Fire safety detection system based on side cloud collaboration

Abstract

The invention discloses a fire safety detection system based on edge-cloud collaboration, and belongs to the technical field of fire safety, the fire safety detection system comprises an edge end and a cloud end, the edge end comprises a sensor module and a fire response module, the cloud end comprises a fire analysis module and an auxiliary traceability module, and the sensor module is connected with the auxiliary traceability module. Comprising a smoke sensor, a light scattering sensor and an infrared sensor and is used for receiving field data in real time, transmitting the field data to the edge end for judgment and transmitting a control signal into the fire-fighting response module based on a judgment result of the edge end. According to the fire safety detection system based on side cloud cooperation, on the basis of the side cloud cooperation technology, the edge end is responsible for field monitoring and emergency alarm, the cloud end is responsible for data integration, analysis, information transmission and auxiliary alarm, data support is provided for subsequent fire decision making, meanwhile, the fire spreading trend and the fire grade are analyzed and predicted in real time, and the fire safety detection efficiency is improved. And the fire treatment efficiency can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of fire safety technology, and specifically is a fire safety detection system based on edge-cloud collaboration. Background Art

[0002] The fire safety detection system is an integrated monitoring and alarm system that aims to improve the fire safety level of buildings and their surrounding environment. It uses various sensors and alarm devices to detect and alarm fires and related hazards in real time.

[0003] Most of the existing fire safety detection systems are offline detection, that is, through sensors set up in fixed areas, abnormal information is captured to trigger firefighting measures and perform alarm operations. However, the levels of fires vary. It is difficult for existing fire safety detection systems to judge the size and spread of fires based on actual fire conditions. It is unable to provide corresponding data support for subsequent firefighters, and it is difficult to provide firefighters with a basis for judging the on-site fire situation. There are problems with practicality and functionality.

[0004] In response to the above, this case proposes a fire safety detection system based on edge-cloud collaboration to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a fire safety detection system based on edge-cloud collaboration to solve the above technical problems by improving the detection method and processing method.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A fire safety detection system based on edge-cloud collaboration includes an edge end and a cloud end, wherein the edge end includes a sensor module and a fire response module, and the cloud end includes a fire situation analysis module and an auxiliary tracing module;

[0008] The sensor module includes a smoke sensor, a light scattering sensor, and an infrared sensor, which are used to receive field data in real time and transmit it to the edge end for determination. Based on the determination result of the edge end, a control signal is transmitted to the fire response module;

[0009] The fire response module includes relevant firefighting equipment in various areas of the scene, and controls the firefighting equipment in the relevant areas to be turned on or off based on the control signal transmitted by the edge end;

[0010] The fire situation analysis module establishes a site area model based on BIM technology according to the application scenario, receives real-time sensor data transmitted by the edge end in real time, marks the location of the fire, and predicts the development trend and development route of the fire in combination with the change trend of the sensor data received by the edge end;

[0011] The auxiliary tracing module backs up relevant data before the fire based on the sensor data transmitted from the edge, compares it with historical normal data, marks the time nodes of abnormal data, and assists in tracing the fire.

[0012] Furthermore, the fire situation analysis module establishes a site area model based on BIM technology according to the application scenario, receives real-time sensor data transmitted by the edge end in real time, marks the location of the fire, and combines the change trend of the sensor data received by the edge end to predict the development trend and development route of the fire. The specific steps are as follows:

[0013] Based on the application scenario of the detection system, the building design drawings and related data, including structure, materials, spatial layout, and location of fire-fighting equipment, are collected. The model is constructed through BIM technology, the fire determination results transmitted by the edge end are received, and the location of the fire is marked in the building model.

[0014] Based on the real-time sensor data transmitted from the edge and combined with the data change trend, the smoke concentration data, scattered light intensity data, and infrared radiation intensity data are analyzed to analyze and predict the development trend and fire level of the fire.

