Fire early warning system based on Internet of Things

Abstract

The invention relates to the technical field of fire early warning, in particular to a fire early warning system based on the Internet of Things, which comprises a fire early warning center, a data acquisition unit, a fire distinguishing unit, a node verification unit, a radiation verification unit, a fire visual unit and an early warning visual unit, according to the invention, the environment information is collected through a plurality of fire monitoring devices, the comprehensive coverage and real-time monitoring of a target area are realized, the fire hazard can be found in time, the accuracy of fire judgment is improved, the situations of false alarm and missing alarm are reduced, and meanwhile, the fire authenticity analysis of two dimensions of node request verification and optical radiation verification is accompanied, so that the accuracy of fire judgment is improved. The method is advantaged in that misjudgment caused by a single factor is reduced, fire hazard early warning accuracy is further improved, information feedback visual analysis is carried out from angles of fire hazard diffusion paths, diffusion grades and the like, information of fire hazard diffusion directions, fire hazard positions and the like can be visually known based on the acquired visual fire hazard model, and targeted fire hazard emergency response decision making is further facilitated.

Description

Technical Field

[0001] This invention relates to the field of fire early warning technology, and in particular to a fire early warning system based on the Internet of Things. Background Technology

[0002] Fire is a serious threat to people's lives and property. Timely and accurate fire warning is crucial to reducing fire losses. Traditional fire warning systems usually use wired connections, which have problems such as complex wiring, high cost, poor flexibility, and limited warning range. They can often only issue alarms locally, making it difficult to achieve remote warning and centralized management. With the development of IoT technology, new solutions have been provided for fire early warning systems. IoT technology can realize wireless communication and data sharing between devices, improving the flexibility and scalability of fire early warning systems. However, existing IoT-based fire early warning systems still have shortcomings in the comprehensiveness and accuracy of data collection, and it is difficult to accurately visualize the development trend of fires, making it difficult to adjust emergency decisions in real time according to the development of fires. To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0003] The purpose of this invention is to provide an Internet of Things-based fire early warning system to address the aforementioned technical deficiencies. This invention collects environmental information through multiple fire monitoring devices, achieving comprehensive coverage and real-time monitoring of the target area. It can promptly detect fire hazards and simultaneously conduct fire authenticity analysis based on two dimensions: node request verification and light radiation verification. This reduces misjudgments caused by single factors. It also provides visual analysis of information feedback from the perspectives of fire spread routes and spread levels, so that based on the obtained visual fire model, one can intuitively understand information such as the direction of fire spread and the location of the fire.

[0004] The objective of this invention can be achieved through the following technical solution: a fire early warning system based on the Internet of Things, comprising a fire early warning center, a data acquisition unit, a fire discrimination unit, a node verification unit, a radiation verification unit, a fire visualization unit, and an early warning visualization unit; The data acquisition unit is used to collect environmental information, light radiation information, etc. of the target area and send them to the fire early warning center for storage; The fire detection unit is used to retrieve environmental information of the target area and perform regional fire identification analysis to determine whether a fire has occurred in the target area. It analyzes the obtained fire identification results to obtain trigger nodes or conventional signals. The node verification unit is used to perform fire authenticity node request analysis on the triggering node, and to distinguish between the obtained real signal and the fire-compliant signal to obtain the fire real signal or the fire error signal. The radiation verification unit is used to perform fire verification and fusion assessment feedback analysis on the optical radiation information of the trigger node, and to perform discrimination processing on the obtained comprehensive feature value to obtain non-fire signal or fire risk signal. The generated real fire signal and fire risk signal are processed to obtain a fire alarm signal or a verification end signal. The fire visualization unit is used to analyze the fire spread and risk level classification of the triggering node, and obtain a visual fire model.

[0005] Preferably, the regional fire identification and analysis process is as follows: The system collects the operating time of each fire monitoring device within the target area and obtains environmental information of the working area of ​​each fire monitoring device within the operating time, including smoke concentration and ambient temperature. The collected environmental information is preprocessed and then input into the fire identification model to obtain the fire identification result output by the fire identification model. The fire identification result is then used to determine whether a fire has occurred, and a fire signal or a regular signal is obtained. The fire monitoring device corresponding to the fire signal is set as the trigger node.

