Building fire safety intelligent early warning method and system based on data feedback

Abstract

The invention discloses a building fire safety intelligent early warning method and system based on data feedback, and relates to the technical field of building fire safety, and the method comprises the steps: obtaining building floor structure information, deploying and controlling a fire early warning system according to the building floor structure information, collecting data collected by each floor monitoring point in a building through the fire early warning system, and storing the collected data in a database; a corresponding floor fire early warning model is constructed based on basic parameter information of each floor monitoring point, historical floor fire-fighting parameter information, historical state information of an acquisition device and historical environment information, then floor monitoring information is obtained through analysis of the model, fire-fighting safety accident data of buildings of the same type are imported into the floor fire early warning model, and a corresponding floor fire early warning model is established. And acquiring fire safety level intervals of the floor monitoring points, determining a coping strategy according to the real-time acquired data in combination with the floor monitoring information corresponding to each monitoring point and the fire safety level intervals of the floor monitoring points, and then implementing the coping strategy to each floor monitoring point.

Description

Technical Field

[0001] The present invention discloses an intelligent early warning method and system for building fire safety based on data feedback, which relates to the technical field of building fire safety. Background Technique

[0002] Currently, in fire early warning operations, devices such as smoke sensors are often set up in building floors, and smoke alarms are used to detect the smoke generated during a fire. Although it can meet some daily fire safety early warning work, it has insufficient danger identification before a fire occurs. On the one hand, it is impossible to determine false alarms, and on the other hand, it is impossible to determine the early warning level and give sufficient coping strategies.

[0003] Since the current building floors are relatively high and the personnel distribution is dense, production and work will be suspended after the fire protection measures are activated, and even property damage will be caused. Therefore, fire early warning must be more accurate. The prior art publication number: CN118486153 A discloses an intelligent early warning method and system for fire safety management, which analyzes the fire safety early warning level based on the data analysis of two types of performance parameters, and also provides certain coping strategies for different levels. However, there are still problems such as insufficient comprehensive data analysis, insufficient consideration of data deviation caused by aging of the acquisition device equipment, and failure to perform multi-level analysis on the data, resulting in insufficient accuracy. Summary of the Invention

[0004] To solve the above technical problems, an intelligent early warning method and system for building fire safety based on data feedback are provided. This technical solution solves the problems of insufficient data types and low data analysis accuracy rate mentioned in the above background technique.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] An intelligent early warning method for building fire safety based on data feedback, including:

[0007] S1. Obtain the building floor structure information, and deploy a fire early warning system according to the building floor structure information. Use the fire early warning system to collect the basic parameter information of each floor monitoring point in the building, the historical information of floor fire parameters, the historical state information of the acquisition device, and the historical environment information. The monitoring points are installed around the emergency exit.

[0008] S2. Based on the basic parameter information of each floor monitoring point, the historical information of floor fire parameters, the historical state information of the acquisition device, and the historical environment information, construct a corresponding floor fire early warning model. Then, perform real-time early warning analysis on each monitoring point through the floor fire early warning model to obtain floor monitoring information.

[0009] S3. Obtain the fire safety accident data of buildings of the same type, import the fire safety accident data into the floor fire warning model, and construct the fire safety level interval of the floor monitoring points;

[0010] S4. Collect the real-time data of the basic parameters, the real-time information of the floor fire protection parameters, the real-time status information of the acquisition devices, and the real-time environmental information of each floor monitoring point, determine the response strategy in combination with the floor monitoring information and the fire safety level interval corresponding to each monitoring point, and then implement the response strategy to each floor monitoring point.

[0011] In an alternative embodiment, the obtaining of the building floor structure information, the deployment of the fire warning system according to the building floor structure information, and the use of the fire warning system to collect the basic parameter information, the historical information of the floor fire protection parameters, the historical status information of the acquisition devices, and the historical environmental information of each floor monitoring point in the building specifically include:

[0012] Generate a BIM floor model through lidar scanning to obtain the building structure information;

[0013] Set up monitoring points based on the building structure information and the location of the escape routes, and synchronously divide the interval areas of the monitoring points;

[0014] Deploy a core server in the cloud according to the building structure information, the distribution information of the monitoring points, and the interval areas of the monitoring points, and construct a data acquisition and sensing system on the core server based on the edge computing and cloud AI hybrid framework;

[0015] Obtain the basic parameter information, the historical information of the floor fire protection parameters, and the historical environmental information at different time nodes based on the data acquisition and sensing system and normalization processing.

