Fire-fighting three-level linkage management and control method and system based on risk dynamic coding

Abstract

The application relates to a fire-fighting three-level linkage management and control method and system based on risk dynamic coding, a computer device and a storage medium. The method comprises the following steps: acquiring multi-source data of a target area, wherein the multi-source data comprises building structure parameters, material combustion characteristic parameters and real-time environmental data; calculating a structure risk quantitative value according to the building structure parameters and temperature parameters and according to a fire spread physical law constraint, and calculating a material risk quantitative value according to the material combustion characteristic parameters and environmental concentration parameters and according to a material combustion and environmental coupling effect constraint; fusing the two into a comprehensive risk value, combining the structure risk quantitative value, the material risk quantitative value and target dynamic parameters, and generating a risk level according to different preset conditions corresponding to different risk levels; in response to low-level triggering inspection, medium-level starting medium-level collaborative disposal and adjusting equipment parameters, and high-level starting high-level collaborative disposal and adjusting equipment parameters, so as to realize accurate evaluation and hierarchical management and control, and form a closed-loop management from early warning to disposal.

Description

Technical Field

[0001] This application relates to the field of intelligent fire protection management technology, and in particular to a fire protection three-level linkage control method, system, computer equipment and storage medium based on dynamic risk coding. Background Technology

[0002] With the acceleration of urbanization, fire safety management in complex architectural settings such as high-rise buildings and ancient city blocks faces severe challenges. High-rise buildings have a significantly higher fire risk than ordinary buildings due to difficulties in vertical evacuation and complex maintenance of fire protection facilities; ancient city blocks have weak fire protection infrastructure and prominent fire risks due to factors such as low fire resistance rating of wooden structures, insufficient fire separation distances, and aging electrical wiring.

[0003] To address these challenges, existing technologies include fire management systems based on risk level color-coded warnings. For example, the "High-Rise Building Fire Safety Code" system developed in Chongqing integrates data such as building height and fire safety facility status, using a fire risk assessment model to classify high-rise buildings into five warning levels: red, orange, yellow, blue, and green. This achieves a "one building, one code, unified management" model. Such systems can classify buildings by risk level and push hazard rectification tasks to the relevant responsible personnel.

[0004] However, existing fire risk management systems still have significant shortcomings in risk calculation and coordinated response. At the risk calculation level, existing systems primarily rely on preset static weights or weighted scoring models to determine risk levels, failing to incorporate building structural parameters (such as cavity dimensions and opening areas) and material combustion characteristic parameters (such as heat release rate and smoke generation rate) into the risk quantification model. This results in risk assessment results that fail to accurately reflect the actual risk status of the building during a fire. At the coordinated response level, existing systems mainly rely on preset rules or manual dispatch for task allocation and equipment control after risk level determination, lacking dynamic priority ranking mechanisms based on real-time risk values ​​and adaptive equipment coordination control mechanisms. These deficiencies lead to technical problems in fire management, including insufficient accuracy in risk assessment and low efficiency in response. Summary of the Invention

[0005] Therefore, it is necessary to provide a fire protection three-level linkage control method, system, computer equipment, and storage medium that can quantify risks based on physical laws and drive hierarchical linkage response, based on risk dynamic coding, to address the above-mentioned technical problems.

[0006] Firstly, this application provides a three-level linkage control method for fire protection based on dynamic risk coding. The method includes: Acquire multi-source data for the target area, including building structure parameters, material combustion characteristic parameters, and real-time environmental data; Based on the building structure parameters and the temperature parameters in the real-time environmental data, and constrained by the physical laws of fire spread, the structural risk quantification value of the target area is calculated; based on the material combustion characteristic parameters and the environmental concentration parameters in the real-time environmental data, and constrained by the coupling effect between material combustion and the environment, the material risk quantification value of the target area is calculated. The structural risk quantification value and the material risk quantification value are merged into a comprehensive risk value. Based on the comprehensive risk value, the structural risk quantification value, the material risk quantification value, and the target dynamic parameters in the real-time environmental data, the risk level of the target area is generated according to different preset conditions corresponding to different risk levels. In response to a low risk level, a basic-level inspection is triggered; in response to a medium risk level, an intermediate-level collaborative response is initiated and the operating parameters of the fire-fighting equipment are adjusted according to the dynamic control mapping relationship; in response to a high risk level, an advanced-level collaborative response is initiated and the operating parameters of the fire-fighting equipment are adjusted according to the dynamic control mapping relationship; wherein the advanced-level collaborative response has a higher priority than the intermediate-level collaborative response.

[0007] In one embodiment, the building structural parameters include at least the cavity height and the opening area; the structural risk quantification value is calculated according to the following formula: in, The cavity height refers to the continuous vertical height of the vertically extending cavity structure within the target area. Let be the area of ​​the opening. The temperature parameter is... As the reference temperature, The cavity structure influence coefficient is the one calibrated in the experiment. This is the temperature index coefficient calibrated for the experiment.

[0008] In one embodiment, the material combustion characteristic parameters include at least the heat release rate and the flue gas generation rate; the environmental concentration parameters include at least the carbon monoxide concentration; and the material risk quantification value is calculated according to the following formula: in, The heat release rate, The flue gas generation rate, The carbon monoxide concentration is [value missing]. The temperature parameter is a thermodynamic temperature. This is a preset dimensionless safety threshold constant. The material combustion coupling coefficient was calibrated in the experiment. The temperature effect index coefficient is a positive real number, determined experimentally. , , and These are the corresponding baseline values.

[0009] In one embodiment, the target dynamic parameters include smoke diffusion rate and population density; generating the risk level of the target area includes: For each risk level, there are corresponding structural risk assessment conditions and material risk assessment conditions. The structural risk assessment condition is that the quantitative value of the structural risk is greater than the structural risk threshold corresponding to the risk level. The material risk assessment condition is that the quantitative value of the material risk is greater than the material risk threshold corresponding to the risk level, the personnel density is greater than the personnel density threshold corresponding to the risk level, and the smoke diffusion rate is greater than the diffusion rate threshold corresponding to the risk level. When the structural risk assessment conditions or the material risk assessment conditions are met, the corresponding risk level is generated.

[0010] In one embodiment, the step of fusing the structural risk quantification value and the material risk quantification value into a comprehensive risk value includes: The overall risk value is calculated using the following formula: in, These are simulation results of the target area based on a fire dynamics simulator; This is the predicted value of the target region based on an artificial intelligence model; The physical simulation weighting coefficients are automatically adjusted according to the duration of the fire. The AI ​​prediction weighting coefficients are automatically adjusted according to the duration of the fire. The historical hazard weighting coefficient is automatically adjusted according to the duration of the fire. These are historical risk factors determined based on historical hazard data.

[0011] In one embodiment, the physical simulation weight coefficient monotonically increases from an initial preset value to converge to 1 as the fire duration increases; the artificial intelligence prediction weight coefficient monotonically decreases from an initial preset value to converge to 0 as the fire duration increases; and the historical hazard weight coefficient is positively correlated with the square root of the number of historical hazard factors.