[0015] Furthermore, the real-time sensor data transmitted based on the edge is combined with the change trend of the data to analyze the smoke concentration data, scattered light intensity data, and infrared radiation intensity data, and analyze and predict the development trend and fire level of the fire. The specific steps are as follows:

[0016] Through the edge sensor, smoke concentration data, scattered light intensity data, and infrared radiation intensity data are received in real time. The smoke concentration change rate, scattered light intensity change rate, and infrared radiation intensity change rate are calculated in combination with the timestamp. The specific algorithm formula is as follows:

[0017]

[0018] in, represents the average rate of change of the relevant sensor data calculated in the sliding window, n represents the size of the sliding window, Δt represents the time interval for data collection, ΔD(t j )-ΔD(t j-1 ) represents the time point t j With t j-1The change in the relevant sensor data between j ) represents the sensor at time point t j The sensor data includes smoke concentration data, scattered light intensity data, and infrared radiation intensity data;

[0019] Based on the normal change rate threshold and the dangerous change rate threshold, the average change rate is determined, and the specific steps are as follows:

[0020] when When the value is less than the normal change rate threshold, it means that the change rate of the relevant sensor data is low and the fire develops slowly;

[0021] When the normal change speed threshold ≤ < Dangerous change rate threshold, indicating that the fire development is normal within the change rate of the relevant sensor data;

[0022] when ≥ Dangerous change rate threshold, indicating that the relevant sensor data changes at a high rate and the fire develops quickly;

[0023] The change rate of smoke concentration, the change rate of scattered light intensity, and the change rate of infrared radiation intensity in the area are combined to determine the fire level of the relevant area, where:

[0024] The basis for high risk determination is that if the change rate of data collected by any two sensors in the relevant area is high, it means that the relevant area is at high risk of fire;

[0025] The medium risk determination basis is that if the change rate of data collected by any two sensors in the relevant area is medium, it means that the relevant area is a medium risk fire;

[0026] The basis for low risk determination is that if the rate of change of data collected by any two sensors in the relevant area is low, it means that the relevant area is a low risk fire.

[0027] Furthermore, the fire situation analysis module also includes a fire spread trend analysis system, which analyzes the fire spread trend based on BIM model related data, and the specific steps are as follows:

[0028] Based on the marking information of the fire location in the building model, data information of the surrounding area is collected, including material information and spatial structure information, and the fire spread trend is analyzed. The specific algorithm formula is:

[0029] K m =HRR×FSR;

[0030]

[0031] Among them, K mRepresents the influence coefficient of different materials on fire spread, HRR and FSR represent the heat release rate and flame propagation rate of related materials respectively, K s represents the spatial structure influence coefficient, V and A represent the room volume and room surface area respectively, and C t represents the fire spread trend index, i represents different materials, and j represents different areas;

[0032] Based on the fire spread trend threshold C θ , when C t ≥C θ When the fire spreads to the relevant area, it is likely to spread, and it will be marked in orange on the BIM building model.

[0033] Furthermore, based on the scenario of the detection system application, the building design drawings and related data, including structure, materials, spatial layout, and location of fire-fighting equipment, are collected, a model is constructed through BIM technology, the fire determination results transmitted by the edge end are received, and the location of the fire is marked in the building model. The specific steps are:

[0034] Building models are built using BIM technology, where the collected structural information includes walls, columns, and beams. At the same time, the materials in each area are marked, including fireproof materials and flammable materials, and the material names are marked. The spatial layout includes rooms, passages, entrances and exits, and the sensor deployment location information is collected. Each data collection area is numbered with Arabic numerals and the surface area and volume are recorded;

[0035] After receiving the fire determination data from the edge, the relevant areas inside the model are marked in red according to the sensor position of the uploaded data, and the areas adjacent to the fire area are marked in blue. By receiving the data information from the edge in real time, the model is updated in real time.

[0036] Furthermore, the auxiliary tracing module backs up the relevant data before the fire based on the sensor data transmitted by the edge end, compares the historical normal data, marks the abnormal data time nodes, and assists in tracing the fire. The specific steps are as follows:

[0037] The edge side extracts the sensor data corresponding to the fire area in the sensor module, including smoke sensors, light scattering sensors, and infrared sensors, and attaches a timestamp, including the data at time T before the fire occurs;

[0038] Collect historical relevant normal sensor data, calculate the mean and standard deviation, obtain the abnormal threshold based on the 3σ criterion, and compare the data at time T before the fire. When the data at time T before the fire exceeds the set abnormal threshold, mark the relevant data as abnormal data and record the timestamp. At the same time, sort the timestamps based on time order, and select the first time point to mark as the starting time of the fire.