[0016] In an alternative embodiment, the constructing of the corresponding floor fire warning model based on the basic parameter information, the historical information of the floor fire protection parameters, the historical status information of the acquisition devices, and the historical environmental information of each floor monitoring point, and then performing real-time warning analysis on each monitoring point through the floor fire warning model to obtain the floor monitoring information specifically includes:

[0017] S2.1. Arbitrarily obtain the historical parameter data of the monitoring points at different time nodes based on the data acquisition and sensing system;

[0018] S2.2. Synchronously obtain the standard node index based on the basic parameter information of the floor, the historical information of the floor fire protection parameters, and the historical environmental information of the monitoring points;

[0019] The calculation formula of the node index:

[0020] ;

[0021] In the formula, is the node index between the moment and the moment, is the number of monitoring parameters, is the weight of the th parameter, is the real-time quantization value of the th parameter at the moment, is the real-time quantization value of the th parameter at the moment, is the safety threshold of the th parameter, is the environmental temperature change rate, is the environmental factor correction coefficient;

[0022] S2.3. According to the data acquisition and sensing system, collect the basic parameter information of each monitoring point's floor, the real-time information of the floor's fire protection parameters, and the real-time environmental information to obtain the standard node index, and then determine the real-time node index at the adjacent time nodes of the monitoring point;

[0023] S2.4. Build a fire warning model based on the real-time node index and the standard node index at the adjacent timestamps of the monitoring point;

[0024] The floor fire warning model:

[0025] ;

[0026] In the formula, is the warning index at the moment of the monitoring point, is the acquisition device status correction coefficient, is the environmental correction coefficient, is the node index between the moment and the moment, is the standard node index at the monitoring point, is the real-time number of people escaping through the corridor at the moment, is the building function coefficient, is the total number of all parameters of the basic parameter information of the floor monitoring point, the floor fire protection parameter information, the acquisition device status information, and the environmental information,

[0027] S2.5. Based on the floor fire warning model and the preset accommodation capacity of the escape route, obtain the limit warning index of the monitoring point;

[0028] S2.6. Obtain the maximum occupancy based on the monitoring point limit warning index, the basic parameter information of the floor monitoring points, the real-time information of the floor fire protection parameters, the real-time status information of the acquisition devices, and the real-time environmental information;

[0029] The calculation formula for the maximum occupancy is as follows:

[0030] ;

[0031] In the formula, is the correction coefficient of the acquisition device status, is the environmental correction coefficient, is the node index between the th moment and the th moment, is the standard node index on the monitoring point, is the maximum occupancy of the area at the th moment, is the building function coefficient, is the total number of all parameters of the basic parameter information of the floor monitoring points, the floor fire protection parameter information, the acquisition device status information, and the environmental information, is the number of abnormally changing parameters,

[0032] In an optional embodiment, obtaining the fire safety accident data of the same type of building, importing the fire safety accident data into the floor fire warning model, and constructing the fire safety level interval of the floor monitoring points specifically includes:

[0033] S3.1. Obtain the critical index of the safety accident through the floor fire warning model;

[0034] The selection formula for the critical index is as follows:

[0035] ;

[0036] In the formula, is the critical index of the safety accident data, is the th moment of the warning coefficient of the monitoring point in different interval states ( is the warning state, emergency state, high-risk state);

[0037] S3.2. Based on the critical index of the safety accident, divide the fire safety level interval of the floor monitoring points through normal distribution and normalization processing. The fire safety level interval of the floor monitoring points includes a warning interval, an emergency interval, and a high-risk interval.

[0038] In an alternative embodiment, collecting the real-time data of the basic parameters of each floor monitoring point, the real-time information of the floor fire protection parameters, the real-time status information of the collection device, and the real-time environment information, and combining the floor monitoring information corresponding to each monitoring point and the fire safety level interval of the floor monitoring point to determine the response strategy, specifically including:

[0039] Based on the floor monitoring information and the fire safety level interval of the floor monitoring point, obtain the floor safety level and determine the response strategy;

[0040] Set the response strategies for the floors at the warning level to inspection and investigation;

[0041] Set the response strategies for the floors at the emergency level to activate the fire extinguishing device and inspection;

[0042] Set the response strategies for the floors at the high-risk level to activate the fire extinguishing device and arrange for evacuation.

