Dynamic fire extinguishing strategy generation method and system based on fire behavior development stage grading

Abstract

The invention discloses a dynamic fire extinguishing strategy generation method and system based on fire behavior development stage grading, belongs to the technical field of artificial intelligence, and aims to solve the problems of rapid fire behavior spreading and toxic and harmful flue gas retention in a fire disaster in a closed space of a multi-layer underground parking lot. The target tracking device firstly uses image identification to position a fire point, then uses the fire source detection device to collect a fire type and a fire behavior degree, and generates triple data; the data are input into a fire behavior stage grading model, and the fire behavior is divided into an incubation period, an accelerated spread period and a deflagration period according to a combustion entropy threshold value. According to the current stage, the corresponding fire extinguishing strategy is loaded from the blocking priority rule base, and in the detonation period, the aerogel flame retardant is only allowed to be put into the top ventilation opening in the fire diffusion direction. And then the fire scene control instruction drives the fire behavior blocking robot to release the flame retardant on time at a fixed point, and environment parameters after release are collected and fed back to the model. And if the combustion entropy value crosses the stage threshold value, the model triggers the blocking strategy to be dynamically switched.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for generating a dynamic fire extinguishing strategy based on fire development stage classification. Background Art

[0002] In the confined spaces of multi-story underground parking garages, due to the closed structure and limited ventilation, once a fire breaks out, smoke and harmful gases generated during combustion are difficult to expel in a timely manner, easily causing localized combustion to spread rapidly. Initially, a fire may be confined to a small area, but as heat and pressure continue to build during combustion, the fire can quickly evolve from a localized burn to a full-scale explosion, posing significant challenges to evacuation and fire control.

[0003] Currently, relevant technologies employ fire-blocking strategies based on time series predictions, predicting fire trends and determining the timing for the application of flame retardants. However, these strategies have significant shortcomings when faced with the complex nature of fire development in confined environments: they fail to effectively distinguish between the dynamic stages of fire development, resulting in significant discrepancies between the timing of flame retardant application and the actual rate of fire spread. Due to the highly nonlinear and sudden nature of fire development, the lack of precise identification of different fire stages often leads to wasted resources or the risk of uncontrolled fires in practical applications, thus failing to achieve ideal fire control results.

[0004] The disclosure of the above background technology content is only used to assist in understanding the concept and technical solution of the present invention. It does not necessarily belong to the prior art of this patent application. In the absence of clear evidence that the above content has been disclosed on the filing date of this patent application, the above background technology should not be used to evaluate the novelty and creativity of this application. Summary of the Invention

[0005] The present application provides a method and system for generating a dynamic fire extinguishing strategy based on fire development stage classification, which is used to solve the problems of rapid fire spread and toxic and harmful smoke gas retention in confined space fires in multi-story underground parking lots.

[0006] To achieve the above objectives, the present application discloses the following technical solutions:

[0007] In a first aspect, an embodiment of the present application provides a method for generating a dynamic fire extinguishing strategy based on fire development stage classification, which is executed by a target tracking device and includes the following steps:

[0008] Identify the location of the fire point using image recognition technology and project a fire source detection device toward the location of the fire point; the fire source detection device is used to determine the type and severity of the fire at the fire point through a sensor and return the information to the target tracking device;

[0009] The fire type, fire severity, and fire environment characteristics collected at each moment are combined into a triplet and input into the fire development stage classification model. The fire is divided into the latent stage, accelerated spread stage, or deflagration stage according to the combustion entropy threshold.

[0010] According to the current fire development stage, the blocking priority rule library bound to the stage is loaded. The blocking priority rule library only allows the aerogel flame retardant to be released during the deflagration stage, and the release position is limited to the top vent in the direction of fire expansion;

[0011] Generate fire scene control instructions according to the blocking priority rule library, and control the fire blocking robot to carry a specified type of flame retardant material and release the flame retardant material at a specified time and at a specified location;

[0012] Receiving fire scene environmental parameters after the release of the flame retardant collected by the fire source detection equipment and the fire blocking robot;

[0013] The fire scene environmental parameters are fed back to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and if the entropy value crosses the stage threshold, it triggers the dynamic switching of the blocking priority rule library.

[0014] In an embodiment of the present application, a target tracking device is used in conjunction with a fire source detection device to accurately locate and monitor a fire in its early stages. Image recognition technology is used to identify the fire point, and sensors are used to obtain the combustion type and fire intensity. Fire environment data is then used to construct a specific data triplet, which is fed into a fire development stage classification model as input. The fire development stage classification model uses the calculation of combustion entropy parameters and the determination of classification thresholds to achieve a qualitative classification of fire development stages. It then determines blocking priority rules and generates fire control instructions based on the fire development stage. This solution enables the fire blocking robot to deploy flame retardants at appropriate times and designated locations according to the fire development stage, ensuring that fire extinguishing operations are synchronized with actual fire changes in real time. This effectively controls the problem of smoke and harmful gas stagnation in confined spaces caused by structural closure and limited ventilation conditions, reduces the risk of local combustion spreading to full-area deflagration, ensures timely and effective fire extinguishing measures, and effectively solves the problems of safe evacuation and fire control caused by inaccurate early fire predictions and rapid fire spread.

