Monitoring sensor arrangement method of fire early warning system and related equipment

Abstract

The invention provides a monitoring sensor arrangement method of a fire early warning system and related equipment. The method comprises the following steps: determining a monitoring area coverage rate of the fire early warning system; according to the relation between the coverage rate of the monitoring area and the ideal coverage rate of the monitoring area of the fire early warning system, determining a monitoring sensor arrangement objective function of the fire early warning system; and performing iterative optimization on the monitoring sensor arrangement target function to obtain sensing arrangement position information of the fire early warning system, and arranging each monitoring sensor in the fire early warning system according to the sensing arrangement position information. The sensing arrangement position information is corresponding sensing arrangement position information when the monitoring sensor arrangement objective function characterizes that all monitoring sensors in the fire early warning system are located in the monitoring area, the area of a monitoring coverage repeated area is minimum, and the area of the monitoring coverage area is maximum; the maximum monitoring range can be covered by using a limited number of monitoring sensors, so that the fire early warning system can reflect in the early stage of the fire, and the fire loss is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of sensor arrangement, and in particular to a monitoring sensor arrangement method and related equipment for a fire early warning system. Background Art

[0002] Fire warning system is one of the most important means to prevent fire. The monitoring sensor in the fire warning system will generate an alarm when it detects a large amount of smoke that may cause a fire. The sensitivity of the monitoring sensor is considered according to the geographical location and application environment.

[0003] The layout of monitoring sensors directly affects the quality of the collected signal components and is of vital importance to the accuracy and timeliness of fire warnings. In application scenarios where items are piled up and the environment is complex, it is difficult for the monitoring sensors simply arranged in the fire warning system to respond to early fires. Therefore, how to arrange the monitoring sensors in the fire warning system and use a limited number of monitoring sensors to cover the largest detection range is a basic issue for early fire warning monitoring.

[0004] At present, the arrangement of monitoring sensors in fire warning systems is mainly based on experience, which adopts uniform distribution or diamond distribution. However, this arrangement is obviously difficult to adapt to all scenarios, resulting in monitoring blind spots or performance waste of monitoring sensors. Summary of the invention

[0005] In this regard, the present application provides a monitoring sensor layout method and related equipment for a fire warning system to solve the problem that the existing layout method using uniform distribution or diamond distribution based on experience is difficult to adapt to all scenarios, resulting in monitoring blind spots or waste of monitoring sensor performance.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0007] The first aspect of the present application discloses a method for arranging monitoring sensors of a fire early warning system, comprising:

[0008] Determine the monitoring area coverage rate of the fire early warning system, the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire early warning system to the number of monitoring area grid points of the fire early warning system, the monitoring area grid point coverage probability is the probability that the monitoring area grid point is covered by all the monitoring sensors in the fire early warning system, the monitoring area of ​​the fire early warning system is gridded to obtain a monitoring area grid, and the monitoring area grid includes a plurality of the monitoring area grid points;

[0009] Determining a monitoring sensor arrangement objective function of the fire early warning system according to a relationship between the monitoring area coverage rate and an ideal monitoring area coverage rate of the fire early warning system;

[0010] The monitoring sensor layout objective function is iteratively optimized to obtain sensor layout location information of the fire warning system, so as to arrange each of the monitoring sensors in the fire warning system according to the sensor layout location information. The sensor layout location information is the sensor layout location information corresponding to the time when the monitoring coverage overlap area of ​​all monitoring sensors in the fire warning system located in the monitoring area is minimized and the monitoring coverage area is maximized as represented by the monitoring sensor layout objective function.

[0011] Optionally, in the above-mentioned method for arranging monitoring sensors of the fire early warning system, determining the monitoring area coverage of the fire early warning system includes:

[0012] Determine the coverage probability of each grid point in the monitoring area in the fire early warning system;

[0013] Sum the coverage probabilities of all the monitoring area grid points in the fire early warning system to obtain the total coverage probability of the monitoring area grid points of the fire early warning system;

[0014] The total coverage probability of the monitoring area grid points is compared with the number of the monitoring area grid points to obtain the monitoring area coverage rate of the fire early warning system.

[0015] Optionally, in the above-mentioned method for arranging monitoring sensors of the fire early warning system, determining the coverage probability of each grid point in the monitoring area of ​​the fire early warning system includes:

[0016] Determine a monitoring sensor position set and a monitoring area grid point position set of the fire early warning system, wherein the monitoring sensor position set includes the position coordinates of each monitoring sensor in the fire early warning system, and the monitoring area grid point position set includes the position coordinates of each monitoring area grid point in the fire early warning system;

[0017] According to the monitoring sensor position set and the monitoring area grid point position set, respectively determine the position distance between each of the monitoring area grid points and each of the monitoring sensors;

[0018] The coverage probability of each monitoring area grid point in the fire early warning system is determined according to the location distance between each monitoring area grid point and each monitoring sensor.

[0019] Optionally, in the above-mentioned method for arranging monitoring sensors of the fire early warning system, the distance between the monitoring area grid point and the monitoring sensor is less than the monitoring effective radius, and the coverage probability of the monitoring area grid point corresponding to the fire early warning system is 1;

[0020] The location distance between the monitoring area grid point and the monitoring sensor is greater than the monitoring effective radius, and the coverage probability of the monitoring area grid point corresponding to the fire early warning system is 0.

[0021] Optionally, in the above-mentioned method for arranging monitoring sensors of a fire warning system, the process of determining the effective monitoring radius includes:

[0022] Determine the monitoring area of ​​the fire warning system, the hoisting height of the monitoring sensor and the monitoring radius, wherein the hoisting height is the distance between the monitoring sensor and the ground;

[0023] The monitoring effective radius is obtained by performing calculations based on the monitoring area, the hoisting height and the monitoring radius.

