Temperature on-line monitoring and early warning system for fire protection clothing

Abstract

The invention discloses a temperature on-line monitoring and early warning system for fire protection clothing, which relates to the technical field of fire protection monitoring and early warning and comprises a data collection module, a data preprocessing module, a calculation processing module and an early warning execution module. Wherein the calculation processing module comprises a dynamic temperature risk unit, a comprehensive environment risk unit and a safety prediction unit. The dynamic temperature risk unit fuses temperature, a safety threshold value, a change rate, material aging, humidity and a heat reflection attenuation coefficient, outputs a dynamic temperature risk coefficient and reflects a safety margin, and the comprehensive environment risk unit introduces gas concentration, the number of hazardous articles, smoke attenuation and an action intensity coefficient based on the dynamic temperature risk coefficient, constructs an environment coupling risk index, and finally performs the safety analysis on the environment coupling risk index. And the safety prediction unit integrates a basic safety time constant, an environment coupling risk index, a dynamic temperature risk coefficient, a heat flux density and an oxygen concentration correction coefficient, outputs a residual safety time prediction value, and guides an evacuation decision of a fireman.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fire monitoring and early warning, in particular to a temperature online monitoring and early warning system for fire protection clothing. BACKGROUND

[0002] Fire protection clothing is the core equipment for protecting firefighters in complex fire environments such as high temperature, smoke and flammable and explosive gases, and its performance is directly related to the safety of firefighters. The fire environment has multiple characteristics such as high temperature dynamics (rapid temperature fluctuation and uneven spatial distribution), multi-factor coupling (coexistence of high temperature, toxic gas, smoke and dangerous goods), and high risk suddenness (frequent occurrence of secondary explosion, structure collapse and other accidents), which puts strict requirements on the real-time safety state monitoring of protective clothing.

[0003] The existing safety monitoring technology of fire protection clothing may be mainly based on a threshold alarm system of a single temperature sensor, which triggers an early warning by presetting a fixed temperature threshold (such as 300℃), and can only realize simple judgment of whether the temperature is over limit; The safety of firefighters is affected by multiple implicit factors. The performance of fire clothing materials decreases with the increase of use frequency, oxidation of the surface heat reflecting layer and increase of the humidity of the inner layer, resulting in a significant decrease in actual heat insulation capacity even if the external temperature does not exceed the threshold, and the increase of smoke concentration in the fire field reduces the visibility and hinders the evacuation path planning. High-intensity movements of firefighters may exacerbate internal heat production and possibly damage the protective layer. These environmental and personnel factors are not included in the risk assessment by the existing monitoring system. The existing technology may lack intelligent prediction ability for the remaining safe time, and can only alert firefighters of the current danger, but cannot guide firefighters when they must evacuate, which may cause the warning to be out of touch with the actual action needs.

[0004] In summary, in view of the accuracy, comprehensiveness and decision guidance needs of fire protection clothing safety monitoring in complex fire environments, it is urgent to build a collaborative monitoring and early warning system that integrates temperature dynamic characteristics, material performance degradation, and environmental multi-factor and personnel state, to realize the technical leap from passive alarm to active safety control. SUMMARY

[0005] The purpose of the present application is to provide a temperature online monitoring and early warning system for fire protection clothing, which solves the problems raised in the background art.

[0006] To achieve the above purpose, the present application provides a temperature online monitoring and early warning system for fire protection clothing, comprising: A data collection module for acquiring temperature risk associated data, environmental risk associated data and safety prediction associated data during use of fire protection clothing; The data preprocessing module is configured to input the temperature risk correlation data, the environmental risk correlation data and the safety prediction correlation data acquired by the input data collection module, clean the input data, and input the cleaned data to the calculation processing module. The calculation processing module is configured to: Based on the current fire suit surface monitoring temperature, the material safety threshold temperature, the temperature change rate, the protective clothing material aging coefficient, the humidity correction coefficient, the heat reflection attenuation coefficient and the environmental risk weight in the temperature risk correlation data, the dynamic temperature risk coefficient is outputted to quantize the dynamic temperature risk of the fire suit; Based on the flammable and explosive gas concentration, the gas explosion lower limit concentration, the smoke attenuation coefficient, the number of dangerous goods identification and the action intensity coefficient in the environmental risk correlation data, the environmental coupling risk index is outputted by weighting processing and combining the dynamic temperature risk coefficient to extend the multi-dimensional evaluation of the use risk of the fire protective clothing; Based on the basic safety time constant, the heat flow density correction factor, the heat damage accumulation coefficient and the oxygen concentration adjustment coefficient in the safety prediction correlation data, the residual safety time prediction value is outputted by combining the dynamic temperature risk coefficient and the environmental coupling risk index, and the quantization result directly guides the evacuation decision of the firefighter; The warning execution module is configured to input the dynamic temperature risk coefficient, the environmental coupling risk index and the residual safety time prediction value outputted by the calculation processing module, trigger the hierarchical warning based on the input data, and guide the action decision of the firefighter.

[0007] Optionally, the calculation processing module includes a dynamic temperature risk unit, a comprehensive environmental risk unit and a safety prediction unit.

[0008] Optionally, the processing flow of the dynamic temperature risk unit is as follows: S1, by analyzing the current heating state of the fire suit, the current fire suit surface monitoring temperature is outputted as the basis for calculating the dynamic temperature risk coefficient, and the difference between the current fire suit surface monitoring temperature and the material safety threshold temperature is processed to calculate the overheating risk, so as to avoid the risk assessment distortion caused by the boundaryless temperature input; S2, by analyzing the change value of the protective clothing surface temperature in a short time interval, the physical quantity for measuring the temperature rise and fall amplitude is outputted as the temperature change amount, and the time interval corresponding to the temperature change amount is combined to output the temperature change rate, so as to reflect the dynamic trend of the temperature change; S3, by analyzing the cumulative number of times of using the fire suit, the heat protection performance decline caused by thermal oxidative aging of aramid fiber after the fire suit is used at high temperature is considered, and the protective clothing material aging coefficient is outputted; S4, by analyzing the relative humidity of the inner layer of the fire-fighting suit, considering the actual heat insulation effect attenuation caused by the sweat and steam of the inner layer of the fire-fighting suit reducing the thermal reflectivity of aramid fiber under the high temperature and high humidity environment of the fire scene, and outputting a humidity correction coefficient; S5, through the camera on the fire helmet worn by the firefighter, the flame area is identified to consider the oxidation blackening of the fire protective clothing under the burning of the flame, the attenuation of the reflective performance is quantified by accumulating the flame exposure time, the thermal reflection attenuation coefficient is calculated, and finally the dynamic temperature risk coefficient is output.

