Fire-fighting equipment intelligent management system and method based on Internet of Things

Abstract

The invention discloses a fire-fighting equipment intelligent management system and method based on Internet of Things, and relates to the technical field of fire-fighting management. The method comprises the steps of obtaining a loss path and loss points and loss sections thereof, calculating on-way loss values and elevation loss values of all the loss sections on the spraying path, constructing a digital twin model of the fire-fighting spraying system, obtaining a loss parameter set of all the loss points, constructing a loss evaluation model, and outputting local loss values of all the loss points on the spraying path. The total lift of the spraying path is calculated, the most disadvantageous spraying head is selected, and whether the pressure value of the most disadvantageous spraying head is within the working pressure range or not is judged so that the rotating speed of the fire pump can be regulated and controlled till the pressure value of the most disadvantageous spraying head is within the working pressure range; under the condition that the working pressure range of each spray head is met, a flexible regulation and control mechanism can be realized for the fire pump, and the working energy consumption can be reduced.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of fire management, in particular to a fire-fighting equipment intelligent management system based on Internet of Things and a method thereof. BACKGROUND

[0002] The fire-fighting spray system is a fire-fighting facility integrating water supply, control, alarm and spraying, which can automatically spray water to extinguish fire and send an alarm signal when a fire breaks out, and is very effective for controlling and extinguishing an initial fire. The common fire-fighting spray system is a wet type, in which the inside of the pipe network is kept full of water, and the spraying can be performed in time when a fire breaks out. In order to meet the working pressure range of each spray head, the traditional water supply method is mostly to meet the total lift of the farthest or highest spray head by using a fire-fighting pump.

[0003] However, in the actual application scenario, on the one hand, the total lift of the farthest or highest spray head is not always the largest, which leads to the fact that the water supply capacity of the fire-fighting pump may not meet the actual demand, and on the other hand, the spray head performing the spraying work is not always the farthest or highest spray head, which leads to the fact that the water supply capacity provided by the fire-fighting pump may exceed the actual demand. Therefore, the prior art lacks a method capable of dynamically regulating and controlling the fire-fighting pump according to the actual demand of the fire-fighting spray system. SUMMARY

[0004] The purpose of the application is to provide a fire-fighting equipment intelligent management system based on Internet of Things and a method thereof, which can meet the working pressure range of each spray head, realize a flexible regulation and control mechanism for the fire-fighting pump and reduce the working energy consumption.

[0005] The purpose of the application can be achieved by the following technical solutions: in the first aspect, a fire-fighting equipment intelligent management method based on Internet of Things, comprising the following steps:

[0006] acquiring collected data, equipment information and historical spraying data at each fire-fighting equipment in a fire-fighting spray system;

[0007] acquiring a shortest path through which water flows from the fire-fighting pump to the spray head as a spraying path, and acquiring each pipe fitting on the spraying path as a loss point and a pipeline between adjacent loss points as a loss section;

[0008] calculating the along-path loss value and the elevation loss value of each loss section on the spraying path according to the collected data and the equipment information;

[0009] constructing a digital twin model of the fire-fighting spray system according to the equipment information and the historical spraying data, and acquiring a loss parameter set of each loss point in the digital twin model;

[0010] construct a loss evaluation model according to the loss parameter set, and output a local loss value of each loss point on the spray path by combining the acquisition data and the equipment information by using the loss evaluation model;

[0011] calculate a total head of the spray path according to the along-path loss value, the elevation loss value, the local loss value, and the equipment information, and guide a spray head of a spray path with the highest total head as the most unfavorable spray head;

[0012] determine whether the pressure value of the most unfavorable spray head is within its working pressure range, if yes, keep the rotating speed of the fire water pump unchanged, and if not, regulate the rotating speed of the fire water pump until the pressure value of the most unfavorable spray head is within its working pressure range.

