Method and device for municipal water intake site selection based on multi-source data fusion and optimization algorithm and readable storage medium thereof

Abstract

The application provides a municipal water taking machine site selection method and device based on multi-source data fusion and an optimization algorithm and a readable storage medium thereof. In view of the problems of fire hazards caused by unordered water taking of existing fire hydrants and high cost and data lag of a traditional site selection method, the method realizes the following steps: collecting fire hydrant water data in real time by using an intelligent cover, fusing multi-source data such as population density, POI, land use type and the positions of existing facilities, and generating a water demand intensity grid; projecting the grid demand based on actual road network distance, inserting nodes and assigning weights; constructing a double-objective optimization model of'maximizing high demand coverage-minimizing water taking distance', and solving the optimal water taking machine position in combination with a budget constraint. The method realizes the improvement of equipment utilization, the increase of coverage demand proportion, the shortening of average water taking distance and the reduction of cost through multi-source dynamic data fusion and road network projection optimization, and effectively balances municipal water demand and equipment deployment efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water resource management and intelligent water taking equipment layout in municipal engineering, and particularly relates to a municipal water taking machine site selection method and device based on multi-source data fusion and optimization algorithm and a readable storage medium thereof. BACKGROUND

[0002] In the municipal water scene of construction sites, environmental sanitation sprinkling, urban greening, etc., the traditional method often takes water through fire hydrants, which leads to insufficient water pressure of fire hydrants in case of fire, threatening public safety. Although the existing technology reduces the abuse of fire hydrants through intelligent monitoring and strengthened law enforcement, the water demand still exists. However, blind setting of water taking points will lead to high basic investment and maintenance cost, and the traditional site selection method based on the EPANET model has problems such as poor data timeliness, low adaptability to old pipe network, and inability to fuse multi-source data, which is difficult to meet the water demand while optimizing the efficiency of equipment deployment.

[0003] Therefore, a municipal water taking machine site selection method and device based on multi-source data fusion and optimization algorithm and a readable storage medium thereof are urgently needed to solve the problems existing in the prior art. SUMMARY

[0004] The embodiments of the present application provide a municipal water taking machine site selection method and device based on multi-source data fusion and optimization algorithm and a readable storage medium thereof, which aims at the problems that the current technology cannot fuse multi-dimensional water demand data (such as fire hydrant water frequency, population density, POI distribution, etc.) in real time, and does not consider the actual road network distance when selecting sites, leading to low equipment utilization rate, insufficient coverage demand, high cost and other defects of water taking machine deployment.

[0005] The core technology of the present application is to collect fire hydrant water data in real time through an intelligent cover, fuse multi-source data such as population density, POI, land use type, etc. to generate water demand intensity grid, project the demand to the road network, and solve the optimal water taking machine position based on the "maximum coverage demand-minimum water taking distance" double target optimization model.

[0006] In a first aspect, the present application provides a municipal water taking machine site selection method based on multi-source data fusion and optimization algorithm, which comprises the following steps:

[0007] Collecting fire hydrant water data and fusing multi-source auxiliary data to generate grid data reflecting the water demand intensity of the region;

[0008] Projecting the grid data to the road network to obtain the road network nodes with water demand weight;

[0009] Solve the water taking machine arrangement position in the road network based on the preset budget constraint, which maximizes the coverage rate of high demand area and minimizes the water taking distance cost of demand point.

[0010] Further, the step of collecting fire hydrant water data includes:

[0011] The intelligent fire hydrant or the intelligent cap installed on the fire hydrant is used to monitor the water usage frequency, duration and abnormal events in real time, and the monitoring data is reported through wireless communication.

[0012] Further, the multi-source auxiliary data includes population density data, POI data, land use type data and existing water taking facility position data, wherein:

[0013] The POI data is assigned different weights according to types, and the influence value is calculated by combining the distance from the demand point to the POI;

[0014] The land use type data is assigned different basic demand values according to residential, commercial, industrial and green land types;

[0015] The existing water taking facility position data is used to generate a demand suppression factor for the surrounding area.

