A fire alarm detector arrangement method and system

Abstract

The present invention relates to a method and system for arranging fire alarm detectors, step S1: constructing a full life cycle objective function by combining the equipment one-time investment cost, equipment operation and maintenance cost, and substation equipment power outage loss cost; step S2: using the full life cycle objective function as particle fitness, the fire alarm equipment wiring network entropy function and the arrangement rule function as constraints, and using a particle swarm algorithm for optimization. The present invention can realize the automatic optimization arrangement of fire alarm detectors.

Description

Technical Field

[0001] The invention relates to the field of transformer substation safety, and in particular to a method and system for arranging fire alarm detectors. Background Art

[0002] There is a risk of fire in the operation of substations, such as main transformers, power cable trenches, control cable trenches, cable shafts, main control rooms, secondary equipment rooms, communication rooms, DC cabinet rooms, battery rooms, flammable dielectric capacitor rooms, and distribution equipment rooms at various voltage levels. These different equipment are either arranged in the open air or laid in the cable trenches of substations or arranged in the main control building of substations. The above parts are the most important dangerous points for fires during the specific operation process. Once a fire occurs in the above parts, it will inevitably affect the safe and stable operation of the substation and even the entire power grid, causing huge losses to people's normal life and production, and causing huge economic losses to enterprises.

[0003] As an important subsystem in the intelligent auxiliary monitoring system of substation, the fire alarm system is crucial to reducing and preventing the harm caused by fire and protecting people’s lives and property.

[0004] Fire alarm detectors are important equipment in the substation fire alarm system. Their main function is to detect the occurrence of fire, give timely alarms, and transmit signals to the substation fire alarm host.

[0005] At present, the layout of fire alarm detectors in substations is mainly manually arranged by designers based on design specifications and the general layout drawing of the substation.

[0006] The existing fire alarm detector layout method will cause the following shortcomings:

[0007] 1. The life cycle cost of the entire fire alarm system is too high;

[0008] 2. The anti-interference ability of the entire fire alarm equipment wiring network is poor;

[0009] 3. It is impossible to achieve automatic optimization of the layout of fire alarm detectors. Summary of the invention

[0010] In view of this, an object of the present invention is to provide a fire alarm detector layout method and system based on multi-objective functions to achieve automatic optimization layout of fire alarm detectors.

[0011] The present invention is implemented by the following scheme: A method for arranging fire alarm detectors based on a multi-objective function, comprising:

[0012] The full life cycle objective function is constructed by combining the equipment primary investment cost, equipment operation and maintenance cost, and substation equipment power outage loss cost;

[0013] Taking the whole life cycle objective function value as the particle fitness, the different particle fitnesses corresponding to the different layout samples of fire alarm detectors are determined, and the particle swarm algorithm is used to optimize the particle fitness of the layout scheme of the fire alarm detectors to find the optimal layout scheme of the fire alarm detectors; wherein the optimal layout scheme satisfies the constraints constituted by the entropy function of the fire alarm equipment wiring network and the layout rule function.

[0014] Furthermore, the constructed full life cycle objective function is:

[0015] LCC=C1+C2+C3=f(n1;n2;l) (1)

[0017] C1 is the one-time investment cost of the equipment; C2 is the equipment operation and maintenance cost; C3 is the equipment power outage loss cost;

[0018] n1 is the number of temperature detectors; n2 is the number of smoke detectors; l is the total cable length; Where n = n1 + n2 is the total number of fire alarm detectors, l i Required cable run length for each detector.

[0019] Furthermore, the primary investment cost includes the purchase, installation and laying costs of the equipment;

[0020] C1=n1k1+n2k2+(n1+n2)k3+l(k4+k5)

[0021] k1 is the unit price of temperature detector; k2 is the unit price of smoke detector; k3 is the installation fee of fire alarm detector; k4 is the unit price of cable; k5 is the cost of laying cable per unit length; n1k1+n2k2 is the purchase cost of detector; (n1+n2)k3 is the installation cost of detector; l(k4+k5) is the cost of laying detector.