[0015] In a second aspect, an embodiment of the present application provides a dynamic fire extinguishing strategy generation system based on fire development stage classification, which is applied to a target tracking device, including:

[0016] A fire source positioning and detection module is used to identify the location of the fire point through image recognition technology and project a fire source detection device to the location of the fire point; the fire source detection device is used to determine the type and severity of the fire at the fire point through sensors and return the information to the target tracking device;

[0017] The fire stage classification module is used to combine the collected fire type, fire severity and fire environment characteristics at each moment into a triplet, which is input into the fire development stage classification model. The fire is classified into the latent stage, accelerated spread stage or deflagration stage according to the combustion entropy threshold.

[0018] A priority rule library module is used to load a blocking priority rule library bound to the current fire development stage according to the current fire development stage. The blocking priority rule library only allows the aerogel flame retardant to be released during the deflagration stage, and the release position is limited to the top vent in the direction of fire expansion;

[0019] An instruction generation and execution module is used to generate a fire scene control instruction based on the blocking priority rule library, and control the fire blocking robot to carry a specified type of flame retardant material and project it to a specified location at a specified time to release the flame retardant material;

[0020] An environmental parameter collection module, configured to receive fire scene environmental parameters collected by the fire source detection equipment and the fire blocking robot after the release of the flame retardant;

[0021] A feedback adjustment module is used to feed back the fire scene environmental parameters to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and if the entropy value crosses the stage threshold, it triggers the dynamic switching of the blocking priority rule library.

[0022] In a third aspect, an embodiment of the present application provides a target tracking device, comprising one or more processors; a storage device on which one or more programs are stored; when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any technical solution of the first aspect.

[0023] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any technical solution of the first aspect is implemented.

[0024] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method described in any technical solution of the first aspect.

[0025] Among them, the technical effects brought about by any design method in the second to fifth aspects can refer to the technical effects brought about by different design methods in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other implementation drawings based on the provided drawings without inventive effort.

[0027] Figure 1 A flowchart of a method for generating a dynamic fire extinguishing strategy based on fire development stage classification provided in some embodiments of the present application;

[0028] Figure 2 A schematic diagram of a system for generating a dynamic fire extinguishing strategy based on fire development stage classification provided in some embodiments of the present application;

[0029] Figure 3 Schematic diagram of the structure of a target tracking device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0030] Specific embodiments of the present invention will now be mentioned in detail. Although the present invention is described in conjunction with these specific embodiments, it should be appreciated that the present invention is not intended to be limited to these specific embodiments. On the contrary, these embodiments are intended to cover substitutions, changes, or equivalent embodiments that may be included within the spirit and scope of the invention defined by the claims. In the following description, a large number of specific details are set forth in order to provide a comprehensive understanding of the present invention. The present invention may be implemented without some or all of these specific details.

[0031] When used in conjunction with "including," "methods comprising," or similar language in this specification and the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0032] Application Overview: In the confined spaces of multi-story underground parking garages, due to the closed structure and limited ventilation, once a fire breaks out, smoke and harmful gases generated during combustion are difficult to expel promptly, easily causing localized combustion to spread rapidly. Initially, a fire may be confined to a small area. However, as heat and pressure accumulate during combustion, the fire can quickly evolve from a localized combustion to a full-scale explosion, posing significant challenges to evacuation and fire control.

[0033] Currently, relevant technologies employ fire-blocking strategies based on time series predictions, predicting fire trends and determining the timing for the application of flame retardants. However, these strategies have significant shortcomings when faced with the complex nature of fire development in confined environments: they fail to effectively distinguish between the dynamic stages of fire development, resulting in significant discrepancies between the timing of flame retardant application and the actual rate of fire spread. Due to the highly nonlinear and sudden nature of fire development, the lack of precise identification of different fire stages often leads to wasted resources or the risk of uncontrolled fires in practical applications, thus failing to achieve ideal fire control results.