[0009] Optionally, the processing flow of the comprehensive environmental risk unit is as follows: A1, by acquiring the concentration of flammable and explosive gas, and adjusting the weight according to the type of gas in the fire scene based on the gas risk weight coefficient, the explosion risk of the gas environment is dynamically quantified, and the gas factor is normalized by combining the corresponding gas explosion lower limit concentration; A2, by analyzing the ambient light intensity when there is no smoke and the light intensity under the current smoke environment, the influence of smoke concentration on the visibility of firefighters is considered, so as to further consider multiple environmental factors, and output a smoke attenuation coefficient; A3, through the camera on the fire helmet and combining the AI target detection model, the number of flammable and explosive articles in the fire scene is identified, the correlation between the number of dangerous goods in the fire scene and the secondary explosion and the expansion of the fire is considered, and the number of dangerous goods is output; A4, by considering the increase of self metabolic heat caused by high-intensity action of the firefighter, the internal temperature rise is analyzed to accelerate the heat damage, the action intensity coefficient is calculated, and the dynamic temperature risk coefficient is combined, and finally the environmental coupling risk index is output.

[0010] Optionally, the processing flow of the safety prediction unit is as follows: B1, by calculating the ratio of the previous heat flow density and the heat flow tolerance limit of the fire-fighting suit, the influence of heat transfer mode on safety time is corrected, and then a heat flow density correction factor is output; B2, by analyzing the thermoelectric conversion efficiency of the fire-fighting suit material through the Seebeck coefficient, a heat damage accumulation coefficient is output; B3, by considering the influence of oxygen concentration on the rate of combustion reaction through the oxygen volume fraction in the fire scene, an oxygen concentration adjustment coefficient is output, and the basic safety time constant, the dynamic temperature risk coefficient and the environmental coupling risk index are combined, and finally the remaining safety time prediction value is output.

[0011] Optionally, the hierarchical warning in the warning execution module is as follows: When the remaining safety time prediction value is less than 30 seconds, an emergency evacuation warning is given, which indicates that the remaining safety time is extremely short and needs to be evacuated immediately; When the remaining safe time prediction is between 30 and 60 seconds, it indicates an evacuation warning. This means that the risk has increased and the current task should be stopped and an evacuation route should be planned. When the predicted remaining safe time is between 60 and 120 seconds, it indicates a risk warning, which means that there is a potential risk and environmental changes need to be closely monitored. When the predicted remaining safe time is greater than 120 seconds, it means there is no warning at this time.

[0012] Optionally, the tiered early warning system of the early warning execution module further includes: When an emergency evacuation warning is issued, the vibration motor on the shoulder of the fire protective suit vibrates at a high intensity of 3 times per second, and the sound and light alarm component of the helmet emits a red flashing light and a 90dB buzzer. When the evacuation preparation warning is issued, the vibration motor on the shoulder of the fire protective suit vibrates at a medium intensity once per second, and the sound and light alarm component of the helmet emits a yellow flashing light and a 75dB buzzer. When a risk warning is issued, the vibration motor on the shoulder of the fire protective suit vibrates at a low intensity of 0.5 times per second, and the audible and visual alarm component of the helmet emits a green flashing light.

[0013] Optionally, the early warning execution module further includes early warning feedback and adjustment, specifically: The early warning execution module repeats the calculations of the processing module every second, updates the remaining safety time prediction value in real time, and dynamically adjusts the early warning level of the graded early warning.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: I. This invention outputs a dynamic temperature risk coefficient through a dynamic temperature risk unit. This unit integrates parameters such as current temperature, safe threshold temperature, temperature change rate, material aging coefficient, humidity correction coefficient, and heat reflection attenuation coefficient to dynamically quantify the temperature risk of fire suits. The difference between the current temperature and the safe threshold reflects the degree to which the temperature exceeds the safe range; the temperature change rate reflects the speed of fire spread or environmental temperature rise; the combination of these two factors allows for a direct assessment of the urgency of the temperature risk. The material aging coefficient considers the degradation of the mechanical properties of aramid fibers after long-term use of the fire suit; the humidity correction coefficient relates to the implicit influence of inner layer humidity on the material's thermal insulation performance; and the heat reflection attenuation coefficient quantifies the oxidation failure of the surface reflective layer under flame burning. These parameters work together to overcome the limitations of traditional methods that rely solely on a single temperature threshold. This allows the unit to capture in real-time the impact of temperature change trends, material performance degradation, and environmental humidity on the protective effect. The resulting dynamic temperature risk coefficient accurately reflects the actual safety margin of the fire suit under the current temperature condition, providing a fundamental and dynamic quantitative basis for subsequent risk assessment.

[0015] Secondly, the application outputs an environmental coupling risk index by synthesizing the environmental risk unit, and the environmental risk unit is based on a dynamic temperature risk coefficient, further introduces factors such as gas concentration, dangerous goods identification quantity, smoke attenuation coefficient and action intensity coefficient, constructs an environmental coupling risk index, and the dynamic temperature risk coefficient as the core input ensures the continuity of the temperature risk, the ratio of the gas concentration to the lower explosive limit concentration quantifies the threat degree of the flammable and explosive gas, the dangerous goods identification quantity reflects the density of the potential explosion source in the fire scene, the smoke attenuation coefficient evaluates the influence of the visibility on the evacuation efficiency through the light intensity change, and the action intensity coefficient relates the increased metabolic heat caused by the high-intensity rescue action of the firefighter and the risk of tearing the protective layer, the coupling of these parameters enables the unit to expand the single temperature risk to a multi-dimensional risk assessment of temperature, gas, dangerous goods, smoke and human action, not only considers the objective dangerous factors of the external environment, but also integrates the influence of the state of the firefighter on the risk, and thus accurately describes the dynamic interactive risk between the human and the environment in the complex fire scene, and provides a comprehensive environmental risk basis for the prediction of the remaining safety time.

[0016] Thirdly, the application outputs a remaining safety time prediction value through a safety prediction unit, the safety prediction unit integrates parameters such as a basic safety time constant, an environmental coupling risk index, a dynamic temperature risk coefficient, a heat flow density correction factor and an oxygen concentration adjustment coefficient, and thus accurately predicts the remaining safety staying time of the firefighter, the basic safety time constant is determined by the thermal conductivity of the fire-fighting suit material and reflects the basic heat insulation capacity of the material itself, the environmental coupling risk index and the dynamic temperature risk coefficient are used as the denominator together, which embodies the core logic that the higher the comprehensive risk is, the shorter the remaining safety time is, the heat flow density correction factor distinguishes the influence of different heat transfer modes on the heat penetration speed, and the oxygen concentration adjustment coefficient relates the effect of the oxygen content of the combustion environment on the fire spread speed, the introduction of these parameters enables the unit to break through the hysteresis of the traditional temperature reaching the threshold value and warning, and can dynamically adjust the remaining safety time according to the current comprehensive risk level, the heat transfer characteristics and the combustion environment, and the quantitative result output can directly guide the evacuation decision of the firefighter and help the firefighter to gain critical escape time in the complex fire scene. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 It is a system structure schematic diagram of the application; Figure 2 It is a structure schematic diagram of a data collection module of the application; Figure 3 It is a structure schematic diagram of a calculation processing module of the application; Figure 4 It is a running process diagram of the calculation processing module of the application. DETAILED DESCRIPTION

