Real-time fireproof monitoring data transmission system for fire engineering construction

Abstract

The invention relates to the technical field of fire-fighting engineering, and discloses a real-time fireproof monitoring data transmission system for fire-fighting engineering construction, which comprises a fire parameter analysis module, an environmental data analysis module, a fire source positioning module, a model construction module and a safety database. The fire parameter analysis module generates a temperature change record table through gridding temperature measurement nodes, estimates the smoke diffusion rate, and evaluates the thermal stress and deformation risk of the building structure; the environment data analysis module associates the air velocity with the smoke diffusion rate and corrects the parameter weight of the evaluation model; the fire source positioning module generates a fire source three-dimensional positioning map by using multispectral imaging equipment; the model construction module constructs a dynamic fire assessment model according to multi-dimensional data and outputs a comprehensive threat level; the security database stores building material parameters, historical case characteristics, and dynamic threshold rules. According to the system, through multi-module cooperation and multi-data fusion, the accuracy and timeliness of fire-fighting monitoring are improved, and the system is suitable for safety management of fire-fighting engineering.

Description

Technical Field

[0001] The present invention relates to the technical field of fire protection engineering, and particularly to a real-time fire prevention monitoring data transmission system for fire protection engineering construction. Background Art

[0002] In the field of modern building fire protection engineering, with the continuous expansion of building scale and the increasing complexity of structure, traditional fire prevention monitoring means are difficult to meet the requirements of real-time and accurate monitoring and dynamic assessment of fires. In the existing technology, most fire prevention monitoring systems have problems such as single data collection, rough analysis models, and lagging risk assessment, resulting in the inability to timely and accurately grasp the development trend of fires and making it difficult to take effective prevention and control measures in the initial stage of fires.

[0003] From the perspective of data collection, traditional systems often rely only on single-point temperature monitoring, lacking a comprehensive perception of the temperature distribution in the monitored area, unable to construct a complete temperature change record form, and thus difficult to accurately estimate the smoke diffusion rate. At the same time, the correlation analysis between the monitoring of environmental factors such as air velocity and fire parameters is insufficient, unable to dynamically measure the distribution relationship between air velocity and smoke concentration, making the input parameters of the fire assessment model incomplete and affecting the accuracy of the assessment results.

[0004] In terms of fire source location, the existing technology mostly uses single sensors or simple signal detection methods, making it difficult to quickly and accurately obtain the coordinate data of each fire source and the heat radiation distribution data under the corresponding fire source intensity, unable to generate a three-dimensional fire source positioning map and update it to the assessment model in real time, resulting in a lag in fire source location and affecting the pertinence and effectiveness of fire prevention and control.

[0005] Regarding the fire risk assessment model, traditional systems usually adopt a simple calculation model with fixed weights, lacking dynamic fusion and analysis of multi-dimensional data. For example, it is impossible to standardize temperature data, building structure data, air velocity data, fire source data, etc. and generate a feature vector set, and it is also difficult to dynamically adjust the weight coefficients of each index according to real-time data, resulting in an unscientific and unreasonable comprehensive threat level of fire spread output, unable to provide a reliable basis for fire protection decision-making.

[0006] In addition, there are obvious defects in the construction of the safety database. The databases of existing systems often only store basic data such as the thermal conductivity coefficient of single building materials, lacking a historical fire case feature library and a dynamic threshold adjustment rule set, unable to provide rich reference bases for fire parameter analysis and risk assessment, and difficult to meet the fire prevention monitoring requirements under different building structures and environmental conditions.

[0007] With the development of smart cities and Internet of Things technologies, the demand for real-time, accurate, and intelligent fire monitoring systems in the field of fire protection engineering is becoming increasingly urgent. How to integrate multi-source data, build a dynamic and intelligent fire assessment model, and achieve real-time monitoring, precise positioning, and risk warning of fires has become a key issue that needs to be urgently addressed in the current field of fire protection engineering technology. Based on the above-mentioned deficiencies in the existing technology, the present invention proposes a real-time fire monitoring data transmission system for fire protection engineering construction, which aims to improve the accuracy and timeliness of fire monitoring through multi-module collaborative work and multi-dimensional data fusion, and provide more reliable technical support for the safety management of fire protection engineering. Summary of the Invention

[0008] The purpose of the present invention is to provide a real-time fire monitoring data transmission system for fire engineering construction to solve the problems raised in the above background technology.

[0009] To achieve the above-mentioned object, the present invention provides the following technical solution: a real-time fire monitoring data transmission system for fire engineering construction, the system comprising: The fire parameter analysis module is used to generate a temperature change record table based on the temperature data of the monitoring area, from which the smoke diffusion rate is estimated, and then a safety assessment of the thermal stress and material deformation of the building structure is conducted; Environmental data analysis module, used to obtain air velocity data, correlate it with smoke diffusion rate, and measure the dynamic distribution relationship between air velocity and smoke concentration; Fire source positioning module, used to obtain the coordinate data of each fire source and the thermal radiation distribution data under the corresponding fire source intensity; The model building module is used to construct a fire dynamic assessment model using temperature data, building structure data, air velocity data, and fire source data as input parameters, and output a comprehensive threat level of fire spread; The security database is used to store the corresponding thermal conductivity coefficient of each building material, the set smoke concentration threshold and the structural deformation threshold.

[0010] Preferably, the fire parameter analysis module specifically includes the following steps: S1. Deploy several temperature measurement nodes in the monitoring area according to the grid principle. During the fire monitoring process, according to the set collection cycle, the temperature data of each temperature measurement node is acquired through infrared sensors. The coordinates, temperature value and collection time of each node are recorded, and a temperature change record table is generated; S2. Calculate the heat accumulation gradient of the monitored area based on the temperature change of each node during the current acquisition cycle. Simultaneously, obtain the spatial parameters of the building structure and calculate the smoke diffusion range based on the heat gradient distribution to estimate the fire spread rate. S3. Analyze the thermal stress of the building structure based on the temperature distribution uniformity, obtain the tolerance coefficient of the building materials, and determine the risk level of the structure; S4. Analyze the material deformation amount based on the temperature difference between adjacent regions, compare with the preset deformation threshold to determine whether there is a risk of structural failure, and if so, calculate the deformation risk value.

[0011] Preferably, the specific operation method of step S2 is as follows: Obtain the length and floor height of the building, calculate the smoke diffusion volume in combination with the heat distribution range, obtain the type of building materials, match it with the corresponding thermal conductivity coefficients of each material stored in the safety database to obtain the material thermal conductivity coefficient, and then calculate the smoke diffusion intensity of each temperature measurement node according to the set heat radiation attenuation rate; Based on the smoke diffusion volume, material thermal conductivity coefficient and smoke diffusion intensity, deduce the smoke concentration values of each monitoring point through the spatial distribution algorithm, and construct a three-dimensional diffusion model based on the spatial coordinates of the monitoring points and the smoke concentration values.