[0016] Further, the step of projecting the grid data to the road network includes:

[0017] The grid center point is taken as the demand point, and the shortest actual path distance to the road network is calculated. If the projection point is located on the road segment, a new node is inserted. The water demand intensity is weighted and distributed according to the distance from the demand point to the road network node, wherein the weighting parameter is determined according to the water supply pipe operation radius and historical water usage habits.

[0018] Further, the step of solving the water taking machine arrangement position is realized by constructing a double objective optimization model, and the double objectives include:

[0019] Maximize the total weight of water demand of covered demand points;

[0020] Minimize the total weighted path distance of all demand points to the nearest water taking machine;

[0021] The optimization model is solved by integer programming algorithm or heuristic algorithm, and the number of road network nodes is reduced by setting the projection threshold to improve the solving efficiency.

[0022] Further, the projection threshold is determined according to the optimal moving radius of engineering demonstration, and when the distance from the demand point to the road network exceeds the threshold, the demand point is ignored.

[0023] Further, the abnormal events monitored by the intelligent cap include water stealing behavior and fire hydrant tilt state, and the monitoring data includes the timestamp and duration of water usage events.

[0024] In a second aspect, the present application provides a municipal water intake site selection device based on multi-source data fusion and optimization algorithm, comprising:

[0025] A collection module is configured to collect fire hydrant water data and fuse multi-source auxiliary data to generate grid data reflecting regional water demand intensity;

[0026] A projection module is configured to project the grid data to a road network to obtain road network nodes with water demand weight;

[0027] A solving module is configured to solve the water intake arrangement position in the road network based on a preset budget constraint, so as to maximize the coverage rate of high demand areas and minimize the water intake distance cost of demand points;

[0028] An output module is configured to output the water intake arrangement position.

[0029] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned municipal water intake site selection method based on multi-source data fusion and optimization algorithm.

[0030] In a fourth aspect, the present application provides a readable storage medium, wherein the readable storage medium stores a computer program, and the computer program comprises program code for controlling a process to execute the process, and the process comprises the above-mentioned municipal water intake site selection method based on multi-source data fusion and optimization algorithm.

[0031] The main contributions and innovations of the present application are as follows:

[0032] 1. The utilization rate of the device is significantly improved

[0033] The utilization rate of the prior art device is only 52%, and the present application improves the utilization rate to 83% by real-time tracking of water demand hotspots using intelligent covers and combining POI data to strengthen the layout of key places, with an improvement of 60%.

[0034] 2. The coverage demand ratio is greatly improved

[0035] The coverage demand ratio of the traditional scheme is 76%, and the present application improves the coverage demand ratio to 95% by correcting the blind area using population density data and deconstructing regional differences using land use weight, with an improvement of 25%, effectively solving the problem of insufficient coverage in high demand areas.

[0036] 3. The average water intake distance is significantly shortened

[0037] The average water intake distance of the prior art is 420 meters, and the average water intake distance is shortened to 320 meters based on the road network projection accuracy optimization and demand weight site selection of the application, with a decrease of 24%, improving the water intake efficiency.

[0038] 4. The gap rate in high demand areas is greatly reduced

[0039] The gap rate in high demand areas is 18% in the traditional scheme, and the gap rate is reduced to 2% by balancing coverage and efficiency through the double-target optimization model of the application, with a decrease of 89%, accurately meeting the water demand of key areas.

[0040] 5. The cost benefit optimization is significant

[0041] The cost recovery period of the prior art is more than 5 years, and the cost recovery period is shortened to less than 3 years by efficient use of equipment and suppression of illegal water intake, with a cost reduction of 40%, and water intake benefit is improved by 48%.

[0042] 6. The technical mechanism advantage is prominent

[0043] Multi-source data fusion: real-time water consumption data combined with static geographic data, demand recognition accuracy up to 92%, breaking through the limitation of traditional models relying only on fire water modeling;

[0044] Road network projection optimization: project demand points based on actual path distance, solve the deviation problem of Euler distance and actual path, improve the reality of site selection;

[0045] Double-target coordination: by quantifying the contradiction between "covering demand" and "water intake efficiency", the precise balance of municipal resource deployment is realized.

