed road network graph. j Nodes, when When =1, it means that the currently generated path includes the path in the currently traversed road network graph. j One node;

[0065] S324. According to the second initial position matrix and the current adjacency matrix Constructing the second slime mold population i Fitness function of slime molds f i ;as follows,

[0066] ;

[0067] In the formula, β A positive number indicates a correction parameter;

[0068] S325. Begin iteration. Before iteration, set the second current iteration number. d 4 is set to 1; during the first iteration, the second slime mold population is used. i Fitness function of slime molds f i , i =1,2,..., Calculate the fitness value of each initial position in the second initial position matrix to obtain a third fitness value set; take the largest fitness value in the third fitness value set and the corresponding initial position of the slime mold as the third global best fitness and the third global best position, respectively; update each initial position in the second initial position matrix according to the third global best fitness and the third global best position; after the update is completed, set the second current iteration number... d Add 4 and 1, then proceed to the next iteration;

[0069] In each iteration, the second slime mold population is used from the [missing information]. i Fitness function of slime molds f i , i =1,2,..., Calculate the fitness value of each slime mold's position obtained in the previous iteration to obtain a fourth fitness value set; take the largest fitness value in the fourth fitness value set and the corresponding initial position of the slime mold as the fourth global best fitness and the fourth global best position, respectively; update the position of each slime mold obtained in the previous iteration again based on the fourth global best fitness and the fourth global best position; after the update is completed, set the second current iteration number... d Add 4 and 1, then proceed to the next iteration;

[0070] S326, when If the condition is met, stop the iteration and obtain the second final global optimal position and the corresponding second final global optimal fitness; otherwise, continue the iteration until... Until then; the second final global best fitness is used as the shortest path length data of the currently traversed road network graph;

[0071] S327. When the traversal of each road network graph in the road network graph matrix is ​​completed, the shortest path length data matrix is ​​obtained;

[0072] In this scheme, the selection of each road network in the road network matrix is ​​iteratively optimized using the slime mold optimization algorithm, and the total path length connecting the selected points is used as the fitness function. Therefore, as the iteration proceeds, the total path length connecting the nodes selected from each road network is minimized, providing a basis for the final selection of fire station construction sites.

[0073] Preferably, step S4 includes the following steps:

[0074] S41. Calculate the shortest path length data matrix. The average value of each row of data is used to obtain the average shortest path length dataset. , This indicates that the initial selection of fire station construction sites is concentrated in the first... i The average of the shortest path length data between each fire station construction site and each fire occurrence point is calculated using the following formula:

[0075] ;

[0076] S42. Select the fire station construction points in the initial fire station construction point set corresponding to the largest shortest path length average data in the shortest path length average data set as the final fire station construction points, and obtain the final fire station construction point set.

[0077] A decision support system for the integrated layout of fire stations and land space includes a fire station layout factor type setting module, a historical layout cost factor data collection module, a historical layout construction cycle factor data evaluation module, a planning model construction module, a planning model solving module, a road network map construction module, a shortest path calculation module, an average shortest path length data calculation module, and a final screening module.

[0078] The present invention has the following beneficial effects:

[0079] 1. This invention comprehensively considers both construction cost and construction period to ensure that the fire stations meet various requirements after completion. By solving the integer programming model for fire station layout, it can determine where fire stations need to be built, minimizing the total construction period while keeping costs within budget. By constructing a road network diagram between each fire station construction point and multiple fire station construction points in the initial selection set, it is found that if the shortest path length between a fire station construction point and the fire accident point is too long, the rescue efficiency will be low. Therefore, this solution performs a final screening of fire station construction points based on the shortest path length data between each fire station construction point and multiple fire accident points, further ensuring the rationality and accuracy of the fire station layout.

[0080] 2. In this invention, by constructing a final SVM classification model, a model tool is provided for subsequent classification and mapping of data on factors influencing the occurrence of fire accidents in multiple locations, thereby filtering out multiple locations with the possibility of fire.

[0081] 3. In this invention, the selection of each road network graph in the road network graph matrix is ​​iteratively optimized using a slime mold optimization algorithm, and the total path length connecting the selected points is used as the fitness function. Therefore, as the iteration proceeds, the total path length connecting the nodes selected from each road network graph is minimized, providing a basis for the final selection of fire station construction sites.

