Fire alarm system based on Internet of Things

Abstract

The invention relates to the technical field of fire-fighting alarm, in particular to a fire-fighting alarm system based on the Internet of Things, which comprises a scene information acquisition module for acquiring scene information and historical fire-fighting data of a target fire-fighting scene, a real-time data acquisition module for acquiring fire-fighting data, sound spectrum data, equipment data and high-rise building data, a scene information analysis module, a real-time data acquisition module for acquiring real-time data of the target fire-fighting scene, and a fire-fighting alarm module. The monitoring module is used for analyzing the ventilation state of a target fire-fighting scene and determining the risk weight of the target fire-fighting scene, and the real-time monitoring module is used for analyzing the real-time environment state and the damage state of stored goods, building the floor spreading weight and building the hidden danger characteristic index of the target fire-fighting scene. The equipment analysis module is used for carrying out iteration on the construction process of the hidden danger characteristic index, and the safety alarm module is used for carrying out fire-fighting alarm to a user. The high-rise building fire alarm system effectively improves the accuracy of high-rise building fire alarm.

Description

Technical Field

[0001] The present invention relates to the technical field of personnel safety warning, and particularly to a fire alarm system based on the Internet of Things. Background Art

[0002] With the acceleration of the urbanization process, high-rise buildings, especially high-rise storage buildings for warehousing and logistics, are increasing day by day. These places usually store a large number of goods. Once a fire breaks out, it will not only cause huge economic losses, but also pose a threat to the lives of personnel. Traditional fire alarm systems often have problems such as slow response and untimely information transmission, and it is difficult to meet the fire safety requirements of modern high-rise buildings.

[0003] Chinese Patent Publication No. CN116052360A discloses a fire alarm system. The invention includes: a target area monitoring point determination unit configured to determine a plurality of monitoring groups in the target area, and each monitoring group includes a plurality of monitoring points evenly distributed at equal intervals; a movable sensor group including a plurality of sensor groups, and each sensor group includes a plurality of sensors with the same quantity and the same type. By dividing a plurality of monitoring groups in the target area and then moving the movable sensor group to each monitoring point in the monitoring group, comprehensive monitoring of the target area is realized. At the same time, during the monitoring process, device data information and environmental data information are combined, and a fire warning model of the environmental data information is used to judge whether a fire breaks out, with higher accuracy. Then, the response level is judged through the device data information. It can be seen that this invention is applied to fire alarm in a single scenario, without performing intelligent analysis on fire alarm in complex scenarios. When performing fire alarm on the target area in complex scenarios, there are problems of low alarm efficiency and low accuracy. Summary of the Invention

[0004] The purpose of the present invention is to provide a fire alarm system based on the Internet of Things to solve at least one of the problems existing in the prior art.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions:

[0006] A fire alarm system based on the Internet of Things, characterized by including:

[0007] A scene information acquisition module for acquiring the scene information and historical fire data of the target fire scene;

[0008] A real-time data acquisition module for acquiring fire data, sound spectrum data, device data, and high-rise building data during the monitoring period;

[0009] A scene information analysis module, which is used to analyze the ventilation state of the target fire scene according to the scene information of the target fire scene, and determine the risk weight of the target fire scene according to the flammability index, storage ratio and ventilation state of the stored goods;

[0010] A real-time monitoring module, which is used to analyze the real-time environmental state according to the fire data, analyze the damaged state of the stored goods according to the sound spectrum data, analyze the floor spread state of the target fire scene according to the high-rise building data, construct a floor spread weight according to the analysis result of the floor spread state, and construct a hidden danger characteristic index of the target fire scene according to the analysis results of the real-time environmental state, the damaged state of the stored goods and the floor spread state;

[0011] A safety alarm module, which is used to give a fire alarm to the user according to the construction result of the hidden danger characteristic index within the monitoring period and the risk weight of the target fire scene.

[0012] Further, the scene information analysis module includes a ventilation state analysis unit, which is used to analyze the ventilation state of the target fire scene according to the scene information of the target fire scene;

[0013] The ventilation state analysis unit is used to calculate the air circulation index α of the target fire scene, and set α = f / S × s / S; where S is the volume of the target fire scene, s is the volume of the stored goods in the target fire scene, and f is the unit circulating air volume of the target fire scene;

[0014] The ventilation state analysis unit analyzes the ventilation state of the target fire scene according to the air circulation index of the target fire scene to determine whether the ventilation state of the target fire scene is abnormal.