[0018] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0019] Please refer to Figures 1 to 4 The present embodiment provides a technical solution: an online temperature monitoring and early warning system for fire-fighting protective clothing, comprising: A data collection module is configured to acquire temperature risk correlation data, environmental risk correlation data and safety prediction correlation data in the use process of the fire-fighting protective clothing. A data preprocessing module is configured to input the temperature risk correlation data, the environmental risk correlation data and the safety prediction correlation data acquired by the data collection module, clean the input data, and input the cleaned data to a calculation processing module. The calculation processing module comprises a dynamic temperature risk unit, a comprehensive environmental risk unit and a safety prediction unit. Based on the current fire-fighting clothing surface monitoring temperature, the material safety threshold temperature, the temperature change rate, the protective clothing material aging coefficient, the humidity correction coefficient, the heat reflection attenuation coefficient and the environmental risk response weight in the temperature risk correlation data, a dynamic temperature risk coefficient is outputted to quantize the dynamic temperature risk of the fire-fighting clothing. Based on the flammable and explosive gas concentration, the gas explosion lower limit concentration, the smoke attenuation coefficient, the number of hazardous substance identification and the action intensity coefficient in the environmental risk correlation data, a weighted processing is performed, and combined with the dynamic temperature risk coefficient, an environmental coupling risk index is outputted to perform multi-dimensional expansion evaluation on the use risk of the fire-fighting protective clothing. Based on the basic safety time constant, the heat flow density correction factor, the heat damage accumulation coefficient and the oxygen concentration adjustment coefficient in the safety prediction correlation data, combined with the dynamic temperature risk coefficient and the environmental coupling risk index, a residual safety time prediction value is outputted, and the quantized result directly guides the evacuation decision of the firefighter. The calculation processing module comprises a dynamic temperature risk unit, a comprehensive environmental risk unit and a safety prediction unit. An early warning execution module is configured to input the dynamic temperature risk coefficient, the environmental coupling risk index and the residual safety time prediction value outputted by the calculation processing module. The early warning execution module triggers a hierarchical early warning based on the input data to guide the action decision of the firefighter. The hierarchical early warning in the early warning execution module is specifically: When the residual safety time prediction value is less than 30 seconds, an emergency evacuation warning is indicated, which means that the residual safety time is extremely short and needs to be evacuated immediately. When in the emergency evacuation warning, the fire protective clothing shoulder vibration motor vibrates at high intensity of 3 times per second, and the sound and light alarm component of the helmet emits red flashing light and 90dB buzzer; When the remaining safety time prediction value is between 30-60 seconds, it indicates the preparation for evacuation warning, which means the risk is high, and the current task should be stopped and the evacuation route should be planned; When in the preparation for evacuation warning, the fire protective clothing shoulder vibration motor vibrates at medium intensity of 1 time per second, and the sound and light alarm component of the helmet emits yellow flashing light and 75dB buzzer; When the remaining safety time prediction value is between 60-120 seconds, it indicates the risk prompt warning, which means there is potential risk and the environmental changes should be closely observed; When in the risk prompt warning, the fire protective clothing shoulder vibration motor vibrates at low intensity of 0.5 times per second, and the sound and light alarm component of the helmet emits green flashing light; When the remaining safety time prediction value is greater than 120 seconds, it indicates no warning; The warning execution module repeats the calculation of the processing module every 1 second, and updates the remaining safety time prediction value in real time, and dynamically adjusts the warning level of the hierarchical warning.

[0020] Based on the above, the calculation result of the dynamic temperature risk unit in the system is the core input item of the comprehensive environmental risk unit, directly participates in the calculation of the environmental coupling risk index, and is the basis for quantifying the temperature and environmental collaborative risk of the comprehensive environmental risk unit. By taking temperature risk as the benchmark variable of environmental comprehensive risk, it ensures that the risk assessment of environmental factors (such as gas and smoke) does not deviate from temperature as the core threat, avoids ignoring the lethality of temperature itself due to excessive attention to environmental factors, and realizes the risk weight distribution logic of temperature dominance and environmental assistance; The calculation result of the comprehensive environmental risk unit is the denominator of the safety prediction unit, which directly determines the compression degree of the remaining safety time, and the dynamic temperature risk coefficient TR of the dynamic temperature risk unit participates in the calculation of the safety prediction unit through the index item, further amplifying the attenuation effect of temperature risk on safety time. By taking the comprehensive environmental risk and temperature risk as the constraint condition of safety time prediction, the prediction result can dynamically respond to the cumulative effect of fire risk (the higher the environmental risk and the greater the temperature risk, the shorter the remaining safety time), avoiding the disconnection between safety time prediction and actual risk, and ensuring the real-time and accuracy of the prediction result; The dynamic temperature risk coefficient TR of the dynamic temperature risk unit is affected by the exponential term in the safety prediction unit, realizing the double influence of temperature risk on safety time, highlighting the core position of temperature risk in safety time prediction. Even if the environmental risk is low, if the temperature risk is extremely high (such as rapid temperature rise and serious material aging), the remaining safety time will be significantly shortened through the exponential term, ensuring effective early warning for pure temperature risk scenarios. The material aging coefficient (reflecting the performance degradation caused by the cumulative use of protective clothing) and the thermal reflection attenuation coefficient (reflecting the decline of thermal protection performance caused by the oxidation of the reflective layer on the surface of the protective clothing) of the dynamic temperature risk unit are directly related to the physical characteristics and life cycle safety state of the protective clothing, focusing the monitoring object of the system on the protection ability of the fire protection clothing itself, rather than simply the environmental temperature. The dynamic temperature risk unit takes the current temperature and temperature change rate as the basis for input, and the environmental risk unit takes temperature risk as the basis for environmental coupling. The safety prediction unit is affected by the exponential term of temperature risk in safety time prediction, making temperature a core clue throughout the whole process of risk assessment, environmental coupling, and safety prediction, ensuring that the system is always based on temperature monitoring; The current temperature, temperature change rate, gas concentration, smoke attenuation coefficient, action intensity coefficient, and heat flux density in the calculation processing module are all collected in real time and dynamically updated by the sensors (thermoelectric sensors, gas sensors, accelerometers, and heat flow meters) integrated in the fire protection clothing, ensuring that risk assessment and safety prediction are based on real-time fire scene data rather than preset or offline information. The remaining safety time prediction value SF of the safety prediction unit is directly used as the basis for early warning triggering. When the remaining safety time is lower than the set threshold, the system sends a withdrawal prompt to the firefighter through sound, light, and vibration, etc. The risk assessment result is converted into a specific early warning instruction, realizing the functional closed loop from monitoring to early warning. The multiple units in the calculation processing module are progressively related through basic quantization, comprehensive integration, and decision output, building a full-chain technical logic from temperature signal collection to risk assessment and action guidance. The dynamic temperature risk unit serves as the input end of risk perception, capturing basic risks at the temperature and material levels. The comprehensive environmental risk unit serves as the processing end of risk integration, deeply coupling basic risks with environmental and personnel factors. The safety prediction unit serves as the execution end of decision output, generating safety time prediction that can directly guide action based on the integrated risk quantization result. The three form a closed loop, enabling the early warning system to have complete capabilities of real-time monitoring, dynamic assessment, and forward-looking early warning. The dynamic temperature risk unit breaks through the limitations of single parameter, static threshold and lagging warning of traditional temperature monitoring systems, realizes precise perception and forward-looking warning of complex fire environment through multi-dimensional parameter coupling and dynamic risk assessment, provides full-process support for firefighters from risk identification to action decision-making, converts abstract risk signals into specific safety time guidance, directly improves the personnel survival support capability in complex fire environment such as high temperature, explosion and smoke, promotes the monitoring technology of fire protection clothing from passive protection to intelligent warning, and provides a reusable multi-dimensional risk assessment framework for the intelligent development of individual protection equipment.