[0024] Optionally, in the above-mentioned method for arranging monitoring sensors of the fire early warning system, determining the monitoring sensor arrangement objective function of the fire early warning system according to the relationship between the monitoring area coverage and the ideal monitoring area coverage of the fire early warning system includes:

[0025] The ideal coverage rate of the monitoring area is subtracted from the coverage rate of the monitoring area to obtain the monitoring sensor layout objective function of the fire early warning system.

[0026] Optionally, in the above-mentioned monitoring sensor arrangement method of the fire early warning system, iteratively optimizing the monitoring sensor arrangement objective function to obtain the sensor arrangement position information of the fire early warning system includes:

[0027] Determining a target optimization algorithm for the fire warning system;

[0028] Iteratively optimizing the monitoring sensor placement objective function using the objective optimization algorithm to determine the minimum value of the monitoring sensor placement objective function;

[0029] The particle position information output by the target optimization algorithm when the monitoring sensor arrangement objective function is at the minimum value is used as the sensor arrangement position information of the fire warning system.

[0030] The second aspect of the present application discloses a monitoring sensor arrangement device for a fire early warning system, comprising:

[0031] A first determining unit is used to determine the monitoring area coverage rate of the fire early warning system, wherein the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire early warning system to the number of monitoring area grid points of the fire early warning system, wherein the monitoring area grid point coverage probability is the probability that the monitoring area grid point is covered by all the monitoring sensors in the fire early warning system, and the monitoring area of ​​the fire early warning system is gridded to obtain a monitoring area grid, wherein the monitoring area grid includes a plurality of the monitoring area grid points;

[0032] A second determining unit is used to determine the monitoring sensor arrangement objective function of the fire early warning system according to the relationship between the monitoring area coverage rate and the ideal monitoring area coverage rate of the fire early warning system;

[0033] An optimization layout unit is used to iteratively optimize the monitoring sensor layout objective function to obtain the sensor layout position information of the fire warning system, so as to arrange each of the monitoring sensors in the fire warning system according to the sensor layout position information. The sensor layout position information is the sensor layout position information corresponding to the time when the monitoring coverage overlap area of ​​all the monitoring sensors in the fire warning system located in the monitoring area is the smallest and the monitoring coverage area is the largest as represented by the monitoring sensor layout objective function.

[0034] The third aspect of the present application discloses an electronic device, including: a memory and a processor;

[0035] Wherein, the memory is used to store computer programs;

[0036] The processor is used to execute the computer program, specifically to implement the monitoring sensor arrangement method of the fire warning system as disclosed in any one of the first aspects.

[0037] The fourth aspect of the present application discloses a computer storage medium for storing a computer program. When the computer program is executed, it is specifically used to implement the monitoring sensor arrangement method of the fire warning system as described in any one of the items disclosed in the first aspect.

[0038] The present invention provides a method for arranging monitoring sensors of a fire early warning system, comprising: determining a monitoring area coverage rate of the fire early warning system, the monitoring area coverage rate being the ratio of the coverage probability of all monitoring area grid points in the fire early warning system to the number of monitoring area grid points of the fire early warning system, the monitoring area grid point coverage probability being the probability that the monitoring area grid points are covered by all monitoring sensors in the fire early warning system, performing grid processing on the monitoring area of ​​the fire early warning system to obtain a monitoring area grid, the monitoring area grid comprising a plurality of monitoring area grid points; determining a monitoring sensor arrangement objective function of the fire early warning system according to a relationship between the monitoring area coverage rate and an ideal monitoring area coverage rate of the fire early warning system; and calculating the monitoring sensor arrangement objective function. The number of iterative optimizations is used to obtain the sensor layout position information of the fire warning system, so that each monitoring sensor in the fire warning system is arranged according to the sensor layout position information. The sensor layout position information is the sensor layout position information corresponding to the time when the monitoring coverage overlap area of ​​all monitoring sensors in the fire warning system is the smallest and the monitoring coverage area is the largest. A limited number of monitoring sensors can be used to cover the largest monitoring range, so that the fire warning system can respond in the early stage of the fire and minimize the fire loss. This solves the problem that the existing layout method of uniform distribution or diamond distribution based on experience is difficult to adapt to all scenarios, resulting in monitoring blind spots or performance waste of monitoring sensors. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0040] Figure 1 A flow chart of a method for arranging monitoring sensors for a fire warning system provided in this application;

[0041] Figure 2 A schematic diagram of a perception model of a monitoring sensor provided in an embodiment of the present application;

[0042] Figure 3 A comparison chart of coverage simulation results of an algorithm provided in an embodiment of the present application;

[0043] Figure 4 A schematic diagram of a basic particle swarm algorithm simulation arrangement result provided in an embodiment of the present application;

[0044] Figure 5 Schematic diagram of simulation arrangement results of an improved particle swarm algorithm provided in an embodiment of the present application

[0045] Figure 6 A comparison diagram of algorithms with different numbers of particle swarms provided in an embodiment of the present application;

[0046] Figure 7 A comparison diagram of algorithms for different numbers of monitoring sensors provided in an embodiment of the present application;

[0047] Figure 8 A schematic diagram of a monitoring sensor arrangement device for a fire warning system provided in an embodiment of the present application;

[0048] Fig. 9 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] The embodiments of the present application provide a method for arranging monitoring sensors for a fire warning system and related equipment to solve the problem that the existing arrangement method using uniform distribution or diamond distribution based on experience is difficult to adapt to all scenarios, resulting in monitoring blind spots or performance waste of monitoring sensors.