[0013] In a second aspect, the fire-fighting equipment intelligent management system based on the Internet of Things comprises the following modules:

[0014] a data acquisition module, configured to acquire acquisition data, equipment information, and historical spray data at each fire-fighting equipment in a fire-fighting spray system;

[0015] a path division module, configured to acquire a shortest path through which water flows from a fire water pump to a spray head and take the shortest path as a spray path, take each pipe on the spray path as a loss point, and take a pipeline between adjacent loss points as a loss section;

[0016] a loss calculation module, configured to calculate an along-path loss value and an elevation loss value of each loss section on the spray path according to the acquisition data and the equipment information;

[0017] a digital twin module, configured to construct a digital twin model of the fire-fighting spray system according to the equipment information and the historical spray data, and acquire a loss parameter set of each loss point in the digital twin model;

[0018] a loss evaluation module, configured to construct a loss evaluation model according to the loss parameter set, and output a local loss value of each loss point on the spray path by combining the acquisition data and the equipment information by using the loss evaluation model;

[0019] a head calculation module, configured to calculate a total head of the spray path according to the along-path loss value, the elevation loss value, the local loss value, and the equipment information, and guide a spray head of a spray path with the highest total head as the most unfavorable spray head;

[0020] a water pump regulation module, configured to determine whether the pressure value of the most unfavorable spray head is within its working pressure range, if yes, keep the rotating speed of the fire water pump unchanged, and if not, regulate the rotating speed of the fire water pump until the pressure value of the most unfavorable spray head is within its working pressure range.

[0021] Thirdly, a computer storage medium stores computer-executable instructions, which, when executed, implement the Internet of Things-based intelligent management method for fire-fighting equipment described in the first aspect.

[0022] Compared with the prior art, the beneficial effects of this application are:

[0023] This application obtains the spray path of each working sprinkler head and sequentially obtains the friction loss value, elevation loss value, and local loss value of each loss point along each loss section according to the water flow direction. Combined with the working pressure range of the corresponding sprinkler head, the total head of different spray paths can be accurately obtained, and then the most unfavorable sprinkler head can be identified. By dynamically adjusting the fire pump according to the real-time status of the most unfavorable sprinkler head, a flexible control mechanism for the fire pump can be achieved while meeting the working pressure range of each sprinkler head, and the working energy consumption can be reduced. Attached Figure Description

[0024] Figure 1 This is a schematic diagram illustrating the steps of the IoT-based intelligent management method for fire-fighting equipment according to this application;

[0025] Figure 2 This is a schematic diagram of the modules of the IoT-based intelligent management system for fire-fighting equipment in this application. Detailed Implementation

[0026] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. The components described and shown in the accompanying drawings can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but only to illustrate selected embodiments of this application.

[0027] Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this application. It should be noted that similar reference numerals and letters in the following figures indicate similar items. Therefore, once an item has been defined in one figure, it does not need to be further defined and explained in subsequent figures. The terms "first", "second", etc. are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0028] During the operation of traditional fire sprinkler systems, the dynamic changes in the pipe network topology and the complex hydraulic coupling effect generated by the coordinated operation of multiple sprinkler heads cause the total head demand of the system to exhibit nonlinear fluctuation characteristics. The statically preset farthest or highest sprinkler head cannot accurately reflect the maximum head demand under actual working conditions, resulting in a mismatch between the output power of the fire pump and the actual system resistance characteristics. This mismatch is particularly significant in scenarios with complex pipe network branch structures and variable sprinkler head opening and closing combinations, directly affecting the stability of the system water supply pressure and energy efficiency optimization.

[0029] In fire sprinkler systems of commercial complexes with multi-level branch pipe networks, when a fire occurs on a middle floor, the water flow path needs to pass through multiple tees, elbows, valves, and other pipe fittings. Traditional methods calculate the total head based on the sprinkler path of the farthest or highest sprinkler head without considering the dynamic changes in the local resistance coefficient under the diversion state. In actual operation, the turbulence effect generated by the water flow at the diversion node causes the local head loss value to exceed the range of the preset calculation model, resulting in the identification error of the most unfavorable sprinkler head exceeding the allowable threshold. If the fire pump maintains a constant speed at this time, it may cause insufficient pressure at the far-end sprinkler head and excessive pressure at the near end, which not only affects the fire extinguishing effect but also generates ineffective energy consumption.

[0030] If the above problems are not resolved, the system will be in an over-pressure or under-pressure state for a long time. Over-pressure conditions accelerate the aging of pipe fitting sealing structures and increase the risk of pipeline leakage. Under-pressure conditions result in insufficient sprinkler intensity, delaying fire control. At the same time, the fire pumps will continue to operate outside the optimal efficiency range, causing energy waste and increased equipment wear. In emergency situations, such control errors may trigger a chain reaction, leading to system response delays or failure of critical nodes, seriously affecting the reliability of building fire safety.