[0034] In response to the above technical problems, the overall idea of ​​the technical solution provided by this application is as follows: a dynamic fire extinguishing strategy generation method based on the classification of fire development stages is provided, which is executed by a target tracking device, including the following steps: identifying the location of the fire point through image recognition technology, and projecting a fire source detection device to the location of the fire point; the fire source detection device is used to determine the fire type and fire severity of the fire point through a sensor, and return it to the target tracking device; the fire type, fire severity and fire scene environment characteristics collected at each moment are combined into a triplet, and input into a fire development stage classification model, and the fire is divided into a latent period, an accelerated spread period or a deflagration period according to the combustion entropy threshold; according to the current fire development stage, the fire is loaded with the stage A bound blocking priority rule library, the blocking priority rule library only allows the release of aerogel flame retardant materials during the deflagration period, and the release location is limited to the top vent in the direction of fire spread; generates fire control instructions based on the blocking priority rule library, controls the fire blocking robot to carry a specified type of flame retardant and project it to a specified location at a specified time to release the flame retardant; receives the fire environment parameters after the release of the flame retardant collected by the fire source detection equipment and the fire blocking robot; feeds back the fire environment parameters to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and if the entropy value crosses the stage threshold, it triggers the dynamic switching of the blocking priority rule library.

[0035] This method uses target tracking equipment in conjunction with fire source detection devices to accurately locate and monitor fires in their initial stages. It employs image recognition technology to identify the fire origin and uses sensors to capture the combustion type and fire intensity. Fire environment data is then used to construct specific data triples, which serve as input to a fire development stage classification model. The fire development stage classification model uses the calculation of combustion entropy parameters and the determination of classification thresholds to qualitatively classify fire development stages. It then determines blocking priority rules and generates fire control instructions based on the fire development stage. This solution enables fire blocking robots to deploy flame retardants at appropriate times and locations according to the fire development stage, ensuring real-time synchronization of fire extinguishing operations with actual fire development. This effectively controls the accumulation of smoke and hazardous gases within confined spaces due to structural enclosure and limited ventilation. This reduces the risk of localized combustion spreading to a full-scale deflagration, ensures timely and effective firefighting measures, and effectively addresses the challenges of safe evacuation and fire control arising from inaccurate early fire predictions and rapid fire spread.

[0036] After introducing the basic principles of this application, various non-limiting implementation methods of this application will be specifically introduced in conjunction with the accompanying drawings. Figure 1 The embodiment of the present application provides a method for generating a dynamic fire extinguishing strategy based on fire development stage classification, which is executed by a target tracking device and includes the following steps:

[0037] S101: Identify the location of the fire point using image recognition technology and project a fire source detection device toward the location of the fire point; the fire source detection device is configured to determine the type and severity of the fire at the fire point using a sensor and return the information to the target tracking device;

[0038] Specifically, the steps of identifying the location of the fire point by using image recognition technology and projecting a fire source detection device to the location of the fire point to determine the type and severity of the fire at the fire point include:

[0039] The first step is to call the multispectral imaging module to identify the flame spectral characteristics and locate the coordinates of the fire point;

[0040] Specifically, a dual detection mechanism of infrared spectroscopy and visible spectroscopy can be adopted. The infrared spectrum is used to identify high-temperature areas, and the visible spectrum is used to identify the optical characteristics of the flame. The precise three-dimensional coordinates of the fire point can be determined by combining the two.

[0041] The second step is to control the projection device to launch the fire source detection equipment toward the coordinates of the fire point in a parabolic trajectory;

[0042] In the third step, the physical detection unit of the fire source detection equipment collects the temperature gradient data of the fire scene through the temperature sensor; specifically, the temperature sensor of the physical detection unit adopts a distributed thermocouple array, covering the four sides of the fire source detection equipment, and collects the temperature gradient data in real time.

[0043] In the fourth step, the chemical detection unit of the fire source detection equipment analyzes the combustible components through a gas chromatography sensor; specifically, the gas chromatography sensor of the chemical detection unit extracts fire gas through a micro sampling pump and analyzes the combustible gas components therein, including carbon monoxide, methane, ethylene, etc., to determine whether the fire type is solid combustion, liquid combustion or gas combustion.

[0044] The fifth step is to integrate the temperature gradient data with the combustible composition to generate fire type and fire intensity parameters. Specifically, the fire type and fire intensity parameters can be classified and determined using a support vector machine (SVM) or a Bayesian network.

[0045] S102: The fire type, fire intensity, and fire environment characteristics collected at each moment are combined into a triplet, which is input into a fire development stage classification model. The fire is classified into a latent stage, an accelerated spread stage, or a deflagration stage according to the combustion entropy threshold;

[0046] Specifically, in some embodiments, the execution entity may form a triplet of the fire type, fire severity, and fire environment characteristics collected at each moment into a fire development stage classification model through the following steps, and classify the fire into a latent stage, an accelerated spread stage, or a deflagration stage based on the combustion entropy threshold:

[0047] The first step is to calculate the combustion entropy based on the fire temperature, combustible material concentration, and oxygen concentration in the triplet. The specific formula is as follows:

[0048]

[0049] Where: E represents the combustion entropy value; T is the current fire temperature; ρ C is the combustible concentration; ρ O2 is the oxygen concentration; T0, ρ C0 , ρ O20 are the reference values ​​of temperature, combustible concentration and oxygen concentration respectively; α, β and γ are weight coefficients used to correct the influence of each sensor parameter on combustion entropy;

[0050] In the second step, if the combustion entropy value is less than or equal to a first preset entropy threshold, it is determined to be in the latent period; illustratively, the first preset entropy threshold may be, but is not limited to, 0.7.