[0021] Please refer to Figure 1 、 Figure 2 、 Figure 3 and Figure 4 , the processing flow of the dynamic temperature risk unit is as follows: S1, by analyzing the current heating state of the fire-fighting clothing, the current fire-fighting clothing surface monitoring temperature is outputted as the basis for calculating the dynamic temperature risk coefficient, and the difference between the current fire-fighting clothing surface monitoring temperature and the material safety threshold temperature is processed to calculate the overheating risk, so as to avoid the risk assessment distortion caused by the boundaryless temperature input; S2, by analyzing the change value of the fire-fighting clothing surface temperature in a short time interval, which is a physical quantity for measuring the temperature rise and fall amplitude, the temperature change amount is outputted, and the temperature change rate is outputted by combining the time interval corresponding to the temperature change amount, so as to reflect the dynamic trend of temperature change; S3, by analyzing the cumulative number of times of using the fire-fighting clothing, the decrease of the heat protection performance of aramid fiber due to thermal oxidative aging after the fire-fighting clothing is used in high temperature is considered, and the protective clothing material aging coefficient is outputted; S4, by analyzing the relative humidity of the inner layer of the fire-fighting clothing, the actual heat insulation effect attenuation caused by the decrease of the thermal reflectivity of aramid fiber due to sweat and steam in the inner layer of the fire-fighting clothing in the high temperature and high humidity environment of the fire scene is considered, and the humidity correction coefficient is outputted; S5, by the camera on the fire helmet worn by the firefighter, the flame area is identified, the oxidation and blackening of the fire protection clothing under the burning of the flame is considered, the thermal reflection attenuation coefficient is calculated by quantifying the reflection performance attenuation through the cumulative flame exposure time, so as to finally output the dynamic temperature risk coefficient; More specifically, the calculation process of the dynamic temperature risk unit is as follows: ; Among them: TR refers to the dynamic temperature risk coefficient; EWA refers to the environmental risk response weight; TRA refers to the current fire suit surface monitoring temperature, unit is Celsius, character is represented as ℃, value range is 0-800 ℃ (in fire scene environment, the surface temperature of fire suit is protected by thermal insulation layer, usually below 500 ℃, in extreme case, such as direct burning of flame, up to 800 ℃), which is collected by the thermoelectric sensor integrated on the surface of fire suit, and can be installed at the core protection area of front chest and back of fire suit; Further, the introduction of the current fire suit surface monitoring temperature TRA directly reflects the current heating state of the fire suit, which is the basis for temperature risk assessment. This parameter, as a core variable, directly determines the degree of temperature deviation from the safety threshold and is the starting point for calculating the dynamic temperature risk coefficient TR. TRB refers to the material safety threshold temperature, unit is Celsius, character is represented as ℃, value range is based on the critical value of thermal damage of mainstream aramid materials of fire suit, when the temperature exceeds this value, the material will be thermally degraded, which can be adjusted according to the model of fire suit; Further, the introduction of the material safety threshold temperature TRB defines the temperature safety boundary, which is used to judge whether the current temperature enters the dangerous interval. This parameter, as a benchmark for temperature deviation, calculates the overheating risk by the difference between the current fire suit surface monitoring temperature TRA, avoiding the distortion of risk assessment caused by the boundaryless temperature input; TRC refers to the temperature change, which is the change value of the surface temperature of fire suit in a very short time interval. This very short time can be the preset sampling interval, such as 0.5 seconds, which is a physical quantity to measure the temperature rise and fall amplitude. The unit is Celsius, character is represented as ℃, and is in positive value indicating temperature rise (mainly concerned in fire scene), and in negative value indicating temperature drop (such as evacuation to low temperature area); TRD refers to the time change, which is the time interval corresponding to the temperature change TRC, and is a benchmark to measure the speed of temperature change. In the system, the time change TRD is the fixed sampling interval time of the sensor, which needs to be set according to the response demand of fire temperature change. In this embodiment, it is set to 0.5 seconds to ensure timely capture of rapid temperature rise scenarios. The unit is second, and the value of time change TRD needs to balance the response speed and data stability. If the value is too small, such as 0.1 s, it may introduce sensor noise. If the value is too large, such as 2 s, it may miss the rapid temperature rise process (such as sudden spread of fire); TRC / TRD refers to the temperature change rate, with a value range of -5-20 ℃ / s, negative value indicating temperature drop, common temperature rise rate in fire scene being 0.5-10 ℃ / s, and up to 20 ℃ / s in rapid fire situation. The calculation formula is as follows: TAC / TAD=(TRAt-TRAt-tt) / ∆t; Wherein, TRA t refers to the current fire suit surface monitoring temperature at t time, TRA t-ttThe current fire suit surface monitoring temperature at the time of t-tt, tt is a sampling interval, and the embodiment is set to 0.5s to ensure the response speed to rapid temperature rise; The introduction of the temperature change rate reflects the dynamic trend of temperature change. The faster the temperature rises, the more rapidly the fire spreads or the heat flow increases, the higher the risk urgency is, and the dynamic characteristics of the temperature risk are amplified. Under the same temperature difference, the higher the temperature rise rate is, the greater the dynamic temperature risk coefficient TR is, and the higher the early warning priority is, avoiding the risk misjudgment of slow temperature rise but eventually over temperature and rapid temperature rise; TRE refers to the aging coefficient of protective clothing materials, and the value range is 1-2, and the calculation formula is as follows: TRE = 1 + 0.01 x n; Wherein, n refers to the cumulative number of times of use of the fire protective clothing, and each use refers to complete participation in one fire fighting task, which can be recorded by a fire suit management system; Further, after the fire suit is used for many times at high temperature, the aramid fiber will be subjected to thermal oxidative aging, resulting in a decrease in thermal protection performance, such as an increase of 15% in thermal conductivity every 50 times of use, which is used to quantify the performance attenuation of the material after long-term use. The more serious the aging is, the greater the aging coefficient TRE of the protective clothing material is, and the higher the dynamic temperature risk coefficient TR is under the same temperature condition, avoiding early warning lag due to implicit reduction of the safety threshold caused by material aging; TRF refers to a humidity correction coefficient, and the value range is 1-3, and the calculation formula is as follows: TRF = 1 + 0.02 x RHH; Wherein, RHH refers to the relative humidity of the inner layer of the fire suit, and RHH is collected by a micro humidity sensor on the inner layer of the fire suit close to the skin side, such as the armpit position; Further, under the high temperature environment of the fire scene, the sweat of the firefighter or the environmental vapor will increase the humidity of the inner layer of the fire suit, and the moisture will reduce the thermal reflectivity of the aramid material (such as a decrease of 15% in thermal reflectivity when RHH = 60%), resulting in a decrease in the actual heat insulation effect. The introduction of this parameter is used to correct the implicit influence of humidity on the heat protection performance. The humidity correction coefficient TRF increases under high humidity, and TR increases, avoiding the misjudgment of the surface temperature not exceeding the threshold but the inner layer heat transfer accelerating; TRG refers to a thermal reflection attenuation coefficient, and the value range is 1-1.5, and the calculation formula is as follows: TRG = 1 + 0.05 x TAGS; Wherein, TAGS is the cumulative time of exposure of the fire suit to fire, in seconds, and the value range is 0-100s. The cumulative time TAGS of exposure of the fire suit to fire can be identified by integrating a camera on the fire helmet and combining a flame area recognition algorithm to identify the flame area; Further, the surface aluminum foil reflective layer of the fire suit will gradually oxidize and turn black under the burning of the flame (e.g. the reflectivity may decrease by 5% after 10s of burning), and the attenuation of the reflective performance leads to more heat penetrating to the inner layer. The introduction of the thermal reflection attenuation coefficient TRG is used to quantify the impact of the attenuation of the reflective layer performance on the risk. The longer the exposure time to the flame, the greater the cumulative time TAGS of the fire suit exposed to the flame, the greater the thermal reflection attenuation coefficient TRG, and the higher the dynamic temperature risk coefficient TR, thereby avoiding the risk of overheating of the inner layer due to the failure of the reflective layer while the surface temperature is normal.