[0039] Furthermore, the edge and the cloud are also provided with an alarm module, which alarms for fire based on different trigger logics of the edge and the cloud, and the specific steps are as follows:

[0040] For the edge end, the fire alarm is made by dialing the preset number, where the preset number includes the fire alarm number and the emergency contact number, and the fire alarm is made by playing the preset building location information;

[0041] For the cloud, the fire level information, fire spread area information, fire development trend information and the starting time of the fire are integrated, and the relevant data are integrated and transmitted to the emergency contact mailbox.

[0042] Furthermore, the sensor module includes a smoke sensor, a light scattering sensor, and an infrared sensor. Through the sensors arranged in various areas of the scene, the field data of various areas of the scene are received in real time, including smoke concentration, scattered light intensity, infrared radiation intensity, and the relevant data are transmitted to the edge end for data judgment. The specific steps are as follows:

[0043] Based on the real-time received smoke concentration C0, scattered light intensity L0, infrared radiation intensity I0, combined with the smoke concentration threshold θ at the edge C , scattered light intensity θ L 、Infrared radiation intensityθ I , to determine the real-time fire situation on site, the steps are as follows:

[0044] When C0 ≥ θ C When , it means that the smoke concentration value in the relevant area is abnormal, and record C = 1;

[0045] When C0<θ C When , it means that the smoke concentration value in the relevant area is normal, and record C = 0;

[0046] When L0 ≥ θ L When , it means that the scattered light intensity value in the relevant area is abnormal, and record L = 1;

[0047] When L0<θ L When L=0, it means that the scattered light intensity value in the relevant area is normal, and L=0 is recorded;

[0048] When I0≥θ IWhen , it means that the infrared radiation intensity value of the relevant area is abnormal, and record I = 1;

[0049] When I0<θ I When , it means that the infrared radiation intensity value of the relevant area is normal, and record I = 0;

[0050] The fire alarm value η is calculated in real time, where η=C+L+I. When η≥2, it means that a fire has occurred in the relevant area, and the transmission opening control signal is sent to the fire response module;

[0051] The fire response module includes sprinkler fire-fighting equipment in various areas of the site. By receiving the opening control signal transmitted by the edge end, the sprinkler fire-fighting equipment in the relevant area is controlled to perform a spraying operation. At the same time, the edge end obtains the fire alarm value η through real-time calculation. When η is less than 2 at any time, a closing control signal is transmitted to the fire response module to close the sprinkler fire-fighting equipment in the relevant area.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1. In the present invention, by combining edge-cloud collaborative technology, a sensor module is set at the edge to receive abnormal data information on the scene, and perform emergency alarm and fire response at the edge based on the abnormal information, thereby reducing the response time. At the same time, the sensor data is transmitted to the cloud in real time, and the real-time data is further analyzed, thereby enhancing the functionality of the system.

[0054] 2. In the present invention, the change rate of sensor data is further analyzed through the cloud, and a building model is established in combination with BIM technology to mark the fire area and its related areas. At the same time, the level and spread trend of the fire are further analyzed to evaluate the fire risk and potential hidden dangers in the building. At the same time, on-site data support is provided for subsequent firefighters to facilitate the determination of the number and scale of police response.

[0055] 3. In the present invention, by using a combination of smoke sensors, light scattering sensors and infrared sensors, it is possible to obtain fire information of the corresponding area in real time from different angles, reducing the risk of misjudgment or missed judgment. At the same time, a three-dimensional simulation model is established based on the application environment. By combining the sensor data transmitted from the edge with the three-dimensional simulation model, the fire scene can be visualized and analyzed in real time on the cloud, which helps fire commanders to better understand the scale, scope and spread trend of the fire and formulate more scientific and reasonable fire extinguishing and rescue plans.

[0056] 4. In the present invention, the collaborative work of the edge and the cloud can achieve efficient data processing and decision support. The sensor module on the edge is responsible for real-time data collection and preliminary processing, and uploads important data to the cloud for comprehensive analysis and deep mining. The fire situation analysis module on the cloud can utilize the computing power and data analysis algorithm of the cloud to process a large amount of sensor data, providing a scientific basis for firefighting decisions. At the same time, the cloud can feed back the analysis results to the edge to guide the fire response module on the edge to take more effective measures.