[0012] Preferably, the specific operation method of step S3 is as follows: S31. Read the temperature data of each monitoring point, and calculate the temperature distribution dispersion through the standard deviation; S32. Take adjacent monitoring points as a group, calculate the temperature difference and spatial distance of each group, calculate the local thermal stress through the product of the temperature gradient and the material thermal expansion coefficient, and obtain the overall thermal stress index after weighted average; S33. Extract the material yield strength set in the safety database, compare it with the overall thermal stress index, and if it is lower than the set threshold, it is determined as a high-risk area, otherwise it is marked as a safe area.

[0013] Preferably, the specific operation method of step S4 is as follows: S41. Obtain the original geometric parameters of the building structure, calculate the temperature difference between the high-temperature area and the adjacent area respectively, and calculate the theoretical deformation amount in combination with the material linear expansion coefficient; S42. Obtain the actual deformation data through a laser rangefinder. If the theoretical deformation amount exceeds the preset threshold, an alarm is triggered and the deformation risk coefficient is output.

[0014] Preferably, the specific operation method of the environmental data analysis module is as follows: Deploy multiple groups of wind speed sensors in the monitoring area, collect air velocity data according to the time series, synchronously extract the smoke concentration values at the corresponding time points, calculate the dynamic correlation between the air velocity and the smoke diffusion through covariance analysis, and generate a velocity-concentration distribution matrix for correcting the parameter weights of the fire dynamic assessment model.

[0015] Preferably, the specific operation method of the fire source location module is as follows: Use a multispectral imaging device to obtain the heat source distribution data of the monitoring area, separate abnormal heat source points through the background difference algorithm, generate a three-dimensional fire location map by combining temperature intensity and spatial coordinates, and update it to the fire dynamic assessment model in real time.

[0016] Preferably, the specific analysis methods for the input parameters and output parameters of the fire dynamic assessment model are as follows: Define that the input parameters include temperature data, building structure parameters, air flow velocity data, and fire source coordinate data. Among them, the temperature data includes the temperature values, acquisition times, and spatial coordinates of each node, and the building structure parameters include material types, geometric dimensions, and thermal conductivity coefficients; Define that the output parameters include the smoke diffusion range, structural thermal stress index, deformation risk value, and fire source threat level, and generate a comprehensive threat assessment result through multi-dimensional data fusion.

[0017] Preferably, the specific operation method of the model construction module is as follows: Perform standardization processing on the input parameters and generate a feature vector set, assign dynamic weight coefficients to each index in the output parameters, calculate the comprehensive fire threat index through the weighted summation algorithm, and generate a threat level according to the preset level division standard; Use the time series prediction algorithm to train the model parameters, input the real-time data into the trained fire dynamic assessment model, and output the current threat level and risk parameter list.

[0018] Preferably, the security database includes a building material thermodynamics parameter library, a historical fire case feature library, and a dynamic threshold adjustment rule set.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: In terms of fire parameter analysis, by arranging temperature measurement nodes in a grid and combining infrared sensors, the temperature data of each node can be obtained in real time according to the set acquisition period, and a detailed temperature change record table can be generated. Based on this table, the system can not only calculate the heat accumulation gradient of the monitoring area, accurately estimate the smoke diffusion range and the fire spread rate in combination with the building structure space parameters, but also analyze the structural thermal stress of the building through the temperature distribution uniformity, obtain the tolerance coefficient of the building material and determine the structural risk level. At the same time, analyze the material deformation amount through the temperature difference between adjacent areas, and compare with the preset threshold to judge the structural failure risk. This all-round fire parameter analysis realizes the dynamic and accurate assessment of the fire development trend and the building structure safety, providing key data support for early fire warning and structural protection.

[0020] The environmental data analysis module collects air velocity data in time series by deploying multiple groups of wind speed sensors, synchronously extracts the smoke concentration values at corresponding time points, calculates the dynamic correlation between the two through covariance analysis, and generates a flow velocity-concentration distribution matrix. This matrix can effectively correct the parameter weights of the fire dynamic assessment model, enabling the model to fully consider the influence of environmental factors on fire development, and improving the scientificity and reliability of the assessment results. This analysis method that combines environmental factors with fire parameters is more in line with the actual fire scenario and provides a more practical reference basis for fire fighting decisions.

[0021] The fire source positioning module uses multi-spectral imaging equipment and background difference algorithm, which can quickly and accurately obtain the heat source distribution data of the monitoring area, separate abnormal heat source points, and generate a three-dimensional fire source positioning map by combining temperature intensity and spatial coordinates, and update it to the fire dynamic assessment model in real time. This technology realizes the precise positioning and dynamic tracking of the fire source, enabling fire fighters to master the location and intensity of the fire source in the first time, providing key information for formulating targeted fire fighting and rescue plans, and greatly improving the efficiency and effectiveness of fire prevention and control.

[0022] The model construction module generates a feature vector set by standardizing the input parameters, assigns dynamic weight coefficients to each index of the output parameters, calculates the comprehensive fire threat index using the weighted summation algorithm, and trains the model parameters by combining the time series prediction algorithm. This intelligent model construction method realizes the dynamic fusion and comprehensive evaluation of multi-dimensional data, can output the current threat level and risk parameter list according to real-time data, provides timely and accurate fire risk assessment results for fire management personnel, and helps them make scientific and reasonable decisions. At the same time, the dynamic training and optimization mechanism of the model enables it to adapt to the fire monitoring requirements in different scenarios and times, further improving the applicability and reliability of the system.

[0023] The safety database not only stores the thermodynamic parameters of building materials, but also includes a historical fire case feature library and a dynamic threshold adjustment rule set. The rich database content provides a comprehensive reference basis for fire parameter analysis and risk assessment, enabling the system to automatically adjust the assessment criteria and thresholds according to different building structures and environmental conditions, and improving the flexibility and adaptability of the system. For example, through the analysis of historical fire case features, the system can draw on past experience to more accurately judge the development trend and potential risks of the current fire; the dynamic threshold adjustment rule set ensures that the system can maintain good monitoring and assessment performance in different time periods and environmental conditions. Description of the Drawings Figure 1 It is the working principle diagram of the real-time fire prevention monitoring data transmission system for fire protection engineering construction described in the present invention; Figure 2 It is the flow chart of smoke diffusion calculation; Figure 3 It is a flowchart for structural deformation analysis; Figure 4 It is a flowchart for environmental data analysis module; Figure 5 It is a flowchart for fire source location module. Specific implementation manners

[0024] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0025] Please refer to Figures 1 - 5 , a real-time fire prevention monitoring data transmission system for fire protection engineering construction involved in the present invention. This system realizes real-time monitoring and data transmission of fires through the collaborative work of multiple modules, and specifically includes the following steps: The system includes a fire parameter analysis module, an environmental data analysis module, a fire source location module, a model construction module, and a safety database.