[0031] Faced with the above problems, this application first considers how to dynamically identify the path of maximum head demand under actual working conditions. Traditional static path selection methods cannot adapt to the dynamic changes in pipeline topology, resulting in deviations in head calculation. To address this, an attempt was made to establish a dynamic path update mechanism by real-time monitoring of water flow path characteristics. However, this method faces implementation obstacles such as high sensor deployment costs and large data processing delays. Instead, the relationship between pipeline structural characteristics and hydraulic loss distribution was studied. It was found that key resistance points are concentrated at pipe joints. The application proposes to use pipe joint nodes as discretized loss calculation units and to calculate the total head by superimposing path losses.

[0032] Therefore, this application proposes an intelligent management method for fire-fighting equipment based on the Internet of Things, such as... Figure 1 As shown, it includes the following steps:

[0033] Acquire data, equipment information, and historical sprinkler data from each fire-fighting equipment location in the fire sprinkler system;

[0034] Obtain the shortest path that the water flows from the fire pump to the sprinkler head and use it as the sprinkler path. Take each pipe fitting on the sprinkler path as a loss point and the pipe between adjacent loss points as a loss segment.

[0035] Calculate the friction loss and elevation loss values ​​for each loss segment along the spray path based on the collected data and the equipment information.

[0036] A digital twin model of the fire sprinkler system is constructed based on the equipment information and the historical sprinkler data, and the set of loss parameters for each loss point is obtained in the digital twin model.

[0037] A loss assessment model is constructed based on the set of loss parameters. The loss assessment model is then used in conjunction with the collected data and the equipment information to output the local loss value of each loss point on the spraying path.

[0038] The total head of the spray path is calculated based on the friction loss value, the elevation loss value, the local loss value, and the equipment information. The spray head guided by the spray path with the highest total head is taken as the most unfavorable spray head.

[0039] Determine whether the pressure value of the most unfavorable sprinkler head is within its working pressure range. If so, keep the speed of the fire pump constant. If not, adjust the speed of the fire pump until the pressure value of the most unfavorable sprinkler head is within its working pressure range.

[0040] The core innovation of this application lies in the construction of a dynamic head control mechanism that integrates digital twins and machine learning. By identifying the total head demand of the most unfavorable sprinkler point in real time, a fire pump speed adaptive adjustment system based on pressure closed loop is established, breaking through the traditional fixed head design mode and realizing the precise matching of water supply capacity and fire protection needs.

[0041] The working process and principle of this application are as follows: First, the operation data, equipment information and historical sprinkler data of each fire-fighting equipment in the fire sprinkler system are collected in real time through Internet of Things technology. These data provide the basis for subsequent analysis.

[0042] Next, the shortest path of water flow from the fire pump to the sprinkler head is determined as the sprinkler path. On this sprinkler path, the pipe connection is set as the loss point, and the pipe between adjacent loss points is set as the loss section. This division method can accurately locate the calculation unit of hydraulic loss.

[0043] Then, based on the collected data, the friction loss and elevation loss values ​​for each loss section are calculated. The friction loss value reflects the head loss caused by pipeline friction, while the elevation loss value reflects the influence of gravity.

[0044] At the same time, a digital twin model of the fire sprinkler system is constructed using equipment information and historical sprinkler data. In the digital twin model, the set of loss parameters for each loss point is obtained, including multi-dimensional parameters such as pressure, flow velocity, and elevation.

[0045] A loss assessment model is constructed based on the acquired set of loss parameters. This model uses a convolutional neural network, which can effectively handle nonlinear relationships such as the geometric features of pipe fittings and the conveying state. By combining the loss assessment model with real-time collected data, the local loss values ​​of each loss point on the spray path can be output.

[0046] By comprehensively considering the head loss value, elevation loss value, local loss value and equipment information, the total head of each spray path is calculated, and the spray head corresponding to the spray path with the highest total head is determined as the most unfavorable spray head.

[0047] Finally, determine whether the pressure value of the most unfavorable sprinkler head is within its working pressure range. If it is within the working pressure range, keep the fire pump speed unchanged. If it is not within the working pressure range, adjust the fire pump speed until the pressure value of the most unfavorable sprinkler head is within its working pressure range.