[0057] 5. In the present invention, an auxiliary tracing module is set up to perform abnormal analysis on relevant data before the fire. Different alarm logics are adopted on the edge and cloud sides, so that the edge and cloud alarm systems do not interfere with each other. The failure of edge devices or delays in the cloud side will not affect the overall alarm function, thereby improving the reliability and fault tolerance of the system.

[0058] The entire fire safety detection system based on edge-cloud collaboration is based on edge-cloud collaborative technology. It is responsible for on-site monitoring and emergency alarms through the edge, and for data integration, analysis, information transmission and auxiliary alarms through the cloud, providing data support for subsequent firefighting decisions. At the same time, it analyzes and predicts fire spread trends and fire levels in real time, which helps to improve fire handling efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a block diagram of a fire safety detection system based on edge-cloud collaboration of the present invention. DETAILED DESCRIPTION

[0060] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] Embodiment 1:

[0062] like Figure 1 As shown, a fire safety detection system based on edge-cloud collaboration includes an edge end and a cloud end, wherein the edge end includes a sensor module and a fire response module, and the cloud end includes a fire situation analysis module and an auxiliary tracing module.

[0063] The sensor module, including smoke sensors, light scattering sensors, and infrared sensors, receives real-time field data from various areas of the site, including smoke concentration, scattered light intensity, and infrared radiation intensity, through sensors arranged in various areas of the site, and transmits relevant data to the edge end for data judgment. The specific steps are as follows:

[0064] Based on the real-time received smoke concentration C0, scattered light intensity L0, infrared radiation intensity I0, combined with the smoke concentration threshold θ at the edge C , scattered light intensity θ L 、Infrared radiation intensityθ I , to determine the real-time fire situation on site, the steps are as follows:

[0065] When C0 ≥ θ C When , it means that the smoke concentration value in the relevant area is abnormal, and record C = 1;

[0066] When C0<θ C When , it means that the smoke concentration value in the relevant area is normal, and record C = 0;

[0067] When L0 ≥ θ L When , it means that the scattered light intensity value in the relevant area is abnormal, and record L = 1;

[0068] When L0<θ L When L=0, it means that the scattered light intensity value in the relevant area is normal, and L=0 is recorded;

[0069] When I0≥θ I When , it means that the infrared radiation intensity value of the relevant area is abnormal, and record I = 1;

[0070] When I0<θ I When , it means that the infrared radiation intensity value of the relevant area is normal, and record I = 0;

[0071] The fire alarm value η is calculated in real time, where η=C+L+I. When η≥2, it means that a fire has occurred in the relevant area, and the transmission opening control signal enters the fire response module.

[0072] The fire response module includes relevant fire-fighting equipment in various areas of the site. Based on the control signal transmitted by the edge end, the fire-fighting equipment in the relevant area is controlled to be turned on or off.

[0073] The fire response module, including the sprinkler fire-fighting equipment in various areas of the site, controls the sprinkler fire-fighting equipment in the relevant area to perform spraying operations by receiving the opening control signal transmitted by the edge end. At the same time, the edge end obtains the fire alarm value η through real-time calculation. When η is less than 2 at any time, the closing control signal is transmitted to the fire response module to close the sprinkler fire-fighting equipment in the relevant area.

[0074] It should be noted that the smoke concentration threshold θ C , scattered light intensity θ L 、Infrared radiation intensityθ IThe setting can be based on empirical methods, that is, setting the threshold according to the average smoke concentration, scattered light intensity and infrared radiation intensity during historical fires. The threshold can also be set by consulting experts in related fields. By using three sensors to conduct three-dimensional fire detection in related areas, false alarms and missed alarms can be avoided.