[0012] In one embodiment, the method further includes: for the same risk level, when initiating corresponding collaborative handling, if there are multiple tasks to be handled, a risk-driven priority algorithm is invoked to calculate the handling priority of each task to be handled and execute them in descending order, wherein: When the risk level is medium, the handling priority is calculated according to the following formula: When the risk level is the high level, the handling priority is calculated according to the following formula: in, This is the overall risk value; It is a risk propagation factor between adjacent areas, and is determined by the product of the sum of the comprehensive risk values ​​of adjacent areas and the structural correlation coefficient, wherein the structural correlation coefficient is determined based on the ventilation duct connectivity or fire separation distance between the target area and adjacent areas. The timeliness factor is taken into account, and the type of hazard is determined based on the historical hazard data of the target area; , , , , , All are weighting coefficients. , ,and .

[0013] Secondly, this application also provides a fire protection three-level linkage control system based on dynamic risk coding. The system includes: A multi-source data acquisition module is used to acquire multi-source data of the target area, including building structure parameters, material combustion characteristic parameters, and real-time environmental data. The risk quantification module is used to calculate the structural risk quantification value of the target area based on the building structure parameters and the temperature parameters in the real-time environmental data, and constrained by the physical laws of fire spread; and to calculate the material risk quantification value of the target area based on the material combustion characteristic parameters and the environmental concentration parameters in the real-time environmental data, and constrained by the coupling effect between material combustion and the environment. The risk level generation module is used to merge the structural risk quantification value and the material risk quantification value into a comprehensive risk value, and generate the risk level of the target area according to different preset conditions corresponding to different risk levels based on the comprehensive risk value, the structural risk quantification value, the material risk quantification value and the target dynamic parameters in the real-time environmental data; The tiered linkage response module is used to trigger a grassroots inspection when the risk level is low; to initiate intermediate-level collaborative response and adjust the operating parameters of the fire-fighting equipment according to the dynamic control mapping relationship when the risk level is medium; and to initiate advanced-level collaborative response and adjust the operating parameters of the fire-fighting equipment according to the dynamic control mapping relationship when the risk level is high. The advanced-level collaborative response has a higher priority than the intermediate-level collaborative response.

[0014] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the aforementioned fire-fighting three-level linkage control method based on dynamic risk coding.

[0015] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the aforementioned fire-fighting three-level linkage control method based on dynamic risk coding.

[0016] The aforementioned fire-fighting three-level linkage control method, system, computer equipment, and storage media based on dynamic risk coding solve the problem of lack of physical law support in risk calculation in existing technologies by quantifying building structural parameters and real-time temperature according to the physical laws of fire spread. This enables the quantified structural risk value to truly reflect the enhancing effect of building cavity structure on fire spread. By quantifying material combustion characteristic parameters and environmental concentration parameters according to the coupling effect of material combustion and environment, dynamic quantitative assessment of the contribution of material combustion characteristics to fire risk is achieved. By integrating structural risk quantification values ​​and material risk quantification values ​​into a comprehensive risk value and generating risk levels according to different preset conditions corresponding to different risk levels, an upgrade from single static threshold alarm to multi-parameter composite logic judgment is achieved, reducing the false alarm rate. By triggering grassroots inspections, intermediate collaborative responses, and advanced collaborative responses according to low, medium, and high risk levels respectively, and adjusting the operating parameters of fire-fighting equipment according to dynamic control mapping relationships, a full-process hierarchical linkage closed-loop management from early warning to response is achieved, improving the intelligence level of fire management and emergency response efficiency. Attached Figure Description

[0017] Figure 1 This is an application environment diagram of a fire protection three-level linkage control method based on risk dynamic coding in one embodiment; Figure 2 This is a flowchart illustrating a three-level fire protection linkage control method based on dynamic risk coding in one embodiment. Figure 3 This is a schematic diagram of the process for generating risk levels in one embodiment; Figure 4 This is a structural block diagram of a fire-fighting three-level linkage control system based on dynamic risk coding in one embodiment; Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] The fire protection three-level linkage control method based on dynamic risk coding provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on the cloud or other network servers. (Described in conjunction with the overall scheme of claim 1). Terminal 102 collects multi-source data within the target area. Server 104 calculates the structural risk quantification value and material risk quantification value based on the multi-source data reported by terminal 102, merges them to generate a comprehensive risk value, generates a risk level according to multi-parameter composite triggering rules, and executes a graded linkage response based on the risk level. Control commands to adjust the operating parameters of fire-fighting equipment are issued through a dynamic control mapping relationship. Terminal 102 is an IoT sensing device and fire equipment controller deployed within the target area. Terminal 102 can also be called a data acquisition terminal, edge node, or fire equipment control terminal. Terminal 102 can be, but is not limited to, various fixed environmental monitoring devices, IoT sensor nodes, fire equipment control units, edge computing gateways, etc. Its specific form depends on the deployment of fire protection facilities in the target area. For example, in high-rise buildings, it may be smoke detectors, heat detectors, and fire door controllers deployed on each floor; in ancient city blocks, it may be electrical fire monitors and fire pump controllers deployed in historical buildings. Server 104 is a fire control platform server deployed at the building level or central control level. Server 104 can be implemented using a standalone server or a server cluster composed of multiple servers. Server 104 can also be called a fire control platform, risk analysis server, or fire linkage decision server. Those skilled in the art can flexibly select or adjust the deployment method and specific form of the above-mentioned devices according to the actual application scenario, as long as they can achieve the functions of the embodiments of this application.

[0020] Firstly, in existing fire management systems, risk level determination mainly relies on preset static weights or weighted scoring models, failing to incorporate building structural parameters and material combustion characteristics into the risk quantification model. This results in risk assessment results that do not accurately reflect the actual risk status of the building during a fire. Furthermore, existing fire management systems primarily rely on preset rules or manual dispatch for task allocation and equipment control after risk level determination, lacking an adaptive linkage control mechanism based on real-time risk values. Therefore, in one embodiment, such as... Figure 2 As shown, a three-level linkage control method for fire protection based on dynamic risk coding is provided, and this method is applied to... Figure 1 Taking terminal 102 as an example, the explanation includes the following steps: S1: Acquire multi-source data for the target area, including building structure parameters, material combustion characteristic parameters, and real-time environmental data.

[0021] In this step, building structure parameters are used to describe the building geometry and spatial structure of the target area, including but not limited to the dimensions of cavities and opening areas that can affect the fire spread rate; material combustion characteristic parameters are used to describe the combustion behavior of the main building and decoration materials in the target area, including but not limited to the heat release rate and smoke generation rate of the materials under heating conditions; real-time environmental data are used to describe the environmental state of the target area at the current moment, including but not limited to temperature, carbon monoxide concentration, smoke concentration, wind speed, and population density. The above multi-source data can be collected in real time through an IoT sensor network deployed in the target area, or obtained through a building information model database and a historical fire database. This embodiment does not limit the specific source of the data. The collection frequency of real-time environmental data can be determined according to the actual application scenario; for example, it can be set to collect data once every 5 seconds to meet the needs of real-time risk monitoring.