[0051] In the third step, if the combustion entropy value is greater than the first preset entropy threshold and less than or equal to the second preset entropy threshold, it is determined to be an accelerated propagation period; illustratively, the second preset entropy threshold may be, but is not limited to, 1.2.

[0052] In the fourth step, if the combustion entropy value is greater than the second preset entropy threshold, it is determined to be the deflagration period.

[0053] This allows physical quantities like temperature and concentration to be converted into entropy values, allowing the fire's development to be described using a quantitative indicator, facilitating precise determination of the fire's stage. Entropy values ​​are used to determine the matching criteria for different fire-fighting measures at different stages of fire development, enabling the selection of blocking measures tailored to the actual fire situation. This enables the automatic conversion and optimization of fire scene data from raw sensory data to quantitative fire severity levels, streamlining fire assessment, reducing the risk of misjudgment, and improving the timeliness and accuracy of firefighting decisions.

[0054] S103: Based on the current fire development stage, a blocking priority rule library bound to the stage is loaded. The blocking priority rule library only allows the aerogel flame retardant to be released during the deflagration stage, and the release position is limited to the top vent in the direction of fire spread;

[0055] Specifically, in some embodiments, the execution entity may load a blocking priority rule library bound to the current fire development stage through the following steps:

[0056] In the first step, if the phase is marked as the latent period, the first rule base is loaded: the use of foam or dry powder flame retardant is allowed, and the placement location is within a preset distance from the center of the fire;

[0057] In the second step, if the phase is marked as accelerated spread, the second rule base is loaded: the high-pressure water mist system is mandatory, and the placement location is the key node of the fire spread path;

[0058] In the third step, if the stage is marked as the deflagration period, the third rule base is loaded: only aerogel flame retardant is allowed to be placed, and the placement location is limited to the top ventilation opening in the direction of fire spread.

[0059] This allows for automatic matching of fire extinguishing strategies to different fire stages by establishing a clear mapping between the fire development stage and a dedicated blocking priority rule base. Once the fire stage is precisely defined, the mapping function converts the incubation period, accelerated spread period, and deflagration period into corresponding rule bases, ensuring that the system immediately activates the most appropriate blocking measures upon detecting changes in the fire state. This ensures that the generation of fire extinguishing commands is highly consistent with the time sequence of fire evolution, reducing the risk of blocking failure due to improper fire extinguishing strategy selection and improving the accuracy and real-time response capabilities of dynamic fire control in confined environments.

[0060] Based on the above embodiment, the execution subject can implement the following steps to block the priority rule base during the deflagration period to allow only the aerogel flame retardant to be released, and the release position is limited to the top vent in the direction of fire spread:

[0061] The first step is to match the fire spread vector based on the building structure topology map and select the vents closest to the fire point and located in the spread direction. The specific formula is as follows:

[0062]

[0063] Where, P v represents the coordinates of the selected top vent; P represents the set of candidate vents, and each candidate vent is represented by its coordinate P; P f represents the coordinates of the fire point; represents the Euclidean distance between the fire point and the candidate vent, where x P ,y P is the component of coordinate P, x f ,y f Fire point P f The coordinate components of the fire; V is the vector of the fire spreading direction; the constraint condition V·(PP f )>0 is used to ensure that only vents located in the direction of fire spread are considered;

[0064] The second step is to generate a set of placement parameters that includes the aerogel material type and vent coordinates. This approach allows for precise and effective intervention during the most dangerous phase of a fire by limiting the use of aerogel flame retardant to the deflagration phase and strictly stipulating that the placement of the flame retardant must be located at the top vent in the direction of fire spread.

[0065] Furthermore, the optimal placement locations are selected based on the geometric distribution of candidate vents within the building structure, the distance between the fire point and the vents, and the direction of fire spread, ensuring that the flame retardant achieves maximum fire extinguishing effectiveness at key locations. This effectively ensures the spatial accuracy and directional fit of the flame retardant placement, making the fire extinguishing process more scientific and rational, and reducing the risk of further spread caused by the rapid spread of fire in confined environments.