[0046] The details of one or more embodiments of the application are presented in the following drawings and description, so that other features, objects and advantages of the application are more concise and easy to understand. BRIEF DESCRIPTION OF DRAWINGS

[0047] The drawings described herein are used to provide further understanding of the application, and form a part of the application. The illustrative embodiments of the application and their descriptions are used to explain the application, and do not constitute an improper limitation on the application. In the drawings:

[0048] Figure 1 is a flowchart of a municipal water intake machine site selection method based on multi-source data fusion and optimization algorithm according to an embodiment of the application;

[0049] Figure 2 is a technical logic diagram of algorithm selection according to an embodiment of the application;

[0050] Figure 3 is a hardware structure schematic diagram of an electronic device according to an embodiment of the application. DETAILED DESCRIPTION

[0051] The exemplary embodiments will be described in detail hereinbelow with reference to the drawings. In the following description, the same drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of the description. Instead, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of the description as detailed in the appended claims.

[0052] It should be noted that the steps of the methods in other embodiments are not necessarily performed in the order shown and described in the present description. In some other embodiments, the steps of the methods can be more or less than described in the present description. Furthermore, a single step described in the present description can be broken down into multiple steps in other embodiments; and multiple steps described in the present description can be combined into a single step in other embodiments.

[0053] The prior art cannot fuse multi-dimensional water demand data (such as fire hydrant water frequency, population density, POI distribution, etc.) in real time, and does not consider the actual road network distance when selecting sites, resulting in low equipment utilization, insufficient coverage demand, high cost and other defects in water taking machine deployment.

[0054] Based on this, the present application generates a water demand intensity grid based on multi-source data, projects the demand to the road network, and solves the optimal water taking machine location based on the "maximum coverage demand-minimum water taking distance" dual-objective optimization model to solve the problems existing in the prior art.

[0055] Embodiment one

[0056] The present application aims to propose a municipal water taking machine site selection method based on multi-source data fusion and optimization algorithm, specifically, referring to Figure 1 , the method comprises the following steps:

[0057] Step one, collect fire hydrant water data and fuse multi-source auxiliary data to generate grid data reflecting regional water demand intensity;

[0058] In this embodiment, if the local fire hydrant has been intelligently modified, the water use data and frequency of the local fire hydrant can be directly obtained. If not, a low-cost intelligent (firefighting) cover can be used for modification to obtain the frequency and intensity of water use of fire hydrants in the area. The intelligent cover has the advantages of low cost and fast modification for fire hydrant modification. Its structure and principle are specific to the existing technology, and its structure and principle will not be repeated here. The intelligent cover can detect the frequency and duration of water use of the fire hydrant in real time, record the timestamp and duration of each time the cover is opened to release water (whether it is for firefighting, municipal operations, green irrigation, or citizens' illegal personal water use), and then count the water use frequency of the entire area. Table 1 below shows the parameters of the intelligent cover:

[0059] Table 1

[0060]

[0061] The comparison of water demand obtained by traditional methods is shown in Table 2:

[0062] Table 2

[0063]

[0064] As can be seen, the smart capping solution offers lower costs, real-time data acquisition, and more comprehensive functionality. Therefore, this invention employs the smart capping solution. The five-dimensional fusion of monitored fire hydrant water usage frequency, combined with population density, key locations (parks, train stations), land use (residential, commercial, industrial, etc., with weighting coefficients adjusted based on actual conditions), and existing water dispenser suppression, generates water demand intensity.

[0065] In this embodiment, the core variables of this step are defined as follows:

[0066] The specified area is divided into M*N grids:

[0067] Grid system: i, j grid row and column index (i=1...M,j=1...N);

[0068] G=[ ] M*N Water demand intensity matrix, Represents the grid cell at row i and column j in two-dimensional space.

[0069] 1. Calculation of basic water intensity for fire hydrant water use events:

[0070] 1) There are smart fire hydrants in the grid:

[0071] Set up grid N inside ij Fire hydrant water use events, each event weight is w eThe direct contribution is:

[0072]

[0073] wherein, represents the grid 's base water demand intensity, i.e. the total weight of all hydrant water events within the grid; e represents a single hydrant water event (e.g. a single water taking operation) within the grid;

[0074] For example: if there are 2 hydrant water events in a grid, one lasting 20 minutes (weight 0.5) and one lasting 40 minutes (weight 1.0), then .