[0048] This dynamic control mechanism can adjust the water pump output according to the real-time status of the fire sprinkler system, ensuring that it can maintain optimal performance under various operating conditions.

[0049] It should be further explained that, in the specific implementation process, the process of acquiring data, equipment information, and historical sprinkler data from various fire-fighting equipment locations within the fire sprinkler system includes:

[0050] The fire sprinkler system is a fire protection facility that integrates water supply, control, alarm, and sprinkler functions. It can automatically spray water to extinguish fires and issue alarm signals when a fire occurs. It is very effective in controlling and extinguishing initial fires. The fire equipment refers to the various components that make up the fire sprinkler system.

[0051] It mainly includes water tanks, fire pumps, pipe networks, wet alarm valves, sprinkler heads, water flow indicators, pressure switches, and hydraulic alarm bells. The pipe network includes pipes (such as horizontal main pipes, risers, distribution pipes, and distribution branch pipes) and pipe fittings (such as elbows, tees, and valves).

[0052] An operation data acquisition unit is deployed at the fire pump to collect real-time operating data of the fire pump, including power, speed, start / stop status, running time, and bearing temperature.

[0053] Pressure acquisition units, velocity acquisition units, and flow acquisition units are deployed at each sprinkler head and at each pipe and fitting in the pipe network to obtain the pressure, velocity, and flow values ​​at the corresponding sprinkler head and at different locations in the pipe network.

[0054] The operation acquisition unit, pressure acquisition unit, flow rate acquisition unit, and flow rate acquisition unit are all acquisition units, and the acquired data includes operation data, pressure value, flow rate value, and flow rate value.

[0055] The equipment information refers to the inherent, non-changing attribute data of each fire-fighting equipment, which can reflect the distribution, physical structure, and performance indicators of each fire-fighting equipment, including the installation location, structural dimensions, and geometric size of each fire-fighting equipment.

[0056] Specifically, the equipment information for fire pumps includes rated power, rated flow rate, and rated head; the equipment information for pipelines includes the inner diameter, material, length, and direction of the pipelines; and the equipment information for sprinkler heads includes the working pressure range and working flow rate range.

[0057] The historical sprinkler data refers to the data collected by each acquisition unit at each fire-fighting equipment location during a single sprinkler event. The sprinkler event refers to the process from the start to the end of the fire sprinkler system during a previous fire.

[0058] It should be further explained that, in the specific implementation process, the process of calculating the friction loss value and elevation loss value of each loss segment on the spray path based on the collected data and the equipment information includes:

[0059] When the temperature sensing element of the sprinkler head is heated and deforms and starts spraying water, it is determined that a fire has occurred, and the shortest path through which the water is transported from the fire pump to the corresponding sprinkler head is taken as its spray path.

[0060] If there is only one sprinkler head spraying water, there is only one spray path. If there are multiple sprinkler heads spraying water, the spray path of the corresponding sprinkler head is obtained. A spray path often contains multiple loss points and multiple loss segments at the same time.

[0061] Obtain the friction loss value of each loss segment along a single spray path. and elevation loss value The friction loss value is used to reflect the head loss along the friction path, and the elevation loss value is used to reflect the hydrostatic head.

[0062] Where L is the length of the corresponding loss section, Q is the flow rate at the corresponding loss section, C is the pipe roughness of the corresponding loss section, which is related to the pipe material and ranges from 80 to 120, and d is the inner diameter of the corresponding loss section. This corresponds to the elevation difference between the two ends of the loss segment, and is usually a positive value.

[0063] It should be further explained that, in the specific implementation process, the process of constructing a digital twin model of the fire sprinkler system based on the equipment information and the historical sprinkler data includes:

[0064] Using 3D modeling tools, a physical model of the fire sprinkler system is constructed based on the equipment information of each fire-fighting equipment. Simulation software is then used to simulate the working process of each fire-fighting equipment based on historical sprinkler data from previous sprinkler events, in addition to the physical model, to obtain the corresponding simulation model.

[0065] When the data collected at each acquisition unit in the simulation model is the same as the historical sprinkler data of the corresponding acquisition unit at the corresponding time, the simulation model at this time is used as the digital twin model of the corresponding sprinkler event, and the digital twin model of the latest sprinkler event is used as the latest digital twin model of the fire sprinkler system.