[0015] Further, the scene state analysis module also includes a risk weight analysis unit, which is used to determine the risk weight of the target fire scene according to the flammability index, storage ratio and the analysis result of the ventilation state of the target fire scene;

[0016] The risk weight analysis unit is used to construct the risk weight of the target fire scene: when the ventilation state of the target fire scene is abnormal, if β×(α - A) / A < K1, the risk weight analysis unit determines that the risk level of the target fire scene is level two, and sets the risk weight of the target fire scene to FQ1; otherwise, the risk weight analysis unit determines that the risk level of the target fire scene is level one, and sets the risk weight of the target fire scene to FQ2;

[0017] When the ventilation state of the target fire scene is normal, if β×(α - A) / A < K2, the risk weight analysis unit determines that the risk level of the target fire scene is level three and sets the risk weight of the target fire scene to FQ3; otherwise, the risk weight analysis unit determines that the risk level of the target fire scene is level two and sets the risk weight of the target fire scene to FQ4;

[0018] Among them, β is the flammability index of the stored goods, and β is set to v1 / v2, where v1 is the volume of the stored goods body and v2 is the volume of the packaging of the stored goods. K1 is the first preset risk coefficient, and K2 is the second preset risk coefficient.

[0019] Furthermore, the real-time monitoring module includes a first environment analysis unit, which is used to analyze the real-time environment state according to the fire data within the monitoring period;

[0020] The first environment analysis unit calculates the hidden danger index γ of the target fire scene, and γ is set to (t - T) / T×a1 + (sd - SD) / SD×a2 + a3×(ρ - H) / H; where t is the temperature of the target fire scene within the monitoring period, sd is the absolute humidity of the target fire scene within the monitoring period, ρ is the line density of the target fire scene within the monitoring period, T is the set temperature of the target fire scene, SD is the set absolute humidity of the target fire scene, H is the set line density of the target fire scene, a1 is the temperature weight, a2 is the humidity weight, a3 is the line density weight, and a1 + a2 + a3 = 1;

[0021] The first environment analysis unit analyzes the real-time environment state of the target fire scene according to the hidden danger index γ of the target fire scene to determine whether the real-time environment state of the target fire scene is abnormal.

[0022] Furthermore, the real-time monitoring module also includes a second environment analysis unit, which is used to analyze the damaged state of the stored goods according to the spectrogram data within the monitoring period;

[0023] The second environment analysis unit performs frame division on the spectrogram data within the monitoring period and extracts the spectrogram features of the spectrogram data;

[0024] The second environment analysis unit matches the spectrogram features with the preset feature set and analyzes the damaged state of the stored goods according to the matching result to determine whether the stored goods are damaged.

[0025] Furthermore, the real-time monitoring module further includes a third environmental analysis unit, which is used to analyze the floor spread state of the target fire scene during the monitoring period based on the high-rise building data, and construct a floor spread weight according to the analysis results: if η < N, the third environmental analysis unit determines that the floor spread state of the target fire scene is normal, constructs a floor spread weight w1, and sets w1 = 1; if η ≥ N, the third environmental analysis unit determines that the floor spread state of the target fire scene is abnormal, constructs a floor spread weight w2, and sets w2 = exp{(η - N) / N};

[0026] Where η is the floor air pressure state index, and η = (p1 - p2) / (P - pd) is set, where p1 is the floor pressure between the target fire scene and the floor below, p2 is the floor pressure between the target fire scene and the floor above, P is the atmospheric pressure at the top floor of the building where the target fire scene is located, pd is the atmospheric pressure of the target fire scene, and N is the air pressure ratio threshold.

[0027] Furthermore, the real-time monitoring module further includes a hidden danger analysis unit, which is used to construct the hidden danger characteristic index of the target fire scene based on the analysis results of the real-time environmental state, the analysis results of the damaged state of the stored goods, and the analysis results of the floor spread state: when the real-time environmental state is abnormal, if the damaged state of the stored goods is damaged, the hidden danger analysis unit sends a fire warning to the user; if the damaged state of the stored goods is not damaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene during the monitoring period to yh1; when the real-time environmental state is normal, if the damaged state of the stored goods is damaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene during the monitoring period to yh2; if the damaged state of the stored goods is not damaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene during the monitoring period to yh3.

[0028] Furthermore, it further includes an equipment analysis module, which is used to iterate the construction process of the hidden danger characteristic index according to the equipment data of the target fire scene;

[0029] The equipment analysis module includes an equipment status analysis unit, which is used to analyze the equipment operation status of the target fire scene according to the equipment data during the monitoring period;

[0030] The equipment status analysis unit is used to analyze the power status of each equipment during the monitoring period, and the analysis results of the power status of the equipment include aging abnormality, normal, and fluctuation abnormality;

[0031] The device status analysis unit counts the number YN of devices with an aging abnormal power status, analyzes the operating status of the devices in the target fire protection scenario according to the statistical results, the analysis result of the operating status of the devices in the target fire protection scenario includes normal and abnormal, and when the operating status of the devices in the target fire protection scenario is abnormal, iterates the preset environmental status index to Y'.

[0032] Further, the device analysis module further includes a historical data analysis unit, and the historical data analysis unit is used to calibrate the iteration process of the hidden danger characteristic index according to the historical fire protection data of the target fire protection scenario. When the historical fire protection frequency r of the target fire protection scenario exceeds the preset fire protection frequency R, the proportionality constant is calibrated to μ'.