[0082] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0083] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, the drawings can be obtained from these drawings without creative effort.

[0084] Figure 1 This is a flowchart illustrating a decision support method for the integrated layout of fire stations and land space according to the present invention. Detailed Implementation

[0085] The technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, and not all embodiments. Based on the embodiments of the invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the invention.

[0086] In the description of this invention, it should be understood that the terms "opening", "upper", "lower", "top", "middle", "inner", etc., which indicate orientation or positional relationship, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the components or elements referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the invention.

[0087] Example 1

[0088] This embodiment is a decision support method for the integrated layout of fire stations and land space, including the following steps:

[0089] S1. Set multiple types of fire station layout cost factors and fire station layout construction cycle factors to obtain a set of fire station layout cost factor types and a set of fire station layout construction cycle factors; collect cost factor data of multiple fire station construction sites based on the fire station layout cost factor type set to obtain a cost factor data matrix; evaluate the construction cycle factor data of multiple fire station construction sites based on the fire station layout construction cycle factor type set to obtain a construction cycle factor data matrix.

[0090] S1 includes the following steps:

[0091] S11. Define the fire station construction area, and set several fire station construction points within the fire station construction area to obtain a set of fire station construction points. , a i Indicates the set number i A fire station construction site, This indicates the total number of designated fire station construction sites;

[0092] By defining multiple types of fire station layout cost factors and fire station layout construction cycle factors, a set of fire station layout cost factor types is obtained. and fire station layout and construction cycle factors type set ; , , , These represent the types of land cost factors, construction cost factors, equipment cost factors, maintenance cost factors, and labor cost factors, respectively. Indicates the set number i Factors affecting the layout and construction cycle of fire stations b This indicates the total number of factors related to the construction cycle of the fire station layout.

[0093] S12. Collect cost factor data for each fire station construction site in the fire station construction site set according to the fire station layout cost factor type set, and obtain a cost factor data matrix. Then, based on the aforementioned fire station layout construction cycle factor type set, the construction cycle factor data of each fire station construction site in the fire station construction site set are evaluated to obtain the construction cycle factor data matrix. ; , They are as follows:

[0094] ; ;

[0095] in, , , , , These respectively represent the concentrated construction sites of the fire stations. i Data on land cost factors, construction cost factors, equipment cost factors, maintenance cost factors, and labor cost factors for each fire station construction site; This indicates that the fire station construction sites are concentrated at the first i The first fire station construction site j Data on various types of construction cycle factors;

[0096] S2. Construct an integer planning model for fire station layout based on the cost factor data matrix and the construction cycle factor data matrix; solve the integer planning model for fire station layout to obtain a preliminary set of fire station construction points;

[0097] S2 includes the following steps:

[0098] S21. Set the total budget for each fire station layout cost factor type in the fire station layout cost factor type set when constructing the fire station, and obtain the fire station layout total budget dataset. , , , , , These represent the total budget data for land cost factors, construction cost factors, equipment cost factors, maintenance cost factors, and labor cost factors, respectively.

[0099] S22. Construct an integer programming model for the fire station layout based on the total budget dataset, construction cycle factor data matrix, and cost factor data matrix. The objective function of the integer programming model for the fire station layout is as follows:

[0100] ;

[0101] In the formula, Indicates the total construction period of the fire station under construction; Indicates the set number i One undetermined coefficient ;

[0102] The constraint set for the integer programming model of the fire station layout is as follows.

[0103] ;

[0104] S23. Solve the integer programming model for the fire station layout to obtain the initial set of fire station construction points. , c 1iThis represents the result of solving the integer programming model for the fire station layout. i A fire station construction site, This represents the total number of fire station construction sites obtained by solving the integer programming model for the fire station layout;

[0105] S23 includes the following steps:

[0106] S231, Constructing the first slime mold population , Indicates the first slime mold population i slime mold, This represents the size of the first slime mold population; the maximum number of iterations for the first slime mold population is set to... d 1. The current iteration number is d 2, denoted as the first maximum iteration number and the first current iteration number, respectively; the search space dimension of the first slime mold population is... ;

[0107] S232. Based on the objective function of the integer programming model for the fire station layout, randomly generate the initial position of each slime mold in the first slime mold population, and obtain the first initial position matrix. ;

[0108] ;

[0109] in, Indicates the first slime mold population in the first group. i The initial position of slime mold is at the first j Components in each search space dimension; ;

[0110] S233. The objective function of the integer programming model for the fire station layout is used as the fitness function of the first slime mold population.