[0026] The fire parameter analysis module is used to generate a temperature change record table according to the temperature data in the monitoring area, estimate the smoke diffusion rate from it, and then conduct a safety assessment on the thermal stress and material deformation of the building structure. The specific process is as follows: First, a number of temperature measurement nodes are arranged in the monitoring area according to the grid principle. During the fire prevention monitoring process, according to the set acquisition period, the temperature data of each temperature measurement node is obtained through an infrared sensor, and the coordinates, temperature values, and acquisition times of each node are recorded to generate a temperature change record table (step S1); then, the heat accumulation gradient of the monitoring area is calculated according to the temperature change amount of each node in the current acquisition period, and at the same time, the spatial parameters of the building structure are obtained, and the smoke diffusion range is calculated in combination with the heat gradient distribution to estimate the fire spread rate (step S2); then, the thermal stress of the building structure is analyzed according to the temperature distribution uniformity, the tolerance coefficient of the building material is obtained, and the risk level of the structure is determined (step S3); finally, the material deformation amount is analyzed according to the temperature difference between adjacent areas, and whether there is a risk of structural failure is judged by comparing with the preset deformation threshold. If so, the deformation risk value is calculated (step S4).

[0027] The environmental data analysis module is used to obtain air velocity data, correlate it with the smoke diffusion rate, and measure the dynamic distribution relationship between air velocity and smoke concentration. Multiple groups of wind speed sensors are deployed in the monitoring area to collect air velocity data in time series, synchronously extract the smoke concentration values at corresponding time points, calculate the dynamic correlation between air velocity and smoke diffusion through covariance analysis, and generate a velocity-concentration distribution matrix for correcting the parameter weights of the fire dynamic assessment model.

[0028] The fire source location module is used to obtain the coordinate data of each fire source and the thermal radiation distribution data under the corresponding fire source intensity. A multi-spectral imaging device is used to obtain the heat source distribution data of the monitoring area, the abnormal heat source points are separated by the background difference algorithm, and a three-dimensional fire source location map is generated by combining the temperature intensity and spatial coordinates and updated to the fire dynamic assessment model in real time.

[0029] The model construction module is used to construct a fire dynamic assessment model with temperature data, building structure data, air velocity data, and fire source data as input parameters, and output the comprehensive threat level of fire spread. The defined input parameters include temperature data, building structure parameters, air velocity data, and fire source coordinate data, where the temperature data includes the temperature values, collection times, and spatial coordinates of each node, and the building structure parameters include material types, geometric dimensions, and thermal conductivity coefficients; the defined output parameters include the smoke diffusion range, structural thermal stress index, deformation risk value, and fire source threat level, and a comprehensive threat assessment result is generated through multi-dimensional data fusion. The input parameters are standardized and a feature vector set is generated, dynamic weight coefficients are assigned to each index in the output parameters, the comprehensive fire threat index is calculated through the weighted summation algorithm, and the threat level is generated according to the preset level division standard; the time series prediction algorithm is used to train the model parameters, the real-time data is input into the trained fire dynamic assessment model, and the current threat level and risk parameter list are output.

[0030] The safety database is used to store the thermal conductivity coefficients corresponding to each building material, the set smoke concentration threshold, and the structural deformation threshold, and the safety database includes a building material thermodynamics parameter library, a historical fire case feature library, and a dynamic threshold adjustment rule set.

[0031] Embodiment 1

[0032] In the fire parameter analysis module, the specific implementation of step S2 is as follows: Obtain the basic spatial parameters of the building structure, including the length and floor height of the building, which can be obtained through building design drawings or on-site surveys to clarify the three-dimensional spatial scale of the building. At the same time, in combination with the heat accumulation gradient calculated from the temperature change amount of each temperature measurement node during the current collection period, determine the distribution range of heat in the monitoring area. The heat accumulation gradient reflects the aggregation speed and distribution difference of heat in a unit space and is the key basic data for evaluating smoke diffusion.

[0033] Obtain the types of building materials, such as concrete, steel, glass, etc. Each material has different heat conduction characteristics. By matching the obtained material types with the corresponding heat conduction coefficients of each material stored in the safety database, the specific heat conduction coefficient of the material can be obtained. The safety database pre-stores a table of heat conduction coefficients of common building materials, which is established based on the physical properties of the materials and relevant industry standards to ensure the accuracy and authority of the data.

[0034] After obtaining the heat conduction coefficient of the material, it is necessary to calculate the smoke diffusion intensity of each temperature measurement node according to the set heat radiation attenuation rate. The heat radiation attenuation rate is a preset physical parameter used to simulate the intensity attenuation of heat radiation during propagation due to factors such as air absorption and scattering. In specific calculations, by combining the heat distribution range, the heat conduction coefficient of the material, and the heat radiation attenuation rate, through a specific mathematical formula (such as a calculation formula based on the heat conduction law and the radiation propagation model), the intensity value of smoke diffusion at each temperature measurement node can be obtained, which reflects the diffusion ability and potential threat of smoke at this node.

[0035] Based on the smoke diffusion volume, the heat conduction coefficient of the material, and the smoke diffusion intensity, the smoke concentration values of each monitoring point are derived through a spatial distribution algorithm. The smoke diffusion volume is obtained by multiplying the length, floor height of the building, and the heat distribution range, which reflects the occupied range of smoke in three-dimensional space. The spatial distribution algorithm can adopt diffusion models in fluid mechanics, such as the Gaussian diffusion model or the finite volume method model. These algorithms can simulate the concentration distribution of smoke at different positions according to the diffusion characteristics and spatial parameters of the smoke. Taking the Gaussian diffusion model as an example, its basic principle is to assume that the smoke follows a normal distribution during diffusion. By inputting parameters such as the smoke source strength, average wind speed, and atmospheric stability, the smoke concentration values at different spatial coordinates can be calculated. In this embodiment, the smoke diffusion intensity is used as the source strength parameter, combined with the influence of the heat conduction coefficient of the material on the diffusion process (for example, a material with a high heat conduction coefficient will accelerate heat transfer, thus affecting the smoke diffusion speed), and through algorithm iteration calculation, the smoke concentration values of each monitoring point are obtained.

[0036] Based on the spatial coordinates of the monitoring points and the corresponding smoke concentration values, a three-dimensional diffusion model is constructed. The spatial coordinates of the monitoring points are determined by a positioning system (such as GPS or on-site coordinate calibration) during grid layout. Each monitoring point corresponds to a coordinate point (x, y, z) in three-dimensional space. Taking the smoke concentration values of each point as attribute values, through three-dimensional modeling software or algorithms, the discrete monitoring point data is converted into a continuous three-dimensional space field distribution model. For example, the Kriging interpolation method or the triangulation method can be used to interpolate the discrete data to generate a continuous smoke concentration surface or volume data, intuitively showing the three-dimensional diffusion form of smoke in the monitoring area, including key information such as the diffusion range, the concentration peak area, and the diffusion front.

[0037] In actual operation, the measurement accuracy of the building length and floor height needs to meet the engineering requirements. Usually, a laser rangefinder or total station is used for measurement, and the error is controlled at the centimeter level. The layout density of the temperature measurement nodes is determined according to the importance of the monitoring area and the fire risk level. For example, in crowded or flammable areas, the node spacing can be set to 1 - 2 meters, while in ordinary areas, the spacing can be appropriately increased to 3 - 5 meters. The accuracy of the infrared sensor needs to reach ±0.5 °C to ensure the accuracy of temperature data. The thermal conductivity coefficient table in the safety database is updated regularly, incorporating data of new building materials to ensure the timeliness and reliability of the matching process.