[0043] In an alternative embodiment, the activation of the fire extinguishing device and the arrangement for evacuation in the determination of the response strategy specifically include:

[0044] Based on the floor fire warning model and the floor monitoring information, obtain the real-time number of people in the escape routes on each floor and the maximum capacity of the monitoring points;

[0045] According to the maximum capacity of the monitoring points and the real-time number of evacuating people, predict the maximum evacuation index of each floor passage;

[0046] The calculation formula for the maximum evacuation index:

[0047] ;

[0048] In the formula, is the maximum evacuation index of the floor at time is the real-time number of evacuating people in the passage at time is the maximum capacity of the th monitoring point on the

[0049] Divide the interval areas of each monitoring point through the indication signs, and guide the people in each divided area to evacuate to the escape route with the maximum evacuation index of the divided area based on the indication signs;

[0050] When there are multiple channels with the same maximum evacuation index around the divided area, preferably select the one with a smaller node index on the monitoring point as the best escape route;

[0051] Through machine learning escape strategies, an optimized escape strategy model is obtained, and the escape strategy is displayed through the indication signs in the interval of each monitoring point.

[0052] In an alternative embodiment, a building fire safety intelligent early warning system based on data feedback is proposed for implementing the above-mentioned building fire safety early warning method, including:

[0053] A data acquisition module, which is used to obtain the basic parameter information, historical floor fire protection parameter information, and historical environment information of each floor monitoring point, and is also used to obtain the real-time data of the basic parameters of each floor monitoring point, real-time floor fire protection parameter information, real-time status information of the acquisition device, and real-time environment information;

[0054] A main control module, which is used to preprocess the acquired data, and based on the basic parameter information, historical floor fire protection parameter information, and historical environment information of each floor monitoring point, construct a floor fire early warning model and a corridor escape model;

[0055] An early warning module, which is used to determine the warning coefficient, critical index of safety accident data, and monitoring point index at each monitoring point through the floor fire alarm early warning model, combined with the basic parameter information, historical floor fire protection parameter information, and historical environment information of each floor monitoring point collected by the data acquisition module, as well as the real-time data of the basic parameters of each floor monitoring point, real-time floor fire protection parameter information, real-time status information of the acquisition device, and real-time environment information, and determine the fire safety degree information of each floor monitoring point;

[0056] A scheduling module, which is used to calculate the number of evacuees on each floor through the escape strategy model, obtain the maximum number of evacuees, optimize the escape routes, and allocate personnel on different floors to evacuate according to the optimal escape strategy;

[0057] A display module, which is used to display the real-time data processing results of the corridor, the changes in the fire situation, and the health conditions of the trapped people, and synchronously display the scheduling results and communication situations of the scheduling module.

[0058] In an alternative embodiment, the data acquisition module includes:

[0059] A sensor unit, which is distributed and installed on the escape routes and fire protection sites of each floor, including smoke sensors, temperature sensors, radar sensors, and gas sensors, and the sensors on each floor are connected point by point;

[0060] A marking unit, which is used to mark the locations of the sensors on each floor and classify the collected marked data on the same floor;

[0061] A transmission unit, which is used to obtain the real-time data collected by the sensor unit. The transmission unit includes a local area network transmission channel, a Bluetooth channel, and a radio transmission channel.

[0062] In an alternative embodiment, the main control module includes:

[0063] A data processing unit, which is used to preprocess the collected data and information;

[0064] A model construction unit, which constructs a fire warning model and a corridor escape model corresponding to each floor based on the processed data.

[0065] In an alternative embodiment, the scheduling module includes:

[0066] A fire fighting module, which is used to extinguish fires and handle emergencies for the fire situation obtained by the main control module;

[0067] An escape scheduling module, which arranges floor escape strategies based on the corridor escape model according to the real-time corridor data to evacuate the crowd.

[0068] Compared with the prior art, the beneficial effects of the present invention are:

[0069] A building fire safety intelligent warning method and system based on data feedback proposed by this solution. The structure of the present invention is simple, and it can evaluate the floor risks according to real-time data. At the same time, it combines multiple types of parameters for judgment and combines the node index and the fire warning model to achieve multiple data judgments, thereby effectively improving the accuracy of floor fire warning. At the same time, it provides response plans for different risk levels, reduces the frequency of excessive fire fighting emergencies, and saves maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a flowchart of a building fire safety intelligent warning method based on data feedback proposed by the present invention;

[0071] Figure 2 It is a flowchart of constructing a fire warning model in the present invention;