[0111] S234. Start the iteration. Before the iteration, set the first current iteration number. d 2 is set to 1; during the first iteration, the fitness value of each initial position in the first initial position matrix is ​​calculated using the fitness function of the first slime mold population, resulting in a first fitness value set; the maximum fitness value in the first fitness value set and the corresponding initial position of the slime mold are taken as the first global optimal fitness and the first global optimal position, respectively; each initial position in the first initial position matrix is ​​updated based on the first global optimal fitness and the first global optimal position, in conjunction with the constraint conditions of the fire station layout integer programming model; after the update is completed, the first current iteration number is set to 1. d 2 plus 1 and proceed to the next iteration;

[0112] In each iteration, the fitness function of the first slime mold population is used to calculate the fitness value of each slime mold's position obtained in the previous iteration, resulting in a second fitness value set. The maximum fitness value in the second fitness value set and the corresponding initial position of the slime mold are taken as the second global optimal fitness and the second global optimal position, respectively. Based on the second global optimal fitness and the second global optimal position, and in conjunction with the constraint set of the fire station layout integer programming model, the position of each slime mold obtained in the previous iteration is updated again. After the update is completed, the first current iteration number is... d 2 plus 1 and proceed to the next iteration;

[0113] S235, when If the first optimal position is found, stop iterating and obtain the first final global optimal position; otherwise, continue iterating until... Until then; remove the fire station construction points in the fire station construction point set corresponding to the position components that are 0 in the first final global best position, and obtain the preliminary set of fire station construction points;

[0114] S3. Construct a road network map between each fire station construction site and multiple fire accident occurrence points in the initial selected fire station construction site set, and obtain a road network map matrix; calculate the shortest path length of each road network map in the road network map matrix, and obtain a shortest path length data matrix;

[0115] S3 includes the following steps:

[0116] S31. Statistically analyze multiple fire accident locations within the fire station construction area to obtain a set of fire accident locations. , This indicates the statistical result of the first... i The location of the fire accident This represents the total number of fire incident locations obtained from statistics; a road network map is constructed between each fire incident location in the fire incident location set and each fire station construction location in the initial selected fire station construction location set, resulting in a road network map matrix. e ;as follows,

[0117] ;

[0118] in, e ij This indicates that the initial selection of fire station construction sites is concentrated in the first... i The fire station construction site is located at the fire location. j Road network diagram between the fire locations;

[0119] S31 involves statistically analyzing multiple fire accident locations within the fire station construction area to obtain a set of fire accident locations, which includes the following steps:

[0120] S311. Define the set of influencing factors for fire accidents. , Indicates the set number i Types of factors influencing the occurrence of fire accidents This indicates the total number of types of factors that influence the occurrence of fire accidents.

[0121] Based on the aforementioned set of fire accident influencing factors, data on fire accident influencing factors for multiple locations where fires have occurred in the past and locations where no fires have occurred were collected to obtain a historical fire accident influencing factor data matrix. g 1 and historical fire accident label dataset , g 2i Indicates the number of collections i Fire incident label data corresponding to each location Indicates the total number of locations where data was collected; g 1. As follows,

[0122] ;

[0123] in, g 1ij Indicates the number of collections i The location of the first j Data on factors influencing the occurrence of various types of fire accidents;

[0124] S312. Construct an initial SVM classification model; train and test the initial SVM classification model using the fire accident occurrence label dataset and the fire accident occurrence influencing factor data matrix; after training and testing are completed, obtain the final SVM classification model.