[0022] Furthermore, the equipment operation and maintenance costs:

[0023] C2=t×k6+t×s×C1

[0024] t is the operating time of the fire alarm detector; t≤20 years k6 is the cost of power loss; s is the proportion of annual maintenance cost to the primary investment cost of the equipment;

[0025] Furthermore, the equipment power outage loss cost includes the power outage cost and repair cost caused by the power outage;

[0026] C3=α×ω×T+λ×γ×m

[0027] α×ω×T is the power outage cost; λ×γ×m is the repair cost; α is the power outage loss per unit of electricity consumed by the user; ω is the power supply interrupted by equipment failure; T is the annual power interruption time of equipment failure; λ is the average number of equipment failures per year;

[0028] γ is the average repair cost of faulty equipment; m is the average repair time of equipment.

[0029] Furthermore, the specific content of the construction constraint condition is:

[0030] The fire alarm equipment wiring network is regarded as a network, the fire alarm detectors are regarded as nodes of the network, and the connections between the fire alarm detectors and between the fire alarm detectors and the fire alarm host are regarded as edges in the complex network;

[0031] The node importance α is defined as follows:

[0032]

[0033] Where: n is the number of nodes in the network, is the average shortest path between nodes, dmin, ij is the shortest distance between any two nodes i and j in the network expressed by the number of edges, V is the set of all nodes in the network; the edge betweenness is defined as follows:

[0034]

[0035] Among them, k is the edge number, N ij is the number of shortest paths between any two nodes i and j in the network, is the sum of the shortest paths between any two nodes in the network; N ij (k) is the number of times the shortest path between any two nodes i and j in the network passes through edge k, It is the sum of the number of times the shortest path between any two nodes in the network passes through edge k;

[0036] Taking node importance and edge betweenness as basic elements, the entropy function of the fire alarm equipment wiring network is constructed:

[0037]

[0038]

[0039] Let f(α ij ,G ij ) is the probability that any two nodes or the edges between them in the network fail, causing the entire network to crash; where, is the average value of the importance of network nodes, G = G k , the total number of edges in the network is m, is the average value of the network edge betweenness;

[0040] The entropy function of the fire alarm equipment wiring network is:

[0041]

[0042] Assume that the coordinates of the projections of two adjacent fire alarm detectors on the horizontal plane are O1(x1, y1) and O2(x2, y2); the protection radius of each fire alarm detector is R, and the layout rule function as a constraint condition is: f(x1, y1, x2, y2) = (x1-x2) 2 +(y1-y2) 2 ≤(2R) 2 .

[0043] Furthermore, the optimization using the particle swarm algorithm described in step S2 specifically includes the following steps:

[0044] The optimization using the particle swarm algorithm described in step S2 specifically includes the following steps:

[0045] Step 1: The two-dimensional point coordinate set formed by discretizing the general layout area of ​​the substation is used as the input of the particle swarm algorithm;

[0046] Step 2: According to the input of the 2D point coordinate set of the general plan, initialize the particles, i.e. the set of random samples of the point coordinates of the fire alarm detectors, and check the connectivity of the topology. If the connectivity is intact, proceed to step 3, otherwise re-initialize;

[0047] Step 3: Iterate the initialized single particle using the full life cycle objective function as the particle fitness;

[0048] Step 4: When the particle evolution reaches the maximum number of iterations or meets the minimum error limit of the fitness value, the optimal particle is found;

[0049] Step 5: Determine whether the optimal particle obtained by iteration satisfies the constraints formed by the network entropy function and the layout rule constraint function;

[0050] Step 6: If not satisfied, the result of this iteration is invalidated; the particles are initialized again, and after initialization, they are different particles, that is, the next particles, and it is determined to start again from step 2; if satisfied, the particle evolution ends, and the optimal particle is output, that is, the automatic optimization layout of the fire alarm detector is completed.

[0051] The present invention provides a fire alarm detector layout device, comprising a full life cycle objective function construction module, a constraint condition construction module and a fire alarm detector automatic optimization layout module; the full life cycle objective function construction module is used to construct a full life cycle objective function; the constraint condition construction module is used to complete constraint condition construction using a fire alarm device wiring network entropy function and a layout rule function as constraint conditions; the fire alarm detector automatic optimization layout module is used to use a particle swarm algorithm to perform optimization to achieve automatic optimization layout of fire alarm detectors.

[0052] The present invention provides a fire alarm detector arrangement system, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor can implement the method steps described above when running the computer program.