[0051] See also Figure 1 The monitoring sensor arrangement method of the fire early warning system mainly includes the following steps:

[0052] S101. Determine the monitoring area coverage of the fire warning system.

[0053] Among them, the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire early warning system to the number of monitoring area grid points in the fire early warning system; the monitoring area grid point coverage probability is the probability that the monitoring area grid points are covered by all monitoring sensors in the fire early warning system.

[0054] In some embodiments, the monitoring area of ​​the fire warning system may be gridded to obtain a monitoring area grid, and the monitoring area grid includes a plurality of monitoring area grid points.

[0055] Specifically, the monitoring area of ​​the fire warning system in this application refers to the two-dimensional detection area of ​​the fire warning system. In practical applications, the two-dimensional detection area of ​​the fire warning system can be obtained by building a two-dimensional model for the three-dimensional monitoring area of ​​the fire warning system.

[0056] It should be noted that the number of grid points in the monitoring area of ​​the fire early warning system can be obtained after gridding the monitoring area of ​​the fire early warning system. For the convenience of explanation, the number of grid points in the monitoring area of ​​the fire early warning system can be expressed as m×n, where m and n represent the horizontal and vertical division numbers of the monitoring area grid, respectively.

[0057] It should also be noted that the number of grid points in the monitoring area of ​​the fire warning system can be divided according to the specific size of the monitoring sensor. The division standard is that the size of a small grid is equivalent to the size of the monitoring sensor. Assuming that the size of the monitoring sensor is 20cm×10cm and the two-dimensional detection area is 10m×5m, then the grid division That is, the number of grids is 2500.

[0058] In some embodiments, the specific execution process of step S101, determining the monitoring area coverage rate of the fire warning system, is as follows, mainly including steps S201 to S203:

[0059] S201. Determine the coverage probability of each grid point in the monitoring area of ​​the fire early warning system.

[0060] In practical applications, the coverage probability of each grid point in the monitoring area of ​​the fire early warning system may be determined in the following manner, which may specifically include steps S301 to S303:

[0061] S301. Determine a monitoring sensor location set and a monitoring area grid point location set of a fire warning system.

[0062] The monitoring sensor location set includes the location coordinates of each monitoring sensor in the fire early warning system, and the monitoring area grid point location set includes the location coordinates of each monitoring area grid point in the fire early warning system.

[0063] In practical applications, assuming that the number of monitoring sensors in the fire warning system is N, the position coordinates of each monitoring sensor can be expressed as z i =(xi,yi), i = 1,2,…,N, the set of monitoring sensor locations of the fire warning system can be expressed as Z = {z1,z2,…,z N}; Since the monitoring area is divided into m×n grid points, the position coordinates of each grid point in the monitoring area are p j =(x j ,y j ), j = m0n0, m0n1, ..., m m n n , the set of grid point locations in the monitoring area of ​​the fire early warning system can be expressed as

[0064] S302: Determine the location distance between each monitoring area grid point and each monitoring sensor according to the monitoring sensor location set and the monitoring area grid point location set.

[0065] The position coordinates of the grid points in the monitoring area are p j =(x j ,y j ) as an example, the monitoring area grid point p j With monitoring sensor i The distance between can be expressed as:

[0066] S303: Determine the coverage probability of each monitoring area grid point in the fire early warning system according to the location distance between each monitoring area grid point and each monitoring sensor.

[0067] In practical applications, the monitoring coverage area of ​​the monitoring sensor is z i The circular area is centered and its radius is the monitoring effective radius.

[0068] A Boolean model can be used to determine the coverage probability of each monitoring area grid point in the fire early warning system according to the size relationship between the location distance of each monitoring area grid point and each monitoring sensor.

[0069] Similarly, the position coordinates of the grid points in the monitoring area are taken as p j =(x j ,y j ) as an example, when the monitoring area grid point p j In monitoring sensor z i When the sensing range is within the monitoring area, the grid point p j The probability of being covered is 1, otherwise it is 0. The corresponding mathematical expression can be: Monitoring area grid point p j The probability of being covered by all monitoring sensors, that is, the monitoring area grid point p j The coverage probability can be expressed as

[0070] It can be understood that when the distance between the grid points in the monitoring area and the monitoring sensor is less than the effective monitoring radius, the coverage probability of the grid points in the monitoring area corresponding to the fire warning system is 1; when the distance between the grid points in the monitoring area and the monitoring sensor is greater than the effective monitoring radius, the coverage probability of the grid points in the monitoring area corresponding to the fire warning system is 0.

[0071] In practical applications, since the monitoring sensor is usually installed on the top of the monitoring area of ​​the fire warning system, its detection range is as follows: Figure 2As shown in the figure, the ground coverage area of ​​the monitoring sensor is the section of its detection spherical range and the ground (the monitoring coverage area of ​​the above-mentioned monitoring sensor), so the space on the ground range of the monitoring sensor is within the detection and perception range of the monitoring sensor.

[0072] According to a large number of tests, the monitoring coverage area of ​​the monitoring sensor is different for different areas and heights due to the difference in the concentration of gas diffusion generated by the fire. Taking into account the performance of the monitoring sensor, the effective monitoring radius of the monitoring sensor can be expressed as: Among them, S represents the monitoring area of ​​the fire warning system, R represents the monitoring radius of the monitoring sensor, and h represents the hoisting height of the monitoring sensor.

[0073] It should be noted that the monitoring radius of the monitoring sensor is the distance between the detection spherical range of the monitoring sensor and the edge of the cross-section of the ground; the effective monitoring radius of the monitoring sensor is the radius of the cross-section between the detection spherical range of the monitoring sensor and the ground, that is, the radius of the monitoring coverage area of ​​the monitoring sensor.