[0125] S313. Select several locations within the fire station construction area to collect data on factors influencing the occurrence of fire accidents, and obtain a data matrix of current factors influencing the occurrence of fire accidents. g 3; as follows,

[0126] ;

[0127] in, g 3ij Indicates the first selected area in the fire station construction area i The location of the first j Data on factors influencing the occurrence of various types of fire accidents. This indicates the total number of locations selected within the fire station construction area;

[0128] Each row of data in the current fire accident influencing factor data matrix is ​​input into the final SVM classification model for classification, resulting in the current fire accident occurrence label dataset. , g 4i This indicates the first selected area from the fire station construction region. i Fire accident occurrence label data is obtained by classifying the data on factors influencing the occurrence of fire accidents at various locations;

[0129] S314. Select the fire accident occurrence tag data corresponding to the fire accidents that have occurred in the current fire accident occurrence tag dataset, and merge the selected locations in the corresponding fire station construction area to obtain the fire occurrence point set;

[0130] S32. Calculate the shortest path length in each network graph of the road network graph matrix to obtain the shortest path length data matrix. ;as follows,

[0131] ;

[0132] in, This indicates that the initial selection of fire station construction sites is concentrated in the first... i The fire station construction site is located at the fire location. j Shortest path length data in the road network diagram between fire locations;

[0133] S32 includes the following steps:

[0134] S321. Traverse each road network graph in the road network graph matrix, and construct the adjacency matrix corresponding to the currently traversed road network graph, denoted as the current adjacency matrix. ;as follows,

[0135] ;

[0136] in, This indicates the current traversal of the road network graph. i The node and the first j The path length value between nodes, when When =0, it indicates that the current traversal of the road network graph is at the 0th position. i The node and the first j There are no road connections between the nodes;

[0137] S322, Constructing a second slime mold population , Indicates the second slime mold population. i slime mold, This indicates the size of the second slime mold population; the maximum number of iterations for the second slime mold population is set to... d 3. The current iteration number is d 4, denoted as the second maximum iteration number and the second current iteration number respectively; the search space dimension of the second slime mold population is... ;

[0138] S323. Set the starting point and ending point of the currently traversed road network graph, denoted as the current starting point and the current ending point, respectively; set the initial position of each slime mold in the second slime mold population according to the current starting point and the current ending point, and obtain the second initial position matrix. ;as follows,

[0139] ;

[0140] in, Indicates the second slime mold population of the first i The initial position of slime mold is in the first place. j Components in each search space dimension ;when When =0, it means that the currently generated path does not include the path in the currently traversed road network graph. j Nodes, when When =1, it means that the currently generated path includes the path in the currently traversed road network graph. j One node;

[0141] S324. According to the second initial position matrix and the current adjacency matrix Constructing the second slime mold population i Fitness function of slime molds f i ;as follows,

[0142] ;

[0143] In the formula, β A positive number indicates a correction parameter;

[0144] S325. Begin iteration. Before iteration, set the second current iteration number. d 4 is set to 1; during the first iteration, the second slime mold population is used. i Fitness function of slime molds f i , i =1,2,..., Calculate the fitness value of each initial position in the second initial position matrix to obtain a third fitness value set; take the largest fitness value in the third fitness value set and the corresponding initial position of the slime mold as the third global best fitness and the third global best position, respectively; update each initial position in the second initial position matrix according to the third global best fitness and the third global best position; after the update is completed, set the second current iteration number... d Add 4 and 1, then proceed to the next iteration;

[0145] In each iteration, the second slime mold population is used from the [missing information]. i Fitness function of myxobacteria f i , i =1,2,..., Calculate the fitness value of each slime mold's position obtained in the previous iteration to obtain a fourth fitness value set; take the largest fitness value in the fourth fitness value set and the corresponding initial position of the slime mold as the fourth global best fitness and the fourth global best position, respectively; update the position of each slime mold obtained in the previous iteration again based on the fourth global best fitness and the fourth global best position; after the update is completed, set the second current iteration number... d Add 4 and 1, then proceed to the next iteration;

[0146] S326, when If the condition is met, stop the iteration and obtain the second final global optimal position and the corresponding second final global optimal fitness; otherwise, continue the iteration until... Until then; the second final global best fitness is used as the shortest path length data of the currently traversed road network graph;

[0147] S327. When the traversal of each road network graph in the road network graph matrix is ​​completed, the shortest path length data matrix is ​​obtained;