[0072] Figure 3 It is a framework diagram of a building fire safety intelligent warning system based on data feedback proposed by the present invention; DETAILED DESCRIPTION OF THE INVENTION

[0073] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0074] Refer to Figure 1 —Figure 2 As shown in the figure, an intelligent early warning method for building fire safety based on data feedback includes:

[0075] S1. Obtain the building floor structure information, deploy the fire warning system according to the building floor structure information, and use the fire warning system to collect the basic parameter information of each floor monitoring point in the building, the historical information of floor fire parameters, the historical state information of the collection device, and the historical environment information;

[0076] S2. Based on the basic parameter information of each floor monitoring point, the historical information of floor fire parameters, the historical state information of the collection device, and the historical environment information, construct the corresponding floor fire warning model, and then conduct real-time warning analysis on each monitoring point through the floor fire warning model to obtain the floor monitoring information;

[0077] S3. Obtain the fire safety accident data of the same type of building, import the fire safety accident data into the floor fire warning model, and construct the fire safety level interval of the floor monitoring point;

[0078] S4. Collect the real-time data of the basic parameters of each floor monitoring point, the real-time information of floor fire parameters, the real-time state information of the collection device, and the real-time environment information, combine the floor monitoring information corresponding to each monitoring point and the fire safety level interval of the floor monitoring point to determine the response strategy, and then implement the response strategy to each floor monitoring point.

[0079] Specifically, the basic parameter information of each floor monitoring point includes the monitoring point position parameter, the escape passage position parameter, and the monitoring point interval area division parameter, which are used to determine the distribution of floor monitoring points and accurately divide the escape area. The historical information of floor fire parameters includes the smoke concentration parameter, the CO concentration parameter, and the fire light intensity parameter, which are important parameters for fire safety assessment. When there are abnormal changes in these parameters, it will have an important impact on the floor safety level. The historical state information of the collection device includes the service life of the sensor, the number of repairs, and the sensitivity deviation, which are used to correct the deviation of the collected parameters. The environment information includes temperature, air pressure, and wind speed, which are used to characterize the environmental impact. The monitoring point position parameter is mainly used to obtain the floor where the collection device is located, the number of devices set in the floor, and the spatial position information. The monitoring point interval area division parameter refers to dividing the area through the midpoint of the spatial length between the monitoring points. For example, the area between the first monitoring point and the second monitoring point is divided into two left and right areas, the left area is denoted as 1-2-left, and the right area is denoted as 1-2-right. The fire light intensity parameter is obtained by the machine vision device and infrared detection in the collection device. The sensitivity deviation refers to the quantization value of the average data error of the same monitoring point under the same state.

[0080] Further, obtain the building floor structure information, and deploy the fire warning system according to the building floor structure information. Use the fire warning system to collect the basic parameter information, historical floor fire parameter information, historical status information of the collection device, and historical environment information of each floor monitoring point in the building, specifically including:

[0081] Generate a BIM floor model through lidar scanning to obtain building structure information;

[0082] Based on the building structure information and the location of the escape route, set monitoring points and synchronously divide the interval areas of the monitoring points;

[0083] According to the building structure information, monitoring point distribution information, and monitoring point interval area, deploy the core server in the cloud, and build a data collection and sensing system on the core server based on the edge computing and cloud AI hybrid framework;

[0084] Based on the data collection and sensing system and normalization processing, obtain the basic parameter information, historical floor fire parameter information, and historical environment information at different time nodes.

[0085] Further, based on the basic parameter information, historical floor fire parameter information, historical status information of the collection device, and historical environment information of each floor monitoring point, construct the corresponding floor fire warning model, and then perform real-time warning analysis on each monitoring point through the floor fire warning model to obtain the floor monitoring information, specifically including:

[0086] S2.1. Arbitrarily obtain the historical parameter data of the monitoring point at different time nodes based on the data collection and sensing system;

[0087] S2.2. Synchronously obtain the standard node index based on the basic parameter information of the floor, historical floor fire parameter information, and historical environment information of the monitoring point;

[0088] Node index calculation formula:

[0089] ;

[0090] In the formula, is the node index between the th moment and the th moment, is the number of monitoring parameters, is the weight of the rd parameter, is the real-time quantization value of the th parameter at the th moment, is the real-time quantization value of the th parameter at the th moment, is the The safety threshold of a parameter is the environmental temperature change rate and is the environmental factor correction coefficient;