[0074] In combination with the above, the process of determining the effective monitoring radius of the monitoring sensor may be as follows, including steps S401 and S402:

[0075] S401. Determine the monitoring area of ​​the fire warning system, the hoisting height of the monitoring sensor, and the monitoring radius.

[0076] Among them, the hoisting height is the distance between the monitoring sensor and the ground.

[0077] It should be noted that the monitoring area of ​​the fire warning system, the lifting height of the monitoring sensor and the monitoring radius can be determined according to the application environment and user needs. This application does not make specific limitations and they are all within the protection scope of this application.

[0078] S402: Calculate based on the monitoring area, hoisting height and monitoring radius to obtain the monitoring effective radius.

[0079] It should be noted that once the monitoring area, the installation height of the monitoring sensor and the monitoring radius of the fire early warning system are determined, the formula Perform calculations to obtain the effective monitoring radius.

[0080] S202: Sum the coverage probabilities of all monitoring area grid points in the fire early warning system to obtain the total coverage probability of the monitoring area grid points of the fire early warning system.

[0081] In practical applications, after determining the coverage probability of each monitoring area grid point in the fire early warning system, the coverage probability of all monitoring area grid points can be summed to obtain the total coverage probability of the monitoring area grid points of the fire early warning system.

[0082] S203. Compare the total coverage probability of the monitoring area grid points with the number of the monitoring area grid points to obtain the monitoring area coverage rate of the fire early warning system.

[0083] In practical applications, the monitoring area coverage of the fire early warning system can be expressed as: in, represents the total coverage probability of the grid points in the monitoring area of ​​the fire early warning system, and m×n represents the number of grid points in the monitoring area of ​​the fire early warning system.

[0084] S102: Determine the monitoring sensor layout objective function of the fire early warning system according to the relationship between the monitoring area coverage rate and the ideal monitoring area coverage rate of the fire early warning system.

[0085] Among them, the ideal coverage rate of the detection area of ​​the fire warning system is generally 1, that is, the monitoring area of ​​the fire warning system can be fully covered by the monitoring sensors.

[0086] In practical applications, the difference between the ideal coverage rate of the monitoring area of ​​the fire early warning system and the coverage rate of the monitoring area can be used as the monitoring sensor layout objective function of the fire early warning system. That is, the ideal coverage rate of the monitoring area is subtracted from the coverage rate of the monitoring area to obtain the monitoring sensor layout objective function of the fire early warning system. Correspondingly, the monitoring sensor layout objective function of the fire early warning system can be expressed as:

[0087] S103, iteratively optimizing the monitoring sensor layout objective function to obtain sensor layout location information of the fire warning system, so as to arrange each monitoring sensor in the fire warning system according to the sensor layout location information.

[0088] Among them, the sensor layout location information is the sensor layout location information corresponding to when the monitoring coverage overlap area of ​​all monitoring sensors in the fire warning system is the smallest and the monitoring coverage area is the largest in the monitoring area characterized by the monitoring sensor layout objective function.

[0089] In practical applications, once the objective function of the monitoring sensor layout of the fire warning system is determined, the optimal layout problem of the monitoring sensors in the fire warning system can be converted into the coverage optimization problem of the monitoring sensors, and then the coverage optimization problem of the monitoring sensors can be converted into the minimum value solution problem of the monitoring sensor layout objective function.

[0090] In some embodiments, the specific process of iteratively optimizing the monitoring sensor layout objective function in step S103 to obtain the sensor layout location information of the fire warning system can be as follows, mainly including steps S501 to S503:

[0091] S501. Determine a target optimization algorithm for a fire warning system.

[0092] In practical applications, the target optimization algorithm of the fire warning system can be an improved particle swarm algorithm (Interval Particle Swarm Optimization, IPSO). The improved particle swarm algorithm can be obtained by improving the basic particle swarm algorithm (Particle Swarm Optimization, PSO) by introducing an improved strategy of adaptive inertia weight and Gaussian random mutation.

[0093] The basic particle swarm algorithm is a swarm intelligence algorithm designed by simulating the predation behavior of bird flocks. There are different food sources of different sizes in the area, and the task of the bird flock is to find the largest food source (global optimal solution). During the entire search process, the bird flock transmits information about their respective positions to each other, letting other birds know the location of the food source. Eventually, the entire bird flock can gather around the food source, that is, the optimal solution is found and the problem converges.

[0094] The goal of the basic particle swarm algorithm is to make all particles find the optimal solution in a multi-dimensional hyper-volume. First, all particles in the space are assigned initial random positions and initial random velocities. The position of each particle is advanced in turn according to its velocity, the best global position known in the problem space, and the best position known to the particle. As the calculation progresses, particles gather or aggregate around one or more optimal locations by exploring and exploiting known favorable positions in the search space.

[0095] The design of the basic particle swarm algorithm is to retain the best global position and the best position known to the particle. The algorithm steps are relatively simple. A group of particles move in the search space, affected by their own best past position pbest and the best past position gbest of the entire particle swarm or the neighboring particles. The speed update formula of particle i in the dth dimension in each iteration is: in, represents the d-dimensional velocity of the i-th particle in the k-1th iteration, is the d-dimensional position of the i-th particle in the k-1th iteration, pbest i,d represents the optimal position of the ith particle in d dimensions during the iteration process, gbest d is the global optimal position of the d-dimensional particle in the iterative process, c1 represents the self-learning factor of the particle, c2 represents the social learning factor of the particle, c1∈(0,2], c2∈(0,2]; r1 and r2 are two random numbers between 0 and 1; w represents the inertia weight, and its value range is [0.1,0.9].