[0075] The fire situation analysis module builds a site area model based on BIM technology according to the application scenario, receives real-time sensor data transmitted by the edge end, marks the location of the fire, and combines the change trend of the sensor data received by the edge end to predict the development trend and development route of the fire. The specific steps are as follows:

[0076] Based on the application scenario of the detection system, the building design drawings and related data, including structure, materials, spatial layout, and location of fire equipment, are collected. The model is constructed through BIM technology, the fire determination results transmitted by the edge end are received, and the location of the fire is marked in the building model. The specific steps are as follows:

[0077] The building model is established through BIM technology, and the structural information collected includes walls, columns, and beams. The materials in each area are marked, including fire-proof materials and flammable materials, and the material names are annotated. The spatial layout includes rooms, passages, entrances and exits, and the sensor deployment location information is collected. Each data collection area is numbered with Arabic numerals and the surface area and volume are recorded.

[0078] After receiving the fire determination data from the edge, the relevant areas inside the model are marked in red according to the sensor position of the uploaded data, and the areas adjacent to the fire area are marked in blue. By receiving the data information from the edge in real time, the model is updated in real time.

[0079] Based on the real-time sensor data transmitted by the edge, combined with the data change trend, the smoke concentration data, scattered light intensity data, and infrared radiation intensity data are analyzed, and the development trend and fire level of the fire are analyzed and predicted. The specific steps are as follows:

[0080] Through the edge sensor, smoke concentration data, scattered light intensity data, and infrared radiation intensity data are received in real time. The smoke concentration change rate, scattered light intensity change rate, and infrared radiation intensity change rate are calculated in combination with the timestamp. The specific algorithm formula is as follows:

[0081]

[0082] in, represents the average change rate of the relevant sensor data calculated in the sliding window, n represents the size of the sliding window, Δt represents the time interval for data collection, ΔD(tj )-ΔD(t j-1 ) represents the time point t j With t j-1 The change in the relevant sensor data between j ) represents the sensor at time point t j The sensor data includes smoke concentration data, scattered light intensity data, and infrared radiation intensity data.

[0083] It should be noted that n represents the size of the sliding window, which indicates the number of data points included in the calculation of the average rate of change. Usually, the value of n is set to 5, and the value of n can also be adjusted according to the actual situation. Δt represents the time interval for data collection, which is usually a fixed value of the sampling time, often set to 2 seconds, and can also be adjusted according to the actual situation. Different time intervals can adjust the sensitivity of the rate of change.

[0084] Based on the normal change rate threshold and the dangerous change rate threshold, the average change rate is determined, and the specific steps are as follows:

[0085] when When the value is less than the normal change rate threshold, it means that the change rate of the relevant sensor data is low and the fire develops slowly;

[0086] When the normal change speed threshold ≤ < Dangerous change rate threshold, indicating that the fire development is normal within the change rate of the relevant sensor data;

[0087] when ≥ Dangerous change rate threshold, indicating that the relevant sensor data changes at a high rate and the fire develops quickly;

[0088] The change rate of smoke concentration, the change rate of scattered light intensity, and the change rate of infrared radiation intensity in the area are combined to determine the fire level of the relevant area, where:

[0089] The basis for high risk determination is that if the rate of change of data collected by any two sensors in the relevant area is high, it means that the relevant area is at high risk of fire.

[0090] The basis for determining medium risk is that if the rate of change of data collected by any two sensors in the relevant area is medium, it means that the relevant area is a medium risk fire.

[0091] The basis for low risk determination is that if the rate of change of data collected by any two sensors in the relevant area is low, it means that the relevant area is a low risk fire.

[0092] It should be noted that the specific method for determining the fire level is as follows:

[0093] S1, S2, and S3 represent the change rate of smoke concentration, the change rate of scattered light intensity, and the change rate of infrared radiation intensity, respectively. The values ​​are 1, 0, and -1, representing high, medium, and low change rates, respectively.

[0094] High risk determination is based on: Any S i =S j =1, where i≠j and i, j∈{1, 2, 3};

[0095] The basis for determining medium risk is: any S i =S j =0, where i≠j and i, j∈{1, 2, 3};

[0096] Low risk determination is based on: Any S i =S j =-1, where i≠j and i, j∈{1, 2, 3}.