[0022] S2: Based on the building structure parameters and temperature parameters in real-time environmental data, and constrained by the physical laws of fire spread, calculate the structural risk quantification value of the target area; based on the material combustion characteristic parameters and environmental concentration parameters in real-time environmental data, and constrained by the coupling effect between material combustion and the environment, calculate the material risk quantification value of the target area.

[0023] In this step, the cavity height and opening area in the building structure parameters determine the spread rate of fire smoke within the vertical cavity structure, while the temperature parameter affects the intensity of the chimney effect. The constraint based on the physical laws of fire spread means that when calculating the structural risk quantification value, a quantitative model based on fire dynamics principles is used. This model reflects the enhancing effect of the building cavity structure on the fire spread rate, rather than using a purely data-driven statistical fitting method. The specific calculation method for the structural risk quantification value in this step can employ any existing fire risk assessment method based on building structure and temperature parameters, such as an empirical model based on ventilation factors or a numerical simulation method based on a fire dynamics simulator. This embodiment does not limit this approach. A higher structural risk quantification value indicates that the building structure in the target area is more conducive to the rapid spread of fire under the current temperature conditions.

[0024] Secondly, the heat release rate in the material combustion characteristic parameters reflects the rate at which the material releases heat during combustion, and the flue gas generation rate reflects the rate at which the material produces flue gas during combustion; the carbon monoxide concentration in the environmental concentration parameters reflects the degree of accumulation of combustion products in the current environment. The constraint of the coupling effect between material combustion and the environment means that when calculating the material risk contribution value, the material's own combustion characteristics are coupled with the current environmental state. That is, the contribution of the material's heat release rate and flue gas generation rate to the carbon monoxide concentration in the environment, as well as the promoting effect of environmental temperature on the material's pyrolysis rate, jointly determine the material's actual fire risk contribution under the current environmental conditions. The higher the material risk contribution value, the easier and more intense the combustion of the material within the target area is under the current environmental conditions.

[0025] S3: The structural risk quantification value and the material risk quantification value are integrated into a comprehensive risk value. Based on the comprehensive risk value, the structural risk quantification value, the material risk quantification value and the target dynamic parameters in the real-time environmental data, the risk level of the target area is generated according to different preset conditions corresponding to different risk levels.

[0026] In this step, the specific method of data fusion can employ any existing data fusion method, such as weighted summation, product method, or rule-based comprehensive evaluation method; this embodiment does not limit this approach. The comprehensive risk value is a quantitative indicator that comprehensively reflects the current fire risk level of the target area; a higher value indicates a greater risk.

[0027] Target dynamic parameters include, but are not limited to, smoke diffusion rate and personnel density, which reflect the dynamic changes at the fire scene. Different risk levels correspond to different preset conditions. The preset conditions for each risk level consist of a set of thresholds, including but not limited to the comprehensive risk value threshold, structural risk quantification value threshold, material risk quantification value threshold, smoke diffusion rate threshold, and personnel density threshold. The specific method for generating risk levels is as follows: the comprehensive risk value, structural risk quantification value, material risk quantification value, and target dynamic parameters are compared with the preset conditions corresponding to each risk level. When the above parameters meet all the preset conditions for a certain risk level, the target area is marked as that risk level. The generation of risk levels is a dynamic process; as real-time environmental data changes, the risk level of the target area can be reassessed and updated.

[0028] S4: In response to a low risk level, a basic-level inspection is triggered; in response to a medium risk level, an intermediate-level collaborative response is initiated and the operating parameters of the fire-fighting equipment are adjusted according to the dynamic control mapping relationship; in response to a high risk level, an advanced-level collaborative response is initiated and the operating parameters of the fire-fighting equipment are adjusted according to the dynamic control mapping relationship; among them, the response priority of the advanced-level collaborative response is higher than that of the intermediate-level collaborative response.

[0029] In this step, "basic inspection" refers to notifying grassroots fire safety management personnel to conduct regular inspections of the target area to identify potential hazards. "Initiating intermediate-level coordinated response" involves notifying the next higher-level management node and coordinating relevant resources for response. "Initiating advanced-level coordinated response" involves notifying even higher-level management nodes and coordinating more resources for emergency response. The dynamic control mapping relationship refers to the correspondence between risk levels and fire equipment operating parameters; different risk levels correspond to different combinations of equipment control parameters. Fire equipment includes, but is not limited to, smoke exhaust fans, fire doors, and fire hydrants. Advanced-level coordinated response has a higher priority than intermediate-level coordinated response; that is, when both intermediate and high-level risks exist simultaneously, the coordinated response task corresponding to the high-level risk is handled first.

[0030] Based on the above, this embodiment incorporates building structural parameters and material combustion characteristic parameters into the risk quantification model, and quantifies them according to the constraints of the physical laws of fire spread and the coupling effect of material combustion with the environment, so that the risk assessment results truly reflect the actual fire risk status of the target area; by executing graded linkage response according to the risk level and adjusting the operating parameters of fire-fighting equipment according to the dynamic control mapping relationship, adaptive graded linkage closed-loop management from early warning to disposal is realized.

[0031] In existing technologies, although some fire management systems consider the impact of building height on fire risk, they fail to explicitly quantify the physical relationship between the specific geometric parameters of the building's cavity structure and the fire spread rate, resulting in a lack of physical support for structural risk quantification. Therefore, in one embodiment, the building structural parameters include at least cavity height and opening area. Specifically, cavity height refers to the continuous vertical height of a vertically connected cavity structure within the target area, such as the vertical height of elevator shafts, stairwells, and pipe shafts in high-rise buildings; opening area refers to the area of ​​the connecting opening between the cavity structure and the external space within the target area, such as the area of ​​windows, doorways, and ventilation openings. In a building fire, when a fire occurs at the bottom or middle of the vertical cavity structure, hot smoke moves upward along the cavity under buoyancy, forming a chimney effect. The greater the cavity height, the longer the smoke travels upward, and the stronger the chimney effect; the larger the opening area, the more sufficient the supply of fresh air, and the more intense the combustion. Therefore, cavity height and opening area are the core geometric parameters determining the intensity of the chimney effect.

[0032] Based on this, the structural risk quantification value is calculated according to the following formula: in, The cavity height is expressed in meters (m). The cavity height is the continuous vertical height of the vertical cavity structure that runs through the target area. The area of ​​the opening is expressed in square meters (m²). 2 ). The temperature parameter is expressed in Kelvin (K), and the ambient temperature is the real-time temperature. The reference temperature is in Kelvin (K) and is a pre-set reference temperature. The cavity structure influence coefficient, calibrated in the experiment, is a dimensionless coefficient that reflects the degree to which a specific cavity structure enhances the spread of fire. The temperature index coefficient is the experimentally calibrated coefficient, which is a dimensionless coefficient and reflects the degree of nonlinear influence of temperature on the intensity of the chimney effect.