[0066] S104: generating a fire scene control instruction according to the blocking priority rule library, controlling the fire blocking robot to carry a specified type of flame retardant material and project it to a specified location at a specified time to release the flame retardant material;

[0067] Specifically, this can be achieved through the following steps:

[0068] In the first step, when the fire coverage area exceeds the control range of a single target tracking device, the phase identifier and the activated blocking priority rule base are sent to the downstream target tracking device in the direction of fire spread;

[0069] In the second step, the downstream target tracking device generates fire scene control instructions based on the received blocking priority rule base;

[0070] The third step is to control the fire blocking robot to carry the flame retardant material type specified by the blocking priority rule library;

[0071] Step 4: Project the projectile to the placement position defined by the blocking priority rule library within the countdown threshold calculated by the fire spread speed;

[0072] The fifth step triggers the fire-blocking robot to release the flame retardant upon reaching the coordinate location. This converts the fire's spread speed and distance into a countdown time, enabling the fire-fighting robot to accurately deploy the flame retardant to the desired location within the predetermined timeframe. Fire scene control commands are generated using a countdown threshold that closely corresponds to the fire's spread. This ensures the fire-fighting robot receives real-time, accurate operational instructions as the fire progresses. This completes the execution of the signal to form a closed data loop, efficiently coordinating operations across all stages. This improves the response speed and control effectiveness of the entire fire-fighting process, ultimately achieving the goal of promptly suppressing the spread of fire in confined spaces.

[0073] S105: receiving fire scene environment parameters collected by the fire source detection equipment and the fire blocking robot after the release of the flame retardant;

[0074] Specifically, in some embodiments, the execution entity may receive the fire scene environment parameters collected by the fire source detection device and the fire blocking robot after the release of the flame retardant through the following steps:

[0075] The first step is to obtain the fire scene temperature distribution map through the infrared sensor of the fire source detection equipment;

[0076] The second step is to collect the oxygen concentration at the ventilation opening through the gas sensor of the fire blocking robot;

[0077] The third step is to integrate the temperature distribution map and oxygen concentration data to generate a feedback parameter set, which is then output to the fire development stage classification model. The specific formula is as follows:

[0078]

[0079] Where: T avg represents the average temperature of the fire scene; O2 represents the oxygen concentration measured at the ventilation opening; n is the number of temperature measurement points; T iis the temperature distribution data, where i = 1, 2, …, n. This allows the fire stage classification model to obtain information that accurately reflects the overall temperature state of the fire scene and the oxygen concentration in the combustion environment, thereby achieving real-time adjustment of the fire stage. Specifically, the temperature distribution data provides spatial temperature information of the combustion area within the fire scene, while the oxygen concentration reflects a key factor in the combustion conditions at the fire scene. The integration of these two sets of data, through mathematical averaging and combination operations, forms a closed-loop feedback input, which helps maintain real-time consistency with the actual fire scene during the fire stage classification process.

[0080] S106: Feedback the fire scene environmental parameters to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and if the entropy value crosses the stage threshold, it triggers the dynamic switching of the blocking priority rule library.

[0081] Specifically, in some embodiments, the dynamic switching of the blocking priority rule base may be triggered by the following steps:

[0082] The first step is to input the feedback parameters into the combustion entropy calculation engine and output the updated combustion entropy value;

[0083] The second step is to compare the updated entropy value with the stage threshold; if the updated entropy value drops from > the second preset entropy threshold to ≤ the second preset entropy threshold, the rule base is triggered to switch from the deflagration period to the accelerated spread period; if the updated entropy value rises from ≤ the first preset entropy threshold to > the first preset entropy threshold, the rule base is triggered to switch from the latent period to the accelerated spread period;

[0084] The third step is to send a rule base switching instruction to the blocking priority rule base loading module.

[0085] In this way, the real-time feedback of fire scene environmental parameters can be used to continuously update the combustion entropy value, ensuring the real-time judgment of the change in combustion entropy, and automatically triggering the switching of the blocking priority rule library based on the relationship between the entropy value and the preset threshold, thereby realizing dynamic adjustment of the fire extinguishing strategy.

[0086] See also Figure 2 Based on the same inventive concept as the method for generating a dynamic fire extinguishing strategy based on fire development stage classification in the aforementioned embodiment, the present embodiment provides a dynamic fire extinguishing strategy generation system based on fire development stage classification, which is applied to a target tracking device and includes:

[0087] The fire source location and detection module 201 is used to identify the location of the fire point through image recognition technology and project a fire source detection device to the location of the fire point; the fire source detection device is used to determine the type and severity of the fire at the fire point through sensors and return the information to the target tracking device;

[0088] The fire stage classification module 202 is used to combine the collected fire type, fire severity, and fire environment characteristics at each moment into a triplet, input it into the fire development stage classification model, and classify the fire into the latent stage, accelerated spread stage, or deflagration stage based on the combustion entropy threshold;

[0089] Priority rule library module 203 is used to load the blocking priority rule library bound to the stage according to the current fire development stage. The blocking priority rule library only allows the aerogel flame retardant to be released during the deflagration stage, and the release position is limited to the top vent in the direction of fire spread;

[0090] The instruction generation and execution module 204 is used to generate a fire scene control instruction based on the blocking priority rule library, and control the fire blocking robot to carry a specified type of flame retardant material and release the flame retardant material at a specified time and at a specified location;

[0091] The environmental parameter collection module 205 is used to receive the fire scene environmental parameters collected by the fire source detection equipment and the fire blocking robot after the release of the flame retardant;

[0092] The feedback adjustment module 206 is used to feed back the fire scene environmental parameters to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and if the entropy value crosses the stage threshold, it triggers the dynamic switching of the blocking priority rule library.