[0066] It should be further explained that, in the specific implementation process, the process of obtaining the set of loss parameters for each loss point in the digital twin model includes:

[0067] In a fire sprinkler system, there are at least three types of energy losses when water is transported from the fire pump to the sprinkler head: first, friction head loss (the energy consumed to overcome long-distance friction in the pipeline); second, local head loss (the energy consumed to overcome local resistance in the pipe fittings); and third, hydrostatic head (the work done to raise the water to a certain height).

[0068] Starting from the fire pump and ending at each sprinkler head, each pipe fitting is marked as a loss point, the pipe between two adjacent loss points is marked as a loss segment, and each loss segment connected to a single loss point in the opposite direction of water flow is taken as its preceding loss segment, and each loss segment connected to a single loss point in the same direction of water flow is taken as its following loss segment.

[0069] In the latest digital twin model, the speed of the fire pump is kept constant at an arbitrary value. The pressure, flow velocity and elevation values ​​of each loss point at each front and rear measuring point at the same time are obtained. The front and rear measuring points are located on the front and rear loss segments of the corresponding loss point, respectively, at a distance of 3-5 times the inner diameter of the loss point.

[0070] If the transport state of the loss point is unidirectional (the loss point has a front loss section and a rear loss section), then obtain its first-class loss value. ;

[0071] If the transport status of the loss point is split (this loss point has one front loss segment and multiple rear loss segments), then its second type of loss value is obtained. ;

[0072] If the transport status of the loss point is merging (this loss point has multiple upstream loss sections and one downstream loss section), then obtain its three types of loss values. ;

[0073] If the transport state of the loss point is mixed flow (this loss point has multiple front loss sections and multiple rear loss sections), then its four types of loss values ​​are obtained. ;

[0074] The first, second, third, and fourth types of loss values ​​all belong to local loss values, which are used to reflect local head loss, where P q P h These are the pressure values ​​at the preceding and following measurement points, respectively, v. q v h These are the flow velocity values ​​at the preceding and following measurement points, respectively, representing the loss point. These are the elevation differences of the loss points under the corresponding conveying conditions;

[0075] z q z h P represents the elevation values ​​at the preceding and following measurement points of the loss point, respectively. q0 P h0 v represents the average pressure values ​​at multiple preceding and subsequent measuring points, respectively, at the point of loss. q0 v h0 The average flow velocity values ​​z at multiple preceding and following measurement points of the loss point are respectively. q0 z h0 These are the average elevation values ​​at multiple pre-measurement points and multiple post-measurement points of the loss point, respectively. For the density of water, It is the acceleration due to gravity;

[0076] The local loss value of a single loss point at the same time, the pressure value (or average pressure value) and flow velocity value (or average flow velocity value) at the preceding measuring point, the elevation difference (or average elevation difference) between the preceding and following measuring points, and the geometric characteristics and conveying status of the pipe fitting corresponding to the loss point are all included in the loss parameter set of the loss point at the corresponding time.

[0077] The geometric features refer to parameters used to reflect the physical form of the pipe fitting corresponding to the loss point. Specifically, the geometric features of an elbow are the elbow angle, the geometric features of a tee are the tee flow splitting ratio, and the geometric features of a valve are the valve opening degree. The conveying states include single flow, split flow, merging flow, and mixed flow.

[0078] Using the same method, the loss parameter sets of each loss point at the same time were obtained. In the latest digital twin model, the speed of the fire pump was adjusted to other values ​​and then kept constant. The loss parameter sets of each loss point at different times were obtained repeatedly.

[0079] It should be further explained that, in the specific implementation process, the process of constructing a loss assessment model based on the set of loss parameters, and using the loss assessment model in conjunction with the collected data and the equipment information to output the local loss values ​​of each loss point on the spraying path includes:

[0080] Based on the different geometric features, transport status, pressure value (or average pressure value), flow velocity value (or average flow velocity value), elevation difference (or average elevation difference) and their corresponding local loss values ​​within the acquired set of various loss parameters, a loss assessment set is generated and divided into a training set and a test set.