[0091] Specifically, the value range of the safety standard value is 0 - 100 points. The weight of the parameter is determined by the entropy weight method, and the sum is 1. The safety threshold of the parameter is obtained with reference to the industry standard, and the value range of the environmental factor correction coefficient is 0.2 - 0.5;

[0092] S2.3. According to the data acquisition and sensing system, collect the basic parameter information of each monitoring point's floor, the real-time information of the floor fire protection parameters, and the real-time environmental information to obtain the standard node index, and then determine the real-time node index at the adjacent time nodes of the monitoring point;

[0093] S2.4. Construct a fire warning model based on the real-time node index and the standard node index at the adjacent timestamps of the monitoring point;

[0094] Floor fire warning model:

[0095] ;

[0096] In the formula, is the warning index at the monitoring point at the is the acquisition device status correction coefficient, is the environmental correction coefficient, is the node index between the moment and the is the standard node index at the monitoring point, is the real-time number of people escaping through the corridor at the is the building function coefficient, is the total number of all parameters of the basic parameter information of the floor monitoring point, the floor fire protection parameter information, the acquisition device status information, and the environmental information, is the number of abnormally changing parameters;

[0097] Specifically, the regional population density is obtained through the thermal imaging installed on the sensor. The building function coefficient is obtained by normalizing the average value taken by the comprehensive scoring of the technical personnel in the fire protection industry according to the nature of the building's use. For example, the coefficient for a shopping mall is 0.8, for an office building is 0.5, and for a residential building is 0.4. The number of abnormally changing parameters refers to the case where the variance of the parameter value change is greater than 0.8 within the same time interval, and it is regarded as an abnormally changing parameter;

[0098] S2.5. Based on the floor fire warning model and the preset accommodation capacity of the escape route, obtain the limit warning index of the monitoring point;

[0099] Specifically, the preset occupancy capacity of the escape route refers to the limited number of people required for different specifications of escape routes according to national fire safety standards. S2.6. Obtain the maximum occupancy capacity based on the extreme warning index of the monitoring point, the basic parameter information of the floor monitoring point, the real-time information of the floor fire protection parameters, the real-time status information of the acquisition device, and the real-time environment information;

[0100] Formula for calculating the maximum occupancy capacity:

[0101] ;

[0102] In the formula, is the correction coefficient of the acquisition device status, is the environmental correction coefficient, is the node index between the th moment and the th moment, is the standard node index on the monitoring point, is the maximum occupancy capacity of the area at the th moment, is the building function coefficient, is the total number of parameters of the basic parameter information of the floor monitoring point, the floor fire protection parameter information, the acquisition device status information, and the environmental information, is the number of abnormal change parameters,

[0103] Furthermore, obtain the fire safety accident data of the same type of building, import the fire safety accident data into the floor fire warning model, and construct the fire safety level interval of the floor monitoring point, specifically including:

[0104] S3.1. Obtain the critical index of the safety accident through the floor fire warning model;

[0105] Formula for selecting the critical index:

[0106] ;

[0107] In the formula, is the critical index of the safety accident data, is the state of different intervals at the th moment, refers to the warning coefficients of the monitoring point in the warning state, emergency state, and high-risk state;

[0108] S3.2. Based on the critical index of the safety accident, divide the fire safety degree interval of the floor monitoring point through normal distribution and normalization processing. The fire safety degree interval of the floor monitoring point includes the warning interval, emergency interval, and high-risk interval.

[0109] Further, collect the real-time data of the basic parameters of each floor monitoring point, the real-time information of the floor fire protection parameters, the real-time status information of the collection device, and the real-time environment information, and combine the floor monitoring information corresponding to each monitoring point and the fire safety level interval of the floor monitoring point to determine the response strategy, specifically including:

[0110] Based on the floor monitoring information and the fire safety level interval of the floor monitoring point, obtain the floor safety level and determine the response strategy;

[0111] Set the response strategies for the floors at the warning level as inspection and investigation;

[0112] Set the response strategies for the floors at the emergency level as activating the fire extinguishing device and inspection;

[0113] Set the response strategies for the floors at the high-risk level as activating the fire extinguishing device and arranging for evacuation.