[0096] The update formula of the d-dimensional position of particle i is:

[0097] The basic particle swarm algorithm has the advantages of fast convergence speed, high computational efficiency, and simple operation. The optimization effect is related to the number of iterations and the number of initial particle swarms. In theory, the more iterations and the larger the number of initial particle swarms, the better the optimization effect. However, the basic particle swarm algorithm can easily fall into local optimality and premature convergence. At this time, the algorithm falls into a local extreme point and cannot jump out. In addition, the larger the initial particle swarm, the higher the time complexity and the slower the iteration speed.

[0098] After comprehensive consideration, this application introduces the improved strategy of adaptive inertia weight and Gaussian random mutation to improve the basic particle swarm algorithm to obtain an improved particle swarm algorithm. The adaptive inertia weight changes the fixed inertia weight into a dynamic adaptive form, that is, the value of the inertia weight w is adjusted in time according to the previous iteration results.

[0099] The adaptive method in the target optimization algorithm of the fire warning system of this application is to linearly adjust the inertia weight w according to the number of iterations. The specific formula is: Among them, w max Indicates the upper limit of the range of inertia weight w, w min It represents the lower limit of the value range of the inertia weight w, t represents the current iteration number, and T represents the maximum iteration number.

[0100] The inertia weight adjustment formula still has certain drawbacks. For example, the algorithm fails to find the range of the optimal solution in the early stage. Then, the global search capability of the algorithm gradually decreases with the increase of the number of iterations. It is difficult to jump out of the local optimal range, resulting in local convergence of the algorithm.

[0101] Therefore, the target optimization algorithm of the fire warning system of the present application is improved by adding a Gaussian random mutation coefficient on the basis of the above. Gaussian random numbers have the characteristics of symmetry and limitations, and the distribution conforms to the normal distribution, that is, when the particle position is updated, a Gaussian random number is added to its speed update, and the particle has the ability to mutate the position, solving the problem of particles falling into local optimality. The improved particle i's d-dimensional position update formula is:

[0102] S502: Iteratively optimize the monitoring sensor placement objective function using a target optimization algorithm to determine the minimum value of the monitoring sensor placement objective function.

[0103] In practical applications, the specific steps of the target optimization algorithm for iterative optimization of the monitoring sensor placement objective function are as follows:

[0104] Step 1: Initialize the basic parameters of the cluster, including setting the initial number of particle swarms M, the maximum number of iterations T, and the upper limit of the inertia weight range wmax , the lower limit of the inertia weight range w min , the particle’s self-learning factor c1, and the particle’s social learning factor c2.

[0105] Step 2: Calculate the adaptability of each particle in each initial particle group and record pbest i,d 、gbest d .

[0106] Step 3: Update the particle's velocity and position according to formulas (1), (2) and (4).

[0107] Step 4: Repeat steps 3 and 4 until the number of iterations reaches the maximum number of iterations, and output pbest i,d and the position of the corresponding particle i.

[0108] Among them, the maximum number of iterations T can be pre-set; this application does not limit its specific value, which is within the protection scope of this application.

[0109] It should be noted that each execution of step 2 and step 3 is considered to complete one iteration.

[0110] S503: Use the particle position information output by the target optimization algorithm when the monitoring sensor arrangement objective function is at the minimum value as the sensor arrangement position information of the fire warning system.

[0111] In practical applications, when the monitoring sensor layout objective function is at the minimum value, the target optimization algorithm will output the particle position information, which is the position of the corresponding particle i in the above step 4. Therefore, the particle position information output by the target optimization algorithm when the monitoring sensor layout objective function is at the minimum value can be used as the sensor layout position information of the fire warning system.

[0112] Based on the above principles, the monitoring sensor arrangement method of the fire warning system provided in this embodiment includes: determining the monitoring area coverage rate of the fire warning system, the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire warning system to the number of monitoring area grid points of the fire warning system, the monitoring area grid point coverage probability is the probability that the monitoring area grid points are covered by all monitoring sensors in the fire warning system, the monitoring area of ​​the fire warning system is gridded to obtain a monitoring area grid, and the monitoring area grid includes a plurality of monitoring area grid points; according to the relationship between the monitoring area coverage rate and the ideal coverage rate of the monitoring area of ​​the fire warning system, determining the monitoring sensor arrangement objective function of the fire warning system; and calculating the monitoring sensor arrangement objective function. The objective function is iteratively optimized to obtain the sensor layout position information of the fire warning system, so that each monitoring sensor in the fire warning system is arranged according to the sensor layout position information. The sensor layout position information is the sensor layout position information corresponding to the minimum monitoring coverage overlap area and the maximum monitoring coverage area of ​​all monitoring sensors in the fire warning system. A limited number of monitoring sensors can be used to cover the largest monitoring range, so that the fire warning system can respond in the early stage of the fire and reduce the fire loss as much as possible. The existing layout method of uniform distribution or diamond distribution based on experience is difficult to adapt to all scenarios, resulting in monitoring blind spots or performance waste of monitoring sensors.

[0113] Based on the monitoring sensor arrangement method of the fire warning system provided in the above embodiment, in practical applications, the improved particle swarm algorithm used in the iterative optimization in this application has the following advantages over the basic particle swarm algorithm:

[0114] A large warehouse with a length of 50 meters, a width of 50 meters and a height of 4 meters is used as an example for analysis and simulation layout, and a simulation comparison is made between the basic particle swarm algorithm and the improved particle swarm algorithm used in this application to verify the feasibility and superiority of the present invention. The experimental parameters are shown in the following table.