[0022] Based on the above, the dynamic temperature risk unit as the basic risk quantification module of the system, by integrating the temperature state, change trend and material performance attenuation, converts the temperature signal of the fire suit into an assessable risk indicator, breaks through the monitoring limitation of traditional temperature threshold, realizes the comprehensive judgment of whether the current temperature is safe, whether the temperature rise is urgent, and whether the material is more fragile due to aging, avoids the risk misjudgment of slow temperature rise but material aging or rapid temperature rise but good material performance, provides the core temperature risk basis for subsequent environmental coupling assessment and safety time prediction, and ensures that the early warning system has a deep perception ability for the dynamic characteristics of temperature from the source; By introducing the humidity correction coefficient and the thermal reflection attenuation coefficient, the humidity of the inner layer of the fire suit (which affects the heat insulation performance of the material) and the oxidation of the surface reflective layer (which affects the thermal reflection efficiency) are included in the risk assessment, breaking through the limitation of traditional temperature threshold, reflecting the implicit performance degradation of the material in the use process; Coupling the temperature change rate with the degree of deviation of the current temperature from the safety threshold makes the risk assessment include both the current state and the change trend, avoids the risk equalization of static overtemperature and dynamic temperature rise, upgrades the temperature risk quantification from single physical quantity record to multi-dimensional coupling calculation of material performance, temperature dynamics and safety threshold, and improves the accuracy and forward-looking of temperature risk assessment.

[0023] Please refer to Figure 1 , Figure 2 , Figure 3 and Figure 4 , the processing flow of the comprehensive environmental risk unit is as follows: A1, by acquiring the concentration of flammable and explosive gas, and based on the gas risk weight coefficient, the weight is adjusted according to the type of fire gas, to dynamically quantify the explosion risk of gas environment, and combined with the corresponding gas explosion lower limit concentration, to normalize the gas factor; A2, by analyzing the ambient light intensity when there is no smoke and the light intensity in the current smoke environment, to consider the influence of smoke concentration on the visibility of firefighters, and further consider multiple environmental factors, to output the smoke attenuation coefficient; A3, through the camera on the fire helmet and combined with the AI target detection model, the number of flammable and explosive goods in the fire field is recognized, so as to consider the correlation between the number of dangerous goods in the fire field and secondary explosion and fire expansion, so as to output the number of dangerous goods identification; A4, by considering the increase of self metabolic heat caused by high intensity action of the firefighter, the internal temperature rise is analyzed to accelerate heat damage, the action intensity coefficient is calculated, and the dynamic temperature risk coefficient is combined, so as to finally output the environmental coupling risk index; More specifically, the calculation process of the comprehensive environmental risk unit is as follows: ; Among them: CR refers to the environmental coupling risk index; CRA refers to the gas risk weight coefficient, the value range is 0.5-2, which can be set according to the gas toxicity and explosive grade, such as ammonia (moderate toxicity) can take 1.2, hydrogen (high explosive) can take 2, and carbon dioxide (non-toxic) takes 0.5; Further, the danger of different gases is significantly different, when high toxicity and explosive gas leaks, even at low concentration, it may cause serious consequences, such as hydrogen explosion limit is wide, so it needs to be paid attention to, the introduction of gas risk weight coefficient CRA is used to adjust the contribution weight of gas concentration to the comprehensive risk, the higher the danger level, the greater the gas risk weight coefficient CRA, the higher the environmental coupling risk index CR under the same concentration, avoiding the risk of low toxic gas high concentration and high toxic gas low concentration; CRB refers to the concentration of flammable and explosive gas, the value range is 0-CRC, CRC is the lower explosive limit concentration of the gas, such as ammonia CRC=15000ppm, so CRB takes the value of 0-15000ppm, which can be collected by the gas sensor integrated on the shoulder of the fire protective clothing, which can be installed on the shoulder area of the fire protective clothing; Further, when the gas concentration is close to the lower explosive limit, it is easy to cause secondary explosion when encountering fire source, which significantly increases the complexity of fire field and the risk of personnel casualty, the introduction of this flammable and explosive gas concentration CRB is used to quantify the explosion risk of gas environment, the greater the flammable and explosive gas concentration CRB, the closer to the lower explosive limit concentration CRC of the gas, the greater the contribution to the environmental coupling risk index CR, and the risk of gas and temperature is upgraded; CRC refers to the lower explosive limit concentration of the gas, the value range is fixed according to the type of gas, such as ammonia 15000ppm, methane 50000ppm and hydrogen 40000ppm; Further, the introduction of the gas explosion lower limit concentration CRC defines the critical concentration of gas explosion risk. When CRB≥CRC, the explosion risk increases sharply, and at this time CRB / CRC≥1, the gas risk term reaches the maximum value. The gas explosion lower limit concentration CRC serves as a normalized reference for gas concentration, making CRB / CRC dimensionless, which facilitates risk comparison and superposition calculation of different gas concentrations. CRD refers to the smoke attenuation coefficient, with a value range of 0-1, and the calculation formula is as follows: CRD = (CRDA - CRDB) / CRDA where CRDA refers to the ambient light intensity without smoke, which is the smoke-free light intensity recorded during system initialization, and CRDB refers to the light intensity in the current smoke environment, which is collected in real time by the helmet camera light sensor. When CRDB = CRDA, it indicates that there is no smoke, and the smoke attenuation coefficient CRD = 0. When CRDB = 0, it indicates that there is complete smoke, and the smoke attenuation coefficient CRD = 1. Further, the higher the smoke concentration, the more serious the light intensity attenuation, resulting in reduced visibility. For example, when the smoke attenuation coefficient CRD = 0.8, the visibility may be less than 0.5 m, making it more difficult for firefighters to plan evacuation routes and prolonging escape time. The introduction of the smoke attenuation coefficient CRD quantifies the impact of smoke on mobility, and the thicker the smoke, the greater the smoke attenuation coefficient CRD, and the higher the environmental coupling risk index CR, allowing the warning to expand from pure risk assessment to risk and mobility coupling assessment. This system quantifies the impact of smoke on escape efficiency through light intensity attenuation, addressing the shortcomings of focusing only on temperature and gas while ignoring the risk of mobility obstruction. CRE refers to the hazardous material weight coefficient, with a value range of 1-5. For example, a gasoline barrel (relatively low power) can take 1, an oxygen cylinder (high pressure and explosive) can take 5, and a liquefied petroleum gas tank (high combustion heat) can take 4. Further, the potential harm of different hazardous materials varies greatly. High-pressure gas cylinder explosions can cause shock waves and fragment damage, which require special attention. The introduction of the hazardous material weight coefficient CRE adjusts the contribution weight of the number of hazardous materials to the overall risk. The higher the hazard level, the greater the hazardous material weight coefficient CRE, and the higher the hazardous material weight coefficient CRA for the same number, avoiding the equalization of risks for ordinary flammable and explosive materials. CRF refers to the number of hazardous material identifications, with a value range of 0-10. It can be identified by the AI target detection model of the fire helmet camera, such as gasoline barrels, oxygen cylinders, and gas tanks, The AI model can directly output the number of identifications, and the AI model can be based on the YOLO architecture. Further, the more dangerous goods in the fire field, the higher the probability of secondary explosion or fire expansion, such as the explosion risk of 2 oxygen cylinders is more than one, the introduction of dangerous goods identification number CRF is used to quantify the density of dangerous goods in the environment, the greater the dangerous goods identification number CRF, the greater the contribution to the environmental coupling risk index CR, and the collaborative risk of multiple sources of dangerous goods is considered in the early warning; CRG refers to the action intensity coefficient, and the calculation formula is as follows: CRG = 1 + 0.3 x CRGS; Among them, CRGS refers to the three-axis acceleration root mean square, with a value of 0-5g, reflecting the intensity of the firefighter's action (firefighter's daily action acceleration 0.5-3g, intense action such as climbing can reach 5g), which can be collected by the three-axis accelerometer integrated in the waist of the fire protective clothing, which can be installed in the waist of the fire protective clothing. Because the action amplitude of this area may be large; Further, high-intensity action may increase the metabolic heat production of firefighters (resting metabolic rate about 100W, intense action may reach 400W), leading to an increase in the temperature of the inner layer of the fire protective clothing, and too large action amplitude may tear the local protective layer (such as the joint), reducing the overall protective performance. By introducing the action intensity coefficient CRG, the influence of the firefighter's own action on the risk is quantified, the greater the action intensity, the higher the three-axis acceleration root mean square CRGS, the greater the action intensity coefficient CRG, and the higher the environmental coupling risk index CR, realizing the dynamic coupling of human state and environmental risk.