[0114] Further, for activating the fire extinguishing device and arranging for evacuation in the determined response strategy, specifically including:

[0115] Based on the floor fire warning model and the floor monitoring information, obtain the real-time number of people in the escape routes on each floor and the maximum capacity of the monitoring points;

[0116] According to the maximum capacity of the monitoring points and the real-time number of evacuating people, predict the maximum evacuation index of each floor passage;

[0117] The calculation formula for the maximum evacuation index:

[0118] ;

[0119] In the formula, is the maximum evacuation index of the floor at time is the real-time number of evacuating people in the passage at time is the maximum capacity of the th monitoring point on the

[0120] Divide the interval areas of each monitoring point through the indication signs, and based on the indication signs, guide the people in each divided area to evacuate to the escape route with the maximum evacuation index in the divided area where they are located;

[0121] When there are multiple passages with the same maximum evacuation index around the divided area where a person is located, preferably select the one with a smaller node index on the monitoring point as the best escape route;

[0122] Through machine learning of the evacuation strategy, obtain the optimal evacuation strategy model, and display the evacuation strategy through the indication signs in the interval areas of each monitoring point.

[0123] Reference Figure 3 As shown, a building fire safety intelligent early warning system based on data feedback is proposed to implement the above-mentioned building fire safety early warning method, including:

[0124] A data acquisition module, which is used to obtain the basic parameter information, historical floor fire protection parameter information, and historical environment information of each floor monitoring point, and is also used to obtain the real-time data of the basic parameters of each floor monitoring point, real-time floor fire protection parameter information, real-time status information of the acquisition device, and real-time environment information;

[0125] A main control module, which is used to preprocess the acquired data, and based on the basic parameter information, historical floor fire protection parameter information, and historical environment information of each floor monitoring point, construct a floor fire early warning model and a corridor escape model;

[0126] An early warning module, which is used to determine the early warning coefficient, critical index of safety accident data, and monitoring point index at each monitoring point, and determine the fire safety degree information of each floor monitoring point through the floor fire alarm early warning model, combined with the basic parameter information, historical floor fire protection parameter information, and historical environment information of each floor monitoring point collected by the data acquisition module, as well as the real-time data of the basic parameters of each floor monitoring point, real-time floor fire protection parameter information, real-time status information of the acquisition device, and real-time environment information;

[0127] A scheduling module, which is used to calculate the number of people escaping from each floor through the escape strategy model, obtain the maximum number of people escaping, optimize the escape route, and allocate personnel on different floors to evacuate according to the optimal escape strategy;

[0128] A display module, which is used to display the real-time data processing results of the corridor, the changes in the fire situation, and the health conditions of the trapped people, synchronously display the scheduling results and communication situations of the scheduling module.

[0129] Furthermore, the data acquisition module includes:

[0130] A sensor unit, which is distributed and installed on the escape routes and fire protection sites of each floor, including smoke sensors, temperature sensors, radar sensors, and gas sensors, and the sensors on each floor are connected point by point;

[0131] A marking unit, which is used to mark the positions of the sensors on each floor and classify the marked data collected on the same floor;

[0132] A transmission unit, which is used to obtain the real-time data collected by the sensor unit, and the transmission unit includes a local area network transmission channel, a Bluetooth channel, and a radio transmission channel.

[0133] Furthermore, the main control module includes:

[0134] A data processing unit, which is used to preprocess the collected data and information;

[0135] A model construction unit, which constructs a fire warning model and a corridor escape model corresponding to each floor based on the processed data.

[0136] Furthermore, the scheduling module includes:

[0137] A fire fighting module, which is used to extinguish fires and handle emergencies for the fire situation obtained by the main control module;

[0138] An escape scheduling module, which arranges floor escape strategies based on the corridor escape model according to real-time corridor data to evacuate the crowd.

[0139] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent early warning method for building fire safety based on data feedback, characterized in that Including: S1. Obtain the building floor structure information, deploy the fire warning system according to the building floor structure information, and use the fire warning system to collect the basic parameter information, historical floor fire parameter information, historical status information of the acquisition device, and historical environmental information of each floor monitoring point in the building. The monitoring points are installed around the escape route exits; S2. Based on the basic parameter information, historical floor fire parameter information, historical status information of the acquisition device, and historical environmental information of each floor monitoring point, construct the corresponding floor fire warning model, and then perform real-time warning analysis on each monitoring point through the floor fire warning model to obtain the floor monitoring information; S3. Obtain the fire safety accident data of the same type of building, import the fire safety accident data into the floor fire warning model, and construct the fire safety level interval of the floor monitoring point; S4. Collect the real-time basic parameter data, real-time floor fire parameter information, real-time status information of the acquisition device, and real-time environmental information of each floor monitoring point, combine the floor monitoring information corresponding to each monitoring point and the fire safety level interval of the floor monitoring point to determine the response strategy, and then implement the response strategy to each floor monitoring point.