[0038] The selection of the spatial distribution algorithm needs to be adjusted according to the complexity of the monitoring area. For a regularly shaped building space, such as a rectangular room, the Gaussian diffusion model can be used for rapid calculation; for a building with a complex structure, such as a multi - storey building with corridors and stairwells, the finite volume method or computational fluid dynamics (CFD) model needs to be used to more accurately simulate the diffusion behavior of smoke between obstacles. The visualization interface of the three - dimensional diffusion model needs to have a real - time update function, which can dynamically display the process of smoke diffusion, facilitating the monitoring personnel to timely grasp the development trend of the fire.

[0039] In addition, when calculating the smoke diffusion volume, the blocking effect of the internal partition structures of the building, such as walls and partitions, on smoke diffusion needs to be considered. For areas with partitions, the monitoring area can be divided into multiple sub - areas, and the smoke diffusion volume of each sub - area is calculated separately. Then, diffusion coupling calculation is carried out through the vents or gaps between the sub - areas to improve the accuracy of the overall calculation. The material thermal conductivity coefficient not only affects the transmission speed of thermal radiation but also indirectly affects air flow by changing the temperature distribution of the building structure, thereby affecting the diffusion path and speed of smoke. Therefore, the coupling effect of multiple physical fields needs to be comprehensively considered in the model construction process.

[0040] Through the above steps, step S2 realizes the complete process from temperature data to the estimation of smoke diffusion rate. Through multi - parameter fusion and algorithm modeling, it provides key smoke diffusion data for fire parameter analysis, providing an important basis for subsequent fire spread assessment, building structure safety assessment, etc. This implementation method is closely combined with engineering practice. Through a standardized data acquisition process, accurate parameter matching, and a scientific algorithm model, it ensures the accuracy and reliability of the smoke diffusion rate estimation and can meet the requirements of real - time fire prevention monitoring in fire protection engineering construction.

[0041] Embodiment 2

[0042] In the fire parameter analysis module, the specific implementation of step S3 is as follows: First, the temperature data of each monitoring point needs to be read. These data include the temperature values, acquisition times, and spatial coordinates of each node, and are transmitted to the analysis module in real time through the data acquisition system. The reading frequency of the temperature data is consistent with the acquisition period to ensure that the latest monitoring information is obtained. Subsequently, the temperature distribution dispersion is calculated through the standard deviation to measure the uniformity of the temperature within the monitoring area. The calculation formula for the standard deviation is: ; where, is the temperature value of each monitoring point, is the average temperature, and n is the number of monitoring points. The greater the dispersion, the more uneven the temperature distribution, which may indicate the risk of local thermal stress concentration.

[0043] Next, taking adjacent monitoring points as a group, a temperature gradient analysis unit is constructed. Two key parameters need to be calculated for each group: the temperature difference and the spatial distance. The temperature difference is obtained by subtracting the temperature values of two adjacent points, which reflects the driving force of heat transfer; the spatial distance is calculated through the coordinate difference between two points, using the Euclidean distance formula: ; where, and are the spatial coordinates of adjacent monitoring points. The temperature gradient is defined as the ratio of the temperature difference to the spatial distance, that is , and its physical meaning is the temperature change rate per unit distance, which is the core parameter for calculating thermal stress.

[0044] Then, the local thermal stress is calculated by multiplying the temperature gradient by the coefficient of thermal expansion of the material. The coefficient of thermal expansion of the material is stored in the thermodynamic parameter library of building materials in the secure database. Different materials (such as concrete, steel, aluminum alloy) have different values. For example, the coefficient of thermal expansion of steel is about , and that of concrete is about . The calculation formula for the local thermal stress is: ; where, E is the elastic modulus of the material, which is also stored in the secure database. The elastic modulus reflects the ability of the material to resist elastic deformation. For example, the elastic modulus of steel is about , and that of concrete is about . Through this formula, the distribution of the temperature field is transformed into the stress distribution inside the structure, quantifying the magnitude of the local thermal stress.

[0045] After calculating the local thermal stresses of all adjacent monitoring point groups, weighted averaging is required to obtain the overall thermal stress index. The weighting factors are determined based on the importance of the spatial positions of the monitoring points. For example, monitoring points closer to load-bearing structures or flammable areas are given higher weights. The weighted averaging formula is as follows: ; where m is the total number of adjacent monitoring point groups, is the weight coefficient of the i-th group ( ), is the local thermal stress value of the i-th group. The overall thermal stress index comprehensively considers the thermal stress contributions of each local area and reflects the overall level of thermal stress in the entire monitoring area.

[0046] Finally, extract the material yield strength set in the safety database and compare it with the overall thermal stress index . The material yield strength is the critical stress value at which the material undergoes significant plastic deformation. For example, the yield strength of Q235 steel is 235 MPa, and the axial compressive yield strength of C30 concrete is approximately 14.3 MPa. If , then the area is determined to be a safe area, indicating that the structural material has not reached the plastic deformation stage; if , then it is determined to be a high-risk area, indicating that the structure may face the risk of failure due to excessive thermal stress.

[0047] In actual operation, the layout of monitoring points needs to follow the grid principle to ensure uniform spacing between adjacent points for facilitating the standardized calculation of temperature gradients. For irregular building structures, adaptive grid division technology can be used to densify monitoring points in complex or heat-prone areas to improve the accuracy of local thermal stress calculation. The data acquisition system needs to have anti-interference capabilities to avoid the influence of electromagnetic radiation, environmental noise, etc. on the accuracy of temperature data. For example, shielded cables can be used to transmit temperature signals, or electromagnetic compatibility design can be carried out on sensors.

[0048] The material mechanical parameters (such as thermal expansion coefficient, elastic modulus, yield strength) in the safety database need to be calibrated according to national standards (such as GB50010 "Code for Design of Concrete Structures", GB50017 "Standard for Design of Steel Structures") or international standards (such as ISO6892 "Tensile Testing of Metallic Materials") to ensure the authority and reliability of the parameters. The setting of the weighting factors needs to be combined with the mechanical analysis of the building structure. For example, the stress sensitivity coefficients of different areas can be determined through finite element simulation to make the weighted average result closer to the actual stress conditions.

[0049] The calculation of the temperature distribution dispersion can be achieved through programming. For example, using the NumPy library in Python or the statistical functions in MATLAB to achieve fast data processing and analysis. For large-scale monitoring areas, a distributed computing architecture can be adopted to process temperature data in chunks to improve the calculation efficiency. When comparing the thermal stress index with the yield strength, the system needs to trigger the warning mechanism in real time. If it is determined as a high-risk area, it will immediately remind the monitoring personnel through means such as sound and light alarms and text messages. At the same time, the spatial location of the high-risk area will be marked on the monitoring interface for quick response and handling.