[0093] In some embodiments, the fire stage classification module 202 is specifically configured to:

[0094] The combustion entropy is calculated based on the fire temperature, combustible material concentration, and oxygen concentration in the triplet. The specific formula is as follows:

[0095]

[0096] Where: E represents the combustion entropy value; T is the current fire temperature; ρ C is the combustible concentration; ρ O2 is the oxygen concentration; T0, ρ C0 , ρ O20 are the reference values ​​of temperature, combustible concentration and oxygen concentration respectively; α, β and γ are weight coefficients used to correct the influence of each sensor parameter on combustion entropy;

[0097] If the combustion entropy value is less than or equal to the first preset entropy threshold, it is determined to be in the latent period;

[0098] If the combustion entropy value is greater than the first preset entropy threshold and less than or equal to the second preset entropy threshold, it is determined to be in the accelerated spread period;

[0099] If the combustion entropy value is greater than the second preset entropy threshold, it is determined to be a deflagration period.

[0100] In some embodiments, the priority rule base module 203 is specifically used to:

[0101] If the stage is marked as the latent period, the first rule base is loaded: the use of foam or dry powder flame retardant is allowed, and the placement location is within a preset distance from the center of the fire;

[0102] If the phase is marked as the accelerated spread phase, the second rule base is loaded: the high-pressure water mist system is mandatory, and the placement location is the key node of the fire spread path;

[0103] If the stage is marked as the deflagration period, the third rule base is loaded: only aerogel flame retardant is allowed to be placed, and the placement position is limited to the top ventilation opening in the direction of fire spread.

[0104] In some embodiments, the priority rule base module 203 is further configured to:

[0105] Based on the building structure topology map, the fire spread vector is matched and the ventilation openings closest to the fire point and located in the expansion direction are selected. The specific formula is as follows:

[0106]

[0107] Where, P v represents the coordinates of the selected top vent; P represents the set of candidate vents, and each candidate vent is represented by its coordinate P; P f represents the coordinates of the fire point; represents the Euclidean distance between the fire point and the candidate vent, where x P ,y P is the component of coordinate P, x f ,y f Fire point P f The coordinate components of the fire; V is the vector of the fire spreading direction; the constraint condition V·(PP f )>0 is used to ensure that only vents located in the direction of fire spread are considered;

[0108] Generate a delivery parameter set that includes the aerogel material type and vent coordinates.

[0109] In some embodiments, the environmental parameter acquisition module 205 is specifically used to:

[0110] Obtain the fire scene temperature distribution map through the infrared sensor of the fire source detection equipment;

[0111] The gas sensor of the fire blocking robot collects the oxygen concentration at the ventilation opening;

[0112] The temperature distribution map and oxygen concentration data are integrated to generate a feedback parameter set, which is then output to the fire development stage classification model. The specific formula is as follows:

[0113] FP={T avg ,O2};

[0114] Where: T avg represents the average temperature of the fire scene; O2 represents the oxygen concentration measured at the ventilation opening; n is the number of temperature measurement points; T i is the temperature distribution data, i=1,2,…,n.

[0115] In some embodiments, the feedback adjustment module 206 is specifically configured to:

[0116] Input the feedback parameters into the combustion entropy calculation engine and output the updated combustion entropy value;

[0117] Compare the updated entropy value with the stage threshold; if the updated entropy value drops from > the second preset entropy threshold to ≤ the second preset entropy threshold, trigger a switch in the rule base from the deflagration period to the accelerated spread period; if the updated entropy value rises from ≤ the first preset entropy threshold to > the first preset entropy threshold, trigger a switch in the rule base from the latent period to the accelerated spread period;

[0118] A rule base switching instruction is sent to the blocking priority rule base loading module 203 .

[0119] In some embodiments, the fire source location and detection module 201 is specifically used to:

[0120] Call the multispectral imaging module to identify the flame spectral characteristics and locate the coordinates of the fire point;

[0121] Controlling the projection device to launch the fire source detection equipment toward the coordinates of the fire point in a parabolic trajectory;

[0122] The physical detection unit of the fire source detection equipment collects fire scene temperature gradient data through temperature sensors;

[0123] The chemical detection unit of the fire source detection equipment analyzes the composition of combustible materials through a gas chromatography sensor;

[0124] Temperature gradient data are combined with combustible composition to generate fire type and fire severity parameters.