[0115] Table 1-1 Experimental simulation parameters

[0116]

[0117]

[0118] According to the above parameters, the basic particle swarm algorithm and the improved particle swarm algorithm are used to optimize the sensor layout. The monitoring area coverage rate of the fire early warning system changes as follows: Figure 3As shown in the figure, as the number of iterations increases, the coverage of the two algorithms continues to increase until they fall into the local optimum and the coverage of the monitoring area no longer changes. The improved strategy of the improved particle swarm algorithm, on the one hand, has an adaptive inertia weight, so its early optimization speed is very fast, and the coverage of the monitoring area increases quickly. On the other hand, the addition of Gaussian random numbers enhances the ability of the algorithm to jump out of the local optimum, and obtains a better optimization effect, that is, a higher coverage rate.

[0119] Also combined Figure 3 In 2500 iterations, the monitoring area coverage rate of the optimized layout of the improved particle swarm algorithm reached 96.73%, while the monitoring area coverage rate of the optimized layout of the basic particle swarm algorithm was only 83.96%. The monitoring area coverage rate of the improved particle swarm algorithm increased by 12.77%. The experiment proves the effectiveness of the optimized layout of the improved particle swarm algorithm. The simulation layout diagram of the two algorithms is shown in the figure below. Figure 4 and Figure 5 shown.

[0120] Further comparison tests are conducted to ensure that other parameters are consistent, and the number of particle swarms is changed to compare the results. The number of particle swarms has a key impact on the optimization speed and optimization results. Generally, the more particle swarms there are, the better the optimization effect, but the corresponding calculation time of the algorithm will also be higher, and the optimization speed will decrease.

[0121] The number of particle swarms was set to 10, 20, 30, 40 and 50 for simulation experiments. The experimental results are shown in Figure 6 As shown in the figure. As the number of particle swarms increases, the coverage of the basic particle swarm algorithm and the improved particle swarm algorithm can reach a peak value. When the number of particle swarms is too high, the coverage rate decreases instead of increasing. By comparing the basic particle swarm algorithm and the improved particle swarm algorithm, it is found that the improved particle swarm algorithm obtains a higher coverage rate under different numbers of particle swarms, and the coverage rate of the basic particle swarm algorithm is lower than that of the improved particle swarm algorithm even if the population size increases, which proves the superiority of the improved particle swarm algorithm.

[0122] The number of monitoring sensors is also a key factor affecting coverage. However, more sensors mean higher costs. The significance of the optimization algorithm is to achieve a higher coverage of the monitoring area by deploying fewer monitoring sensors. Keep other parameters unchanged and change the number of monitoring sensors to compare the results.

[0123] The number of monitoring sensors is set to 10, 20, 30, 40, and 50 to compare the coverage changes of the two algorithms. Figure 7As shown in the figure, the results show that under different numbers of monitoring sensors, the coverage of the improved particle swarm algorithm is greater than that of the basic particle swarm algorithm. When the number of monitoring sensors reaches 50, the coverage of the monitoring sensor layout optimized by the improved particle swarm algorithm is almost 100%, which shows that the improved particle swarm algorithm can better save resources and obtain better optimization layout solutions.

[0124] In summary, this application can combine the monitoring performance of monitoring sensors, conduct model analysis on monitoring scenarios, sample adaptive inertia coefficients and Gaussian random optimized particle swarm algorithm for optimal arrangement, and ensure that limited monitoring sensors can cover the maximum monitoring area. The results of simulation experiments compared with the basic particle swarm algorithm show that this application has the following advantages:

[0125] ① Without changing the time complexity, the improved particle swarm algorithm can obtain higher sensor coverage than the basic particle swarm algorithm.

[0126] ② Under the same experimental parameters, the improved particle swarm algorithm performs better in terms of optimization speed and optimization accuracy.

[0127] ③ The feasibility and superiority of using the improved particle swarm algorithm to optimize the layout of monitoring sensors in the fire early warning system are proved, which provides a basis for the optimal layout of monitoring sensors in the fire early warning system.

[0128] It should be noted that the above is only a specific example provided by the present application. In practical applications, the monitoring sensor arrangement method of the fire warning system provided in the above embodiment can also be modified. As long as the principle is the same as that of the present application, it is within the protection scope of the present application.

[0129] Optionally, another embodiment of the present application further provides a monitoring sensor arrangement device for a fire warning system, such as Figure 8 As shown, it mainly includes:

[0130] The first determining unit 101 is used to determine the monitoring area coverage rate of the fire early warning system, wherein the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire early warning system to the number of monitoring area grid points in the fire early warning system, wherein the monitoring area grid point coverage probability is the probability that the monitoring area grid point is covered by all the monitoring sensors in the fire early warning system, and the monitoring area of ​​the fire early warning system is gridded to obtain a monitoring area grid, wherein the monitoring area grid includes a plurality of the monitoring area grid points;

[0131] A second determining unit 102 is used to determine the monitoring sensor arrangement objective function of the fire early warning system according to the relationship between the monitoring area coverage rate and the ideal monitoring area coverage rate of the fire early warning system;

[0132] The optimal arrangement unit 103 is used to iteratively optimize the monitoring sensor arrangement objective function to obtain the sensor arrangement location information of the fire warning system, so as to arrange each of the monitoring sensors in the fire warning system according to the sensor arrangement location information. The sensor arrangement location information is the sensor arrangement location information corresponding to the time when the monitoring coverage overlap area of ​​all the monitoring sensors in the fire warning system within the monitoring area is minimized and the monitoring coverage area is maximized as represented by the monitoring sensor arrangement objective function.