2. The intelligent early warning method for building fire safety based on data feedback according to claim 1, characterized in that The obtaining of the building floor structure information, deploying the fire warning system according to the building floor structure information, and using the fire warning system to collect the basic parameter information, historical floor fire parameter information, historical status information of the acquisition device, and historical environmental information of each floor monitoring point in the building specifically includes: Generate through lidar scanning Floor models to obtain building structure information; Based on the building structure information and the location of the escape route, set the monitoring points and synchronously divide the interval areas of the monitoring points; According to the building structure information, the distribution information of the monitoring points, and the interval areas of the monitoring points, deploy the core server in the cloud, and construct a data acquisition and sensing system on the core server based on the edge computing and cloud AI hybrid framework; Based on the data acquisition and sensing system and normalization processing, obtain the basic parameter information, historical floor fire parameter information, and historical environmental information at different time nodes.

3. The intelligent fire safety early warning method for buildings based on data feedback according to claim 1, characterized in that, The constructing of the corresponding floor fire warning model based on the basic parameter information, historical floor fire parameter information, historical status information of the acquisition device, and historical environmental information of each floor monitoring point, and then performing real-time warning analysis on each monitoring point through the floor fire warning model to obtain the floor monitoring information specifically includes: S2.

1. Arbitrarily obtain the historical parameter data of the monitoring points at different time nodes based on the data acquisition and sensing system; S2.

2. Synchronously obtain the standard node index based on the basic floor parameter information, historical floor fire parameter information, and historical environmental information of the monitoring points; The calculation formula of the node index: ； In the formula, is the node index between the th moment and the th moment, is the number of monitoring parameters, is the weight of the th parameter, is the real-time quantization value of the th parameter at the th moment, is the real-time quantization value of the th parameter at the th moment, is the safety threshold of the th parameter, is the environmental temperature change rate, is the environmental factor correction coefficient; S2.

3. According to the data acquisition and sensing system, collect the basic floor parameter information, real-time floor fire parameter information, and real-time environmental information of each monitoring point to obtain the standard node index, and then determine the real-time node index of the adjacent time nodes of the monitoring points; S2.

4. Construct a fire warning model according to the real-time node index and the standard node index of the adjacent time stamps of the monitoring points; The floor fire warning model: ； Wherein, is the warning index at the monitoring point at a certain moment, is the state correction coefficient of the acquisition device, is the environmental correction coefficient, is the index between the moment and the moment, is the standard node index at the monitoring point, is the real-time number of people escaping downstairs at a certain moment, is the building function coefficient, is the total number of all parameters of the basic parameter information of the floor monitoring point, the floor fire protection parameter information, the acquisition device state information and the environmental information, is the number of abnormal change parameters; S2.

5. Based on the floor fire warning model and the preset accommodation capacity of the escape route, obtain the limit warning index of the monitoring points; S2.

6. Obtain the maximum occupancy based on the extreme warning index of the monitoring points, the basic parameter information of the floor monitoring points, the real-time information of the floor fire protection parameters, the real-time status information of the acquisition devices, and the real-time environmental information. The calculation formula for the maximum occupancy: ； In the formula, is the correction coefficient of the acquisition device status, is the environmental correction coefficient, is the node index between the time and the is the standard node index at the monitoring point, is the maximum number of people that can be accommodated in the area at the is the building function coefficient, is the total number of all parameters of the basic parameter information of the floor monitoring point, the floor fire protection parameter information, the acquisition device status information and the environmental information, is the number of abnormal change parameters, is the limit warning index of the monitoring point.

4. The intelligent early warning method for building fire safety based on data feedback according to claim 1, characterized in that, Obtain the fire safety accident data of the same type of building, and import the fire safety accident data into the floor fire warning model to construct the fire safety level interval of the floor monitoring points, which specifically includes: S3.

1. Obtain the critical index of the safety accident through the floor fire warning model. The selection formula for the critical index: ； In the formula, is the critical index of safety accident data, is the early warning coefficient of the monitoring point under different interval states at the moment; S3.

2. Based on the critical index of the safety accident, divide the fire safety level interval of the floor monitoring points through normal distribution and normalization processing. The fire safety level interval of the floor monitoring points includes the warning interval, the emergency interval, and the high-risk interval.