[0033] Further, the safety alarm module is used to analyze the fire safety level of the target fire protection scenario according to the result of constructing the hidden danger characteristic index within the monitoring period and the risk weight of the target fire protection scenario, and perform a fire alarm to the user according to the analysis result: if (risk weight + hidden danger characteristic index) × stv < AQ1, the safety alarm module determines that the fire safety level of the target fire protection scenario within the monitoring period is level three and does not alarm the user; if AQ1 ≤ (risk weight + hidden danger characteristic index) × stv < AQ2, the safety alarm module determines that the fire safety level of the target fire protection scenario within the monitoring period is level two and gives an audible and visual alarm to the user; if (risk weight + hidden danger characteristic index) × stv ≥ AQ2, the safety alarm module determines that the fire safety level of the target fire protection scenario within the monitoring period is level one and gives a broadcast alarm to the user;

[0034] Wherein, stv is the rising temperature of the target fire protection scenario within the monitoring period, AQ1 is the first preset alarm weight, AQ2 is the second preset alarm weight, and AQ1 < AQ2.

[0035] Compared with the prior art, the beneficial effects of the present invention are as follows: aiming at the unique ventilation state, floor spread characteristics and storage goods characteristics of high-rise buildings, providing customized analysis logic to effectively cope with complex scenarios that are difficult to handle by traditional systems; based on historical fire protection data and device operating status, the system can dynamically calibrate parameters to improve the stability and adaptability of long-term operation; relying on the Internet of Things technology to realize real-time data collection and analysis, reducing manual intervention, and improving the efficiency and reliability of fire monitoring, which is applicable to large-scale warehousing and high-rise building management. Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0037] Figure 1 This is a schematic structural diagram of the fire alarm system based on the Internet of Things in this embodiment.

[0038] Figure 2 This is a schematic structural diagram of the scene information analysis module in this embodiment.

[0039] Figure 3 This is a schematic structural diagram of the real-time monitoring module in this embodiment.

[0040] Figure 4 This is a schematic structural diagram of the device analysis module in this embodiment. Specific implementation manners

[0041] To describe the present invention more clearly, the present invention will be further described below in conjunction with preferred embodiments and the accompanying drawings. Similar components in the drawings are denoted by the same reference numerals. Those skilled in the art should understand that the content specifically described below is illustrative rather than restrictive, and should not be used to limit the protection scope of the present invention.

[0042] It should be noted that although terms such as first, second, and third may be used in the embodiments of the present application for description, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, without departing from the scope of the embodiments of the present application, the first may also be referred to as the second, and similarly, the second may also be referred to as the first.

[0043] Specifically, a fire alarm system based on the Internet of Things described in this embodiment is applied to the fire alarm of high-rise buildings. The high-rise buildings described in this embodiment are specifically high-rise storage buildings, and the high-rise storage buildings described in this embodiment are specifically storage warehouses for storing glass products and their flammable packaging; at the same time, the system described in this embodiment acts on the fire data processing server.

[0044] Please refer to Figure 1 as shown, which is a schematic structural diagram of the fire alarm system based on the Internet of Things in this embodiment, including:

[0045] A scene information collection module, which is used to collect the scene information and historical fire data of the target fire scene;

[0046] Specifically, the target fire scene described in this embodiment is specifically a high-rise building; the scene information includes the volume of the target fire scene, the volume of the stored goods in the target fire scene, the unit circulating air volume of the target fire scene, the flammability index of the stored goods, the volume of the stored goods body, and the volume of the packaging of the stored goods; the historical fire data includes the historical fire frequency of the target fire scene.

[0047] Please continue to refer to Figure 1As shown, the system further includes:

[0048] A real-time data acquisition module for acquiring fire data, sound spectrum data, equipment data, and high-rise building data within a monitoring period; the fire data includes the temperature of the target fire scene, the absolute humidity of the target fire scene, and the line density of the target fire scene; the sound spectrum data includes the sound spectrum within the detection period; the equipment data includes the rated power of the equipment, the operating power of the equipment within the monitoring period, and the minimum operating power for the equipment to operate normally; the high-rise building data includes the floor pressure between the target fire scene and the downstairs, the floor pressure between the target fire scene and the upstairs, the atmospheric pressure at the top floor of the building where the target fire scene is located, and the atmospheric pressure of the target fire scene.

[0049] Specifically, in this embodiment, no specific limitation is imposed on the value of the duration of the monitoring period, and those skilled in the art can freely set it as long as the value requirement of the duration of the monitoring period is met. In this embodiment, the value of the duration of the monitoring period is set to 5 seconds.

[0050] Specifically, in this embodiment, the scene information and historical fire data of the target fire scene are collected through user interaction input, and the fire data, sound spectrum data, equipment data, and high-rise building data are collected by intelligent sensors in the fire protection system through the Internet of Things; by collecting the volume of the target fire scene, the storage ratio of goods, historical fire data, etc., comprehensive basic data is provided for subsequent analysis to ensure the comprehensiveness and accuracy of risk assessment; combined with the historical fire frequency, the system parameters can be dynamically adjusted to enhance the pertinence to high-frequency risk scenarios; real-time acquisition of fire data (temperature, humidity, line density), sound spectrum data, equipment data, and high-rise building data is realized to achieve multi-dimensional monitoring, covering the key indicators of fire hazards, and the Internet of Things technology is used to quickly collect data through intelligent sensors to improve the real-time performance and response speed of the system.