[0053] The present invention provides a computer-readable storage medium, on which a computer program that can be executed by a processor is stored. When the processor executes the computer program, the method steps described above are executed.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] (1) The optimal life cycle based on the equipment’s initial investment cost, equipment operation and maintenance cost, and substation equipment power outage loss cost;

[0056] (2) The stability of the fire alarm system equipment wiring network is optimal;

[0057] (3) Meet the equipment layout rules of the fire alarm system;

[0058] Automatic optimization layout of substation fire alarm system equipment. The fire alarm system equipment layout scheme obtained by this method and system is significantly better than the traditional layout method in terms of the entire life cycle of the fire alarm system, the stability of the equipment wiring network, and the layout efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 Schematic diagram of a node according to an embodiment of the present invention.

[0060] Figure 2 Schematic diagram of edge betweenness calculation according to an embodiment of the present invention.

[0061] Figure 3 The particle swarm optimization flow chart of an embodiment of the present invention.

[0062] Figure 4 The figure is a flow chart of a method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0064] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0065] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0066] like Figure 4 As shown, this embodiment provides a method for arranging fire alarm detectors, including:

[0067] From the perspective of the entire life cycle of the equipment, the objective function of the entire life cycle of the fire alarm system is constructed so that the optimal layout plan of the fire alarm system in the entire life cycle can be obtained in the subsequent optimization results;

[0068] The full life cycle theory mainly considers each step of the equipment from planning and design, equipment procurement, to subsequent maintenance and repair, and decommissioning on the basis of ensuring the performance and operational reliability of the equipment itself. It is a management method based on the long-term economic benefits of the equipment to ensure that the equipment achieves the lowest cost throughout its entire life cycle.

[0069] First, we need to construct the basic components of the life cycle objective function to prevent the neglect of certain important cost elements;

[0070] The full life cycle objective function is constructed by combining the equipment primary investment cost, equipment operation and maintenance cost, and substation equipment power outage loss cost;

[0071] Taking the whole life cycle objective function value as the particle fitness, the different particle fitnesses corresponding to the different layout samples of fire alarm detectors are determined, and the particle swarm algorithm is used to optimize the particle fitness of the layout scheme of the fire alarm detectors to find the optimal layout scheme of the fire alarm detectors; wherein the optimal layout scheme satisfies the constraints constituted by the entropy function of the fire alarm equipment wiring network and the layout rule function.

[0072] In this embodiment, a full life cycle objective function is constructed:

[0073] The whole life cycle cost is composed of the equipment one-time investment cost, equipment operation and maintenance cost, and equipment power outage loss cost; the constructed whole life cycle objective function is formula (1):

[0074] LCC=C1+C2+C3=f(n1;n2;l) (1)

[0075] C1 is the one-time investment cost of the equipment; C2 is the equipment operation and maintenance cost; C3 is the equipment power outage loss cost;

[0076] n1 is the number of temperature detectors; n2 is the number of smoke detectors; l is the total cable length; Where n = n1 + n2 is the total number of fire alarm detectors, l i Required cable run length for each detector.

[0077] In this embodiment, the one-time investment cost includes the purchase fee, installation fee and laying fee of the equipment;

[0078] C1=n1k1+n2k2+(n1+n2)k3+l(k4+k5)

[0079] k1 is the unit price of temperature detector; k2 is the unit price of smoke detector; k3 is the installation fee of fire alarm detector; k4 is the unit price of cable; k5 is the cost of laying cable per unit length; n1k1+n2k2 is the purchase cost of detector; (n1+n2)k3 is the installation cost of detector; l(k4+k5) is the cost of laying detector.

[0080] In this embodiment, the equipment operation and maintenance cost refers to the cost incurred during the period of inspection and maintenance required to ensure safe operation of the equipment after it is put into operation.

[0081] The operation and maintenance costs include the operation and maintenance costs of equipment inspection, fault elimination and maintenance, as well as the electricity costs consumed by the equipment.