[0006] Preferably, the analysis process of the node verification unit is as follows: The triggering node sends a verification request to neighboring nodes within a preset range based on its own location information and network topology. The request information includes detailed abnormal parameters. After receiving the verification request, the neighboring node monitors the abnormal parameters in the triggering node's environment parameters and feeds back the abnormal parameters and timestamps collected from the triggering node's environment parameters to the triggering node. The data received by the trigger node is set as the initial data, and the initial data is preprocessed.

[0007] Preferably, a time correlation analysis is performed on the preprocessed initial data: S1: Record the time when each adjacent node first detects an anomaly, forming a time series; S2: Calculate the distance between each adjacent node and the trigger node to form a distance sequence; S3: The anomaly diffusion rate is calculated based on time series and distance series analysis; S4 performs discrimination processing on abnormal diffusion rates to obtain either interference signals or true signals.

[0008] Preferably, spatial consistency analysis is performed on the preprocessed initial data: SS1: Establish a polar coordinate space model centered on the trigger node; SS2: Maps the position coordinates and anomaly parameter intensity of each adjacent node to the polar coordinate space model; SS3: Calculate the attenuation coefficient of anomaly parameter intensity as distance increases; SS4: The attenuation coefficient is processed to determine whether it conforms to the fire signal or not.

[0009] Preferably, the generated real signal and the fire-compliant signal are processed for discrimination. If a real signal and a fire-compliant signal are generated, a real fire signal is obtained; if no real signal and a fire-compliant signal are generated, a fire error signal is obtained.

[0010] Preferably, the analysis process of the radiation verification unit is as follows: The light radiation information of the trigger node during the runtime is obtained. The light radiation information includes external radiation, visible light and near-infrared radiation. The collected light radiation information is preprocessed. Based on the preprocessed optical radiation information, spectral features, temporal features, and polarization features are obtained, and the spectral features, temporal features, and polarization features are normalized. Simultaneously, the weighting coefficients corresponding to the spectral features, temporal features, and polarization features are obtained, and the sum of the products of the spectral features, temporal features, and polarization features with their respective weighting coefficients is set as the comprehensive feature value. The comprehensive characteristic values ​​are then processed to determine whether they are non-fire signals or fire risk signals. The generated real fire signal and fire risk signal are processed to obtain a fire alarm signal or a verification end signal.

[0011] Preferably, the analysis process of the fire visualization unit is as follows: Starting from the trigger node, the adjacent nodes in each direction of the trigger node are obtained, and the triggering order of the adjacent nodes in each direction is obtained. Triggering means that the adjacent node becomes the trigger node. Based on the triggering order, the next node in the same direction as each triggered adjacent node and the suspected diffusion direction is obtained, and the next node in the same direction is set as the diffusion node. The environmental information of the diffusion node within a set time period is obtained. The environmental information within the set time period is preprocessed and input into the fire identification model. If a fire signal is obtained, the diffusion node is set as the confirmation point. If a normal signal is obtained, the diffusion node is set as the error point. The line connecting the trigger node, the triggered adjacent node, and the confirmation point is set as the diffusion path. The distance between the diffusion node and the trigger node is obtained, and the diffusion duration between the time when the fire monitoring device is set as the trigger node and the time when the diffusion node is set as the confirmation point is also obtained. The diffusion rate is obtained based on the distance between the diffusion node and the trigger node and the diffusion duration, and the diffusion rate is processed to obtain the diffusion level. Obtain the pre-set building BIM model of the target area, and mark the diffusion path, trigger node, adjacent trigger nodes, confirmation point and diffusion level in the pre-set building BIM model to obtain a visual fire model; The suspected diffusion direction indicates the direction from the triggering node to the adjacent node of the first trigger.