[0075] 2) For grids without hydrants, the base water demand intensity is obtained by spatial interpolation:

[0076] Let N(i,j) represent the set of hydrant water events within the grid 's neighborhood (the neighborhood range can be set according to actual needs, such as a circular area with the grid center as the center), then:

[0077]

[0078] wherein d k,ij is the distance from event point k to the network center; k is the kth water event in the neighborhood; is the weight of event k (estimated based on water duration or flow, reflecting water intensity).

[0079] For example, there are 3 water events in the grid neighborhood:

[0080] Event 1: , weight term ;

[0081] Event 2: , weight term ;

[0082] Event 3: , weight term .

[0083] Calculation process:

[0084] Numerator: 0.02 + 0.00375 + 0.04 = 0.06375;

[0085] Denominator: ;

[0086] Result: .

[0087] H ij Normalized to get:

[0088]

[0089] in, is the normalized basic water demand intensity; is the minimum value of the basic water demand in all grids; It is the maximum value of the basic water demand in all grids.

[0090] Conclusion: The water demand intensity of this grid is estimated to be 1.214, which is mainly dominated by event 3 (weight 1.0) with the closest distance (5m), which is consistent with the actual water use pattern of "close distance and high impact".

[0091] 2. Auxiliary data normalization machine fusion:

[0092] Population density data: set grid The population density (people / square meter) is P ij :

[0093]

[0094] in, : The minimum population density in the entire area; : The maximum population density within the entire region. This formula uses Min-Max Normalization (Min-Max Normalization) to linearly transform the raw population density data to the interval [0, 1]. This eliminates dimensional differences in data from different dimensions and enables the fusion and calculation of multi-source data (such as population density, POI impact, and land use type) at the same scale.

[0095] 3. POI data grid The impact of internal POI data is :

[0096]

[0097]

[0098] Where m represents the POI type (such as park, station, etc.); ω m is the weight of this type of POI; d ij,n is the distance from the grid center to the nth POI; σ m It is the influence range parameter of this type of POI; It is a standardized population density index with a value range of [0,1].

[0099] 4. Land use type:

[0100] Set up grid The land use type is L ij , assign different basic requirement values ​​ℓ according to the type ij (Residential area = 0.8, Commercial area = 1.0, Industrial area = 0.3, Green area = 0.6):

[0101]

[0102] in, It is the standardized land use demand index, and its value range is [0, 1].

[0103] 5. Suppression of existing water intake machines or water intake facilities: Set grid G ij The nearest existing water intake facility is s ij , then the inhibition factor is:

[0104]

[0105] where β is the inhibitory strength ( ), which controls the maximum suppression amplitude; θ is the suppression range parameter, which determines the speed at which the suppression effect decays with distance. (grid adjacent to existing facilities), the inhibition factor , that is, the demand intensity is suppressed to the greatest extent (the suppression amount is );along with Increase, the inhibitory effect weakens exponentially. When the inhibitory factor , the distance exceeds The inhibitory effect was significantly reduced.

[0106] So, through Reduce the demand weight of grids around existing facilities to prevent over-intensive deployment of water intake machines and reduce infrastructure investment costs; ), , the demand intensity is not suppressed, ensuring that new water dispensers give priority to covering areas with blank demand.

[0107] 6. Final water demand intensity of each grid:

[0108]

[0109] , are the center coordinates of the grid cell, is the water demand intensity of the grid unit; is the weight coefficient ( ), and adjust the impact ratio of each factor according to the municipal scenario.

[0110] Step two, project the grid data to the road network, get the road network nodes with water demand weight;

[0111] In this embodiment, since the water demand intensity is a continuous or gridded distribution in two-dimensional space (i.e. each geographic grid cell has a demand intensity value). And the road network is a linear network structure composed of nodes (intersections, road points) and edges (road segments). The planar water demand needs to be allocated to the nearest network node or road segment in order to conduct road network-based analysis (such as shortest path calculation to water intake machines, water intake service area coverage analysis, etc.). There is a huge difference between the Euclidean distance and the actual path. All cannot be based on the Euclidean distance but on the network distance.