[0082] C2=t×k6+t×s×C1

[0083] t is the operating time of the fire alarm detector; t≤20 years k6 is the cost of power loss; s is the proportion of annual maintenance cost to the primary investment cost of the equipment;

[0084] In this embodiment, currently, the substation is generally unattended and requires regular inspections by special personnel. Once a fault that is not conducive to the normal operation of the equipment occurs, it will affect the normal operation of the power distribution system. If the fire alarm detection equipment is not adequately configured and the safety hazards cannot be timely known and immediately handled, the electrical equipment may be damaged, resulting in serious consequences.

[0085] Equipment power outage loss costs include power outage costs and repair costs caused by power outage;

[0086] C3=α×ω×T+λ×γ×m

[0087] α×ω×T is the power outage cost; λ×γ×m is the repair cost; α is the power outage loss per unit of electricity consumed by the user; ω is the power supply interrupted by equipment failure; T is the annual power interruption time of equipment failure; λ is the average number of equipment failures per year;

[0088] γ is the average repair cost of faulty equipment; m is the average repair time of equipment.

[0089] In this embodiment, in a conventional 220kV hub substation fire alarm system, more than 100 fire alarm detectors are usually deployed. Therefore, the huge fire alarm equipment wiring network can be regarded as a complex network. The fire alarm detectors can be regarded as nodes of the complex network. The connections between the fire alarm detectors and between the fire alarm detectors and the fire alarm host can be regarded as edges in the complex network.

[0090] Based on the complex network theory, a network stability evaluation objective function is constructed so that the optimal video surveillance system layout plan can be obtained in the subsequent optimization results.

[0091] In this embodiment, the specific contents of the constraint conditions are:

[0092] The fire alarm equipment wiring network is regarded as a network, the fire alarm detectors are regarded as nodes of the network, and the connections between the fire alarm detectors and between the fire alarm detectors and the fire alarm host are regarded as edges in the complex network;

[0093] Calculate node importance: Node importance is a basic parameter for studying complex network topology. It is used to describe the direct influence of a node in the network. Its value is the number of nodes directly connected to the node.

[0094] Below Figure 1 Taking the network shown as an example, the node importance of node 9 is 8.

[0095] The node importance α is defined as follows:

[0096]

[0097] Where: n is the number of nodes in the network, is the average shortest path between nodes, dmin,ij is the shortest distance between any two nodes i and j in the network expressed by the number of edges, V is the set of all nodes in the network; from the definition, it can be seen that if the node is in a hub position in the network, its importance is higher.

[0098] The betweenness of an edge is also a basic parameter for studying the topological structure of a complex network. It refers to the number of times the edge is passed by the shortest path between all nodes in the network, which can reflect the importance of the edge to the network.

[0099] The edge betweenness is defined as follows:

[0100]

[0101] Among them, k is the edge number, N ij is the number of shortest paths between any two nodes i and j in the network, is the sum of the shortest paths between any two nodes in the network; N ij (k) is the number of times the shortest path between any two nodes i and j in the network passes through edge k, is the sum of the number of times the shortest path between any two nodes in the network passes through edge k; Figure 2 As shown;

[0102] When pursuing the optimal layout, we do not want the importance of a node in the network to be much higher than other nodes, so that once a key node is damaged, it will bring immeasurable consequences to the entire network. Similarly, we do not want the betweenness of a certain edge in the network to be much higher than other edges, so that once a key edge is damaged, it will bring immeasurable consequences to the entire network.

[0103] Taking node importance and edge betweenness as basic elements, the entropy function of the fire alarm equipment wiring network is constructed:

[0104]

[0105]

[0106] Let f(α ij ,G ij ) is the probability that any two nodes or the edges between them in the network fail, causing the entire network to crash; where, is the average value of the importance of network nodes, G = G k , the total number of edges in the network is m, is the average value of the network edge betweenness;

[0107] The entropy function of the fire alarm equipment wiring network is:

[0108]

[0109] The smaller the value of the network entropy function, the more stable the network.

[0110] Assume that the coordinates of the projections of two adjacent fire alarm detectors on the horizontal plane are O1(x1, y1) and O2(x2, y2); the protection radius of each fire alarm detector is R, and the layout rule function as a constraint condition is: f(x1, y1, x2, y2) = (x1-x2)2 +(y1-y2) 2 ≤(2R) 2 .

[0111] In this embodiment, the full life cycle objective function is used as the particle fitness, the anti-interference and layout rule functions of the fire alarm equipment wiring network are used as constraints, and the particle swarm algorithm is used for optimization to obtain an automatic optimization layout method for fire alarm detectors.