[0012] The beneficial effects of this invention are as follows: (1) This invention collects environmental information through multiple fire monitoring devices, achieving comprehensive coverage and real-time monitoring of the target area. It can promptly detect fire hazards and conduct in-depth analysis and judgment of environmental information, improving the accuracy of fire judgment and reducing false alarms and missed alarms. At the same time, it is accompanied by fire authenticity analysis in two dimensions: node request verification and light radiation verification, reducing misjudgments caused by a single factor, thereby improving the accuracy of fire early warning and enabling timely response to fire early warning management to reduce fire hazards. (2) This invention performs visual analysis of information feedback from the perspectives of fire spread routes and spread levels, so that the obtained visual fire model can intuitively understand the fire spread direction, fire location and other information, thereby helping to make targeted fire emergency response decisions. Attached Figure Description

[0013] The invention will now be further described with reference to the accompanying drawings; Figure 1 This is a flowchart of the system of the present invention; Figure 2 This is a partial analysis reference diagram of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments; Example 1

[0016] Please see Figures 1 to 2As shown, the present invention is a fire early warning system based on the Internet of Things, including a fire early warning center, a data acquisition unit, a fire discrimination unit, a node verification unit, a radiation verification unit, a fire visualization unit, and an early warning visualization unit. The fire early warning center and the data acquisition unit have a bidirectional communication connection, the fire early warning center and the fire discrimination unit have a unidirectional communication connection, the fire discrimination unit and the node verification unit, the radiation verification unit and the early warning visualization unit all have unidirectional communication connections, the node verification unit and the radiation verification unit have a unidirectional communication connection, the radiation verification unit and the fire visualization unit have a unidirectional communication connection, and the fire visualization unit and the early warning visualization unit have a unidirectional communication connection. The data acquisition unit is used to collect environmental information, light radiation information, etc. of the target area and send them to the fire early warning center for storage; The fire detection unit is used to retrieve environmental information of the target area and perform regional fire identification and analysis to determine whether a fire has occurred in the target area. The specific regional fire identification and analysis process is as follows: The system collects the operating time of each fire monitoring device within the target area and obtains environmental information of the working area of ​​each fire monitoring device during the operating time, including smoke concentration, ambient temperature, etc. The collected environmental information is preprocessed, including cleaning and noise reduction. The preprocessed environmental information is input into the fire identification model, the fire identification result output by the fire identification model is obtained, and the fire identification result is judged to determine whether a fire has occurred. If so, a fire signal is generated, the fire monitoring device corresponding to the fire signal is obtained, and the fire monitoring device corresponding to the fire signal is set as a trigger node. If not, a normal signal is generated, the early warning visual unit responds to the normal signal, and immediately executes continuous monitoring of the normal signal. This means that by collecting environmental information through multiple fire monitoring devices, comprehensive coverage and real-time monitoring of the target area can be achieved, fire hazards can be detected in a timely manner, and in-depth analysis and judgment of environmental information can be carried out to improve the accuracy of fire judgment and reduce false alarms and missed alarms. When a fire signal is generated, the node verification unit performs a fire authenticity node request analysis on the triggering node, that is, analyzes from the node's perspective whether a fire has occurred at the triggering node. The specific fire authenticity node request analysis process is as follows: The triggering node sends a verification request to neighboring nodes within a preset range based on its own location information and network topology. The request information contains detailed abnormal parameters, enabling neighboring nodes to adjust their monitoring strategies accordingly. The preset range is dynamically adjusted according to the node density, which reduces the network communication burden while ensuring the accuracy of verification. After receiving a verification request, neighboring nodes monitor abnormal parameters in the triggering node's environmental parameters. For example, if the triggering node detects abnormal smoke, neighboring nodes will strengthen the monitoring of smoke and temperature parameters, while reducing the sampling frequency of other parameters, thus optimizing energy consumption while ensuring data validity. Neighboring nodes will feed back abnormal parameters and timestamps from the collected environmental parameters of the triggering node to the triggering node; The data received by the trigger node is set as the initial data, and the initial data is preprocessed; Perform time correlation analysis on the preprocessed initial data: S1: Record the time when each adjacent node first detects an anomaly, forming a time series; S2: Calculate the distance between each adjacent node and the trigger node to form a distance sequence; S3: The abnormal spread rate is calculated based on time series and distance series analysis. In real fires, the nodes farther away from the triggering node are usually detected later, showing a positive correlation. S4 performs a discrimination process on the abnormal diffusion speed. If the abnormal diffusion speed is greater than the preset abnormal diffusion speed threshold, an interference signal is generated. If the abnormal diffusion speed is less than the abnormal diffusion speed threshold, a real signal is generated. Spatial consistency analysis was performed on the preprocessed initial data: SS1: Establish a polar coordinate space model centered on the trigger node; SS2: Maps the position coordinates and anomaly parameter intensity of each adjacent node to the polar coordinate space model; SS3: Calculate the attenuation coefficient of the intensity of abnormal parameters as distance increases. In real fires, parameters such as temperature and smoke usually exhibit exponential attenuation characteristics. SS4: The attenuation coefficient is judged. If the attenuation coefficient conforms to the preset fire spread attenuation model, a fire signal is generated. If the attenuation coefficient does not conform to the preset fire spread attenuation model, a fire signal is generated. The generated real signal and the fire-compliant signal are processed for discrimination. If a real signal and a fire-compliant signal are generated, the real fire signal is obtained. If no real signal and a fire-compliant signal are generated, the fire error signal is obtained. This invention utilizes multi-dimensional collaborative analysis to fully leverage the spatial and temporal characteristics of fire spread and comprehensively capture the typical patterns of real fires. Example 2