[0148] S4. Calculate the average shortest path length data for each fire station construction point in the shortest path length data matrix to obtain the average shortest path length dataset; perform final screening on the initial set of fire station construction points based on the average shortest path length dataset to obtain the final set of fire station construction points;

[0149] S4 includes the following steps:

[0150] S41. Calculate the shortest path length data matrix. The average value of each row of data is used to obtain the average shortest path length dataset. , This indicates that the initial selection of fire station construction sites is concentrated in the first... iThe average of the shortest path length data between each fire station construction site and each fire occurrence point is calculated using the following formula:

[0151] ;

[0152] S42. Select the fire station construction points in the initial fire station construction point set corresponding to the largest shortest path length average data in the shortest path length average data set as the final fire station construction points, and obtain the final fire station construction point set.

[0153] Example 2

[0154] This embodiment discloses a decision support system for the integrated layout of fire stations and land space. The system can implement the methods of the above embodiments, including a fire station layout factor type setting module, a historical layout cost factor data collection module, a historical layout construction cycle factor data evaluation module, a planning model construction module, a planning model solving module, a road network map construction module, a shortest path calculation module, an average shortest path length data calculation module, and a final screening module.

[0155] The fire station layout factor type setting module is used to set multiple fire station layout cost factor types and fire station layout construction cycle factor types, so as to obtain a fire station layout cost factor type set and a fire station layout construction cycle factor type set.

[0156] The historical layout cost factor data acquisition module is used to collect cost factor data of multiple fire station construction sites according to the fire station layout cost factor type set, and obtain a cost factor data matrix.

[0157] The historical layout construction cycle factor data evaluation module is used to evaluate the construction cycle factor data of multiple fire station construction sites according to the fire station layout construction cycle factor type set, and obtain a construction cycle factor data matrix.

[0158] The planning model construction module is used to construct an integer planning model for the layout of fire stations based on the cost factor data matrix and the construction cycle factor data matrix.

[0159] The planning model solving module is used to solve the integer planning model of the fire station layout to obtain the initial set of fire station construction points;

[0160] The road network diagram construction module is used to construct a road network diagram between each fire station construction point and multiple fire station construction points in the initial selection of fire station construction points, thereby obtaining a road network diagram matrix;

[0161] The shortest path calculation module is used to calculate the shortest path length of each road network graph in the road network graph matrix, and obtain the shortest path length data matrix;

[0162] The average short path length data calculation module is used to calculate the average shortest path length data of each fire station construction point in the shortest path length data matrix, and obtain the average shortest path length dataset.

[0163] The final filtering module is used to perform a final filtering on the initial set of fire station construction points based on the average dataset of the shortest path length, so as to obtain the final set of fire station construction points.

[0164] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0165] The preferred embodiments of the invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A decision support method for the integrated layout of fire stations and land use, characterized in that, Includes the following steps: S1. Set multiple types of fire station layout cost factors and fire station layout construction cycle factors to obtain a set of fire station layout cost factor types and a set of fire station layout construction cycle factors; collect cost factor data of multiple fire station construction sites based on the fire station layout cost factor type set to obtain a cost factor data matrix; evaluate the construction cycle factor data of multiple fire station construction sites based on the fire station layout construction cycle factor type set to obtain a construction cycle factor data matrix. S2. Construct an integer planning model for fire station layout based on the cost factor data matrix and the construction cycle factor data matrix; solve the integer planning model for fire station layout to obtain a preliminary set of fire station construction points; Specifically, it includes: S21. Set the total budget for each type of fire station layout cost factor in the fire station layout cost factor type set when constructing the fire station, and obtain the fire station layout total budget dataset. S22. Construct an integer programming model for the fire station layout based on the total budget dataset for the fire station layout, the construction cycle factor data matrix, and the cost factor data matrix. S23. Solve the integer programming model for the layout of the fire station to obtain the initial set of fire station construction points; S3. Construct a road network map between each fire station construction site and multiple fire accident occurrence points in the initial selected fire station construction site set, and obtain a road network map matrix; calculate the shortest path length of each road network map in the road network map matrix, and obtain a shortest path length data matrix; Specifically, it includes: S31. Statistically analyze multiple fire accident occurrence points in the fire station construction area to obtain a fire occurrence point set; construct a road network map between each fire occurrence point in the fire occurrence point set and each fire station construction point in the initial selected fire station construction point set to obtain a road network map matrix; Specifically, this includes: setting a set of fire accident influencing factor types; collecting fire accident influencing factor data corresponding to multiple locations where fire accidents have occurred and locations where no fire accidents have occurred, based on the fire accident influencing factor type set, to obtain a historical fire accident influencing factor data matrix and a historical fire accident label dataset; constructing an initial SVM classification model; training and testing the initial SVM classification model using the fire accident label dataset and the fire accident influencing factor data matrix; obtaining a final SVM classification model after training and testing; selecting several locations in the fire station construction area to collect fire accident influencing factor data, to obtain a current fire accident influencing factor data matrix; inputting each row of data in the current fire accident influencing factor data matrix into the final SVM classification model for classification, to obtain a current fire accident label dataset; selecting fire accident label data corresponding to fire accidents that have occurred in the current fire accident label dataset, and merging the locations selected in the corresponding fire station construction area to obtain a fire occurrence point set; S32. Construct a second slime mold population to iteratively calculate the shortest path length in each network graph of the road network graph matrix. When the maximum number of iterations is reached, the shortest path length data matrix is ​​obtained. S4. Calculate the average shortest path length data for each fire station construction point in the shortest path length data matrix to obtain the average shortest path length dataset; perform final screening on the initial set of fire station construction points based on the average shortest path length dataset to obtain the final set of fire station construction points.