[0081] Convolutional neural networks are constructed by using different geometric features, transport states, pressure values ​​(or average pressure values), flow velocity values ​​(or average flow velocity values), and elevation differences (or average elevation differences) in the training set as input data for the convolutional neural network, and the corresponding local loss values ​​in the training set as output data for the convolutional neural network. The initial convolutional neural network is obtained by training the convolutional neural network using the training set.

[0082] The initial convolutional neural network is validated using a test set, and the initial convolutional neural network whose output is less than or equal to the preset test error threshold is used as the corresponding loss evaluation model.

[0083] The pressure value (or average pressure value), flow velocity value (or average flow velocity value), elevation difference (or average elevation difference) between the preceding and following measuring points, geometric characteristics and conveying status of the pipe fitting corresponding to each loss point at the current moment are input into the loss assessment model to obtain the local loss value of each loss point.

[0084] It should be further explained that, in the specific implementation process, the process of calculating the total head of the spray path based on the friction loss value, the elevation loss value, the local loss value, and the equipment information includes:

[0085] If there is only one spray path, the spray head it leads to is taken as the most unfavorable spray head. If there are multiple spray paths, the friction loss value and elevation loss value at each loss segment on each spray path at the current moment are obtained according to the water flow direction, as well as the local loss value at each loss point.

[0086] The sum of the local loss values ​​at each loss point, the friction loss values ​​along the path, and the elevation loss values ​​at each loss segment along a single spray path at the current moment is taken as the total loss value S of the spray path. z And combined with the working pressure range of the spray head guided by the spray path [P] min P max The total head is obtained from the intermediate value P. ;

[0087] Wherein, the intermediate value The working pressure range refers to the range of pressure that the sprinkler head needs to maintain in order to achieve its designed fire extinguishing effect. The total head of each sprinkler path is obtained using the same method, and the sprinkler head guided by the sprinkler path with the highest total head is taken as the most unfavorable sprinkler head.

[0088] It should be further explained that, in the specific implementation process, the process of determining whether the pressure value of the most unfavorable sprinkler head is within its working pressure range includes:

[0089] The real-time pressure value P of the most unfavorable sprinkler head at the current moment. t Its working pressure range [P] min P max Compare, if P min ≤P t ≤P max If the pressure value of the most unfavorable sprinkler head is within its working pressure range, then mark it as a normal pressure state, determine that the pressure value of the sprinkler head is within its working pressure range, and keep the speed of the fire pump constant.

[0090] If P t <P min If the pressure value of the most unfavorable sprinkler head is not within its operating pressure range, mark it as a low-pressure state. Increase the speed of the fire pump until the pressure value of the most unfavorable sprinkler head is within its operating pressure range. If P t >P max If the pressure value of the most unfavorable sprinkler head is not within its working pressure range, then the speed of the fire pump is reduced until the pressure value of the most unfavorable sprinkler head is within its working pressure range.

[0091] In the above-mentioned technical solution of this application, an intelligent management method for fire-fighting equipment based on the Internet of Things is provided for dynamically controlling the speed of fire pumps. However, in the process of method execution, there is a lack of a systematic modular architecture to realize the closed-loop management of the entire process of data acquisition, path analysis, loss calculation, model building, loss assessment, head calculation and pump control, which results in limited execution efficiency and difficulty in responding to dynamic changes in complex pipe network environments in real time.

[0092] Therefore, this application further provides an intelligent management system for fire-fighting equipment based on the Internet of Things, such as Figure 2 As shown, it includes the following modules:

[0093] The data acquisition module is used to acquire data, equipment information, and historical sprinkler data from various fire-fighting equipment locations in the fire sprinkler system.

[0094] The path division module is used to obtain the shortest path that the water flow takes from the fire pump to the sprinkler head and use it as the sprinkler path. Each pipe fitting on the sprinkler path is used as a loss point and the pipe between adjacent loss points is used as a loss segment.

[0095] The loss calculation module is used to calculate the friction loss value and elevation loss value of each loss segment on the spray path based on the collected data and the equipment information.

[0096] The digital twin module is used to construct a digital twin model of the fire sprinkler system based on the equipment information and the historical sprinkler data, and to obtain the set of loss parameters for each loss point in the digital twin model.

[0097] The loss assessment module is used to construct a loss assessment model based on the set of loss parameters, and to output the local loss value of each loss point on the spraying path by combining the loss assessment model with the collected data and the equipment information.