[0017] When a fire signal is generated, the radiation verification unit is used to perform fire verification and fusion evaluation feedback analysis on the optical radiation information of the triggering node. That is, it performs joint discrimination from multiple dimensions to improve the accuracy of fire identification. The specific fire verification and fusion evaluation feedback analysis process is as follows: Obtain the light radiation information of the trigger node during the runtime period. The light radiation information includes external radiation, visible light and near-infrared radiation. The collected optical radiation information is preprocessed, for example, by using an adaptive wavelet denoising algorithm to remove environmental noise, especially power frequency interference and random noise, from the signal; then baseline correction is performed to eliminate the influence of detector dark current and background light; finally, standard light source calibration is used to achieve spectral consistency between different detectors to ensure the reliability of feature extraction. Based on the preprocessed optical radiation information, spectral features (such as ultraviolet band radiation intensity), temporal features (such as radiation intensity fluctuation frequency) and polarization features (such as the degree of polarization in the ultraviolet band) are obtained. The spectral features, temporal features and polarization features are normalized, and the min-max normalization method is used to map each feature value to the [0,1] interval to eliminate the influence of the difference in dimensions between different features. Simultaneously, the weighting coefficients corresponding to the spectral features, temporal features, and polarization features are obtained, and the sum of the products of the spectral features, temporal features, and polarization features with their respective weighting coefficients is set as the comprehensive feature value. The comprehensive feature value is then processed for discrimination. If the comprehensive feature value is less than the preset comprehensive feature value threshold, a non-fire signal is generated. If the comprehensive feature value is greater than or equal to the preset comprehensive feature value threshold, a fire risk signal is generated. The generated real fire signal and fire risk signal are processed for discrimination. If at least one of the real fire signal and fire risk signal is generated, a fire alarm signal is obtained. If at least one of the real fire signal and the fire risk signal is not generated, a verification end signal is obtained. The early warning visual unit responds to the fire alarm signal or the verification end signal and immediately executes the preset early warning operation corresponding to the fire alarm signal or the verification end signal, so as to make a reasonable fire response early warning based on the feedback information, so as to respond to fire management in a timely manner and reduce the risk of fire hazards. Example 3