[0133] In some embodiments, the first determination unit 101 is specifically used to: determine the coverage probability of each grid point in the monitoring area in the fire early warning system;

[0134] Sum the coverage probabilities of all the monitoring area grid points in the fire early warning system to obtain the total coverage probability of the monitoring area grid points of the fire early warning system;

[0135] The total coverage probability of the monitoring area grid points is compared with the number of the monitoring area grid points to obtain the monitoring area coverage rate of the fire early warning system.

[0136] In some embodiments, determining the coverage probability of each of the monitoring area grid points in the fire early warning system includes:

[0137] Determine a monitoring sensor position set and a monitoring area grid point position set of the fire early warning system, wherein the monitoring sensor position set includes the position coordinates of each monitoring sensor in the fire early warning system, and the monitoring area grid point position set includes the position coordinates of each monitoring area grid point in the fire early warning system;

[0138] According to the monitoring sensor position set and the monitoring area grid point position set, respectively determine the position distance between each of the monitoring area grid points and each of the monitoring sensors;

[0139] The coverage probability of each monitoring area grid point in the fire early warning system is determined according to the location distance between each monitoring area grid point and each monitoring sensor.

[0140] In some embodiments, the distance between the monitoring area grid point and the monitoring sensor is less than the monitoring effective radius, and the coverage probability of the monitoring area grid point corresponding to the fire early warning system is 1;

[0141] The location distance between the monitoring area grid point and the monitoring sensor is greater than the monitoring effective radius, and the coverage probability of the monitoring area grid point corresponding to the fire early warning system is 0.

[0142] In some embodiments, the process of determining the monitoring effective radius includes:

[0143] Determine the monitoring area of ​​the fire warning system, the hoisting height of the monitoring sensor and the monitoring radius, wherein the hoisting height is the distance between the monitoring sensor and the ground;

[0144] The monitoring effective radius is obtained by performing calculations based on the monitoring area, the hoisting height and the monitoring radius.

[0145] In some embodiments, the second determining unit 102 is specifically configured to:

[0146] The ideal coverage rate of the monitoring area is subtracted from the coverage rate of the monitoring area to obtain the monitoring sensor layout objective function of the fire early warning system.

[0147] In some embodiments, the optimal placement unit 103 is specifically used to:

[0148] Determining a target optimization algorithm for the fire warning system;

[0149] Iteratively optimizing the monitoring sensor placement objective function using the objective optimization algorithm to determine the minimum value of the monitoring sensor placement objective function;

[0150] The particle position information output by the target optimization algorithm when the monitoring sensor arrangement objective function is at the minimum value is used as the sensor arrangement position information of the fire warning system.

[0151] The monitoring sensor arrangement device of the fire warning system provided in this embodiment includes: a first determination unit 101 is used to determine the monitoring area coverage rate of the fire warning system, the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire warning system to the number of monitoring area grid points of the fire warning system, the monitoring area grid point coverage probability is the probability that the monitoring area grid points are covered by all the monitoring sensors in the fire warning system, the monitoring area of ​​the fire warning system is gridded to obtain a monitoring area grid, and the monitoring area grid includes a plurality of monitoring area grid points; a second determination unit 102 is used to determine the monitoring sensor arrangement objective function of the fire warning system according to the relationship between the monitoring area coverage rate and the ideal coverage rate of the monitoring area of ​​the fire warning system; optimizing The arrangement unit 103 is used to iteratively optimize the monitoring sensor arrangement objective function to obtain the sensor arrangement location information of the fire warning system, so as to arrange each of the monitoring sensors in the fire warning system according to the sensor arrangement location information. The sensor arrangement location information is the sensor arrangement location information corresponding to the time when the monitoring coverage overlap area of ​​all the monitoring sensors in the fire warning system within the monitoring area is the smallest and the monitoring coverage area is the largest, as represented by the monitoring sensor arrangement objective function. A limited number of monitoring sensors can be used to cover the largest monitoring range, so that the fire warning system can respond in the early stage of the fire and minimize the fire loss. This solves the problem that the existing arrangement method of uniform distribution or diamond distribution based on experience is difficult to adapt to all scenarios, resulting in monitoring blind spots or performance waste of monitoring sensors.

[0152] It should be noted that, for the relevant description of each unit in the monitoring sensor arrangement device of the fire warning system, reference can be made to the corresponding embodiment of the above method, which will not be repeated here.

[0153] Optionally, another embodiment of the present application further provides a computer storage medium for storing a computer program. When the computer program is executed, it is specifically used to implement the monitoring sensor deployment method of the fire warning system provided in any embodiment of the present application.

[0154] It should be noted that, for the relevant description of the method for arranging monitoring sensors of the fire warning system, reference can be made to the above-mentioned embodiment, which will not be repeated here.

[0155] Optionally, another embodiment of the present application further provides an electronic device, such as Fig. 9 As shown, the electronic device includes a memory 601 and a processor 602 .

[0156] Wherein, the memory 601 is used to store computer programs;

[0157] The processor 602 is used to execute a computer program, specifically to implement the monitoring sensor arrangement method of the fire warning system provided in any embodiment of the present application.

[0158] It should be noted that the relevant description of the method for arranging monitoring sensors of the fire warning system can also be found in the above embodiment and will not be repeated here.