[0024] Based on the above, the comprehensive environmental risk unit as a multi-dimensional risk integration module of the system, on the basis of the temperature risk of the dynamic temperature risk unit, introduces the fire field environmental risk factors (gas, smoke, dangerous goods) and the firefighter's own state (action intensity), constructs a temperature, environment and human collaborative risk assessment system, expands the single temperature risk to a comprehensive scene risk, solves the defect that the traditional monitoring only pays attention to the physical parameters and ignores the environmental complexity and the influence of personnel behavior, makes the risk assessment more close to the actual characteristics of the dynamic, complex and multi-factor interlaced fire field, provides a comprehensive environmental risk input for the remaining safety time prediction, ensures that the prediction result not only reflects the temperature threat, but also covers the influence of secondary disasters (such as explosion, smoke obstruction) and personnel's own state on safety; The influence of smoke on the action ability (difficulty of evacuation caused by reduced visibility) is quantified by a smoke attenuation coefficient, and the action state of the firefighter is related by an action intensity coefficient (high-intensity action aggravates the risk of internal heat production and damage to the protective layer), to realize dynamic interaction evaluation of environmental risk and personnel state, and different dangerous levels of gas and articles are given different influence weights by a gas risk weight coefficient and a dangerous article weight coefficient, to avoid the risk of low concentration of high risk and high concentration of low risk being treated equally, so that the risk assessment is expanded from temperature single factor to multi-source coupling calculation of temperature, gas, smoke, dangerous articles and personnel action, to solve the problem of insufficient adaptability of traditional monitoring to complex fire environment.

[0025] Please refer to Figure 1 、 Figure 2 、 Figure 3 and Figure 4 Figure 1 Figure 2 Figure 3 Figure 4 , the processing flow of the safety prediction unit is: B1, by comparing the front heat flux density with the heat flux tolerance limit of the fire suit, to correct the influence of heat transfer mode on safety time, and then output the heat flux correction factor; B2, by the Seebeck coefficient of the fire suit material, to analyze the thermoelectric conversion efficiency, to output the heat damage accumulation coefficient; B3, by the oxygen volume fraction of the fire scene, to consider the influence of oxygen concentration on the rate of combustion reaction, to output the oxygen concentration adjustment coefficient, and combine the basic safety time constant, the dynamic temperature risk coefficient and the environmental coupling risk index, to finally output the remaining safety time prediction value; More specifically, the calculation process of the safety prediction unit is as follows: ; Wherein: SF refers to the remaining safety time prediction value; SFA refers to the basic safety time constant, with a unit of seconds, and a value range of 200-400s, which can be set according to the thermal protection performance of the fire suit material; Further, when there is no additional risk factor (such as high temperature, gas and dangerous articles), the basic safety stay time provided by the fire suit reflects the heat insulation ability of the material itself, which is used as the baseline value of the remaining safety time, the greater the basic safety time constant SFA, the higher the basic value of the remaining safety time prediction value SF, which is the bottom parameter of the predicted safety time; SFB refers to the heat flux correction factor, and the calculation formula is as follows: SFB = Q1 / Q2; Wherein, Q1 is the heat flux tolerance limit of the fire suit, which is set to 20kW / m² in this embodiment, and Q2 is the current heat flux, which can be collected by the fire suit surface heat flux sensor, which can be installed on the elbow and knee of the fire suit; SFB = 1 when Q2 = 20 kW / m2, SFB = 0.2 when Q2 = 100 kW / m2; Further, at the same temperature, the heat flux (heat transfer rate per unit area) determines the heat penetration speed, and high radiant heat flux (such as 50 kW / m2) may cause material thermal damage speed to be several times faster than that of convective heat flux (such as 10 kW / m2). The introduction of the heat flux correction factor SFB is used to correct the influence of heat transfer mode on safety time. The higher the current heat flux Q2 is, the smaller the heat flux correction factor SFB is. Avoiding the misjudgment of the same safety time under the same temperature and different heat fluxes, the heat flux correction base safety time solves the problem of damage speed difference caused by the inability to distinguish heat transfer mode by temperature alone, making the prediction more in line with the actual thermal damage mechanism; α refers to a small positive number, such as 0.1, to avoid the case where the numerator is too large when the denominator is 0, because even if there is no environmental risk, there may still be temperature risk; SFC refers to the thermal damage accumulation coefficient, and the calculation formula is as follows: SFC = 1 / (SAS x 10 -3 ); Wherein, SAS refers to the Seebeck coefficient of the fire-fighting clothing material, which reflects the thermoelectric conversion efficiency of the material. The higher the efficiency, the faster the carrier migration speed at high temperature, resulting in accelerated accumulation of internal thermal damage of the material, which can be obtained by material thermoelectric performance test; Further, the exponential term quantifies the cumulative effect of thermal damage. The larger the thermal damage accumulation coefficient SFC is, the stronger the attenuation effect of the dynamic temperature risk coefficient TR on the predicted value SF of the remaining safety time, and the faster the safety time decreases at high temperature; SFE refers to the oxygen concentration adjustment coefficient, with a value range of -0.2 to 0.3, and the calculation formula is as follows: SFE = 0.1 x (O2 - 21%); Wherein, O2 refers to the oxygen volume fraction of the fire scene, which is collected by a portable oxygen sensor carried by the fire-fighting clothing, which can be installed on the collar of the fire-fighting clothing, that is, close to the breathing area, with a value of 15%-25% (normal air O2 = 21%), so SFE = 0.1 x (O2 - 21%), when O2 = 19%, SFE = -0.2, and when O2 = 24%, SFE = 0.3; Further, oxygen concentration affects the combustion reaction rate. An oxygen-rich environment (O2 > 23%) will accelerate the spread of flames (20% increase in combustion rate), leading to rapid rise in temperature and heat flux, while an oxygen-deficient environment (O2 < 19%) will slow down combustion; The safety time decay rate is adjusted by an exponential term. When the oxygen concentration is rich, the oxygen concentration adjustment coefficient SFE is positive, the exponential term decreases, and the basic safety time constant SFA is shortened. When the oxygen concentration is poor, the oxygen concentration adjustment coefficient SFE is negative, the exponential term increases, and the basic safety time constant SFA is extended, so that the prediction is more in line with the actual combustion environment. The residual time decay rate is adjusted by the oxygen concentration, so as to avoid the lag of early warning in a high-oxygen environment or the misjudgment of excessive early warning in an oxygen-deficient environment.