[0018] When a fire alarm signal is generated, the fire visualization unit is used to perform fire spread and risk level classification analysis on the triggering node. The specific fire spread and risk level classification analysis process is as follows: Starting from the trigger node, the adjacent nodes in each direction (south, southeast, etc.) of the trigger node are obtained, and the triggering order of the adjacent nodes in each direction is obtained. Triggering means that the adjacent node becomes the trigger node. Based on the triggering order, the next node in the same direction as each triggered adjacent node and the suspected diffusion direction (the direction connected to the first triggered adjacent node starting from the trigger node) is obtained, and the next node in the same direction is set as the diffusion node. The environmental information of the diffusion node within a set time period is obtained. The environmental information within the set time period is preprocessed and input into the fire identification model. The output result of the fire identification model is judged. If a fire signal is generated, the diffusion node is set as the confirmation point. If a normal signal is generated, the diffusion node is set as the error point. The line connecting the trigger node, the triggered adjacent node, and the confirmation point is set as the diffusion path. The distance between the diffusion node and the trigger node is obtained, as well as the diffusion duration between the time when the fire monitoring device is set as the trigger node and the time when the diffusion node is set as the confirmation point. The diffusion rate is obtained based on the distance between the diffusion node and the trigger node and the diffusion duration, and the diffusion rate is judged. If the diffusion rate belongs to the corresponding preset diffusion rate range, the diffusion level set in the corresponding preset diffusion rate range is obtained. It should be noted that the preset diffusion rate ranges are set in ascending order, and each preset diffusion rate range is set with a diffusion level, which is also set in ascending order. The system obtains a pre-set building BIM model of the target area, marks the diffusion path, trigger nodes, adjacent trigger nodes, confirmation points, and diffusion levels on the pre-set building BIM model to obtain a visual fire model, and the early warning visual unit responds to the visual fire model so that the fire diffusion direction, fire location and other information can be intuitively understood based on the visual fire model, which helps to make targeted fire emergency response decisions. In summary, this invention collects environmental information through multiple fire monitoring devices, achieving comprehensive coverage and real-time monitoring of the target area. This enables timely detection of fire hazards and in-depth analysis and judgment of environmental information, improving the accuracy of fire assessment and reducing false alarms and missed alarms. Furthermore, the invention incorporates fire authenticity analysis along two dimensions: node request verification and light radiation verification, reducing misjudgments caused by single factors and thus improving the accuracy of fire early warning. This facilitates timely response to fire warning management, reducing fire hazards. Additionally, the invention provides visual feedback analysis from the perspectives of fire spread routes and spread levels, allowing for intuitive understanding of fire spread direction and location based on the obtained visual fire model, thereby aiding in targeted fire emergency response decisions.

[0019] The threshold is set for comparative analysis of results to determine whether they are good or bad. The value of the threshold is determined by a combination of large-scale model analysis of sample data and human experience. It can also be adjusted appropriately based on seasonal or common-sense influencing factors.

[0020] The size of the coefficient is a specific value obtained by quantifying each parameter to facilitate subsequent comparison. The size of the coefficient depends on the amount of sample data and the corresponding operating coefficient initially set by those skilled in the art for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantified value.

[0021] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A fire early warning system based on the Internet of Things, characterized in that, It includes a fire early warning center, a data acquisition unit, a fire discrimination unit, a node verification unit, a radiation verification unit, a fire visualization unit, and an early warning visualization unit; The data acquisition unit is used to collect environmental information, light radiation information, etc. of the target area and send them to the fire early warning center for storage; The fire detection unit is used to retrieve environmental information of the target area and perform regional fire identification analysis to determine whether a fire has occurred in the target area. It analyzes the obtained fire identification results to obtain trigger nodes or conventional signals. The node verification unit is used to perform fire authenticity node request analysis on the triggering node, and to distinguish between the obtained real signal and the fire-compliant signal to obtain the fire real signal or the fire error signal. The radiation verification unit is used to perform fire verification and fusion assessment feedback analysis on the optical radiation information of the trigger node, and to perform discrimination processing on the obtained comprehensive feature value to obtain non-fire signal or fire risk signal. The generated real fire signal and fire risk signal are processed to obtain a fire alarm signal or a verification end signal. The fire visualization unit is used to analyze the fire spread and risk level classification of the triggering node, and obtain a visual fire model.

2. The fire early warning system based on the Internet of Things according to claim 1, characterized in that, The process for identifying and analyzing fires in the area is as follows: The system collects the operating time of each fire monitoring device within the target area and obtains environmental information of the working area of ​​each fire monitoring device within the operating time, including smoke concentration and ambient temperature. The collected environmental information is preprocessed and then input into the fire identification model to obtain the fire identification result output by the fire identification model. The fire identification result is then used to determine whether a fire has occurred, and a fire signal or a regular signal is obtained. The fire monitoring device corresponding to the fire signal is set as the trigger node.