[0051] Please continue to refer to Figure 1 As shown, the system further includes a scene information analysis module. The scene information analysis module is connected to the scene information acquisition module. The scene information analysis module is used to analyze the ventilation state of the target fire scene according to the scene information of the target fire scene, and determine the risk weight of the target fire scene according to the flammability index, storage ratio of the stored goods, and ventilation state of the target fire scene.

[0052] Please refer to Figure 2 As shown, the scene information analysis module includes:

[0053] A ventilation state analysis unit for analyzing the ventilation state of the target fire scene according to the scene information of the target fire scene;

[0054] The ventilation state analysis unit is used to calculate the air circulation index α of the target fire scene, and set α = f / S × s / S; where S is the volume of the target fire scene, s is the volume of the stored goods in the target fire scene, and f is the unit circulating air volume of the target fire scene.

[0055] The ventilation state analysis unit analyzes the ventilation state of the target fire scene according to the air circulation index of the target fire scene: if α < A, the ventilation state analysis unit determines that the ventilation state of the target fire scene is abnormal; if α ≥ A, the ventilation state analysis unit determines that the ventilation state of the target fire scene is normal; where A is the preset air circulation index; by quantifying the ventilation state through the air circulation index (α) and combining with the preset threshold (A) to judge abnormality, it provides a scientific basis for risk assessment and avoids subjective misjudgment.

[0056] Specifically, in this embodiment, the value of the preset air circulation index A is not specifically limited, and those skilled in the art can freely set it as long as it meets the value requirements of the preset air circulation index A. In this embodiment, the preset air circulation index A can be set to 0.2; it can be understood that the optimal value of the preset air circulation index A in this embodiment is determined based on the stored goods and the scene tightness of the target fire scene. In this embodiment, a mathematical model is used to construct the minimum point of the influence of the volume and storage volume of the target fire scene on the air inlet and outlet, and the air circulation index at this time is used as the preset air circulation index A. The mathematical model in this embodiment includes four variables: the volume of the target fire scene, the storage volume, and the air inlet and outlet rate. The specific implementation process is fully disclosed in the prior art and will not be elaborated here.

[0057] Please continue to refer to Figure 2 As shown, the scene state analysis module further includes:

[0058] A risk weight analysis unit, which is connected to the ventilation state analysis unit. The risk weight analysis unit is used to determine the risk weight of the target fire scene according to the flammability index, storage ratio of the stored goods, and the analysis result of the ventilation state of the target fire scene.

[0059] The risk weight analysis unit is used to construct the risk weight of the target fire scene: when the ventilation state of the target fire scene is abnormal, if β × (α - A) / A < K1, the risk weight analysis unit determines that the risk level of the target fire scene is secondary, and sets the risk weight of the target fire scene as FQ1, and sets FQ1 = 1 + [β × (α - A) / A - K1] / K1; if β × (α - A) / A ≥ K1, the risk weight analysis unit determines that the risk level of the target fire scene is primary, and sets the risk weight of the target fire scene as FQ2, and sets FQ2 = 1 + exp{[β × (α - A) / A - K1] / K1};

[0060] When the ventilation state of the target fire scene is normal, if β×(α - A) / A < K2, the risk weight analysis unit determines that the risk level of the target fire scene is level three, and sets the risk weight of the target fire scene to FQ3, where FQ3 = 1; otherwise, the risk weight analysis unit determines that the risk level of the target fire scene is level two, and sets the risk weight of the target fire scene to FQ4, where FQ4 = 1 + [β×(α - A) / A - K2] / K2; Based on the flammability index (β), storage ratio, and ventilation state, dynamically calculate the risk weights (FQ1 - FQ4) to achieve hierarchical early warning and improve the refinement of risk identification;

[0061] Among them, β is the flammability index of the stored goods, and β = v1 / v2 is set, where v1 is the volume of the stored goods itself, v2 is the packaging volume of the stored goods, K1 is the first preset risk coefficient, and K2 is the second preset risk coefficient.

[0062] Specifically, in this embodiment, the values of the first preset risk coefficient K1 and the second preset risk coefficient K2 are not specifically limited, and those skilled in the art can freely set them as long as the value requirements of the first preset risk coefficient K1 and the second preset risk coefficient K2 are met. In this embodiment, the best value of the first preset risk coefficient K1 is 0.2, and the best value of the second preset risk coefficient K2 is 0.3.

[0063] Please continue to refer to Figure 1 As shown, the system further includes a real-time monitoring module, which is connected to the real-time data collection module, and the real-time monitoring module is used to analyze the real-time environmental state according to the fire data within the monitoring period.