[0050] In addition, the time series characteristics of temperature data need to be considered, and the change trend of thermal stress is analyzed through historical data comparison. For example, if the overall thermal stress index of a certain area continues to rise in multiple consecutive acquisition cycles, even if it has not exceeded the yield strength, it should be regarded as a potential risk area, and the monitoring frequency should be increased or the emergency plan should be activated. The thermal expansion coefficient and elastic modulus of materials may change non-linearly with temperature. In high-precision evaluations, temperature-related material property parameters can be introduced and corrected through piecewise functions or polynomial fittings to improve the accuracy of thermal stress calculations.

[0051] Through the above steps, step S3 realizes the complete process from temperature data to the thermal stress assessment of the building structure. Through statistical methods, material mechanics theories, and data comparison and analysis, the thermal stress risk level of the structure is quantified. This implementation method combines the actual engineering requirements, adopts a standardized data processing process and a scientific mechanical model, ensuring the accuracy and reliability of the thermal stress assessment, and providing a key basis for the fire monitoring system to timely discover structural safety hazards and formulate protection measures.

[0052] Example 3

[0053] In the fire parameter analysis module, the specific implementation method of step S4 is as follows: Obtain the original geometric parameters of the building structure, which include basic dimension data such as the length, width, and height of building components, as well as spatial topology information such as node coordinates and component connection relationships. Usually, it is obtained through architectural design drawings or three-dimensional modeling files (such as BIM models) to ensure that the data is consistent with the actual structure. The original geometric parameters are the benchmark for calculating the material deformation amount, and their accuracy directly affects the reliability of subsequent analysis.

[0054] Determine the division of the high-temperature area and the adjacent area. The high-temperature area is defined as the monitoring area where the temperature value exceeds the preset high-temperature threshold, which is set according to the building's usage function and material heat resistance characteristics (for example, it can be set to 200°C for ordinary civil buildings, and can be adjusted according to the type of combustibles in industrial factories). The adjacent area is the monitoring area that is directly adjacent to the high-temperature area in space, and the two are judged based on the spatial coordinate distance of the monitoring points being less than or equal to the preset spacing (such as 1 meter).

[0055] Calculate the temperature difference between the high-temperature area and the adjacent area . The temperature difference is obtained by the average temperature value of the monitoring points in the high-temperature area subtracted from the average temperature value of the monitoring points in the adjacent area , that is: ; wherein, is the arithmetic mean of the temperature values of all monitoring points in the high-temperature area, is the arithmetic mean of the temperature values of all monitoring points in the adjacent area. The temperature difference reflects the heat transfer gradient between adjacent areas and is the key factor driving the thermal deformation of materials

[0056] Calculate the theoretical deformation amount in combination with the linear expansion coefficient of the material. The linear expansion coefficient of the material is stored in the thermodynamic parameter library of building materials in the secure database, which characterizes the linear elongation rate of the material under unit temperature change, and the unit is . The linear expansion coefficients of different materials vary significantly. For example, that of steel is about , that of concrete is about , and that of glass is about . The formula for the theoretical deformation amount is: ; wherein, is the original length of the building component (unit: meter), taking the geometric length of the component at the junction of the high-temperature area and the adjacent area. This formula is based on the physical principle of thermal expansion and contraction, assuming that the material expands or contracts uniformly under temperature change and the deformation is in the elastic stage

[0057] Obtain the actual deformation data through a laser rangefinder. The laser rangefinder needs to be arranged at key monitoring positions of the building structure (such as beam-column joints, wall corners, etc.). By emitting a laser beam and measuring the time difference of the reflected signal, the actual length change amount of the component can be accurately obtained. The accuracy of the laser rangefinder needs to reach the sub-millimeter level (such as ±0.1 mm) to meet the high-precision requirements of deformation monitoring. The acquisition frequency of the actual deformation data is synchronized with the temperature data to ensure one-to-one correspondence between the two in the time dimension

[0058] Compare the theoretical deformation amount with the preset deformation threshold . The preset deformation threshold is set according to the design safety standard of the building structure, usually 0.1%-0.5% of the original length of the component (for example, for a steel beam with an original length of 5 meters, the threshold can be set to 5 mm - 25 mm). If , then it is determined that there is a risk of structural failure, and the system automatically triggers the alarm mechanism and sends an alarm to the fire monitoring center through sound and light signals, text messages or network notifications. At the same time, the deformation risk value is calculated based on the ratio of the theoretical deformation variable to the threshold value. , the calculation formula is: ; This risk value is dimensionless and is used to quantify the degree of danger of structural deformation. A larger value indicates a higher risk. , it is marked as safe and continues to be monitored in real time.

[0059] In practice, the acquisition of original geometric parameters requires two-person verification to ensure that the drawing data is consistent with the on-site structure. For complex structures (such as curved curtain walls and special-shaped components), 3D laser scanning technology can be used to generate point cloud data, and reverse modeling can be used to obtain accurate geometric parameters. The demarcation of high-temperature areas can be dynamically adjusted based on the temperature field cloud map. For example, by setting a temperature gradient threshold (e.g., a temperature change exceeding 50°C per meter), the boundaries of high-temperature areas can be determined to avoid misjudgments caused by a single threshold.

[0060] Laser rangefinder placement should adhere to the following principles: 1) Cover all boundaries between high-temperature areas and adjacent areas; 2) Avoid obstacles that could obstruct the laser path; and 3) Ensure the instrument is securely mounted to prevent vibration from affecting measurement accuracy. For multi-story buildings or high-altitude structures, drones equipped with laser rangefinder modules can be used for periodic scanning to address deformation monitoring in areas inaccessible to humans.

[0061] Preset deformation thresholds in the security database must be categorized and stored by building structure type. For example, different threshold systems correspond to steel structures, reinforced concrete structures, and masonry structures. The threshold setting process should refer to national standards such as the Code for Loads on Building Structures (GB50009) and the Standard for Design of Steel Structures (GB50017), and be determined through a combination of structural mechanics calculations and engineering experience. For buildings undergoing renovation or reinforcement, the thresholds can be dynamically adjusted based on structural inspection reports.

[0062] When calculating theoretical deformation, the effects of multi-directional thermal deformation must be considered. For example, for rectangular cross-section components, in addition to linear deformation along the length, deformation along the width and height may also occur. However, for preliminary assessments, only deformation along the principal load direction can be calculated. For higher-precision analysis, a three-dimensional thermal expansion model can be introduced to account for the anisotropic properties of the material. Furthermore, temperature difference calculations must exclude interference from environmental factors (such as sunlight and air conditioning airflow). Time series analysis of temperature data (e.g., removing periodic fluctuations) can be used to extract the actual temperature variation caused by the fire.

[0063] When the system triggers an alarm, a 3D model of the risk area will automatically pop up on the monitoring interface, marking the positions of the high-temperature area, adjacent areas, and deformation monitoring points, and displaying the distribution of deformation risk values with different color gradients. At the same time, the system automatically generates a risk report, including key information such as temperature difference, theoretical deformation amount, actual deformation data, and risk value, for the joint judgment of fire engineers and structural engineers to formulate targeted emergency plans (such as temporary support, cooling, personnel evacuation, etc.).