[0098] The head calculation module is used to calculate the total head of the spray path based on the friction loss value, the elevation loss value, the local loss value, and the equipment information, and to designate the spray head of the spray path with the highest total head as the most unfavorable spray head.

[0099] The water pump control module is used to determine whether the pressure value of the most unfavorable sprinkler head is within its working pressure range. If so, the speed of the fire pump is kept constant; otherwise, the speed of the fire pump is adjusted until the pressure value of the most unfavorable sprinkler head is within its working pressure range.

[0100] In the above-mentioned technical solution of this application, an intelligent management method for fire-fighting equipment based on the Internet of Things is provided for dynamically regulating the water supply capacity of fire pumps. However, the specific implementation of this method depends on the coordinated execution of steps such as real-time data acquisition, model calculation and equipment control. If there is a lack of clear definition of the execution carrier of the method, it may lead to the method being limited by a specific hardware environment or unable to achieve cross-platform compatibility when deployed, thereby affecting the stability and scalability of the fire sprinkler system regulation.

[0101] To this end, this application further provides a computer storage medium storing computer-executable instructions, which, when executed, implement the aforementioned IoT-based intelligent management method for fire-fighting equipment.

[0102] The above embodiments are only used to illustrate the technical methods of this application and are not intended to limit it. Although this application has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of this application without departing from the spirit and scope of the technical methods of this application.

Claims

1. A method for intelligent management of fire-fighting equipment based on the Internet of Things, characterized in that, Includes the following steps: Acquire data, equipment information, and historical sprinkler data from each fire-fighting equipment location in the fire sprinkler system; Obtain the shortest path that the water flows from the fire pump to the sprinkler head and use it as the sprinkler path. Take each pipe fitting on the sprinkler path as a loss point and the pipe between adjacent loss points as a loss segment. Calculate the friction loss and elevation loss values ​​for each loss segment along the spray path based on the collected data and the equipment information. A digital twin model of the fire sprinkler system is constructed based on the equipment information and the historical sprinkler data, and the set of loss parameters for each loss point is obtained in the digital twin model. A loss assessment model is constructed based on the set of loss parameters. The loss assessment model is then used in conjunction with the collected data and the equipment information to output the local loss value of each loss point on the spraying path. The total head of the spray path is calculated based on the friction loss value, the elevation loss value, the local loss value, and the equipment information. The spray head guided by the spray path with the highest total head is taken as the most unfavorable spray head. Determine whether the pressure value of the most unfavorable sprinkler head is within its working pressure range. If so, keep the speed of the fire pump constant. If not, adjust the speed of the fire pump until the pressure value of the most unfavorable sprinkler head is within its working pressure range.

2. The intelligent management method for fire-fighting equipment based on the Internet of Things according to claim 1, characterized in that, The collected data includes pressure values, flow velocity values, and flow rate values. The equipment information refers to attribute data reflecting the distribution, physical structure, and performance indicators of various fire-fighting equipment. The friction loss value at each loss segment along the spray path is calculated based on the length, flow rate, pipe roughness, and inner diameter of each loss segment. The elevation loss value at each loss segment is calculated based on the elevation difference between the two ends of each loss segment along the spray path.

3. The intelligent management method for fire-fighting equipment based on the Internet of Things according to claim 1, characterized in that, The process of building a digital twin model includes: The historical sprinkler data includes data collected from various fire-fighting equipment locations during a single sprinkler event. The sprinkler event refers to the process of the fire sprinkler system from the start to the end of water spraying when a fire occurs. A physical model of the fire sprinkler system is constructed using 3D modeling tools based on the equipment information of each fire-fighting device. Simulation software is then used to simulate the working process of each fire-fighting device based on historical sprinkler data from previous sprinkler events, thereby obtaining a digital twin model.