[0112] Therefore, this step takes the center point (or barycenter) of each grid cell as a demand point, and the demand weight of the grid is the water demand intensity value of the grid. In this way, a set of discrete demand point sets are obtained, each point with position coordinates and demand weight.

[0113] The specific steps of projecting water demand to the road network are as follows:

[0114] 1. For each demand point, find the nearest point on the road network (may be a node, or a point on an edge). If projected to an edge, a new node needs to be inserted on the edge to allocate demand to the point:

[0115] Road network: , where V is the set of nodes, and E is the set of edges.

[0116] For the center point of each grid cell :

[0117] Calculate the distance and position of the center point to the nearest point p ij on the road network graph R ij , which may belong to an edge e ∈ E or may be a node.

[0118] If P ij is on the edge e = (v a , v b ), then:

[0119] Insert a new node v new on the edge e (position p ij ), and split the edge e into two edges: (v a , v new ) (v new , v b ). Assign demand weight g ij to v new ;

[0120] If p ij is the network node v∈V, then directly add the demand weight g ij to the node;

[0121] And the weighted formula is as follows:

[0122]

[0123] Wherein:

[0124] is the grid-node association indicator factor, which is 1 when the projection point of the grid is associated with the node , otherwise 0; is the distance from the grid center to the node;

[0125] is the distance attenuation coefficient σ, that is is the distance attenuation function, which represents the attenuation relationship of the influence of grid demand on the node with distance;

[0126] is an empirical parameter, which is adjusted according to the actual situation. In this scheme is 50 by default. Through actual experience and simulation verification, the following Table 3 and Table 4 are obtained:

[0127] Table 3 Engineering empirical data

[0128]

[0129] Table 4 Simulation verification data

[0130]

[0131] It can be seen that the traditional method uses a fixed attenuation coefficient (such as 1 / d), which cannot match the characteristics of municipal operations; while the present application achieves the optimal balance between suppressing violations (>88%) and improving equipment utilization (>79%) through σ=50m, dynamically adapts to the length of the water delivery pipe and the operation habit, and makes the violation water suppression rate reach 88%, which verifies the engineering adaptability of the distance attenuation model.

[0132] 2. In order to avoid too complex network, threshold filtering mechanism is used, only when the distance from demand point to road network is less than the threshold, projection is carried out, otherwise it is considered that the demand point cannot be served by road network (ignored or specially processed in subsequent analysis).

[0133] 3. Finally, a new network graph R'=(V',E') is obtained, where V' contains the original nodes and newly added nodes, and each node v k ∈V' has a water demand weight wk represents the water demand intensity at the node.

[0134] Step three, based on the preset budget constraint, solve the water taking machine arrangement position in the road network which maximizes the high demand area coverage rate and minimizes the water taking distance cost of demand points.

[0135] In this embodiment, under the given budget constraint (the maximum number of installable water taking machines P), combined with the road network graph R'=(V',E') of the above derived auxiliary water demand weight, the scheme selects the water taking machine deployment point in combination with two principles:

[0136] Maximize the high demand area coverage rate and minimize the water taking distance cost of all demand points. However, the two requirements are contradictory, so the most core goal of the scheme is to solve the double contradiction in the municipal water taking machine site selection:

[0137] Coverage contradiction: high demand areas need to be covered first (maximize water demand, target 100% coverage), for example, if all water taking machines are deployed in high demand areas (such as commercial areas and large parks), although 100% coverage of high weight demand points can be achieved, users in remote residential areas need to walk more than 500 meters to take water, and the average distance is significantly increased, which is inefficient;

[0138] Efficiency contradiction: the water taking distance of all users should be as short as possible, for example, if water taking machines are evenly distributed to minimize the distance of each point, it may lead to resource dispersion, and some low demand areas are over-covered, while high demand industrial areas are not prioritized due to long distance, resulting in "demand gap";

[0139] Traditional single-target site selection (only considering coverage or only considering distance) is expected to lead to:

[0140] When coverage is prioritized, the average water taking distance increases by 200-300 meters;

[0141] When distance is prioritized, the high demand area gap rate rises to 15%-20%.