5. A method for intelligent early warning of building fire safety based on data feedback according to claim 1, characterized in that, Collect the real-time data of the basic parameters, the real-time information of the floor fire protection parameters, the real-time status information of the acquisition devices, and the real-time environmental information of each floor monitoring point, and combine the floor monitoring information corresponding to each monitoring point and the fire safety level interval of the floor monitoring points to determine the response strategies, which specifically include: Based on the floor monitoring information and the fire safety level interval of the floor monitoring points, obtain the floor safety level and determine the response strategies. Set the response strategies for the floors at the warning level as inspection and investigation. Set the response strategies for the floors at the emergency level as activating the fire extinguishing device and inspection. Set the response strategies for the floors at the high-risk level as activating the fire extinguishing device and arranging for evacuation.

6. The intelligent early warning method for building fire safety based on data feedback according to claim 5, characterized in that The activating the fire extinguishing device and arranging for evacuation in the determination of the response strategies specifically includes: Based on the floor fire warning model and the floor monitoring information, obtain the real-time number of people in the escape routes on each floor and the maximum occupancy of the monitoring points. Predict the maximum escape index of each floor passage according to the maximum occupancy of the monitoring points and the real-time number of evacuating people. The calculation formula for the maximum escape index: ； Wherein, is the maximum escape index of the floor at time is the real-time number of people escaping in the corridor at time is the maximum capacity of the th monitoring point on the Divide the interval areas of each monitoring point through indicator signs, and guide the people in each divided area to escape through the escape route with the maximum escape index of the divided area based on the indicator signs. When there are multiple passages with the same maximum escape index around the divided area, preferably select the one with a smaller node index on the monitoring point as the best escape route. Obtain the optimized escape strategy model through machine learning of the escape strategies, and display the escape strategies through the indicator signs in the interval areas of each monitoring point.

7. An intelligent early warning system for building fire safety based on data feedback, characterized in that, Used to implement the building fire safety warning method described in any one of claims 1-6, including: A data acquisition module, which is used to obtain the basic parameter information, the historical information of the floor fire protection parameters, and the historical environmental information of each floor monitoring point, and is also used to obtain the real-time data of the basic parameters, the real-time information of the floor fire protection parameters, the real-time status information of the acquisition devices, and the real-time environmental information of each floor monitoring point. A main control module, which is used to perform data preprocessing on the collected data, and construct a floor fire warning model and a corridor escape model based on the basic parameter information of each floor monitoring point, the historical information of the floor fire protection parameters, and the historical environmental information. An early warning module, which is used to determine the early warning coefficient, the critical index of safety accident data, and the monitoring point index on each monitoring point, and determine the fire safety degree information of each floor monitoring point by combining the basic parameter information, historical information of floor fire protection parameters and historical environment information of each floor monitoring point collected by the data acquisition module, as well as the real-time data of basic parameters, real-time information of floor fire protection parameters, real-time status information of the acquisition device and real-time environment information of each floor monitoring point through the floor fire warning model; A scheduling module, which is used to calculate the number of people escaping from each floor through the escape strategy model, obtain the maximum number of people escaping, optimize the escape routes, and allocate the personnel on different floors to evacuate according to the optimal escape strategy; A display module, which is used to display the real-time data processing results of the corridor, the fire change situation and the health status of the trapped people, synchronously display the scheduling results of the scheduling module and the communication situation.

8. An intelligent early warning system for building fire safety based on data feedback according to claim 7, characterized in that, The data acquisition module includes: A sensor unit, which is distributed and installed on the escape routes and fire protection sites of each floor, including smoke sensors, temperature sensors, radar sensors and gas sensors, and the sensors on each floor are connected point by point; A marking unit, which is used to mark the locations of the sensors on each floor and classify the collected marking data of the same floor; A transmission unit, which is used to obtain the real-time data collected by the sensor unit. The transmission unit includes a local area network transmission channel, a Bluetooth channel and a radio transmission channel.

9. An intelligent early warning system for building fire safety based on data feedback according to claim 7, characterized in that, The main control module includes: A data processing unit, which is used to preprocess the collected data and information; A model construction unit, which constructs a fire warning model and a corridor escape model corresponding to each floor based on the processed data.

10. The intelligent early warning system for building fire safety based on data feedback according to claim 7, characterized in that, The scheduling module includes: A fire fighting unit, which is used to extinguish fires and handle police situations for the fire situation obtained by the main control module; An escape scheduling unit, which arranges the floor escape strategy according to the real-time corridor data based on the corridor escape model and evacuates the crowd.

Images