[0033] In one feasible manner, the reference temperature A value of 293.15K (i.e., 20℃) can be taken, which is a reference temperature under normal environmental conditions. Cavity structure influence coefficient. and temperature index coefficient Obtained through experimental calibration. The physical meaning of is the enhancement coefficient of the cavity structure on the fire spread speed. The larger the value, the faster the fire spreads under the same cavity height and opening area. The calibration method is as follows: Under standard experimental conditions, select multiple groups of different cavity heights. and different opening areas The combined operating conditions were used to measure the fire spread rate under each condition. Substitute the measured data into the formula Perform nonlinear regression fitting, where The baseline fire spread rate for a cavity-free structure was obtained simultaneously through regression analysis. and The value of . In one feasible way, The value can be 0.05. The value can be 0.7. Opening area With cavity height The product of the square roots The ventilation factor has the dimension L. 5 / 2 Ventilation factor is a standard physical quantity used in fire dynamics to characterize the ventilation conditions of cavity structures. The ventilation factor has an approximately linear relationship with the fire heat release rate; therefore, the potential intensity of a fire can be assessed by calculating the ventilation factor. Temperature ratio This reflects the amplifying effect of temperature on the chimney effect; the higher the temperature, the stronger the chimney effect. Temperature index coefficient. A value greater than 0 indicates that the structural risk quantification value increases monotonically with increasing temperature.

[0034] The physical derivation of this formula is based on the following: In fire dynamics, the rising velocity of smoke in a vertical cavity is driven by buoyancy, and the magnitude of buoyancy is proportional to the temperature difference between the inside and outside of the cavity. When the ambient temperature changes from... Rise to At that time, the buoyancy of the flue gas increases, and the chimney effect enhancement factor increases with temperature ratio. It is directly proportional to a power function. Meanwhile, the ventilation conditions of the cavity are determined by the ventilation factor. Characterized by a higher ventilation factor, more sufficient air supply, and more intense combustion. Therefore, the structural risk quantification value... Based on baseline value 1 (basic risk without chimney effect), an enhanced chimney effect term is added. .

[0035] This embodiment uses ventilation factors Compared to temperature The power function establishes an explicit quantitative relationship between cavity height, opening area, and temperature parameters on the structural risk quantification value, giving the calculation of the structural risk quantification value clear physical meaning and physical law constraints.

[0036] In existing technologies, the contribution of material combustion characteristics to fire risk is typically assessed using fixed risk level scores or static weights, without coupling and quantifying the material's heat release rate and smoke generation rate with dynamic parameters such as real-time environmental carbon monoxide concentration and temperature. Therefore, in one embodiment, the material combustion characteristic parameters include at least the heat release rate and the smoke generation rate.

[0037] Specifically, the Heat Release Rate (HRR) refers to the amount of heat released by a material per unit time during combustion. It is a core parameter for assessing the fire hazard of a material; a higher HRR indicates that the material releases more heat during combustion, thus promoting fire development. The Smoke Production Rate (SPR) refers to the amount of smoke generated by a material per unit time during combustion; a higher SPR indicates that the material produces more smoke during combustion, thus hindering evacuation and fire rescue efforts. Environmental concentration parameters include at least carbon monoxide concentration. Carbon monoxide is the main toxic gas produced when materials undergo incomplete combustion, and its concentration reflects the completeness of the combustion reaction and the degree of oxygen deficiency in the environment. The carbon monoxide concentration (C) is collected in real time by carbon monoxide sensors deployed within the target area.

[0038] Based on this, the material risk quantification value is calculated according to the following formula: in, The heat release rate is expressed in kilowatts (kW), and represents the measured heat release rate of the main building materials within the target area. The flue gas generation rate is expressed as m² / sqm. 2 / s), which represents the measured flue gas generation rate of the main building materials within the target area. The concentration of carbon monoxide is expressed in parts per million (ppm), representing the real-time measurement of carbon monoxide by a sensor within the target area. The temperature parameter is a thermodynamic temperature, measured in Kelvin (K), and represents the real-time measurement value of the temperature sensor within the target area. This is a preset dimensionless safety threshold constant used to prevent the calculation results from diverging due to an excessively small denominator. The material combustion coupling coefficient, calibrated for experimental purposes, reflects the degree to which temperature promotes the pyrolysis rate of the material. The temperature effect index coefficient is a positive real number calibrated for experimental purposes, reflecting the nonlinearity of the temperature-induced pyrolysis rate promoting effect on materials. The heat release rate is the baseline value, expressed in kilowatts (kW), representing the heat release rate of the reference material under standard experimental conditions. This is the baseline value for flue gas generation rate, expressed in square meters per second (m²).2 / s), which is the flue gas generation rate of the reference material under standard experimental conditions. This is the baseline value for carbon monoxide concentration, expressed in parts per million (ppm). It serves as a reference value for carbon monoxide concentration. This is the temperature reference value, in Kelvin (K), and is the reference temperature.

[0039] In one feasible approach, the heat release rate (HRR) and flue gas formation rate (SPR) can be measured using a cone calorimeter experiment according to the ISO 5660 standard method, or obtained from a material combustion characteristics database. (Reference values) and The reference materials were tested under standard experimental conditions (thermal radiation flux of 50 kW / m²). 2 The heat release rate and flue gas generation rate under these conditions are used to perform dimensionless processing of HRR and SPR. Carbon monoxide concentration C is collected in real time by carbon monoxide sensors deployed within the target area, with a reference value... As a reference value for carbon monoxide concentration, in a feasible manner A value of 500 ppm is acceptable. The temperature parameter T is the thermodynamic temperature (in K), obtained in real-time by a temperature sensor and converted to a temperature scale; the reference value is... As a reference temperature, in one feasible way A possible value is 293.15K. This is the safety threshold constant. Given a pre-defined dimensionless positive number, in one feasible manner, The value can be 0.01. Material combustion coupling coefficient. Temperature effect index coefficient Obtained through experimental calibration. The physical meaning of is the temperature-dependent pyrolysis rate promotion coefficient of a material; the larger the value, the stronger the promoting effect of temperature increase on the pyrolysis of the material. The calibration method is as follows: In a controlled environment test chamber, different ambient temperatures TT are set, and the pyrolysis rate of the standard sample at each temperature is measured. The measured data are then substituted into the formula for fitting to obtain the result. and The value of . In one feasible way, The value can be 0.001. The value can be 1.2. The value of is greater than 0, and usually greater than 1, indicating that the pyrolysis rate of the material increases rapidly with increasing temperature.

[0040] The physical meanings of each term in the formula are as follows: First item This reflects the material's contribution to combustion intensity under current conditions. Molecular portion. Dimensionless indicators of a material's combustion characteristics: Higher HRR and SPR indicate a higher inherent flammability of the material. (Denominator part) This reflects the inhibitory effect of accumulated combustion products in the current environment on further combustion: The larger the value, the more combustion products have accumulated in the environment, the lower the relative oxygen concentration, and the relatively smaller the contribution of increased risk from material combustion. Safety threshold constant. Ensure the denominator is always greater than zero. The entire first term is dimensionless because both the numerator and denominator are dimensionless ratios.