[0142] And in order to solve this double contradiction, the following methods are adopted in the present application:

[0143] = total coverage benefit - total distance cost

[0144] Wherein, the coverage benefit is the total weight of the covered demand points, that is, is the node demand weight, indicates that it is covered); the distance cost is the total weighted distance of all demand points to the nearest water taking machine, that is, is the path distance, indicates that it is served by water taking point j); the balance parameter​​ is the value range [0,1], which determines the priority of coverage and distance The larger, the more biased to coverage; The smaller, the more biased to distance.

[0145] Objective function:

[0146]

[0147] Where, C max (theoretically maximum coverable demand) is the sum of the demand weights of all demand points, ;

[0148] D min_val (minimum theoretical total distance) is the weighted total distance when all demand points are assigned to the nearest candidate point, which is 0 if all nodes are candidate points, ;

[0149] The set of candidate locations of water taking machines C∈V', D max_val (the maximum theoretical total distance) is the weighted total distance when all demand points are assigned to the farthest candidate point, ;

[0150] D max is the maximum service distance of the water taking machine.

[0151] Positive term: water taking coverage demand weight:

[0152]

[0153] Where, ∈{0,1} indicates whether the demand point k is covered; indicates the demand intensity of the demand point, the larger the value, the more high-weight (strong water demand) areas are served.

[0154] It can be seen that the positive term (coverage benefit) amplifies the importance of high-demand areas, ensuring that commercial areas, construction sites, and other high-weight areas are prioritized for coverage.

[0155] Negative term: water usage weighted total distance:

[0156]

[0157] Where, indicates the demand intensity of the demand point; ∈{0,1} indicates whether the demand point k is served by the water taking point j; indicates the shortest network distance (based on road network R') from water demand point k to water taking point j, calculated using Dijkstra algorithm based on road network R'. The smaller the value, the higher the overall water taking efficiency.​

[0158] As can be seen, the negative term (distance cost) penalizes long distance water fetching, and encourages a more balanced layout of water fetching machines, reducing the cost of walking for users.

[0159] As shown in the R' network diagram, when the number of nodes is less than 300 nodes, an exact algorithm (global optimal solution) such as an integer programming solver CPLEX / Gurobi is used for solving, and when the number of nodes is greater than 1000, an ALNS (adaptive large neighborhood search, approximate optimal solution) is used for solving. Figure 2 For example, 300 and 1000 are selected as the demarcation points, based on the following measured data:

[0160] When the number of nodes is less than 300, the exact algorithm takes <0.5h, and the solution quality improvement (compared with the heuristic) is >20%;

[0161] When the number of nodes is greater than 1000, the heuristic algorithm takes <3h, and the solution quality loss is <5%, and the cost performance is significantly higher than that of the exact algorithm.

[0162] As described above, in order to reduce the scale of operation, a projection threshold of the water fetching machine can also be set, and the effect is as shown in the following table 5:

[0163] Table 5

[0164]

[0165] When the threshold is 100m, the ALNS algorithm takes 5.2h→2.7h in a 1000-node scenario.

[0166] As can be seen, the three-layer mechanism of "scale judgment + algorithm adaptation + threshold filtering" of the present application not only guarantees the accuracy of site selection, but also takes into account the engineering feasibility, so that the water fetching machine site selection method of the present application can not only handle small-area fine layout, but also cope with large-scale network planning at the city level, and embodies the unity of theoretical rigor and engineering practicality.

[0167] Preferably, the real-time dynamic monitoring of the intelligent cover of the present application + multi-source static data fusion improves the water fetching machine deployment index as shown in the following table 6:

[0168] Table 6

[0169]

[0170] As can be seen, the present application realizes the upgrade from "passive response to fire hydrant water" to "active prediction of global demand", and solves the contradiction of "high-demand area coverage and low-demand area over-coverage" in traditional site selection, and provides data support for precise layout of municipal water fetching machines.

[0171]

[0172] ​​Embodiment Two

[0173] Based on the same idea, the application also provides a municipal water intake machine site selection device based on multi-source data fusion and optimization algorithm, comprising:

[0174] The acquisition module is configured to acquire fire hydrant water data and fuse multi-source auxiliary data to generate grid data reflecting regional water demand intensity.

[0175] The projection module is configured to project the grid data to the road network to obtain road network nodes with water demand weight.