[0159] The features recorded in the various embodiments in this specification can be replaced or combined with each other, and the same and similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The system and system embodiments described above are only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without creative work. Professionals can also further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented in electronic hardware, computer software or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0160] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

[0161] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

Claims

1. A method for arranging monitoring sensors for a fire early warning system, characterized in that: include: Determine the monitoring area coverage rate of the fire early warning system, the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire early warning system to the number of monitoring area grid points of the fire early warning system, the monitoring area grid point coverage probability is the probability that the monitoring area grid point is covered by all the monitoring sensors in the fire early warning system, the monitoring area of ​​the fire early warning system is gridded to obtain a monitoring area grid, and the monitoring area grid includes a plurality of the monitoring area grid points; Determining a monitoring sensor arrangement objective function of the fire early warning system according to a relationship between the monitoring area coverage rate and an ideal monitoring area coverage rate of the fire early warning system; The monitoring sensor layout objective function is iteratively optimized to obtain sensor layout location information of the fire warning system, so as to arrange each of the monitoring sensors in the fire warning system according to the sensor layout location information. The sensor layout location information is the sensor layout location information corresponding to the time when the monitoring coverage overlap area of ​​all monitoring sensors in the fire warning system located in the monitoring area is minimized and the monitoring coverage area is maximized as represented by the monitoring sensor layout objective function.

2. The method for arranging monitoring sensors of a fire early warning system according to claim 1, characterized in that: Determine the monitoring area coverage of the fire early warning system, including: Determine the coverage probability of each grid point in the monitoring area in the fire early warning system; Sum the coverage probabilities of all the monitoring area grid points in the fire early warning system to obtain the total coverage probability of the monitoring area grid points of the fire early warning system; The total coverage probability of the monitoring area grid points is compared with the number of the monitoring area grid points to obtain the monitoring area coverage rate of the fire early warning system.

3. The method for arranging monitoring sensors of a fire early warning system according to claim 2, characterized in that: Determining the coverage probability of each grid point in the monitoring area in the fire early warning system includes: Determine a monitoring sensor position set and a monitoring area grid point position set of the fire early warning system, wherein the monitoring sensor position set includes the position coordinates of each monitoring sensor in the fire early warning system, and the monitoring area grid point position set includes the position coordinates of each monitoring area grid point in the fire early warning system; According to the monitoring sensor position set and the monitoring area grid point position set, respectively determine the position distance between each of the monitoring area grid points and each of the monitoring sensors; The coverage probability of each monitoring area grid point in the fire early warning system is determined according to the location distance between each monitoring area grid point and each monitoring sensor.

4. The method for arranging monitoring sensors of a fire early warning system according to claim 3, characterized in that: The distance between the monitoring area grid point and the monitoring sensor is less than the monitoring effective radius, and the coverage probability of the monitoring area grid point corresponding to the fire early warning system is 1; The location distance between the monitoring area grid point and the monitoring sensor is greater than the monitoring effective radius, and the coverage probability of the monitoring area grid point corresponding to the fire early warning system is 0.

5. The method for arranging monitoring sensors of a fire early warning system according to claim 4, characterized in that: The process of determining the monitoring effective radius includes: Determine the monitoring area of ​​the fire warning system, the hoisting height of the monitoring sensor and the monitoring radius, wherein the hoisting height is the distance between the monitoring sensor and the ground; The monitoring effective radius is obtained by performing calculations based on the monitoring area, the hoisting height and the monitoring radius.

6. The method for arranging monitoring sensors of a fire early warning system according to claim 1, characterized in that: According to the relationship between the monitoring area coverage rate and the ideal monitoring area coverage rate of the fire early warning system, determining the monitoring sensor layout objective function of the fire early warning system includes: The ideal coverage rate of the monitoring area is subtracted from the coverage rate of the monitoring area to obtain the monitoring sensor layout objective function of the fire early warning system.

7. The method for arranging monitoring sensors of a fire early warning system according to claim 1, characterized in that: Iteratively optimizing the monitoring sensor layout objective function to obtain sensor layout location information of the fire warning system includes: Determining a target optimization algorithm for the fire warning system; Iteratively optimizing the monitoring sensor placement objective function using the objective optimization algorithm to determine the minimum value of the monitoring sensor placement objective function; The particle position information output by the target optimization algorithm when the monitoring sensor arrangement objective function is at the minimum value is used as the sensor arrangement position information of the fire warning system.

8. A monitoring sensor arrangement device for a fire early warning system, characterized in that: include: A first determining unit is used to determine the monitoring area coverage rate of the fire early warning system, wherein the monitoring area coverage rate is the ratio of the coverage probability of all monitoring area grid points in the fire early warning system to the number of monitoring area grid points of the fire early warning system, wherein the monitoring area grid point coverage probability is the probability that the monitoring area grid point is covered by all the monitoring sensors in the fire early warning system, and the monitoring area of ​​the fire early warning system is gridded to obtain a monitoring area grid, wherein the monitoring area grid includes a plurality of the monitoring area grid points; A second determining unit is used to determine the monitoring sensor arrangement objective function of the fire early warning system according to the relationship between the monitoring area coverage rate and the ideal monitoring area coverage rate of the fire early warning system; An optimization layout unit is used to iteratively optimize the monitoring sensor layout objective function to obtain the sensor layout position information of the fire warning system, so as to arrange each of the monitoring sensors in the fire warning system according to the sensor layout position information. The sensor layout position information is the sensor layout position information corresponding to the time when the monitoring coverage overlap area of ​​all the monitoring sensors in the fire warning system located in the monitoring area is the smallest and the monitoring coverage area is the largest as represented by the monitoring sensor layout objective function.

9. An electronic device, characterized in that: include: Memory and processor; Wherein, the memory is used to store computer programs; The processor is used to execute the computer program, specifically to implement the monitoring sensor arrangement method for the fire early warning system according to any one of claims 1 to 7.

10. A computer storage medium, characterized in that: Used to store a computer program, which, when executed, is specifically used to implement the monitoring sensor deployment method for a fire warning system as described in any one of claims 1 to 7.

Images