2. The decision support method for integrated layout of fire stations and land space according to claim 1, characterized in that, S1 includes the following steps: S11. Define the fire station construction area, and set several fire station construction points in the fire station construction area to obtain a set of fire station construction points; define multiple fire station layout cost factor types and fire station layout construction cycle factor types to obtain a set of fire station layout cost factor types and a set of fire station layout construction cycle factor types. S12. Collect cost factor data for each fire station construction point in the fire station construction point set according to the fire station layout cost factor type set, and obtain a cost factor data matrix; then evaluate the construction cycle factor data for each fire station construction point in the fire station construction point set according to the fire station layout construction cycle factor type set, and obtain a construction cycle factor data matrix.

3. The decision support method for integrated layout of fire stations and land space according to claim 1, characterized in that: In S23, the slime mold optimization algorithm is used to solve the integer programming model of the fire station layout.

4. The decision support method for integrated layout of fire stations and land space according to claim 1, characterized in that, S32 includes the following steps: S321. Traverse each road network graph in the road network graph matrix and construct the adjacency matrix corresponding to the currently traversed road network graph, denoted as the current adjacency matrix; S322. Construct a second slime mold population; set the maximum number of iterations for the second slime mold population as follows. d 3. The current iteration number is d 4, denoted as the second maximum iteration count and the second current iteration count, respectively; S323. Set the starting point and ending point of the road network graph being traversed, and denote them as the current starting point and the current ending point, respectively; set the initial position of each slime mold in the second slime mold population according to the current starting point and the current ending point, and obtain the second initial position matrix; S324. Construct a fitness function for each slime mold in the second slime mold population based on the second initial position matrix and the current adjacency matrix. S325. Start the iteration; in each iteration, use the fitness function of each slime mold in the second slime mold population to calculate the fitness value of the position of each slime mold obtained in the previous iteration, and update the position of each slime mold obtained in the previous iteration again. S326, when If the condition is met, stop the iteration and obtain the second final global optimal position and the corresponding second final global optimal fitness; otherwise, continue the iteration until... Until then; the second final global best fitness is used as the shortest path length data of the currently traversed road network graph; S327. When the traversal of each road network graph in the road network graph matrix is ​​completed, the shortest path length data matrix is ​​obtained.

5. The decision support method for integrated layout of fire stations and land space according to claim 1, characterized in that, S4 includes the following steps: S41. Calculate the average value of each row of data in the shortest path length data matrix to obtain the average shortest path length dataset. S42. Select the fire station construction points in the initial fire station construction point set corresponding to the largest shortest path length average data in the shortest path length average data set as the final fire station construction points, and obtain the final fire station construction point set.

6. A system for implementing the decision support method for integrated layout of fire stations and national land space as described in any one of claims 1-5.

Images