[0097] Embodiment 2:

[0098] The fire situation analysis module also includes a fire spread trend analysis system, which analyzes the fire spread trend based on BIM model related data. The specific steps are as follows:

[0099] Based on the marking information of the fire location in the building model, data information of the surrounding area is collected, including material information and spatial structure information, and the fire spread trend is analyzed. The specific algorithm formula is:

[0100] K m =HRR×FSR;

[0101]

[0102] Among them, K m Represents the influence coefficient of different materials on fire spread. HRR and FSR represent the heat release rate and flame propagation rate of related materials respectively. K s represents the spatial structure influence coefficient, V and A represent the room volume and room surface area respectively, and C t Represents the fire spread trend index, i represents different materials, and j represents different areas.

[0103] It should be noted that C tIt represents the fire spread trend index and is used to measure the possibility and speed of fire spread. By summing up all materials or areas, the combined impact of different materials and spatial structures in the relevant area on the spread of fire can be calculated. HRR is usually measured in kilojoules per kilogram, which indicates the energy released when the material burns. The higher the heat release rate, the more violent the material burns and the greater the impact on the spread of fire. FSR is usually measured in meters per minute, which indicates the speed at which flames spread on the surface of the material. The higher the flame spread rate, the faster the fire spreads. It can be obtained by querying information or consulting experts in related fields.

[0104] Based on the fire spread trend threshold C θ , when C t ≥C θ When the fire spreads to the relevant area, it is likely to spread, and it will be marked in orange on the BIM building model.

[0105] It should be noted that i represents different materials, including wood, plastic, metal, etc. For each material, the correlation between its combustion characteristics and the volume and surface area of ​​the area is calculated, and these results are added to obtain a comprehensive fire spread trend index. By comparing with the fire spread trend threshold, the fire spread trend analysis can be obtained. The fire spread trend threshold can be set by collecting case data of past fires, analyzing the distribution of fire spread trend indicators in these cases, and setting the fire spread trend threshold.

[0106] Embodiment 3:

[0107] The auxiliary traceability module backs up the relevant data before the fire based on the sensor data transmitted by the edge end, compares the historical normal data, marks the time nodes of abnormal data, and assists in fire traceability. The specific steps are as follows:

[0108] The edge end extracts the sensor data corresponding to the fire area in the sensor module, including smoke sensors, light scattering sensors, and infrared sensors, and attaches a timestamp, including the data at time T before the fire occurred.

[0109] Collect historical relevant normal sensor data, calculate the mean and standard deviation, obtain the abnormal threshold based on the 3σ criterion, and compare the data at time T before the fire. When the data at time T before the fire exceeds the set abnormal threshold, mark the relevant data as abnormal data and record the timestamp. At the same time, sort the timestamps based on time order, and select the first time point to mark as the starting time of the fire.

[0110] It should be noted that by comparing the data at time T before the fire, it can help discover the time when the abnormal data was generated, thereby determining the start time of the fire. At the same time, when the data at time T is abnormal, further collect data 2T before the fire to ensure that the starting data is normal data, so as to avoid the occurrence of incorrect judgment of the start time of the fire. The time T can be set flexibly and is usually set to 6 hours.

[0111] The edge and cloud are also equipped with alarm modules, which alarm for fires based on different trigger logics of the edge and cloud. The specific steps are as follows:

[0112] For the edge end, a fire alarm is made by dialing a preset number, where the preset number includes the fire alarm phone number and the emergency contact phone number, and the fire alarm is made by playing the preset building location information.

[0113] For the cloud, the fire level information, fire spread area information, fire development trend information and the starting time of the fire are integrated, and the relevant data are integrated and transmitted to the emergency contact mailbox.

[0114] It should be noted that the fire spread area information can be obtained based on the different color markings of the relevant areas in the BIM model. By integrating the fire level information, fire spread area information, fire development trend information and the starting time of the fire, it can help firefighters determine the number of police officers to be dispatched, determine the scale of the fire, and formulate a fire extinguishing plan.