[0064] To improve the reliability of deformation assessment, a redundant monitoring mechanism can be introduced. For example, a laser rangefinder and a strain gauge are simultaneously arranged at the same monitoring point. The strain value measured by the strain gauge is used to inversely calculate the deformation amount , which is compared and verified with the laser ranging result. If the difference between the two exceeds the preset error range (such as 5%), the system will automatically mark the data as abnormal and prompt for equipment calibration or fault troubleshooting.

[0065] Through the above steps, step S4 realizes a complete process from temperature data to material deformation risk assessment. By means of geometric parameter analysis, thermal deformation calculation, comparison of measured data, and risk quantification, a real-time early warning mechanism for structural failure risk is established. This implementation method combines engineering measurement technology and material mechanics theory, adopts a standardized data processing process and precise monitoring means, ensuring the accuracy and timeliness of deformation assessment, and providing key technical support for the structural safety protection of fire engineering.

[0066] Embodiment 4

[0067] In the environmental data analysis module, its specific implementation method focuses on the dynamic correlation analysis of air velocity and smoke concentration. First, multiple groups of wind speed sensors need to be reasonably arranged in the monitoring area. The arrangement principle needs to comprehensively consider the building space structure and fire risk distribution. For example, at key air flow nodes such as the atrium, corridor intersections, and stairwell entrances of high-rise buildings, as well as areas prone to smoke accumulation such as the gaps between warehouse shelves and around factory equipment, the sensors are deployed in a grid or array pattern. The distance between adjacent sensors is set to 5 - 10 meters according to the space scale to ensure coverage of the main air flow channels and the periphery of potential fire sources. The wind speed sensors can be ultrasonic or thermal anemometers. The former is suitable for high-dust or harsh environments, and the latter has high sensitivity and can accurately capture wind speed changes as low as 0.1 m / s.

[0068] The sensor collects air velocity data in a time series, and the collection frequency is synchronized with the temperature data collection period of the fire parameter analysis module (e.g., once per second) to ensure data alignment in the time dimension. Each time data is collected, the sensor synchronously records the current timestamp and three-dimensional spatial coordinates (obtained through built-in GPS or on-site coordinate calibration) to form a structured data frame. For example, a certain sensor collects an air velocity of 2.3 m / s at coordinates (X = 10 m, Y = 8 m, Z = 3 m) at 14:00:01, and the data frame format is [Time: 14:00:01, Coordinates: (10, 8, 3), Velocity: 2.3 m / s].

[0069] Synchronously extract the smoke concentration value at the corresponding time point. This data is sourced from the concentration data of each monitoring point output by the three-dimensional diffusion model in the fire parameter analysis module. For example, at 14:00:01, the smoke concentration calculated by the temperature measurement node adjacent to the wind speed sensor coordinates (10, 8, 3) is 150 ppm (parts per million concentration). The two are correlated through a spatial matching algorithm to form a set of "velocity-concentration" data pairs (2.3 m / s, 150 ppm).

[0070] Calculate the dynamic correlation between air velocity and smoke diffusion through covariance analysis. Covariance analysis is a statistical method used to measure the co-variation trend of two variables in a time series. In specific operations, the system collects all "velocity-concentration" data pairs within a certain period (e.g., 30 minutes) to form a two-dimensional data set. For example, in a certain monitoring area, a total of 1800 data pairs are obtained, covering different wind speed ranges (0.5 - 5.0 m / s) and corresponding smoke concentration values (50 - 500 ppm). By calculating the covariance value, judge the direction and strength of their correlation: if the covariance is positive, it indicates a positive correlation between wind speed and smoke concentration (e.g., the concentration increases when the wind speed increases); if it is negative, it indicates a negative correlation (e.g., the concentration decreases when the wind speed increases); the larger the absolute value of the number, the stronger the correlation.

[0071] Generating a velocity-concentration distribution matrix is the core output of this module. The matrix uses air velocity as the row dimension and smoke concentration as the column dimension, and statistically distributes the frequency after dividing the data pairs by intervals. For example, divide the wind speed into five intervals: 0 - 1 m / s, 1 - 2 m / s, 2 - 3 m / s, 3 - 4 m / s, 4 - 5 m / s, and divide the smoke concentration into five intervals: 0 - 100 ppm, 100 - 200 ppm, 200 - 300 ppm, 300 - 400 ppm, 400 - 500 ppm to construct a 5×5 matrix. Each matrix cell records the number of data pairs within the corresponding wind speed and concentration intervals, reflecting the probability of this combination occurring. For example, the value of the cell "wind speed 1 - 2 m / s, concentration 100 - 200 ppm" in the matrix is 230, indicating that within the statistical period, this wind speed and concentration combination occurred 230 times, accounting for 12.8% of the total data volume.

[0072] The distribution matrix is used to correct the parameter weights of the fire dynamic assessment model. In the model construction module, parameters such as temperature, building structure, air velocity, and fire source are used to generate a comprehensive threat index through weighted summation. For example, the original weight distribution is 40% for temperature, 30% for building structure, 20% for air velocity, and 10% for fire source. By analyzing the matrix, it is found that when the wind speed is greater than 3 m / s, the probability of the smoke concentration exceeding 300 ppm increases significantly, indicating that the impact of high wind speed on smoke diffusion far exceeds expectations. Therefore, the system automatically increases the weight of the air velocity parameter to 25% and adjusts the weights of other parameters accordingly (such as adjusting the temperature to 35%) to make the model focus more on risk assessment in high wind speed scenarios.

[0073] In practical applications, the installation of wind speed sensors should avoid human interference sources, such as air conditioner outlets and areas with frequently opened doors and windows, to ensure that the collected data reflects the real air flow caused by natural air currents or fires. For large-space buildings (such as stadiums and airport terminals), a hierarchical installation strategy can be adopted: focus on monitoring the low-speed air flow in the areas where people are active on the ground floor, and install sensors below the roof to monitor the high-speed air flow caused by the chimney effect.

[0074] During the data synchronization process, there may be timestamp errors (such as clock deviations between different devices), and the clock needs to be calibrated through the Network Time Protocol (NTP) to ensure that the wind speed and concentration data are accurately aligned in time. The spatial matching algorithm can adopt the nearest neighbor interpolation method. When the wind speed sensor and the temperature measurement node do not completely coincide, the concentration value of the nearest temperature measurement node is selected as the associated data, and the error is controlled within 1 / 2 of the sensor spacing.

[0075] The time window for covariance analysis can be adjusted dynamically: in the initial stage of the fire (when the smoke concentration is low), a longer time window (such as 60 minutes) is adopted to accumulate sufficient data; in the development stage of the fire (when the concentration is rising rapidly), it is switched to a shorter window (such as 5 minutes) to track the correlation changes in real time. The distribution matrix is updated every 10 minutes to ensure that the model parameters can reflect the current environmental characteristics in a timely manner.