[0041] Second item This reflects the promoting effect of temperature on the pyrolysis rate of materials. Temperature The higher the temperature, the faster the pyrolysis rate of the material, and the greater its contribution to fire risk. It is a dimensionless ratio. The coefficient is dimensionless. It is a positive real number, and the entire second term is dimensionless.

[0042] This embodiment introduces a benchmark value to make each physical quantity dimensionless, and uses the above formula to couple and quantify the material's heat release rate and flue gas generation rate with the real-time carbon monoxide concentration and temperature in the environment, so that the calculation of the material's risk contribution value can be dynamically adjusted according to changes in environmental conditions.

[0043] In existing technologies, risk level determination typically employs either a single-parameter threshold comparison method or a weighted scoring method compared to a threshold. The former is prone to false alarms due to fluctuations in a single parameter, while the latter suffers from inaccurate results due to the subjectivity of weight allocation. Therefore, in one embodiment, as follows... Figure 3 As shown, the target dynamic parameters include smoke diffusion rate and personnel density; the risk level of the target area is generated, including: For each risk level, there are corresponding structural risk assessment conditions and material risk assessment conditions. The structural risk assessment condition is that the quantified structural risk value is greater than the structural risk threshold corresponding to the risk level. The material risk assessment condition is that three sub-conditions must be met simultaneously: the quantified material risk value is greater than the material risk threshold corresponding to the risk level, the personnel density is greater than the personnel density threshold corresponding to the risk level, and the smoke diffusion rate is greater than the diffusion rate threshold corresponding to the risk level.

[0044] When the structural risk assessment criteria or the material risk assessment criteria are met, a corresponding risk level is generated.

[0045] Specifically, the smoke diffusion rate reflects how quickly fire smoke spreads within the target area; the higher the value, the faster the smoke spreads and the greater the threat to personnel evacuation. Personnel density reflects the degree of personnel gathering within the target area; the higher the value, the more people need to be evacuated and the greater the potential risk of casualties from the fire.

[0046] In other words, for a given risk level, the target area is marked as such as the risk level if either of the following two conditions is met: (1) The structural risk quantification value exceeds the structural risk threshold of the level. In this case, the risk level is generated regardless of the material risk, personnel density and smoke diffusion speed; (2) The material risk quantification value exceeds the material risk threshold of the level, the personnel density exceeds the personnel density threshold of the level, and the smoke diffusion speed exceeds the diffusion speed threshold of the level. In this case, the risk level is generated even if the structural risk quantification value does not exceed the structural risk threshold of the level.

[0047] The above judgment logic means that structural risk represents the inherent fire risk of the building structure itself, which is independent of personnel distribution and smoke diffusion. Therefore, as long as the structural risk reaches a certain level, a response of that level will be triggered. The actual hazard level of material risk is closely related to personnel density and smoke diffusion rate. Only when material risk, personnel density, and smoke diffusion rate are all high simultaneously will a corresponding level of response be triggered. This judgment logic avoids false alarms caused by fluctuations in a single non-critical parameter, while ensuring timely response when critical parameters exceed limits.

[0048] Based on the above, this embodiment adopts a multi-parameter determination method using "OR" and "AND" compound logic, which can adaptively determine the risk level according to different risk triggering scenarios, effectively reducing the false alarm rate.

[0049] In existing technologies, although data-driven AI prediction models are used for fire risk prediction, pure AI prediction models lack the constraints of physical laws and have insufficient generalization ability in scenarios outside the coverage of training data. Meanwhile, while pure physical models have clear physical meaning, they are computationally intensive and have slow response times. Therefore, in one embodiment, structural risk quantification values ​​and material risk quantification values ​​are merged into a comprehensive risk value, including: The overall risk value is calculated using the following formula: in, These are simulation results of the target area based on a fire dynamics simulator; This represents the predicted value of the target area based on an artificial intelligence model. The physical simulation weighting coefficients are automatically adjusted according to the duration of the fire. The AI ​​prediction weighting coefficients are automatically adjusted according to the duration of the fire. The historical hazard weighting coefficient is automatically adjusted according to the duration of the fire; Historical risk factors, determined based on historical hazard data, reflect the fundamental contribution of long-term hazard conditions to overall risk. The duration of the fire is expressed in minutes (min), which is the cumulative time from the moment the fire started to the present moment.

[0050] Before calculating the overall risk value, it is necessary to... , and Normalization is performed to a common numerical range (e.g., between 0 and 1) to ensure that the dimensions of each component are consistent and their contributions are comparable when weighted summing. Normalization can be achieved using the min-max normalization method. ,in and These represent the minimum and maximum values ​​of each parameter in the historical data. Because... , and All three are dimensionless quantities; after normalization, their dimensions are consistent, allowing for direct weighted summation. In this embodiment... This refers to the AI ​​prediction weighting coefficient, which represents the weight of the AI ​​prediction value in the overall risk value, and is related to the aforementioned material combustion coupling coefficient. These are completely different parameters; the difference between the two lies in: the aforementioned These are constants calibrated in the experiment and used to calculate the material risk quantification value; while in this embodiment... These are time-varying weighting coefficients used for the fusion calculation of physical model simulation values ​​and AI prediction values.

[0051] The above three weighting coefficients , and The sum is equal to 1 at any time, that is In the early stages of a fire, artificial intelligence predicts weighting coefficients. Higher values ​​are chosen to leverage the rapid response advantage of AI models; as the duration of the fire increases, the weighting coefficients of the physical simulation decrease. The contribution of the physical model gradually increases, ensuring that the prediction results are always constrained by the physical laws of fire dynamics.

[0052] In one feasible approach, a Fire Dynamics Simulator (FDS) can be used. FDS solves the Navier-Stokes equations for low-speed, thermally driven flow using numerical methods, paying particular attention to smoke and heat transport generated by a fire. The core algorithm of FDS employs Large Eddy Simulation (LES) to directly solve for large-scale vortex motion, while using a sub-grid model to approximate small-scale motion. In one feasible approach, the input parameters of FDS include: the geometric model of the target area (including cavity height H and opening area A), the heat release rate curve of the fire source, the ambient temperature TT, and boundary conditions. The output of FDS includes time-series data of physical quantities such as temperature, velocity, and smoke concentration at each monitoring point. It can be used to output comprehensive risk indicators for FDS, such as the ratio of the average temperature of monitoring points near the fire source to a preset temperature threshold.