[0115] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation; the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0116] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A fire safety detection system based on edge-cloud collaboration, characterized by: It includes the edge and cloud. The edge includes the sensor module and the fire response module, and the cloud includes the fire analysis module and the auxiliary tracing module. The sensor module includes a smoke sensor, a light scattering sensor, and an infrared sensor, which are used to receive field data in real time and transmit it to the edge end for determination. Based on the determination result of the edge end, a control signal is transmitted to the fire response module; The fire response module includes relevant firefighting equipment in various areas of the scene, and controls the firefighting equipment in the relevant areas to be turned on or off based on the control signal transmitted by the edge end; The fire situation analysis module establishes a site area model based on BIM technology according to the application scenario, receives real-time sensor data transmitted by the edge end in real time, marks the location of the fire, and predicts the development trend and development route of the fire in combination with the change trend of the sensor data received by the edge end; The auxiliary tracing module backs up relevant data before the fire based on the sensor data transmitted from the edge, compares it with historical normal data, marks the time nodes of abnormal data, and assists in tracing the fire.

2. According to claim 1, a fire safety detection system based on edge-cloud collaboration is characterized in that: The fire situation analysis module establishes a site area model based on BIM technology according to the application scenario, receives real-time sensor data transmitted by the edge end in real time, marks the location of the fire, and predicts the development trend and development route of the fire in combination with the change trend of the sensor data received by the edge end. The specific steps are as follows: Based on the application scenario of the detection system, the building design drawings and related data, including structure, materials, spatial layout, and location of fire-fighting equipment, are collected. The model is constructed through BIM technology, the fire determination results transmitted by the edge end are received, and the location of the fire is marked in the building model. Based on the real-time sensor data transmitted from the edge and combined with the data change trend, the smoke concentration data, scattered light intensity data, and infrared radiation intensity data are analyzed to analyze and predict the development trend and fire level of the fire.

3. According to the fire safety detection system based on edge-cloud collaboration according to claim 2, it is characterized by: The real-time sensor data transmitted based on the edge is combined with the change trend of the data to analyze the smoke concentration data, scattered light intensity data, and infrared radiation intensity data, and analyze and predict the development trend and fire level of the fire. The specific steps are as follows: Through the edge sensor, smoke concentration data, scattered light intensity data, and infrared radiation intensity data are received in real time. The smoke concentration change rate, scattered light intensity change rate, and infrared radiation intensity change rate are calculated in combination with the timestamp. The specific algorithm formula is as follows: in, represents the average rate of change of the relevant sensor data calculated in the sliding window, n represents the size of the sliding window, Δt represents the time interval for data collection, ΔD(t j )-ΔD(t j-1 ) represents the time point t j With t j-1 The change in the relevant sensor data between j ) represents the sensor at time point t j The sensor data includes smoke concentration data, scattered light intensity data, and infrared radiation intensity data; Based on the normal change rate threshold and the dangerous change rate threshold, the average change rate is determined, and the specific steps are as follows: when This means that the rate of change of relevant sensor data is low and the fire develops slowly; when It means that the fire is developing normally in the rate of change of the relevant sensor data; when It means that the relevant sensor data changes at a high rate and the fire develops quickly; The change rate of smoke concentration, the change rate of scattered light intensity, and the change rate of infrared radiation intensity in the area are combined to determine the fire level of the relevant area, where: The basis for high risk determination is that if the change rate of data collected by any two sensors in the relevant area is high, it means that the relevant area is at high risk of fire; The medium risk determination basis is that if the change rate of data collected by any two sensors in the relevant area is medium, it means that the relevant area is a medium risk fire; The basis for low risk determination is that if the rate of change of data collected by any two sensors in the relevant area is low, it means that the relevant area is a low risk fire.

4. The fire safety detection system based on edge-cloud collaboration according to claim 2 is characterized in that: The fire situation analysis module also includes a fire spread trend analysis system, which analyzes the fire spread trend based on BIM model related data. The specific steps are as follows: Based on the marking information of the fire location in the building model, data information of the surrounding area is collected, including material information and spatial structure information, and the fire spread trend is analyzed. The specific algorithm formula is: K m =HRR×FSR; Among them, K m Represents the influence coefficient of different materials on fire spread. HRR and FSR represent the heat release rate and flame propagation rate of related materials respectively. K s represents the spatial structure influence coefficient, V and A represent the room volume and room surface area respectively, and C t represents the fire spread trend index, i represents different materials, and j represents different areas; Based on the fire spread trend threshold C θ , when C t ≥C θ When the fire spreads to the relevant area, it is likely to spread, and it will be marked in orange on the BIM building model.