[0064] Please refer to Figure 3 As shown, the real-time monitoring module includes a first environmental analysis unit, which is used to analyze the real-time environmental state according to the fire data within the monitoring period;

[0065] The first environmental analysis unit calculates the hidden danger index γ of the target fire scene, and γ = (t - T) / T×a1 + (sd - SD) / SD×a2 + a3×(ρ - H) / H is set; where t is the temperature of the target fire scene within the monitoring period, sd is the absolute humidity of the target fire scene within the monitoring period, ρ is the line density of the target fire scene within the monitoring period, T is the set temperature of the target fire scene, SD is the set absolute humidity of the target fire scene, H is the set line density of the target fire scene, a1 is the temperature weight, a2 is the humidity weight, a3 is the line density weight, and a1 + a2 + a3 = 1; Comprehensively evaluate the deviation degree of temperature, humidity, and line density through the hidden danger index, quickly judge environmental anomalies, and reduce the risk of missed reports;

[0066] The first environmental analysis unit analyzes the real-time environmental state of the target fire scene according to the hidden danger index γ of the target fire scene: if γ < Y, the first environmental analysis unit determines that the real-time environmental state of the target fire scene during the monitoring period is normal; otherwise, the first environmental analysis unit determines that the real-time environmental state of the target fire scene during the monitoring period is abnormal; where Y is a preset environmental state index.

[0067] Specifically, in this embodiment, no specific limitation is imposed on the value of the preset environmental state index Y, and those skilled in the art can freely set it as long as it meets the value requirements of the preset environmental state index Y. The optimal value of the preset environmental state index Y in this embodiment is 0.5; it can be understood that the value of the preset environmental state index Y in this embodiment needs to be determined in combination with the set offset value of the target fire scene. The set offset value includes the allowable temperature offset value, humidity offset value, and line density offset value. The specific calculation process is to substitute these set offset values into the formula for calculating γ for T, SD, and H respectively, and the resulting value is the optimal value of Y. The allowable temperature offset value, humidity offset value, and line density offset value are all freely set by the user; at the same time, the values of a1, a2, and a3 are also freely set by the user, and the optimal values given in this embodiment are 0.5, 0.3, and 0.2 respectively.

[0068] Please continue to refer to Figure 3 As shown, the real-time monitoring module further includes a second environmental analysis unit, which is used to analyze the damaged state of the stored goods according to the spectrogram data within the monitoring period;

[0069] The second environmental analysis unit performs frame division on the spectrogram data within the monitoring period and extracts the spectrogram features of the spectrogram data;

[0070] The second environmental analysis unit matches the spectrogram features with a preset feature set and analyzes the damaged state of the stored goods according to the matching result: if the match is successful, the second environmental analysis unit determines that the damaged state of the stored goods during the monitoring period is damaged; if the match fails, the second environmental analysis unit determines that the damaged state of the stored goods during the monitoring period is undamaged; using the spectrogram feature matching technology, accurately identify the damaged state of the stored goods (such as glass products) to avoid secondary fires caused by damaged goods.

[0071] Specifically, the preset feature set in this embodiment is the spectrogram features of the stored goods (glass products) breaking; this embodiment does not specifically limit the process of extracting spectrogram data, and its technical means are fully disclosed in the prior art, so this application will not elaborate here.

[0072] Please continue to refer to Figure 3As shown, the real-time monitoring module further includes a third environmental analysis unit, which is used to analyze the floor spread state of the target fire scene during the monitoring period according to the high-rise building data, and construct a floor spread weight according to the analysis result: if η < N, the third environmental analysis unit determines that the floor spread state of the target fire scene is normal, constructs a floor spread weight w1, and sets w1 = 1; if η ≥ N, the third environmental analysis unit determines that the floor spread state of the target fire scene is abnormal, constructs a floor spread weight w2, and sets w2 = exp{(η - N) / N};

[0073] Among them, η is the floor air pressure state index, and it is set that η = (p1 - p2) / (P - pd), where p1 is the layer pressure between the target fire scene and the floor below, p2 is the layer pressure between the target fire scene and the floor above, P is the atmospheric pressure at the top floor of the building where the target fire scene is located, pd is the atmospheric pressure of the target fire scene, and N is the air pressure ratio threshold; a floor spread weight is constructed based on the floor air pressure state index (η) to predict the fire spread trend and numerically judge the chimney effect of high-rise buildings.

[0074] Specifically, in this embodiment, no specific limitation is made on the value of the air pressure ratio threshold N, and those skilled in the art can freely set it as long as the value requirement of the air pressure ratio threshold N is met. The best value of the air pressure ratio threshold N in this embodiment is 0.2. It can be understood that in this embodiment, if the target fire scene is separated from the top floor by n floors, the conservative value of N can be 1 / n.