[0026] Based on the above, the safety prediction unit as the decision output module of the system directly predicts the time that the firefighter can safely stay in the current environment based on the risk quantification results of the first two groups of units, converts the abstract risk index into specific action guidance basis, realizes the leap from risk monitoring to action decision, avoids the early warning being limited to qualitative judgment of whether it is dangerous, but provides quantitative guidance on how long it can still be safe to stay, so that the firefighter can plan evacuation or rescue action according to the remaining time, is the core carrier of the system warning function, and directly improves the survival ability of the firefighter in a high-risk environment through clear safety time prediction, and changes passive response to active avoidance; The influence of different heat transfer modes (radiation, convection) on the safety time is distinguished by the heat flux correction factor (high radiation heat flux at the same temperature leads to faster heat penetration), and the oxygen concentration adjustment coefficient is used to associate the oxygen concentration of the combustion environment (oxygen-rich accelerates combustion, and oxygen-deficient slows down combustion), so that the safety time prediction is in line with the dynamic combustion characteristics of the fire scene. The cumulative effect of temperature risk is taken into account in the prediction by the heat damage accumulation coefficient (the higher the temperature risk, the faster the material heat damage accumulates, and the more significant the safety time decay), so as to avoid the prediction deviation of instantaneous risk and cumulative risk, and to upgrade the safety time prediction from static material insulation time to dynamic coupling calculation of environmental risk, heat transfer characteristics, combustion state and risk accumulation, and to improve the matching degree of the prediction result and the actual safety boundary of the fire scene.

[0027] It is worth noting that the present embodiment gives an iterative form, which further operates the environmental coupling risk index CR calculated by the comprehensive environmental risk unit to affect and iterate the environmental risk feedback weight EWA in the dynamic temperature risk unit, so as to play the purpose of echoing and circular optimization, and the specific iterative processing process is as follows: ; Wherein: EWA k+1 EWA k EWA EWA k EWA CRSS refers to the environmental risk threshold, which is preset to 5 in the embodiment, and can be divided based on the fire environment risk level, such as less than 3 for low risk, between 3 and 7 for medium risk, and greater than 7 for high risk; E1 refers to an iteration step factor, which is set to 0.1 in the embodiment, to control the smoothness of weight adjustment and avoid drastic fluctuations; tanh refers to the hyperbolic tangent function, which is used to compress the input in the parentheses after tanh to [-1, 1], so that the weight adjustment changes nonlinearly with the deviation of the environmental coupling risk index CR and the environmental risk threshold CRSS, avoiding extreme values leading to weight out of control; It is worth noting that an iteration termination condition also needs to be set, and the convergence of the iteration is based on two termination conditions in the embodiment, and the iteration is terminated when any one of the following two conditions is met; Condition one: the number of iterations reaches the upper limit, which is set to 10 times in the embodiment to avoid the iteration from falling into a dead loop and to ensure the real-time performance of the system; Condition two: |EWA k+1 -EWA k | < 0.01; Based on the above, the iteration system adjusts the environmental risk feedback weight EWA through iteration, so that the dynamic temperature risk coefficient TR is no longer a static temperature parameter combination, but can dynamically respond to the environmental comprehensive risk quantified by the environmental comprehensive risk unit. When the environmental risk increases (such as detecting high concentration of hydrogen and thick smoke), the environmental risk feedback weight EWA increases, increasing the weight of temperature risk in the overall assessment, so that the dynamic temperature risk coefficient TR more sensitively reflects the superimposed danger of high temperature and complex environment, avoiding the lag of early warning caused by single-dimensional evaluation; In a low environmental risk scenario (such as high temperature without dangerous goods), the environmental risk feedback weight EWA tends to 1, and the temperature risk is evaluated according to the original logic. In a high environmental risk scenario (such as high temperature and multiple oxygen cylinders), the environmental risk feedback weight EWA increases (such as close to 2), which strengthens the weight of temperature risk, so that the system responds to the high-priority warning of the superposition of high temperature and environmental danger, avoiding the underestimation of risk due to insufficient consideration of environmental factors; Traditional static formulas are difficult to cope with the dynamic changes of the fire environment (such as sudden increase in gas concentration and increase in the number of dangerous goods), and the iteration mechanism can make the dynamic temperature risk coefficient and the environmental coupling risk index CR feedback and dynamically adjust each other, ensuring that the risk assessment result is updated in real time with the change of the environment, making the early warning decision more in line with the actual dangerous situation of the fire scene, and providing more accurate safety time prediction and evacuation guidance for firefighters.

[0028] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary of the principles and application of the present application. Numerous modifications and adaptions can be effected without departing from the spirit and scope of the present application, which is not limited to the exact construction and arrangement described. It is intended, therefore, to cover all modifications and adaptions that fall within the scope of the claims and their equivalents.