3. A fire early warning system based on the Internet of Things according to claim 1, characterized in that, The analysis process of the node verification unit is as follows: The triggering node sends a verification request to neighboring nodes within a preset range based on its own location information and network topology. The request information includes detailed abnormal parameters. After receiving the verification request, the neighboring node monitors the abnormal parameters in the triggering node's environment parameters and feeds back the abnormal parameters and timestamps collected from the triggering node's environment parameters to the triggering node. The data received by the trigger node is set as the initial data, and the initial data is preprocessed.

4. A fire early warning system based on the Internet of Things according to claim 3, characterized in that, Perform time correlation analysis on the preprocessed initial data: S1: Record the time when each adjacent node first detects an anomaly, forming a time series; S2: Calculate the distance between each adjacent node and the trigger node to form a distance sequence; S3: The anomaly diffusion rate is calculated based on time series and distance series analysis; S4 performs discrimination processing on abnormal diffusion rates to obtain either interference signals or true signals.

5. A fire early warning system based on the Internet of Things according to claim 4, characterized in that, Spatial consistency analysis was performed on the preprocessed initial data: SS1: Establish a polar coordinate space model centered on the trigger node; SS2: Maps the position coordinates and anomaly parameter intensity of each adjacent node to the polar coordinate space model; SS3: Calculate the attenuation coefficient of anomaly parameter intensity as distance increases; SS4: The attenuation coefficient is processed to determine whether it conforms to the fire signal or not.

6. A fire early warning system based on the Internet of Things according to claim 5, characterized in that, The generated real signal and the fire-compliant signal are processed for discrimination. If a real signal and a fire-compliant signal are generated, the real fire signal is obtained. If no real signal and a fire-compliant signal are generated, the fire error signal is obtained.

7. A fire early warning system based on the Internet of Things according to claim 1, characterized in that, The analysis process of the radiation verification unit is as follows: The light radiation information of the trigger node during the runtime is obtained. The light radiation information includes external radiation, visible light and near-infrared radiation. The collected light radiation information is preprocessed. Based on the preprocessed optical radiation information, spectral features, temporal features, and polarization features are obtained, and the spectral features, temporal features, and polarization features are normalized. Simultaneously, the weighting coefficients corresponding to the spectral features, temporal features, and polarization features are obtained, and the sum of the products of the spectral features, temporal features, and polarization features with their respective weighting coefficients is set as the comprehensive feature value. The comprehensive feature values ​​are then processed to determine whether they are non-fire signals or fire risk signals. The generated real fire signal and fire risk signal are processed to obtain a fire alarm signal or a verification end signal.

8. A fire early warning system based on the Internet of Things according to claim 1, characterized in that, The analysis process of the fire visualization unit is as follows: Starting from the trigger node, the adjacent nodes in each direction of the trigger node are obtained, and the triggering order of the adjacent nodes in each direction is obtained. Triggering means that the adjacent node becomes the trigger node. Based on the triggering order, the next node in the same direction as each triggered adjacent node and the suspected diffusion direction is obtained, and the next node in the same direction is set as the diffusion node. The environmental information of the diffusion node within a set time period is obtained. The environmental information within the set time period is preprocessed and input into the fire identification model. If a fire signal is obtained, the diffusion node is set as the confirmation point. If a normal signal is obtained, the diffusion node is set as the error point. The line connecting the trigger node, the triggered adjacent node, and the confirmation point is set as the diffusion path. The distance between the diffusion node and the trigger node is obtained, and the diffusion duration between the time when the fire monitoring device is set as the trigger node and the time when the diffusion node is set as the confirmation point is also obtained. The diffusion rate is obtained based on the distance between the diffusion node and the trigger node and the diffusion duration, and the diffusion rate is processed to obtain the diffusion level. Obtain the pre-set building BIM model of the target area, and mark the diffusion path, trigger node, adjacent trigger nodes, confirmation point, and diffusion level in the pre-set building BIM model to obtain a visual fire model; The suspected diffusion direction indicates the direction from the triggering node to the adjacent node of the first trigger.

Images