[0112] like Figure 3 As shown, the optimization using the particle swarm algorithm in step S2 specifically includes the following steps:

[0113] Step 1: The two-dimensional point coordinate set formed by discretizing the general layout area of ​​the substation is used as the input of the particle swarm algorithm;

[0114] Step 2: According to the input of the 2D point coordinate set of the general plan, initialize the particles, i.e. the set of random samples of the point coordinates of the fire alarm detectors, and check the connectivity of the topology. If the connectivity is intact, proceed to step 3, otherwise re-initialize;

[0115] Step 3: Iterate the initialized particles using the full life cycle objective function as particle fitness;

[0116] Step 4: When the particle evolution reaches the maximum number of iterations or meets the minimum error limit of the fitness value, the optimal particle is found;

[0117] Step 5: Determine whether the optimal particle obtained by iteration satisfies the constraints formed by the network entropy function and the layout rule constraint function;

[0118] Step 6: If not satisfied, the result of this iteration is invalidated; the particles are initialized again, and after initialization, they are different particles, that is, the next particles, and it is determined to start again from step 2; if satisfied, the particle evolution ends, and the optimal particle is output, that is, the automatic optimization layout of the fire alarm detector is completed.

[0119] The present embodiment provides a fire alarm detector layout device, including a full life cycle objective function construction module, a constraint condition construction module and a fire alarm detector automatic optimization layout module; the full life cycle objective function construction module is used to construct a full life cycle objective function; the constraint condition construction module is used to complete the constraint condition construction by taking the fire alarm equipment wiring network entropy function and the layout rule function as constraints; the fire alarm detector automatic optimization layout module is used to realize the automatic optimization layout of fire alarm detectors by using a particle swarm algorithm for optimization.

[0120] This embodiment provides a fire alarm detector deployment system, including a memory and a processor. The memory stores a computer program, and the processor can implement the method steps described above when running the computer program.

[0121] This embodiment further provides a computer-readable storage medium, on which a computer program that can be executed by a processor is stored. When the processor executes the computer program, the method steps described above are executed.

[0122] Preferably, this embodiment combines the equipment primary investment cost, equipment operation and maintenance cost, and substation equipment power outage loss cost to construct a full life cycle objective function;

[0123] The whole life cycle objective function value is taken as the particle fitness. Different fire alarm detector layout samples correspond to different particle fitness. The sample with the best particle fitness must meet the constraints composed of the fire alarm equipment wiring network entropy function and the layout rule function. The particle swarm algorithm is used to optimize the layout of the fire alarm detector and find the optimal layout sample of the fire alarm detector as the optimal layout of the fire alarm detector.

[0124] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0125] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0126] The above description is only a preferred embodiment of the present invention. All equivalent changes and modifications made according to the scope of the patent application of the present invention should fall within the scope of the present invention.

Claims

1. A method for arranging fire alarm detectors, characterized in that: include: The full life cycle objective function is constructed by combining the equipment primary investment cost, equipment operation and maintenance cost, and substation equipment power outage loss cost; Taking the value of the full life cycle objective function as the particle fitness, determine the different particle fitness corresponding to the different fire alarm detector layout samples, use the particle swarm algorithm to optimize the particle fitness of the fire alarm detector layout scheme, and find the optimal layout scheme of the fire alarm detector; wherein the optimal layout scheme satisfies the constraints formed by the fire alarm equipment wiring network entropy function and the layout rule function; The specific contents of the constraints are: The wiring of the fire alarm equipment is regarded as a network, the fire alarm detectors are regarded as nodes of the network, and the connections between the fire alarm detectors and between the fire alarm detectors and the fire alarm host are regarded as edges in the network; The node importance α is defined as follows: Where: n is the number of nodes in the network, is the average shortest path d between nodes min,ij is the shortest distance between any two nodes i and j in the network expressed by the number of edges, and V is the set of all nodes in the network; The edge betweenness is defined as follows: Among them, k is the edge number, N ij is the number of shortest paths between any two nodes i and j in the network, is the sum of the shortest paths between any two nodes in the network; N ij (k) is the number of times the shortest path between any two nodes i and j in the network passes through edge k, It is the sum of the number of times the shortest path between any two nodes in the network passes through edge k; Taking node importance and edge betweenness as basic elements, the entropy function of the fire alarm equipment wiring network is constructed: f(α ij ,G ij ) is the probability that any two nodes or the edges between them in the network fail, causing the entire network to crash; where, is the average value of the importance of network nodes, G = G k , the total number of edges in the network is m, is the average value of the network edge betweenness; The entropy function of the fire alarm equipment wiring network is: Assume that the coordinates of the projections of two adjacent fire alarm detectors on the horizontal plane are O1(x1, y1) and O2(x2, y2) respectively; the protection radius of each fire alarm detector is R, and the layout rule function as a constraint condition is: f(x1, y1, x2, y2) = (x1-x2) 2 +(y1-y2) 2 ≤(2R) 2 .