[0075] Please continue to refer to Figure 3 As shown, the real-time monitoring module further includes a hidden danger analysis unit, which is connected to the first environmental analysis unit, the second environmental analysis unit, and the third environmental analysis unit. The hidden danger analysis unit is used to construct a hidden danger characteristic index of the target fire scene according to the real-time environmental state analysis result, the storage goods damage state analysis result, and the floor spread state analysis result:

[0076] When the real-time environmental state is abnormal, if the damage state of the storage goods is damaged, the hidden danger analysis unit sends a fire warning to the user; if the damage state of the storage goods is not damaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene during the monitoring period as yh1, and sets yh1 = (γ - Y) / Y × floor spread weight;

[0077] When the real-time environmental state is normal, if the damaged state of the warehoused goods is damaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene within the monitoring period to yh2, and sets yh2 = floor spread weight; if the damaged state of the warehoused goods is undamaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene within the monitoring period to yh3, and sets yh3 = 0; combining the real-time environment, goods state and floor spread weight, dynamically construct the hidden danger characteristic index (yh1 - yh3) to achieve multi-condition linkage alarm and improve the rigor of the early warning logic.

[0078] Please continue to refer to Figure 1 As shown, the system further includes an equipment analysis module, which is connected to the real-time monitoring module, and the equipment analysis module is used to iterate the construction process of the hidden danger characteristic index according to the equipment data of the target fire scene.

[0079] Please refer to Figure 4 As shown, the equipment analysis module includes an equipment status analysis unit, which is used to analyze the equipment operation status of the target fire scene according to the equipment data within the monitoring period;

[0080] The equipment status analysis unit is used to analyze the power status of each equipment within the monitoring period: if gp(i) ≥ GP(i), the equipment status analysis unit determines that the power status of the equipment is aging abnormally; if DP(i) ≤ gp(i) < GP(i), the equipment status analysis unit determines that the power status of the equipment is normal; if gp(i) < DP(i), the equipment status analysis unit determines that the power status of the equipment is fluctuating abnormally;

[0081] Among them, GP(i) represents the rated power of the i-th equipment, gp(i) represents the operating power of the i-th equipment within the monitoring period, and DP(i) represents the minimum operating power for the normal operation of the i-th equipment;

[0082] The equipment status analysis unit counts the number of equipment YN whose power status is aging abnormally, and analyzes the equipment operation status of the target fire scene according to the statistical result: if YN / ZN < μ, the equipment status analysis unit determines that the equipment operation status of the target fire scene within the monitoring period is normal and does not perform iteration; if YN / ZN ≥ μ, the equipment status analysis unit determines that the equipment operation status of the target fire scene within the monitoring period is abnormal, and iterates the preset environmental state index to Y’, and sets Y’ = Y × exp(μ - YN / ZN);

[0083] Among them, μ is a proportional constant, and ZN is the total number of equipment; through power status analysis (aging abnormality, normal, fluctuating abnormality), identify equipment failure risks, and timely adjust the preset environmental state index to avoid false alarms or missed alarms caused by equipment aging.

[0084] It can be understood that in this embodiment, the value of the proportional constant μ is not specifically limited, and those skilled in the art can freely set it as long as the value requirement of the proportional constant μ is met. The optimal value of the proportional constant μ in this embodiment is 0.1. It should be noted that the value of the proportional constant μ in this embodiment needs to be determined in combination with practical experience and mathematical models. This part of the content has been fully disclosed in the prior art and will not be elaborated herein. In this embodiment, when the proportional constant μ is greater than 0.1, the probability of a fire accident will increase.

[0085] Please continue to refer to Figure 4 As shown, the device analysis module further includes a historical data analysis unit, which is connected to the device state analysis unit. The historical data analysis unit is used to calibrate the iterative process of the hidden danger characteristic index according to the historical fire data of the target fire scenario: if r < R, the historical data analysis unit determines that the historical fire frequency of the target fire scenario is normal and does not perform calibration; if r ≥ R, the historical data analysis unit determines that the historical fire frequency of the target fire scenario is abnormal and calibrates the proportional constant to μ', where μ' = μ × ln{e^(-(r - R) / R)}; where r is the historical fire frequency of the target fire scenario, R is the preset fire frequency, and e is the natural logarithm. By calibrating the proportional constant in combination with the historical fire frequency (r), the system parameters are dynamically optimized to enhance the adaptability to high-frequency risk scenarios.

[0086] Specifically, in this embodiment, the value of the preset fire frequency R is not specifically limited, and those skilled in the art can freely set it as long as the value requirement of the preset fire frequency R is met. The optimal value of the preset fire frequency R in this embodiment is 2 times / year. In this embodiment, the historical fire frequency specifically refers to the frequency of the fire alarm system, not the actual frequency of fires.