5. The fire safety detection system based on edge-cloud collaboration according to claim 2 is characterized in that: The scenario based on the application of the detection system collects building design drawings and related data, including structure, materials, spatial layout, and location of fire-fighting equipment, builds a model through BIM technology, receives the fire determination results transmitted by the edge end, and marks the location of the fire in the building model. The specific steps are as follows: Building models are built using BIM technology, where the collected structural information includes walls, columns, and beams. At the same time, the materials in each area are marked, including fireproof materials and flammable materials, and the material names are marked. The spatial layout includes rooms, passages, entrances and exits, and the sensor deployment location information is collected. Each data collection area is numbered with Arabic numerals and the surface area and volume are recorded; After receiving the fire determination data from the edge, the relevant areas inside the model are marked in red according to the sensor position of the uploaded data, and the areas adjacent to the fire area are marked in blue. By receiving the data information from the edge in real time, the model is updated in real time.

6. The fire safety detection system based on edge-cloud collaboration according to claim 1 is characterized in that: The auxiliary tracing module backs up the relevant data before the fire based on the sensor data transmitted by the edge end, compares the historical normal data, marks the abnormal data time nodes, and assists in tracing the fire. The specific steps are as follows: The edge side extracts the sensor data corresponding to the fire area in the sensor module, including smoke sensors, light scattering sensors, and infrared sensors, and attaches a timestamp, including the data at time T before the fire occurs; Collect historical relevant normal sensor data, calculate the mean and standard deviation, obtain the abnormal threshold based on the 3σ criterion, and compare the data at time T before the fire. When the data at time T before the fire exceeds the set abnormal threshold, mark the relevant data as abnormal data and record the timestamp. At the same time, sort the timestamps based on time order, and select the first time point to mark as the starting time of the fire.

7. The fire safety detection system based on edge-cloud collaboration according to claim 6 is characterized in that: The edge and the cloud are also provided with an alarm module, which alarms for fire based on different trigger logics of the edge and the cloud. The specific steps are as follows: For the edge end, the fire alarm is made by dialing the preset number, where the preset number includes the fire alarm number and the emergency contact number, and the fire alarm is made by playing the preset building location information; For the cloud, the fire level information, fire spread area information, fire development trend information and the starting time of the fire are integrated, and the relevant data are integrated and transmitted to the emergency contact mailbox.

8. The fire safety detection system based on edge-cloud collaboration according to claim 1 is characterized in that: The sensor module includes a smoke sensor, a light scattering sensor, and an infrared sensor. Through the sensors arranged in various areas of the scene, the field data of various areas of the scene are received in real time, including smoke concentration, scattered light intensity, infrared radiation intensity, and the relevant data are transmitted to the edge end for data judgment. The specific steps are as follows: Based on the real-time received smoke concentration C0, scattered light intensity L0, infrared radiation intensity I0, combined with the smoke concentration threshold θ at the edge C , scattered light intensity θ L 、Infrared radiation intensityθ I , to determine the real-time fire situation on site, the steps are as follows: When C0 ≥ θ C When , it means that the smoke concentration value in the relevant area is abnormal, and record C = 1; When C0<θ C When , it means that the smoke concentration value in the relevant area is normal, and record C = 0; When L0 ≥ θ L When , it means that the scattered light intensity value in the relevant area is abnormal, and record L = 1; When L0<θ L When L=0, it means that the scattered light intensity value in the relevant area is normal, and L=0 is recorded; When I0≥θ I When , it means that the infrared radiation intensity value of the relevant area is abnormal, and record I = 1; When I0<θ I When , it means that the infrared radiation intensity value of the relevant area is normal, and record I = 0; The fire alarm value η is calculated in real time, where η=C+L+I. When η≥2, it means that a fire has occurred in the relevant area, and the transmission opening control signal is sent to the fire response module; The fire response module includes sprinkler fire-fighting equipment in various areas of the site. By receiving the opening control signal transmitted by the edge end, the sprinkler fire-fighting equipment in the relevant area is controlled to perform a spraying operation. At the same time, the edge end obtains the fire alarm value η through real-time calculation. When η is less than 2 at any time, a closing control signal is transmitted to the fire response module to close the sprinkler fire-fighting equipment in the relevant area.

Images