2. A method for arranging fire alarm detectors according to claim 1, characterized in that: The constructed full life cycle objective function is: LCC=C1+C2+C3=f(n1;n2;l)(1) C1 is the one-time investment cost of the equipment; C2 is the equipment operation and maintenance cost; C3 is the equipment power outage loss cost; n1 is the number of temperature detectors; n2 is the number of smoke detectors; l is the total cable length; Where n = n1 + n2 is the total number of fire alarm detectors, l i Required cable run length for each detector.

3. A method for arranging fire alarm detectors according to claim 2, characterized in that: The one-time investment cost includes the purchase, installation and laying costs of the equipment; C1=n1k1+n2k2+(n1+n2)k3+l(k4+k5) k1 is the unit price of the heat detector; k2 is the unit price of the smoke detector; k3 is the installation fee of the fire alarm detector; k4 is the unit price of the cable; k5 is the cable laying fee per unit length; n1k1+n2k2 is the purchase cost of the detector; (n1+n2)k3 is the installation cost of the detector; l(k4+k5) is the laying cost of the detector.

4. A method for arranging fire alarm detectors according to claim 2, characterized in that: Equipment operation and maintenance cost: C2=t×k6+t×s×C1 t is the operating time of the fire alarm detector, t≤20 years; k6 is the power loss cost; s is the proportion of annual maintenance cost to the equipment's primary investment cost.

5. A method for arranging fire alarm detectors according to claim 2, characterized in that: Equipment power outage loss costs include power outage costs and repair costs caused by power outage; C3=α×ω×T+λ×γ×m α×ω×T is the power outage cost; λ×γ×m is the repair cost; α is the power outage loss per unit of electricity consumed by the user; ω is the power supply interrupted by equipment failure; T is the annual power supply interruption time of equipment failure; λ is the average annual number of equipment failures; γ is the average repair cost of faulty equipment; and m is the average equipment repair time.

6. A method for arranging fire alarm detectors according to claim 1, characterized in that: The optimization using the particle swarm algorithm described in step S2 specifically includes the following steps: Step 1: The two-dimensional point coordinate set formed by discretizing the general layout area of ​​the substation is used as the input of the particle swarm algorithm; Step 2: According to the input of the 2D point coordinate set of the general plan, initialize the particles, i.e. the set of random samples of the point coordinates of the fire alarm detectors, and check the connectivity of the topology. If the connectivity is intact, proceed to step 3, otherwise re-initialize; Step 3: Iterate the initialized single particle using the full life cycle objective function as the particle fitness; Step 4: When the particle evolution reaches the maximum number of iterations or meets the minimum error limit of the fitness value, the optimal particle is found; Step 5: Determine whether the optimal particle obtained by iteration satisfies the constraints formed by the network entropy function and the layout rule constraint function; Step 6: If not satisfied, the result of this iteration is invalidated; the particles are initialized again, and after initialization, they are different particles, that is, the next particles, and it is determined to start again from step 2; if satisfied, the particle evolution ends, and the optimal particle is output, that is, the automatic optimization layout of the fire alarm detector is completed.

7. A fire alarm detector deployment system, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the memory, and the processor can implement the method according to any one of claims 1 to 6 when running the computer program.

8. A computer-readable storage medium, characterized in that: A computer program that can be executed by a processor is stored thereon, and when the processor executes the computer program, the method as described in any one of claims 1 to 6 is executed.

Images