[0125] In some embodiments, the steps of generating a fire scene control instruction according to the blocking priority rule library and controlling the fire blocking robot to carry a specified type of flame retardant material and project it to a specified location to release the flame retardant material include:

[0126] When the fire coverage area exceeds the control range of a single target tracking device, the phase identification and activated blocking priority rule base are sent to the downstream target tracking device in the direction of fire spread;

[0127] The downstream target tracking device generates fire scene control instructions based on the received blocking priority rule base;

[0128] Controlling the fire blocking robot to carry the flame retardant material type specified by the blocking priority rule library;

[0129] Projecting to the placement position defined by the blocking priority rule library within a countdown threshold calculated by the fire spreading speed;

[0130] Trigger the fire blocking robot to release flame retardant when it reaches the coordinate position.

[0131] It is understandable that the modules and references in the dynamic fire extinguishing strategy generation system based on fire development stage classification are Figure 1 The steps in the method for generating a dynamic fire extinguishing strategy based on fire development stage classification correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method are also applicable to the dynamic fire extinguishing strategy generation system based on fire development stage classification and the modules contained therein, and will not be repeated here.

[0132] See also Figure 3 Based on the inventive concept of a method for generating a dynamic fire extinguishing strategy based on fire development stage classification in the aforementioned embodiment, an embodiment of the present application provides a target tracking device. The target tracking device may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), etc., and fixed terminals such as digital TVs, desktop computers, etc. The target tracking device includes a processing device 301 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM 302 (read-only memory) or the program loaded from the storage device 308 into RAM 303 (random access memory). Various programs and data required for the operation of the target tracking device are also stored in RAM 303. The processing device 301, ROM 302 and RAM 303 are connected to each other via a bus 304. The input / output interface (i.e., I / O interface 305) is also connected to the bus 304.

[0133] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the target tracking device to communicate with other devices wirelessly or by wire to exchange data.

[0134] In particular, according to some embodiments of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network via the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present application are performed.

[0135] It should be noted that the computer-readable medium described in some embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present application, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In some embodiments of the present application, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0136] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an adhoc peer-to-peer network), as well as any currently known or future developed network.

[0137] The computer-readable medium may be included in the target tracking device, or may exist independently without being incorporated into the target tracking device. The computer-readable medium carries one or more programs. When executed by the target tracking device, the target tracking device can implement the method steps of any of the above technical solutions.

[0138] Computer program code for performing the operations of some embodiments of the present application can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0139] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0140] The modules described in some embodiments of the present application may be implemented in software or hardware. The modules described may also be provided in a processor. It is understood that the names of these modules do not, in certain circumstances, constitute limitations on the modules themselves.

[0141] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0142] Some embodiments of the present application further provide a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for generating a dynamic fire extinguishing strategy based on fire development stage classification.

[0143] Although the present invention has been described in detail above using general descriptions and specific embodiments, it will be apparent to those skilled in the art that modifications and improvements may be made thereto. Therefore, such modifications and improvements, without departing from the spirit of the present invention, are intended to be within the scope of protection claimed herein.

Claims

1. A method for generating a dynamic fire extinguishing strategy based on fire development stage classification, characterized in that: Executed by the target tracking device, including the following steps: Identify the location of the fire point using image recognition technology and project a fire source detection device toward the location of the fire point; the fire source detection device is used to determine the type and severity of the fire at the fire point through a sensor and return the information to the target tracking device; The fire type, fire severity, and fire environment characteristics collected at each moment are combined into a triplet and input into the fire development stage classification model. The fire is divided into the latent stage, accelerated spread stage, or deflagration stage according to the combustion entropy threshold. According to the current fire development stage, the blocking priority rule library bound to the stage is loaded. The blocking priority rule library only allows the aerogel flame retardant to be released during the deflagration stage, and the release position is limited to the top vent in the direction of fire expansion; Generate fire scene control instructions according to the blocking priority rule library, and control the fire blocking robot to carry a specified type of flame retardant material and release the flame retardant material at a specified time and at a specified location; Receiving fire scene environmental parameters after the release of the flame retardant collected by the fire source detection equipment and the fire blocking robot; The fire scene environmental parameters are fed back to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and if the entropy value crosses the stage threshold, it triggers the dynamic switching of the blocking priority rule library.