[0087] Please continue to refer to Figure 1As shown, the system further includes a safety alarm module, which is connected to the real-time monitoring module and the scenario information analysis module. The safety alarm module is used to analyze the fire safety level of the target fire scenario according to the construction result of the hidden danger characteristic index within the monitoring period and the risk weight of the target fire scenario, and conduct a fire alarm to the user according to the analysis result: If (risk weight + hidden danger characteristic index) × stv < AQ1, the safety alarm module determines that the fire safety level of the target fire scenario within the monitoring period is level three and does not alarm the user; If AQ1 ≤ (risk weight + hidden danger characteristic index) × stv < AQ2, the safety alarm module determines that the fire safety level of the target fire scenario within the monitoring period is level two and gives an audible and visual alarm to the user; If (risk weight + hidden danger characteristic index) × stv ≥ AQ2, the safety alarm module determines that the fire safety level of the target fire scenario within the monitoring period is level one and gives a broadcast alarm to the user; By comprehensively considering the risk weight, hidden danger characteristic index, and temperature rise value (stv), three-level alarm levels (no alarm at level three, audible and visual alarm at level two, broadcast alarm at level one) are divided to achieve hierarchical response and avoid over-alarming from disturbing the user; Combining with Internet of Things technology, alarm information can be quickly pushed to the user terminal to improve the emergency response efficiency;

[0088] Among them, stv is the rising temperature of the target fire scenario within the monitoring period, AQ1 is the first preset alarm weight, AQ2 is the second preset alarm weight, and AQ1 < AQ2.

[0089] Specifically, in this embodiment, the values of the first preset alarm weight AQ1 and the second preset alarm weight AQ2 are not specifically limited, and those skilled in the art can freely set them as long as the value requirements of the first preset alarm weight AQ1 and the second preset alarm weight AQ2 are met. In this embodiment, the optimal values of the first preset alarm weight AQ1 and the second preset alarm weight AQ2 are 0.3 and 0.5 respectively; It can be understood that in this embodiment, the levels of three, two, and one represent the levels of fire alarms from safe to dangerous; At the same time, in this embodiment, the value of the second preset alarm weight AQ2 is the lowest value of {(risk weight + hidden danger characteristic index) × stv} during historical fire accidents, and the value of the first preset alarm weight AQ1 is 80% of {(risk weight + hidden danger characteristic index) × stv}.

[0090] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. A fire alarm system based on the Internet of Things, characterized in that: include: A scene information collection module is used to collect scene information and historical fire data of the target fire scene; Real-time data acquisition module, used to collect fire data, sound spectrum data, equipment data and high-rise building data within the monitoring period; A scene information analysis module is used to analyze the ventilation status of the target fire scene according to the scene information of the target fire scene, and determine the risk weight of the target fire scene according to the flammability index, storage ratio and ventilation status of the stored goods; A real-time monitoring module is used to analyze the real-time environmental status according to the fire data, and to analyze the damaged status of the stored goods according to the sound spectrum data. It is also used to analyze the floor spread status of the target fire scene according to the high-rise building data, and to construct the floor spread weight according to the analysis results of the floor spread status. It is also used to construct the hidden danger characteristic index of the target fire scene according to the real-time environmental status analysis results, the damaged status analysis results of the stored goods and the floor spread status analysis results; The safety alarm module is used to issue fire alarms to users based on the hidden danger characteristic index construction results within the monitoring period and the risk weight of the target fire scene.

2. The fire alarm system based on the Internet of Things according to claim 1 is characterized in that: The scene information analysis module includes a ventilation state analysis unit, which is used to analyze the ventilation state of the target fire scene according to the scene information of the target fire scene; The ventilation state analysis unit is used to calculate the air circulation index α of the target fire scene, and α is set to be f / S×s / S; wherein S is the volume of the target fire scene, s is the volume of the goods stored in the target fire scene, and f is the unit ventilation air volume of the target fire scene; The ventilation state analysis unit analyzes the ventilation state of the target fire fighting scene according to the air circulation index of the target fire fighting scene to determine whether the ventilation state of the target fire fighting scene is abnormal.

3. The fire alarm system based on the Internet of Things according to claim 2 is characterized in that: The scenario state analysis module also includes a risk weight analysis unit, which is used to determine the risk weight of the target fire scene according to the flammability index of the stored goods, the storage ratio and the ventilation state analysis results of the target fire scene; The risk weight analysis unit is used to construct the risk weight of the target fire scene: when the ventilation state of the target fire scene is abnormal, if β×(α-A) / A<K1, the risk weight analysis unit determines that the risk level of the target fire scene is level 2, and sets the risk weight of the target fire scene to FQ1; otherwise, the risk weight analysis unit determines that the risk level of the target fire scene is level 1, and sets the risk weight of the target fire scene to FQ2; When the ventilation state of the target fire scene is normal, if β×(α-A) / A<K2, the risk weight analysis unit determines that the risk level of the target fire scene is level three, and sets the risk weight of the target fire scene to FQ3; otherwise, the risk weight analysis unit determines that the risk level of the target fire scene is level two, and sets the risk weight of the target fire scene to FQ4; Among them, β is the flammability index of the stored goods, and β is set to v1 / v2, where v1 is the volume of the stored goods, v2 is the packaging volume of the stored goods, K1 is the first preset risk coefficient, and K2 is the second preset risk coefficient.