[0053] In one feasible approach, the artificial intelligence model can employ a Long Short-Term Memory (LSTM) network. The input to the LSTM model is a sequence of historical environmental data, specifically including time-series data such as temperature, carbon monoxide concentration, smoke concentration, wind speed, and population density from the past N time points (e.g., the past 10 time points, with each time point spaced 10 seconds apart). The output of the LSTM model is the comprehensive risk prediction value for the current time point. The training process of the LSTM model is as follows: First, a large amount of historical fire scene data is collected, using the data from the N time points prior to each current time point as input samples, and the actual risk level at that time point as the training label; then, the model is trained using the Backpropagation Through Time (BPTT) algorithm, with Mean Squared Error (MSE) as the loss function; during training, mini-batch gradient descent is used to update the network weights; when the loss function value of the model on the validation set no longer decreases for 10 consecutive training epochs, training is stopped, and the current model parameters are saved as the trained LSTM model. In one feasible approach, the artificial intelligence model can also be a Transformer model or a ConvLSTM model, with the same input and output settings as the LSTM model. The model structure can adopt the standard architecture of each model, which is not limited in this embodiment.

[0054] Historical risk factors, determined based on historical hazard data, reflect the fundamental contribution of the long-term hazard status of the target area to the current fire risk. The method for determining the historical risk factor is as follows: Historical hazard records for the target area within a preset historical time period (e.g., the past 12 months) are statistically analyzed, and the ratio of the number of historical hazards to the preset total number of hazards is calculated as the baseline value. In one feasible approach... It can be determined in the following way: ,in This represents the total number of historical hazard records for the target area within a preset historical time period. This is the pre-set total number of potential hazards. The value range is between 0 and 1.

[0055] This embodiment integrates the simulated values ​​from the physical model with the predicted values ​​from artificial intelligence according to dynamically adjusted weights. This leverages the rapid response advantage of the AI ​​model while ensuring that the prediction results do not violate the basic laws of fire dynamics through the physical model.

[0056] During the development of a fire, the focus of risk assessment differs at different stages: in the early stages, the situation is unclear and a rapid response is needed; at this time, AI prediction models can quickly provide predictions based on historical data patterns. As the fire duration increases and more on-site data accumulates, the simulation results of the physical model become more reliable. Therefore, in one embodiment, the physical simulation weight coefficient monotonically increases from an initial preset value to converge to 1 as the fire duration increases; the AI ​​prediction weight coefficient monotonically decreases from an initial preset value to converge to 0 as the fire duration increases; and the historical hazard weight coefficient is positively correlated with the square root of the number of historical hazards.

[0057] In one feasible approach, the physical simulation weighting coefficients The initial preset value can be 0.7, and as the fire duration increases, The value gradually increases and approaches 1. This indicates that as the fire progresses, the simulation results of the physical model have an increasingly larger weight in the overall risk value, ultimately dominating the calculation of the overall risk value.

[0058] In one feasible way The initial preset value can be 0.3, and as the fire duration increases, The value gradually decreases and approaches 0. This indicates that as the fire progresses, the weight of the AI ​​prediction results becomes smaller and smaller, eventually exiting the calculation of the overall risk value.

[0059] Weighting coefficient for historical risks The more historical hidden dangers there are in the target area, the better. The larger the value of , the greater the contribution of historical hazard factors to the overall risk value. In one feasible approach, The value of can be expressed as .because The value is positively correlated with the square root of the number of historical hazards, increasing with the increase in the number of historical hazards, but the rate of increase gradually slows down. It should be noted that in this embodiment, The value of does not change over time, but is determined by the historical potential hazards in the target area, remaining constant throughout the entire fire event. In one feasible approach, when hour, ;when hour, .

[0060] In one feasible way and The specific value can be determined in the following way: Where t is the duration of the fire; It is the base of the natural logarithm, approximately equal to 2.71828.

[0061] In the above formula, as the fire duration t increases, The value gradually increases from an initial value of 0.7 and approaches 1. Accordingly from the initial value The weighting coefficients gradually decreased and approached zero, achieving a smooth transition from AI model-dominated to physics model-dominated weighting. When the fire duration t reached 30 minutes, This means that the weighting coefficients of the physical simulation are close to their convergence value of 1.

[0062] This embodiment achieves adaptive weight allocation among the physical model, AI model, and historical hazard factors in the comprehensive risk value calculation by limiting the variation of each weight coefficient with the duration of the fire and the number of historical hazards.

[0063] In existing technologies, when multiple tasks exist under the same risk level, the execution order of these tasks is typically determined manually or arranged according to their creation time, lacking a dynamic priority ranking mechanism based on risk values. Therefore, in one embodiment, this method further includes: for the same risk level, when initiating corresponding collaborative handling, if multiple tasks exist, a risk-driven priority algorithm is invoked to calculate the handling priority of each task and execute them in descending order. The risk-driven priority algorithm uses different calculation formulas based on the risk level of each task.

[0064] in: When the risk level is medium, the priority of handling is calculated according to the following formula: When the risk level is high, the priority of handling is calculated according to the following formula: in, The priority is the task to be handled, and the score is a dimensionless comprehensive score. The higher the score, the higher the priority of the task to be handled. This represents the overall risk value for the target area. The risk propagation factor of adjacent areas reflects the potential impact of the risk propagation from adjacent areas to the target area. It is determined by the product of the sum of the comprehensive risk values ​​of adjacent areas and the structural correlation coefficient. The structural correlation coefficient is determined based on the ventilation duct connectivity or fire separation distance between the target area and adjacent areas. The timeliness factor for handling these issues, and the determination of hazard types based on historical hazard data for the target area, reflects the urgency of the tasks to be addressed. To and Different parameters, This reflects the urgency of the tasks currently pending. , , These are the three weighting coefficients for medium-level risk. ,and That is, under medium-level risk, the comprehensive risk value The risk transmission factor in adjacent areas contributes the most to the priority of treatment. The contribution of timeliness is secondary. Its contribution was the smallest. , , These are the three weighting coefficients for high-level risk. ,and That is, under high-level risk, the comprehensive risk value The timeliness factor still contributes the most to the priority of disposal. The contribution is the smallest. The difference between the weighting coefficients for high-level and medium-level classifications lies in: That is, under high-level risk, the risk transmission factor in adjacent areas. The weight given to high-level fires is greater. This is because high-level fires are more likely to spread to adjacent areas, thus requiring greater attention to the risk transmission effect in adjacent areas.

[0065] Specifically, the calculation method for the risk transmission factor between adjacent areas is as follows: in, Let be the comprehensive risk value of the i-th neighboring region. The comprehensive risk value of each neighboring region is obtained using the same fusion calculation method as the target region. N is the total number of neighboring regions of the target region. is the structural correlation coefficient, which is a dimensionless coefficient with a value range between 0 and 1.

[0066] Structural correlation coefficient The fire safety distance is determined based on the connectivity of ventilation ducts between the target area and adjacent areas, or the fire separation distance. When there are direct ventilation ducts connecting the target area and adjacent areas, fire and smoke may spread to the adjacent areas through the ventilation ducts. The value is relatively high, and it is implemented in a feasible way. A value of 0.8 is acceptable; when there is no ventilation duct connecting the target area and adjacent areas, but the fire separation distance is insufficient, the fire may spread to the adjacent area through heat radiation or flying sparks. The value is moderate, and it is implemented in a feasible way. A value of 0.5 is acceptable; this applies when there are no ventilation ducts connecting the target area to adjacent areas and the fire separation distance meets the standard requirements. The value is relatively low, in one feasible way. It can take the value 0.2.