[0176] The solving module is configured to solve, based on a preset budget constraint, a water intake machine arrangement position that maximizes high-demand area coverage and minimizes demand point water intake distance cost in the road network.

[0177] The output module is configured to output the water intake machine arrangement position.

[0178] Embodiment Three

[0179] The embodiment also provides an electronic device, referring to Figure 2 comprising a memory 404 and a processor 402, the memory 404 storing a computer program, and the processor 402 being configured to run the computer program to perform the steps in any of the method embodiments.

[0180] Specifically, the processor 402 can include a central processing unit (CPU), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits configured to implement the embodiments of the application.

[0181] The memory 404 can include a mass storage that stores data or instructions. For example, and without limitation, the memory 404 can include a Hard Disk Drive (HDD), a floppy disk drive, a Solid State Drive (SSD), a flash drive, a Compact Disc Read Only Memory (CD-ROM), a magneto-optical disk, a magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. The memory 404 can be removable and / or non-removable (or fixed) as appropriate. The memory 404 can be internal or external as appropriate. In particular embodiments, the memory 404 is a Non-Volatile memory. In particular embodiments, the memory 404 includes a Read-Only Memory (ROM) and a Random Access Memory (RAM). The ROM can be a mask-programmed ROM, a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), an Electrically Alterable ROM (EAROM), or a FLASH memory, or a combination of two or more of these, as appropriate. The RAM can be a Static Random-Access Memory (SRAM) or a Dynamic Random Access Memory (DRAM), which can be a Fast Page Mode Dynamic Random Access Memory (FPMDRAM), an Extended Data Output Dynamic Random Access Memory (EDODRAM), a Synchronous Dynamic Random-Access Memory (SDRAM), or the like, as appropriate.

[0182] The memory 404 can be used to store or buffer various data files needed for processing and / or communication, and possible computer program instructions executed by the processor 402.

[0183] The processor 402 implements the municipal water intake site selection method based on multi-source data fusion and optimization algorithm in any of the above embodiments by reading and executing the computer program instructions stored in the memory 404.

[0184] Optionally, the electronic device described above can further include a transmission device 406 connected with the processor 402 and an input / output device 408 connected with the processor 402.

[0185] The transmission device 406 can be used to receive or send data via a network. Specific examples of the network can include wired or wireless networks provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (NIC) which can be connected with other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (RF) module which is used to communicate with the Internet in a wireless manner.

[0186] The input / output device 408 is used to input or output information.

[0187] Embodiment Four

[0188] The embodiment also provides a readable storage medium, and the readable storage medium stores a computer program. The computer program includes program codes for controlling a process to execute the process. The process includes the municipal water intake site selection method based on multi-source data fusion and optimization algorithm according to the embodiment one.

[0189] It should be noted that the specific examples in the embodiment can refer to the examples described in the above embodiments and optional implementation manners, and the embodiment will not be described here.

[0190] In general, the various embodiments can be implemented in hardware or special purpose circuits, software, logic or any combination thereof. Some aspects of the application can be implemented in hardware, while other aspects can be implemented in firmware or software which can be executed by a controller, microprocessor or other computing device, but the application is not limited thereto. While various aspects of the application can be illustrated and described as block diagrams, flow charts, or using some other pictorial representation, it is well understood that these blocks, apparatus, systems, techniques or methods described herein can be implemented in, as non-limiting examples, hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controler or other computing devices, or some combination thereof.

[0191] Embodiments of the application can be implemented by computer software executable by a data processor of the mobile device such as in the processor entity, or by hardware, or by a combination of software and hardware. Computer software or program, also called program product, including software routines, applets and / or macros, can be stored in any apparatus-readable data storage medium and they comprise program instructions to perform particular tasks. The program product can include one or more computer-executable components such as those described above. The one or more computer-executable components can be one or more Figure 1 Any block in the logical flow of the above described embodiments can represent a module, segment, or portion of code which comprises one or more executable instructions implemented in digital electronic form, that is, in ones and zeros that are human-readable. In this regard, the above described embodiments can be implemented in hardware and / or in software (including firmware, resident software, micro-code, etc.). In these or other units, it should be noted that any of the functions of the above described embodiments can be performed by a state machine that has no stored program instructions, but rather executes all of its instructions using only electronic logic. In this regard, the above described embodiments can be implemented in digital electronic form, in tangibly-embodied computer software or firmware, in

[0192] Those skilled in the art should clearly understand that each technical feature in the above embodiments can be combined with any other technical feature, and for the sake of brevity, each technical feature in the above embodiments is not described in all possible combinations, but it should be considered that any combination of technical features is within the scope of the present disclosure.