4. The intelligent management method for fire-fighting equipment based on the Internet of Things according to claim 1, characterized in that, The process of obtaining the set of loss parameters includes: The preceding loss segment, preceding measuring point, following loss segment, and following measuring point of each loss point on the sprinkler path are obtained. In the digital twin model, the rotation speed of the fire pump is kept constant at an arbitrary value. The pressure, flow velocity, and elevation values ​​of the preceding and following measuring points of each loss point at the same moment are obtained. The local loss value of each loss point is calculated in combination with the delivery status of each loss point. The local loss value of a single loss point at the same time, the pressure value and flow velocity value at the preceding measuring point, the elevation difference between the preceding and following measuring points, and the geometric characteristics and conveying state of the pipe fitting corresponding to the loss point are all included in the loss parameter set of the loss point at the corresponding time. The conveying states include single flow, split flow, merging flow, and mixed flow. The geometric features refer to parameters that reflect the physical form of the pipe fittings corresponding to the loss points. In the digital twin model, the speed of the fire pump is adjusted to other values ​​and then kept constant. The loss parameter sets of each loss point at different times are repeatedly obtained.

5. The intelligent management method for fire-fighting equipment based on the Internet of Things according to claim 4, characterized in that, The preceding loss segment refers to each loss segment connected to the corresponding loss point in the opposite direction of the water flow, and the following loss segment refers to each loss segment connected to the corresponding loss point in the downstream direction of the water flow. The preceding measuring point and the following measuring point are located on the preceding and following loss segments of the corresponding loss point at a distance of 3-5 times the inner diameter of the loss point.

6. The intelligent management method for fire-fighting equipment based on the Internet of Things according to claim 1, characterized in that, The process of building a loss assessment model includes: Based on the different geometric features, conveying status, pressure value, flow velocity value, elevation difference, and corresponding local loss values ​​within the acquired set of various loss parameters, a loss assessment set is generated and divided into a training set and a test set. Convolutional neural networks are constructed, and the initial convolutional neural network is obtained by training the convolutional neural network using the training set. The initial convolutional neural network is then validated using the test set. The initial convolutional neural network whose output is less than or equal to the preset test error threshold is used as the loss evaluation model.

7. The intelligent management method for fire-fighting equipment based on the Internet of Things according to claim 1, characterized in that, The process of outputting local loss values ​​includes: The pressure value, flow velocity value, elevation difference between the preceding and following measuring points, geometric characteristics and conveying status of the pipe fitting corresponding to each loss point at the current moment are input into the loss assessment model to output the local loss value of each loss point.

8. The intelligent management method for fire-fighting equipment based on the Internet of Things according to claim 7, characterized in that, The process of calculating the total head includes: The total loss value of a single spray path is calculated by summing the local loss value output at each loss point and the calculated friction loss value and elevation loss value at each loss segment. The total head is then calculated by combining this with the working pressure range of the spray head guided by the spray path. The working pressure range refers to the pressure range that the spray head needs to maintain in order to achieve its designed fire extinguishing effect.

9. An intelligent management system for fire-fighting equipment based on the Internet of Things, characterized in that, Includes the following modules: The data acquisition module is used to acquire data, equipment information, and historical sprinkler data from various fire-fighting equipment locations in the fire sprinkler system. The path division module is used to obtain the shortest path that the water flow takes from the fire pump to the sprinkler head and use it as the sprinkler path. Each pipe fitting on the sprinkler path is used as a loss point and the pipe between adjacent loss points is used as a loss segment. The loss calculation module is used to calculate the friction loss value and elevation loss value of each loss segment on the spray path based on the collected data and the equipment information. The digital twin module is used to construct a digital twin model of the fire sprinkler system based on the equipment information and the historical sprinkler data, and to obtain the set of loss parameters for each loss point in the digital twin model. The loss assessment module is used to construct a loss assessment model based on the set of loss parameters, and to output the local loss value of each loss point on the spraying path by combining the loss assessment model with the collected data and the equipment information. The head calculation module is used to calculate the total head of the spray path based on the friction loss value, the elevation loss value, the local loss value, and the equipment information, and to designate the spray head of the spray path with the highest total head as the most unfavorable spray head. The water pump control module is used to determine whether the pressure value of the most unfavorable sprinkler head is within its working pressure range. If so, the speed of the fire pump is kept constant; otherwise, the speed of the fire pump is adjusted until the pressure value of the most unfavorable sprinkler head is within its working pressure range.

10. A computer storage medium storing computer-executable instructions, characterized in that, When the computer-executable instructions are executed, the intelligent management method for fire-fighting equipment based on the Internet of Things as described in any one of claims 1-8 is implemented.

Images