[0067] The calculation method for the timeliness factor is as follows: in, This is the weighting coefficient for the hazard type, a dimensionless positive number, determined based on the hazard types in the historical hazard data of the target area. Different hazard types correspond to different weights for handling timeliness: electrical fire hazards, due to their rapid development and high risk, have a corresponding weighting... A higher value indicates a lower risk of electrical fires in a feasible manner. A value of 0.9 is acceptable; the potential danger of debris accumulation develops relatively slowly, and the corresponding... With a lower value, the potential for debris accumulation can be mitigated in a feasible manner. It can take the value 0.3. This is a correction factor for the number of potential hazards, a dimensionless positive number, determined based on the historical number of potential hazards in the target area. In one feasible approach... It can be determined in the following way: ,in This represents the total number of historical hazard records for the target area within a preset historical time period. The more hazards there are, the higher the threshold. The larger the value, the higher the processing time factor.

[0068] In one feasible approach, when there are multiple tasks pending handling under a medium-level risk, the specific values ​​of each weight coefficient can be: , , When there are multiple tasks pending handling under a high-level risk, the specific values ​​of each weighting coefficient can be: , , It should be noted that the specific values ​​mentioned above are merely examples. In practical applications, they can be adjusted according to the specific circumstances of the target area and the needs of fire management, as long as the aforementioned weighting coefficients are satisfied.

[0069] This embodiment uses a risk-driven priority algorithm to dynamically calculate the priority of each task to be handled based on risk level, comprehensive risk value, risk propagation factor of adjacent areas, and handling timeliness factor, thus upgrading the handling tasks from manual sorting to risk-driven automatic sorting.

[0070] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps.

[0071] Secondly, based on the same inventive concept, this application also provides a system for implementing the aforementioned fire-fighting three-level linkage control method based on dynamic risk coding. The solution provided by this system is similar to the solution described in the above method; therefore, the specific limitations in one or more system embodiments provided below can be found in the limitations of the fire-fighting three-level linkage control method based on dynamic risk coding described above, and will not be repeated here.

[0072] In one embodiment, such as Figure 4 As shown, the system includes: a multi-source data acquisition module, a risk quantification module, a risk level generation module, and a tiered linkage response module. Among them: The multi-source data acquisition module is used to acquire multi-source data of the target area, including building structure parameters, material combustion characteristic parameters, and real-time environmental data. The risk quantification module is used to calculate the structural risk quantification value of the target area based on the temperature parameters in the building structure parameters and real-time environmental data, and constrained by the physical laws of fire spread; and to calculate the material risk quantification value of the target area based on the material combustion characteristic parameters and environmental concentration parameters in the real-time environmental data, and constrained by the coupling effect between material combustion and the environment. The risk level generation module is used to merge the structural risk quantification value and the material risk quantification value into a comprehensive risk value, and generate the risk level of the target area according to different preset conditions corresponding to different risk levels based on the comprehensive risk value, the structural risk quantification value, the material risk quantification value and the target dynamic parameters in the real-time environmental data. The tiered linkage response module is used to trigger grassroots inspections when the risk level is low; to initiate intermediate-level collaborative response and adjust the operating parameters of fire-fighting equipment according to the dynamic control mapping relationship when the risk level is medium; and to initiate advanced-level collaborative response and adjust the operating parameters of fire-fighting equipment according to the dynamic control mapping relationship when the risk level is high. The response priority of advanced-level collaborative response is higher than that of intermediate-level collaborative response.

[0073] In one embodiment, the risk quantification module includes a structural risk quantification value calculation unit. The structural risk quantification value calculation unit calculates the structural risk quantification value according to the following formula: in, The cavity height is the continuous vertical height of the vertically extending cavity structure within the target area. Let be the area of ​​the opening. For temperature parameters, As the reference temperature, The cavity structure influence coefficient is the one calibrated in the experiment. This is the temperature index coefficient calibrated for the experiment.

[0074] In one embodiment, the risk quantification module includes a material risk quantification value calculation unit. This unit calculates the material risk quantification value using the following formula: in, For heat release rate, For flue gas generation rate, This refers to the carbon monoxide concentration. The temperature parameter is a thermodynamic temperature. This is a preset dimensionless safety threshold constant. The material combustion coupling coefficient was calibrated in the experiment. The temperature effect index coefficient is a positive real number, determined experimentally. , , and These are the corresponding baseline values.

[0075] In one embodiment, the risk level generation module includes a risk level generation unit. The risk level generation unit is used to set structural risk assessment conditions and material risk assessment conditions for each risk level. The structural risk assessment condition is that the quantified structural risk value is greater than the structural risk threshold corresponding to the risk level. The material risk assessment condition is that the quantified material risk value is greater than the material risk threshold corresponding to the risk level, the personnel density is greater than the personnel density threshold corresponding to the risk level, and the smoke diffusion rate is greater than the diffusion rate threshold corresponding to the risk level. The risk level generation unit is used to generate the corresponding risk level when either the structural risk assessment condition or the material risk assessment condition is met.

[0076] In one embodiment, the rating generation module includes a comprehensive risk value calculation unit. The comprehensive risk value calculation unit calculates the comprehensive risk value using the following formula: in, These are simulation results of the target area based on a fire dynamics simulator; This represents the predicted value of the target area based on an artificial intelligence model. The physical simulation weighting coefficients are automatically adjusted according to the duration of the fire. The AI ​​prediction weighting coefficients are automatically adjusted according to the duration of the fire. The historical hazard weighting coefficient is automatically adjusted according to the duration of the fire; These are historical risk factors determined based on historical hazard data.

[0077] In one embodiment, the comprehensive risk value calculation unit includes a weight coefficient configuration subunit. The comprehensive risk value calculation unit is configured to: the physical simulation weight coefficient monotonically increases from an initial preset value to converge to 1 as the fire duration increases; the artificial intelligence prediction weight coefficient monotonically decreases from an initial preset value to converge to 0 as the fire duration increases; and the historical hazard weight coefficient is positively correlated with the square root of the number of historical hazards.

[0078] In one embodiment, the hierarchical linkage response module includes an execution control unit. This execution control unit, when initiating corresponding coordinated response for the same risk level, if multiple tasks are pending, invokes a risk-driven priority algorithm to calculate the priority of each task and executes them in descending order of priority. When the risk level is medium, the priority of handling is calculated according to the following formula: When the risk level is high, the priority of handling is calculated according to the following formula: in, This is the overall risk value; It is the risk propagation factor between adjacent areas, and is determined by the sum of the comprehensive risk values ​​of adjacent areas and the structural correlation coefficient. The structural correlation coefficient is determined based on the ventilation duct connectivity or fire separation distance between the target area and adjacent areas. The timeliness of the response is taken into account, and the types of hazards are determined based on the historical hazard data of the target area. , , , , , All are weighting coefficients. , ,and .