[0193] The above embodiments only express several implementation manners of the present application, and the description is relatively specific and detailed, but it should not be understood as a limitation on the scope of the present application. It should be noted that for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present application, and these are within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A municipal water intake machine site selection method based on multi-source data fusion and optimization algorithm, characterized in that: The following steps are involved: Smart caps installed on fire hydrants monitor water usage frequency, duration, and abnormal events in real time, and report monitoring data via wireless communication to obtain fire hydrant water usage data. This data is then integrated with population density data, POI data, land use type data, and existing water facility location data as multi-source auxiliary data to generate grid data reflecting regional water demand intensity. Projecting the grid data onto a road network to obtain road network nodes with water demand weights; By constructing a dual-objective optimization model, based on a preset budget constraint, the water intake machine layout location is solved in the road network so as to maximize the coverage of high-demand areas and minimize the water intake distance cost of demand points.

2. A municipal water intake machine site selection method based on multi-source data fusion and optimization algorithm as claimed in claim 1, characterized in that: The POI data is assigned different weights according to its type, and the impact value is calculated based on the distance between the demand point and the POI; The land use type data is assigned different basic demand values ​​according to residential, commercial, industrial and green land types; The existing water intake facility location data is used to generate a demand suppression factor for the surrounding area.

3. The municipal water extraction machine site selection method based on multi-source data fusion and optimization algorithm according to claim 1 is characterized in that: The steps to project grid data onto a road network include: The center point of the grid is taken as the demand point, and the shortest actual path distance from it to the road network is calculated. If the projection point is located on the road section, a new node is inserted; the water demand intensity is weighted according to the distance from the demand point to the road network node, where the weighting parameter is determined according to the operating radius of the water pipeline and historical water use habits.

4. The municipal water extraction machine site selection method based on multi-source data fusion and optimization algorithm according to claim 1 is characterized in that: The dual-objective optimization model includes: Maximize the sum of water demand weights of covered demand points; Minimize the sum of weighted path distances from all demand points to the nearest water dispenser; The optimization model is solved by an integer programming algorithm or a heuristic algorithm, and the number of road network nodes is reduced by setting a projection threshold to improve the solution efficiency.

5. The municipal water extraction machine site selection method based on multi-source data fusion and optimization algorithm as claimed in claim 4, characterized in that: The projection threshold is determined based on the optimal moving radius verified by engineering practice. When the distance between a demand point and the road network exceeds the threshold, the demand point is ignored.

6. The municipal water extraction machine site selection method based on multi-source data fusion and optimization algorithm according to claim 1, characterized in that: Abnormal events monitored by the smart cover also include water theft and fire hydrant tilt status, and the monitoring data includes the timestamp and duration of the water use event.

7. A municipal water intake machine site selection device based on multi-source data fusion and optimization algorithm, characterized in that: include: The acquisition module is used to monitor the frequency, duration, and abnormal events of water use in real time through smart caps installed on fire hydrants, and report the monitoring data through wireless communication to obtain fire hydrant water use data. It also integrates population density data, POI data, land use type data, and existing water facility location data as multi-source auxiliary data to generate grid data reflecting the intensity of regional water demand; The projection module is used to project the grid data onto the road network to obtain road network nodes with water demand weights; A solution module is used to construct and solve a dual-objective optimization model to find the water dispenser layout in the road network that maximizes the coverage of high-demand areas and minimizes the water extraction distance cost at demand points based on a preset budget constraint; Output module, used to output the layout location of the water dispenser.

8. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the municipal water extraction machine site selection method based on multi-source data fusion and optimization algorithm as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which includes a program code for controlling a process to execute a process, and the process includes the municipal water extraction machine site selection method based on multi-source data fusion and optimization algorithm according to any one of claims 1 to 6.

Images