2. The method for generating a dynamic fire extinguishing strategy based on fire development stage classification according to claim 1 is characterized in that: The fire type, fire severity, and fire environment characteristics collected at each moment are combined into a triplet and input into the fire development stage classification model. The steps of classifying the fire into the latent stage, accelerated spread stage, or deflagration stage according to the combustion entropy threshold include: The combustion entropy is calculated based on the fire temperature, combustible material concentration, and oxygen concentration in the triplet. The specific formula is as follows: Where: E represents the combustion entropy value; T is the current fire temperature; ρ C is the combustible concentration; ρ O2 is the oxygen concentration; T0, ρ C0 、 are the reference values ​​of temperature, combustible concentration and oxygen concentration respectively; α, β and γ are weight coefficients used to correct the influence of each sensor parameter on combustion entropy; If the combustion entropy value is less than or equal to the first preset entropy threshold, it is determined to be in the latent period; If the combustion entropy value is greater than the first preset entropy threshold and less than or equal to the second preset entropy threshold, it is determined to be in the accelerated spread period; If the combustion entropy value is greater than the second preset entropy threshold, it is determined to be a deflagration period.

3. The method for generating a dynamic fire extinguishing strategy based on fire development stage classification according to claim 2 is characterized in that: Based on the current fire development stage, the steps for loading the blocking priority rule base bound to the stage include: If the stage is marked as the latent period, the first rule base is loaded: the use of foam or dry powder flame retardant is allowed, and the placement location is within a preset distance from the center of the fire; If the phase is marked as the accelerated spread phase, the second rule base is loaded: the high-pressure water mist system is mandatory, and the placement location is the key node of the fire spread path; If the stage is marked as the deflagration period, the third rule base is loaded: only aerogel flame retardant is allowed to be placed, and the placement position is limited to the top ventilation opening in the direction of fire spread.

4. The method for generating a dynamic fire extinguishing strategy based on fire development stage classification according to claim 3 is characterized in that: The blocking priority rule base only allows the aerogel flame retardant to be released during the deflagration period, and the release position is limited to the top vent in the direction of fire spread, including the following steps: Match the fire spread vector based on the building structure topology map and select the ventilation holes closest to the fire point and located in the expansion direction; Generate a delivery parameter set that includes the aerogel material type and vent coordinates.

5. The method for generating a dynamic fire extinguishing strategy based on fire development stage classification according to claim 4 is characterized in that: The step of receiving the fire scene environment parameters collected by the fire source detection equipment and the fire blocking robot after the release of the flame retardant material includes: Obtain the fire scene temperature distribution map through the infrared sensor of the fire source detection equipment; The gas sensor of the fire blocking robot collects the oxygen concentration at the ventilation opening; The temperature distribution map and oxygen concentration data are integrated to generate a feedback parameter set, which is then output to the fire development stage classification model.

6. The method for generating a dynamic fire extinguishing strategy based on fire development stage classification according to any one of claims 1 to 5, characterized in that: Feedback of the fire scene environmental parameters to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and triggers the dynamic switching of the blocking priority rule library if the entropy value crosses the stage threshold, including the following steps: Input the feedback parameters into the combustion entropy calculation engine and output the updated combustion entropy value; Compare the updated entropy value with the stage threshold; if the updated entropy value drops from > the second preset entropy threshold to ≤ the second preset entropy threshold, trigger a switch in the rule base from the deflagration period to the accelerated spread period; if the updated entropy value rises from ≤ the first preset entropy threshold to > the first preset entropy threshold, trigger a switch in the rule base from the latent period to the accelerated spread period; A rule base switching instruction is sent to the blocking priority rule base loading module.

7. A dynamic fire extinguishing strategy generation system based on fire development stage classification, characterized by: Applied to target tracking equipment, including: A fire source positioning and detection module is used to identify the location of the fire point through image recognition technology and project a fire source detection device to the location of the fire point; the fire source detection device is used to determine the type and severity of the fire at the fire point through sensors and return the information to the target tracking device; The fire stage classification module is used to combine the collected fire type, fire severity and fire environment characteristics at each moment into a triplet, which is input into the fire development stage classification model. The fire is classified into the latent stage, accelerated spread stage or deflagration stage according to the combustion entropy threshold. A priority rule library module is used to load a blocking priority rule library bound to the current fire development stage according to the current fire development stage. The blocking priority rule library only allows the aerogel flame retardant to be released during the deflagration stage, and the release position is limited to the top vent in the direction of fire expansion; An instruction generation and execution module is used to generate a fire scene control instruction based on the blocking priority rule library, and control the fire blocking robot to carry a specified type of flame retardant material and project it to a specified location at a specified time to release the flame retardant material; An environmental parameter collection module, configured to receive fire scene environmental parameters collected by the fire source detection equipment and the fire blocking robot after the release of the flame retardant; A feedback adjustment module is used to feed back the fire scene environmental parameters to the fire development stage classification model in real time; the fire development stage classification model recalculates the combustion entropy value based on the feedback parameters, and if the entropy value crosses the stage threshold, it triggers the dynamic switching of the blocking priority rule library.

8. A target tracking device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which implements the method according to any one of claims 1 to 6 when executed by a processing device.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processing device, the method according to any one of claims 1 to 6 is implemented.

Images