4. The fire alarm system based on the Internet of Things according to claim 3 is characterized in that: The real-time monitoring module includes a first environment analysis unit, which is used to analyze the real-time environment status according to the fire data within the monitoring period; The first environmental analysis unit calculates the hidden danger index γ of the target fire scene, and sets γ=(tT) / T×a1+(sd-SD) / SD×a2+a3×(ρ-H) / H; wherein t is the temperature of the target fire scene during the monitoring period, sd is the absolute humidity of the target fire scene during the monitoring period, ρ is the line density of the target fire scene during the monitoring period, T is the set temperature of the target fire scene, SD is the set absolute humidity of the target fire scene, H is the set line density of the target fire scene, a1 is the temperature weight, a2 is the humidity weight, a3 is the line density weight, and a1+a2+a3=1; The first environment analysis unit analyzes the real-time environment state of the target fire scene according to the hidden danger index γ of the target fire scene to determine whether the real-time environment state of the target fire scene is abnormal.

5. The fire alarm system based on the Internet of Things according to claim 4 is characterized in that: The real-time monitoring module further includes a second environment analysis unit, which is used to analyze the damage status of the stored goods according to the sound spectrum data within the monitoring period; The second environment analysis unit performs a frame operation on the sound spectrum data within the monitoring period and extracts the sound spectrum features of the sound spectrum data; The second environment analysis unit matches the sound spectrum feature with a preset feature set, and analyzes the damage state of the stored goods according to the matching result to determine whether the stored goods are damaged.

6. The fire alarm system based on the Internet of Things according to claim 5 is characterized in that: The real-time monitoring module further includes a third environment analysis unit, which is used to analyze the floor spread state of the target fire scene within the monitoring period according to the high-rise building data, and construct a floor spread weight according to the analysis result: if η<N, the third environment analysis unit determines that the floor spread state of the target fire scene is normal, and constructs a floor spread weight w1, setting w1=1; If η≥N, the third environment analysis unit determines that the floor spread state of the target fire scene is abnormal, constructs a floor spread weight w2, and sets w2=exp{(η-N) / N}; Among them, η is the floor air pressure state index, set η = (p1-p2) / (P-pd), p1 is the layer pressure between the target fire scene and the downstairs, p2 is the layer pressure between the target fire scene and the upstairs, P is the atmospheric pressure on the top floor of the building where the target fire scene is located, pd is the atmospheric pressure of the target fire scene, and N is the air pressure ratio threshold.

7. The fire alarm system based on the Internet of Things according to claim 6 is characterized in that: The real-time monitoring module also includes a hidden danger analysis unit for constructing a hidden danger characteristic index of the target fire scene according to the real-time environmental status analysis results, the damaged status analysis results of the stored goods and the floor spread status analysis results: when the real-time environmental status is abnormal, if the damaged status of the stored goods is damaged, the hidden danger analysis unit sends a fire warning to the user; if the damaged status of the stored goods is undamaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene within the monitoring period to yh1; when the real-time environmental status is normal, if the damaged status of the stored goods is damaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene within the monitoring period to yh2; if the damaged status of the stored goods is undamaged, the hidden danger analysis unit sets the hidden danger characteristic index of the target fire scene within the monitoring period to yh3.

8. The fire alarm system based on the Internet of Things according to claim 7 is characterized in that: It also includes an equipment analysis module, which is used to iterate the construction process of the hidden danger characteristic index according to the equipment data of the target fire scene; The equipment analysis module includes an equipment status analysis unit, which is used to analyze the equipment operation status of the target fire scene according to the equipment data within the monitoring period; The device status analysis unit is used to analyze the power status of each device within the monitoring period, and the power status analysis results of the device include aging abnormality, normal and fluctuation abnormality; The device status analysis unit counts the number of devices YN whose power status is abnormal aging, and analyzes the device operation status of the target fire scene based on the statistical results. The equipment operation status analysis results of the target fire scene include normal and abnormal, and when the equipment operation status of the target fire scene is abnormal, the preset environmental status index is iterated to Y'.

9. The fire alarm system based on the Internet of Things according to claim 8, characterized in that: The equipment analysis module also includes a historical data analysis unit, which is used to calibrate the iterative process of the hidden danger characteristic index according to the historical fire data of the target fire scene, and when the historical fire frequency r of the target fire scene exceeds the preset fire frequency R, the proportional constant is calibrated to μ'.

10. The fire alarm system based on the Internet of Things according to claim 9, characterized in that: The security alarm module is used to analyze the fire safety level of the target fire scene according to the hidden danger characteristic index construction result and the risk weight of the target fire scene within the monitoring period, and to issue a fire alarm to the user according to the analysis result: if (risk weight + hidden danger characteristic index) × stv < AQ1, the security alarm module determines that the fire safety level of the target fire scene within the monitoring period is level three, and does not issue an alarm to the user; if AQ1≤(risk weight + hidden danger characteristic index) × stv < AQ2, the security alarm module determines that the fire safety level of the target fire scene within the monitoring period is level two, and issues an audible and visual alarm to the user; if (risk weight + hidden danger characteristic index) × stv≥AQ2, the security alarm module determines that the fire safety level of the target fire scene within the monitoring period is level one, and issues a broadcast alarm to the user; Wherein, stv is the rising temperature of the target fire scene within the monitoring period, AQ1 is the first preset alarm weight, AQ2 is the second preset alarm weight, and AQ1<AQ2.

Images