[0079] The modules in the aforementioned fire-fighting three-level linkage control system based on dynamic risk coding can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0080] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores all data required for system operation. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a risk-dynamic coding-based three-level fire alarm linkage control method.

[0081] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0082] Thirdly, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described in the above method embodiments.

[0083] Fourthly, a computer-readable storage medium is provided, on which a computer program is stored, which, when executed by a processor, implements the steps of any of the methods described in the above method embodiments.

[0084] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0085] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0086] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A fire safety three-level linkage control method based on dynamic risk coding, characterized in that, The method includes: Acquire multi-source data for the target area, including building structure parameters, material combustion characteristic parameters, and real-time environmental data; Based on the building structure parameters and the temperature parameters in the real-time environmental data, and constrained by the physical laws of fire spread, the structural risk quantification value of the target area is calculated; based on the material combustion characteristic parameters and the environmental concentration parameters in the real-time environmental data, and constrained by the coupling effect between material combustion and the environment, the material risk quantification value of the target area is calculated. The structural risk quantification value and the material risk quantification value are merged into a comprehensive risk value. Based on the comprehensive risk value, the structural risk quantification value, the material risk quantification value, and the target dynamic parameters in the real-time environmental data, the risk level of the target area is generated according to different preset conditions corresponding to different risk levels. In response to a low risk level, a basic-level inspection is triggered; in response to a medium risk level, an intermediate-level collaborative response is initiated and the operating parameters of the fire-fighting equipment are adjusted according to the dynamic control mapping relationship; in response to a high risk level, an advanced-level collaborative response is initiated and the operating parameters of the fire-fighting equipment are adjusted according to the dynamic control mapping relationship; wherein the advanced-level collaborative response has a higher priority than the intermediate-level collaborative response.

2. The method according to claim 1, characterized in that, The building structural parameters include at least the cavity height and the opening area; the structural risk quantification value is calculated according to the following formula: in, The cavity height refers to the continuous vertical height of the vertically extending cavity structure within the target area. Let be the area of ​​the opening. The temperature parameter is... As the reference temperature, The cavity structure influence coefficient is the one calibrated in the experiment. This is the temperature index coefficient calibrated for the experiment.

3. The method according to claim 1, characterized in that, The combustion characteristic parameters of the material include at least the heat release rate and the flue gas generation rate; the environmental concentration parameters include at least the carbon monoxide concentration; the material risk quantification value is calculated according to the following formula: in, The heat release rate, The flue gas generation rate, The carbon monoxide concentration is [value missing]. The temperature parameter is a thermodynamic temperature. This is a preset dimensionless safety threshold constant. The material combustion coupling coefficient was calibrated in the experiment. The temperature effect index coefficient is a positive real number, determined experimentally. , , and These are the corresponding baseline values.

4. The method according to claim 1, characterized in that, The target dynamic parameters include smoke diffusion rate and personnel density; The risk level of the target area is generated as follows: For each risk level, there are corresponding structural risk assessment conditions and material risk assessment conditions. The structural risk assessment condition is that the quantitative value of the structural risk is greater than the structural risk threshold corresponding to the risk level. The material risk assessment condition is that the quantitative value of the material risk is greater than the material risk threshold corresponding to the risk level, the personnel density is greater than the personnel density threshold corresponding to the risk level, and the smoke diffusion rate is greater than the diffusion rate threshold corresponding to the risk level. When the structural risk assessment conditions or the material risk assessment conditions are met, the corresponding risk level is generated.

5. The method according to claim 1, characterized in that, The process of integrating the structural risk quantification value and the material risk quantification value into a comprehensive risk value includes: The overall risk value is calculated using the following formula: in, These are simulation results of the target area based on a fire dynamics simulator; This is the predicted value of the target region based on an artificial intelligence model; The physical simulation weighting coefficients are automatically adjusted according to the duration of the fire. The AI ​​prediction weighting coefficients are automatically adjusted according to the duration of the fire. The historical hazard weighting coefficient is automatically adjusted according to the duration of the fire. These are historical risk factors determined based on historical hazard data.

6. The method according to claim 5, characterized in that, The physical simulation weight coefficient monotonically increases from an initial preset value to converge to 1 as the fire duration increases; the artificial intelligence prediction weight coefficient monotonically decreases from an initial preset value to converge to 0 as the fire duration increases; and the historical hazard weight coefficient is positively correlated with the square root of the number of historical hazard factors.

7. The method according to any one of claims 1 to 6, characterized in that, Also includes: For the same risk level, when initiating the corresponding collaborative handling, if there are multiple tasks to be handled, the risk-driven priority algorithm is invoked to calculate the handling priority of each task and execute them in descending order, wherein: When the risk level is medium, the handling priority is calculated according to the following formula: When the risk level is the high level, the handling priority is calculated according to the following formula: in, This is the overall risk value; It is a risk propagation factor between adjacent areas, and is determined by the product of the sum of the comprehensive risk values ​​of adjacent areas and the structural correlation coefficient, wherein the structural correlation coefficient is determined based on the ventilation duct connectivity or fire separation distance between the target area and adjacent areas. The timeliness factor is taken into account, and the type of hazard is determined based on the historical hazard data of the target area; , , , , , All are weighting coefficients. , ,and .

8. A fire protection three-level linkage control system based on dynamic risk coding, characterized in that, The system includes: A multi-source data acquisition module is used to acquire multi-source data of the target area, including building structure parameters, material combustion characteristic parameters, and real-time environmental data. The risk quantification module is used to calculate the structural risk quantification value of the target area based on the building structure parameters and the temperature parameters in the real-time environmental data, and constrained by the physical laws of fire spread; and to calculate the material risk quantification value of the target area based on the material combustion characteristic parameters and the environmental concentration parameters in the real-time environmental data, and constrained by the coupling effect between material combustion and the environment. The risk level generation module is used to merge the structural risk quantification value and the material risk quantification value into a comprehensive risk value, and generate the risk level of the target area according to different preset conditions corresponding to different risk levels based on the comprehensive risk value, the structural risk quantification value, the material risk quantification value and the target dynamic parameters in the real-time environmental data; The tiered linkage response module is used to trigger a grassroots inspection when the risk level is low; to initiate intermediate-level collaborative response and adjust the operating parameters of the fire-fighting equipment according to the dynamic control mapping relationship when the risk level is medium; and to initiate advanced-level collaborative response and adjust the operating parameters of the fire-fighting equipment according to the dynamic control mapping relationship when the risk level is high. The advanced-level collaborative response has a higher priority than the intermediate-level collaborative response.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the fire protection three-level linkage control method based on risk dynamic coding as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the fire protection three-level linkage control method based on risk dynamic coding as described in any one of claims 1 to 7.

Images