[0076] Taking a commercial complex as an example: 10 sets of wind speed sensors are arranged in the supermarket area on the basement floor. Among them, 3 sets are located in the shelf aisles (wind speed 0.5 - 1.5 m / s), 4 sets are located at the escalator entrances in the atrium (wind speed 1.0 - 2.5 m / s), and 3 sets are located near the smoke exhaust outlets (wind speed 2.0 - 4.0 m / s). During a certain simulated fire experiment, after a fire broke out in the shelf area, the wind speed sensors monitored that the wind speed in the aisle gradually increased to 1.2 m / s, and the corresponding smoke concentration increased from 80 ppm to 220 ppm; the wind speed at the escalator entrances in the atrium stabilized at 1.8 m / s, and the concentration increased to 350 ppm; the wind speed near the smoke exhaust outlets reached 3.5 m / s, and the concentration remained at about 450 ppm. Through covariance analysis, it was found that there was a strong positive correlation between the wind speed and the concentration in the atrium area (covariance value 0.85), indicating that the air flow accelerated the diffusion of smoke into the atrium; while in the smoke exhaust outlet area, due to the intervention of mechanical smoke exhaust, there was a negative correlation between the wind speed and the concentration (covariance value -0.68), indicating that the high-speed air flow effectively reduced the local concentration. Based on this, the system increased the weight of the air flow velocity parameter in the atrium area from 20% to 30%, and strengthened the diffusion prediction of this area in the model.

[0077] Through the above process, the environmental data analysis module realizes a closed-loop from data collection, correlation analysis to model correction. By capturing the dynamic relationship between air flow velocity and smoke concentration in real time, it provides support for fire assessment at the environmental dynamics level. This implementation method combines specific building scenarios, and through scientific point layout strategies, precise data synchronization and statistical analysis, it ensures the dynamic adaptability of model parameters and improves the response ability of the fire monitoring system to complex environments.

[0078] Example 5

[0079] In the fire source location module, its specific implementation method realizes the precise location and dynamic tracking of the fire source through multi-spectral imaging technology and data processing algorithms. Taking an industrial factory building as an example, the factory building contains complex structures such as production line equipment, storage shelves and ventilation ducts, and it is necessary to monitor potential fire sources (such as overheating of electrical equipment, chemical leakage and fire).

[0080] Deploy multi-spectral imaging equipment. According to the height of the factory building space (about 10 meters) and the monitoring range (80 meters long and 50 meters wide), 4 multi-spectral cameras are evenly installed on the roof to cover the entire area without dead angles. The cameras support multi-band imaging in visible light (400 - 700 nm), near-infrared (700 - 1400 nm), mid-infrared (3 - 5 μm) and far-infrared (8 - 14 μm), and can capture the radiation characteristics of heat sources at different temperatures. For example, the initial overheating of electrical equipment (temperature about 100 - 200 °C) mainly radiates in the near-infrared band, while open flames (temperature > 500 °C) have strong signals in the mid-infrared and far-infrared bands.

[0081] The device continuously acquires multi-spectral images of the monitoring area at a set frame rate (e.g., 25 frames per second). Each group of images contains visible and infrared band data at the same moment. For example, in a certain frame of the image, the visible light image shows that the conveyor belt in area A of the production line is running normally, the near-infrared image shows that the temperature of the housing of a certain motor in this area has increased abnormally (showing a bright red light spot), the mid-infrared image shows that the temperature field distribution of the light spot is concentrated, and the far-infrared image shows that the heat radiation spreads to the surrounding shelves.

[0082] The abnormal heat source points are separated by the background difference algorithm. This algorithm first establishes a background model of the monitoring area. Based on the multi-spectral image data in the non-fire scene (such as continuous 1-hour images during normal production in the factory building), the mean and variance of each pixel point in different bands are calculated to form a background feature library. When real-time images are input, the system performs differential calculations for each pixel point band by band, comparing the difference between the current pixel value and the corresponding value in the background model. If the brightness value of a certain pixel point in the near-infrared band exceeds 3 times the standard deviation of the background mean, it is determined as an abnormal heat source point. For example, the brightness value of the pixel point in the motor housing area in the near-infrared band is 4.2 times the background mean, triggering an abnormal mark.

[0083] The three-dimensional positioning map of the fire source is generated by combining the temperature intensity and spatial coordinates. The temperature intensity is obtained by converting the radiation brightness value in the infrared band. According to Planck's radiation law, the radiation brightness in different bands has a non-linear relationship with temperature. The system has a temperature conversion table for each band. For example, the corresponding relationship between the radiation brightness value L and temperature T in the mid-infrared band (3 - 5μm) is obtained by looking up the table and interpolation. When L = 1500W / m²·sr, it is converted to temperature T = 300℃. The spatial coordinates are calculated through the calibration parameters of the camera. Using the principle of binocular vision, based on the imaging parallax of the same heat source point by 4 cameras, the three-dimensional coordinates (X, Y, Z) of the heat source are solved. For example, the abnormal heat source point of the motor housing is triangulated by 4 cameras, and its coordinates are determined as (X = 20 meters, Y = 15 meters, Z = 2 meters), corresponding to the equipment layer 2 meters above the ground.

[0084] The process of real-time updating to the fire dynamic assessment model is as follows: The fire source positioning module generates a three-dimensional positioning map of the fire source once every second, which contains parameters such as the coordinates of the heat source point, temperature intensity, and radiation range. For example, at t = 10:05:00, the map shows a heat source with a temperature of 300℃ and a radiation radius of 1.5 meters in the motor area, marked as a first-level fire source (low intensity); at t = 10:05:05, the temperature rises to 450℃ and the radiation radius expands to 2.8 meters, upgraded to a second-level fire source (medium intensity). After receiving the data, the model automatically updates the threat level of the fire source and adjusts the source strength parameters of the smoke diffusion model. For example, the smoke diffusion intensity is increased from the initial value of 1000m³ / s to 1800m³ / s.

[0085] In practical applications, multi-spectral imaging devices need to be regularly radiometrically calibrated and geometrically calibrated. Radiometric calibration is completed through a blackbody furnace (a standard heat source with a known temperature) to ensure the accuracy of temperature conversion; geometric calibration uses a checkerboard calibration plate to correct image distortion caused by lens aberration. For example, the blackbody furnace calibration is performed on the camera once a month, and when the temperature error of a certain camera is detected to exceed ±5°C, the calibration process is automatically triggered.

[0086] The background difference algorithm needs to have the ability of adaptive learning to cope with environmental changes (such as the movement of equipment in the factory building and the change of lighting conditions). The system automatically collects background images for 30 minutes every day at dawn (non-production period) to update the background model. If there is a sudden environmental change (such as a new large piece of equipment blocking part of the monitoring area) during the production process during the day, the operator can manually trigger the update of the background model to avoid false alarms.

[0087] Taking the fire on the shelf in the storage area as an example: The multi-spectral camera first detects an abnormal temperature (150°C) at a certain position on the bottom layer of the shelf in the near-infrared band and marks it as a suspected heat source point; as the fire develops, the temperature rises to 400°C in the mid-infrared band, and at the same time, smoke appears in the visible light image, confirming the fire source; through three-dimensional positioning calculation, the coordinates of the fire source are determined to be (X = 50 meters, Y = 30 meters, Z = 1.5 meters), which is on the second layer of the shelf; the positioning map is pushed to the monitoring interface in real time, the fire source position is marked with a red cube, the edge flashes to indicate dynamic changes, and a temperature gradient false color map is superimposed to show the heat radiation distribution. The fire dynamic assessment model predicts that the smoke will spread to the entrance of the storage area within 3 minutes based on the fire source intensity data, triggering the regional evacuation alarm.