Claims

1. A temperature on-line monitoring and early warning system for fire protection clothing, characterized in that, include: Data collection module: used to acquire temperature risk correlation data, environmental risk correlation data, and safety prediction correlation data during the use of fire protective clothing; Data preprocessing module: This module is used to input temperature risk correlation data, environmental risk correlation data, and safety prediction correlation data obtained by the data collection module, clean the input data, and input the cleaned data into the calculation and processing module. Calculation and processing module: Based on the current surface monitoring temperature of the fire suit, material safety threshold temperature, temperature change rate, protective suit material aging coefficient, humidity correction coefficient, heat reflection attenuation coefficient, and environmental risk feedback weight in the temperature risk correlation data, a dynamic temperature risk coefficient is output to dynamically quantify the temperature risk of the fire suit. Based on the concentration of flammable and explosive gases, lower explosion limit concentration of gases, smoke attenuation coefficient, number of hazardous materials identified, and action intensity coefficient in the environmental risk association data, a weighted average is applied and combined with a dynamic temperature risk coefficient to output an environmental coupling risk index, so as to conduct a multi-dimensional extended assessment of the risk of fire protective clothing use. Based on the basic safety time constant, heat flux density correction factor, thermal damage accumulation coefficient and oxygen concentration adjustment coefficient in the safety prediction correlation data, and combined with the dynamic temperature risk coefficient and environmental coupling risk index, the remaining safety time prediction value is output. The output quantitative results directly guide firefighters' evacuation decisions. Early warning execution module: It is used to input the dynamic temperature risk coefficient, environmental coupling risk index and remaining safe time prediction value output by the calculation and processing module. The early warning execution module triggers graded early warnings based on the input data to guide firefighters' action decisions.

2. The temperature on-line monitoring and early warning system for fire fighting protective clothing according to claim 1, characterized in that: The computational processing module includes a dynamic temperature risk unit, a comprehensive environmental risk unit, and a safety prediction unit.

3. The temperature on-line monitoring and early warning system for fire fighting protective clothing according to claim 2, characterized in that: The processing flow of the dynamic temperature risk unit is as follows: S1. By analyzing the current heat state of the fire suit, the current surface monitoring temperature of the fire suit is output as the basis for calculating the dynamic temperature risk coefficient. The difference between the current surface monitoring temperature of the fire suit and the material safety threshold temperature is processed to calculate the overheating risk and avoid the distortion of risk assessment caused by unbounded temperature input. S2. By analyzing the change in surface temperature of protective clothing over a short time interval, a physical quantity is used to measure the magnitude of temperature rise and fall, outputting the amount of temperature change. Combined with the time interval corresponding to the amount of temperature change, the rate of temperature change is output, thereby reflecting the dynamic trend of temperature change. S3. By analyzing the cumulative number of times the fire suits are used, the thermal protection performance of the aramid fibers will decrease due to thermal oxidation and aging after high-temperature use, so as to output the aging coefficient of the protective clothing material. S4. By analyzing the relative humidity of the inner layer of the fire suit, the actual heat insulation effect is reduced due to the decrease in the heat reflectivity of aramid fibers caused by sweat and vapor in the inner layer of the fire suit under the high temperature and high humidity environment of the fire scene, so as to output the humidity correction coefficient. S5. The fire zone is identified by the camera on the fire helmet worn by firefighters. The oxidation and blackening of the fire protective clothing under the flame is taken into account. The reflection performance attenuation is quantified by accumulating the flame exposure time to calculate the heat reflection attenuation coefficient, and finally output the dynamic temperature risk coefficient.

4. The temperature on-line monitoring and early warning system for fire fighting protective clothing according to claim 3, characterized in that: The processing flow for the integrated environmental risk unit is as follows: A1. By obtaining the concentration of flammable and explosive gases and adjusting the weights according to the types of gases in the fire scene based on the gas risk weight coefficient, the explosion risk of the gas environment is dynamically quantified. Combined with the corresponding lower explosion limit concentration of the gas, the gas factors are normalized. A2. By analyzing the ambient light intensity in the absence of smoke and the light intensity in the current smoke environment, the impact of smoke concentration on firefighter visibility is considered, thereby further considering multiple environmental factors to output the smoke attenuation coefficient. A3. By using the camera on the fire helmet and combining it with an AI target detection model, the quantity of flammable and explosive materials in the fire scene is identified, in order to consider the correlation between the quantity of hazardous materials in the fire scene and secondary explosions and fire expansion, so as to output the quantity of hazardous materials identified. A4. By considering the increased metabolic heat generated by firefighters due to high-intensity movements, the internal temperature rise is analyzed to accelerate thermal damage, so as to calculate the movement intensity coefficient and combine it with the dynamic temperature risk coefficient, thus finally outputting the environmental coupling risk index.

5. The online temperature monitoring and early warning system for fire-fighting protective clothing according to claim 4, characterized in that: The processing flow of the security prediction unit is as follows: B1. By calculating the ratio between the front heat flux density and the heat flux tolerance limit of the fire suit, the influence of heat transfer mode on safety time is corrected, and then the heat flux density correction factor is output. B2. Analyze the thermoelectric conversion efficiency using the Seebeck coefficient of the fire suit material to output the thermal damage accumulation coefficient; B3. By considering the oxygen volume fraction in the fire, the rate of combustion reaction affected by oxygen concentration is determined, and an oxygen concentration adjustment coefficient is output. This coefficient is then combined with the basic safe time constant, dynamic temperature risk coefficient, and environmental coupling risk index to ultimately output the predicted value of the remaining safe time.

6. The online temperature monitoring and early warning system for fire-fighting protective clothing according to claim 1, characterized in that: The tiered early warning system in the early warning execution module specifically includes: When the predicted remaining safe time is less than 30 seconds, it indicates an emergency evacuation warning, meaning that the remaining safe time is extremely short and evacuation is necessary immediately. When the remaining safe time prediction is between 30 and 60 seconds, it indicates an evacuation warning. This means that the risk has increased and the current task should be stopped and an evacuation route should be planned. When the predicted remaining safe time is between 60 and 120 seconds, it indicates a risk warning, which means that there is a potential risk and environmental changes need to be closely monitored. When the predicted remaining safe time is greater than 120 seconds, it means there is no warning at this time.

7. The online temperature monitoring and early warning system for fire-fighting protective clothing according to claim 6, characterized in that: The tiered early warning system of the early warning execution module further includes: When an emergency evacuation warning is issued, the vibration motor on the shoulder of the fire protective suit vibrates at a high intensity of 3 times per second, and the sound and light alarm component of the helmet emits a red flashing light and a 90dB buzzer. When the evacuation preparation warning is issued, the vibration motor on the shoulder of the fire protective suit vibrates at a medium intensity once per second, and the sound and light alarm component of the helmet emits a yellow flashing light and a 75dB buzzer. When a risk warning is issued, the vibration motor on the shoulder of the fire protective suit vibrates at a low intensity of 0.5 times per second, and the audible and visual alarm component of the helmet emits a green flashing light.

8. The online temperature monitoring and early warning system for fire-fighting protective clothing according to claim 1, characterized in that: The early warning execution module also includes early warning feedback and adjustment, specifically: The early warning execution module repeats the calculations of the processing module every second, updates the remaining safety time prediction value in real time, and dynamically adjusts the early warning level of the graded early warning.

Images