[0088] The fire source positioning module is deeply integrated with the video monitoring system. When the monitoring personnel click on the heat source point in the positioning map, they can directly retrieve the real-time video images of the corresponding camera to view the situation at the fire source site. For example, when clicking on the heat source point in the motor area, a split screen display of the visible light and infrared images of the camera in this area pops up. The left visible light image shows that there is no obvious abnormality in the appearance of the equipment, and the right infrared image clearly shows that the temperature distribution on the motor shell is uneven, and the local hot spot temperature reaches 350°C, which helps to judge that it is an overheat caused by a short circuit in the internal coil.

[0089] Through the above process, the fire source positioning module realizes the full-chain processing from multi-spectral image acquisition, abnormal detection to three-dimensional positioning. Combining with the specific scenario of the industrial plant, through multi-band data fusion and real-time algorithm response, it ensures the accuracy and timeliness of fire source positioning. This implementation method utilizes the technical advantages of multi-spectral imaging to effectively distinguish different types of heat sources, provides accurate fire source basic data for the fire monitoring system, and supports the dynamic update of the fire spread model and the risk level assessment.

[0090] It should be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device.

[0091] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time fire prevention monitoring data transmission system for fire protection engineering construction, characterized in that, The system specifically includes the following modules: A fire parameter analysis module, which is used to generate a temperature change record table based on the temperature data in the monitoring area, estimate the smoke diffusion rate from it, and then conduct a safety assessment of the thermal stress and material deformation of the building structure; An environmental data analysis module, which is used to obtain air velocity data, correlate it with the smoke diffusion rate, and measure the dynamic distribution relationship between air velocity and smoke concentration; A fire source location module, which is used to obtain the coordinate data of each fire source and the thermal radiation distribution data under the corresponding fire source intensity; A model construction module, which is used to construct a fire dynamic assessment model with temperature data, building structure data, air velocity data, and fire source data as input parameters, and output the comprehensive threat level of fire spread; A safety database, which is used to store the thermal conductivity coefficients corresponding to various building materials, the set smoke concentration threshold, and the structural deformation threshold.

2. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 1, characterized in that: The fire parameter analysis module specifically includes the following steps: S1. Arrange a number of temperature measurement nodes in the monitoring area according to the grid principle. During the fire prevention monitoring process, obtain the temperature data of each temperature measurement node through an infrared sensor according to the set collection period, record the coordinates, temperature values, and collection times of each node, and generate a temperature change record table; S2. Calculate the heat accumulation gradient of the monitoring area according to the temperature change amount of each node in the current collection period, and at the same time obtain the spatial parameters of the building structure. Combine the heat gradient distribution to calculate the smoke diffusion range, so as to estimate the fire spread rate; S3. Analyze the thermal stress of the building structure according to the temperature distribution uniformity, obtain the tolerance coefficient of the building material, and determine the risk level of the structure; S4. Analyze the material deformation amount according to the temperature difference between adjacent areas, compare it with the preset deformation threshold to judge whether there is a risk of structural failure, and if so, calculate the deformation risk value.

3. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 2, characterized in that: The specific operation method of step S2 is: Obtain the length and floor height of the building, calculate the smoke diffusion volume in combination with the heat distribution range, obtain the type of building material, match it with the thermal conductivity coefficients corresponding to each material stored in the safety database, obtain the material thermal conductivity coefficient, and then calculate the smoke diffusion intensity of each temperature measurement node according to the set thermal radiation attenuation rate; Based on the smoke diffusion volume, material thermal conductivity coefficient, and smoke diffusion intensity, deduce the smoke concentration values of each monitoring point through a spatial distribution algorithm, and construct a three-dimensional diffusion model based on the spatial coordinates and smoke concentration values of the monitoring points.

4. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 2, characterized in that: The specific operation method of step S3 is: S31. Read the temperature data of each monitoring point and calculate the temperature distribution dispersion through the standard deviation; S32. Take adjacent monitoring points as a group, calculate the temperature difference and spatial distance of each group, calculate the local thermal stress through the product of the temperature gradient and the material thermal expansion coefficient, and obtain the overall thermal stress index after weighted average; S33. Extract the set material yield strength in the safety database, compare it with the overall thermal stress index. If it is lower than the set threshold, it is determined as a high-risk area, otherwise it is marked as a safe area.

5. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 2, characterized in that: The specific operation method of step S4 is: S41. Obtain the original geometric parameters of the building structure, calculate the temperature difference between the high-temperature area and the adjacent area respectively, and calculate the theoretical deformation amount in combination with the material linear expansion coefficient; S42. Obtain the actual deformation data through a laser rangefinder. If the theoretical deformation amount exceeds the preset threshold, trigger an alarm and output the deformation risk coefficient.

6. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 3, characterized in that: The specific operation method of the environmental data analysis module is as follows: Deploy multiple groups of wind speed sensors in the monitoring area, collect air flow velocity data according to the time series, synchronously extract the smoke concentration values at the corresponding time points, calculate the dynamic correlation between the air flow velocity and smoke diffusion through covariance analysis, and generate a flow velocity-concentration distribution matrix for correcting the parameter weights of the fire dynamic assessment model.

7. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 1, characterized in that: The specific operation method of the fire source location module is as follows: Use a multi-spectral imaging device to obtain the heat source distribution data of the monitoring area, separate the abnormal heat source points through the background difference algorithm, and generate a three-dimensional fire source location map by combining the temperature intensity and spatial coordinates, and update it to the fire dynamic assessment model in real time.

8. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 1, characterized in that: The specific analysis methods of the input parameters and output parameters of the fire dynamic assessment model are as follows: Define that the input parameters include temperature data, building structure parameters, air flow velocity data, and fire source coordinate data. Among them, the temperature data includes the temperature values, acquisition times, and spatial coordinates of each node, and the building structure parameters include material types, geometric dimensions, and heat conduction coefficients; Define that the output parameters include the smoke diffusion range, structural thermal stress index, deformation risk value, and fire source threat level, and generate a comprehensive threat assessment result through multi-dimensional data fusion.

9. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 8, characterized in that: The specific operation method of the model construction module is as follows: Perform standardization processing on the input parameters and generate a feature vector set, assign dynamic weight coefficients to each index in the output parameters, calculate the comprehensive fire threat index through the weighted summation algorithm, and generate the threat level according to the preset level division standard; Use the time series prediction algorithm to train the model parameters, input the real-time data into the trained fire dynamic assessment model, and output the current threat level and risk parameter list.

10. A real-time fire prevention monitoring data transmission system for fire protection engineering construction according to claim 1, characterized in that: The safety database includes a building material thermodynamics parameter library, a historical fire case feature library, and a dynamic threshold adjustment rule set.

Images