Intelligent protection method and system for fire extinguishing protective clothing based on impact mechanical analysis

Abstract

The invention belongs to the technical field of fire protection equipment, and discloses an intelligent protection method and system for a fire extinguishing protective suit based on impact mechanical analysis, and the method comprises the steps: quantifying sound wave dominant frequency energy, thermal radiation intensity and a human impact force vector, and constructing an environment risk portrait; performing grading processing on different types of data, calculating a human body injury risk index, a collapse risk index and a secondary collapse probability, and generating a collaborative threat grading table; monitoring the physiological state data of the firefighter in real time, triggering a protection action according to the threat level and the response priority, and dynamically generating a physiology-environment linkage instruction set; detecting a high-risk position and a triggering condition through group topological coordinate and risk area mapping, generating a directional defense instruction, driving a tactile vibration array, and synchronously recording a group protection execution log; and dynamically correcting the calculation precision of a threat level threshold, a linkage instruction strategy, a tactile feedback parameter and a threat index in the threat level table.

Description

Technical Field

[0001] This invention relates to the field of fire protection equipment technology, and more specifically, to an intelligent protection method and system for fire extinguishing protective clothing based on impact mechanics analysis. Background Technology

[0002] As the complexity and danger of fire accidents continue to escalate, the comprehensive protective capabilities of traditional firefighter protective clothing in dynamic environments face severe challenges. Existing protective equipment primarily relies on high-performance flame-retardant fibers and multi-layered composite structures (such as an outer layer, a waterproof and breathable layer, and a heat insulation layer) to achieve fire resistance, heat insulation, and chemical protection. However, its passive protection mode is insufficient to cope with dynamically changing risks such as collapses and falling debris impacts in a fire. Furthermore, traditional protective clothing has a low level of intelligence. Although some products integrate basic sensors such as temperature and heart rate, they lack the ability to analyze the correlation between environmental risks and physiological abnormalities, making it impossible to dynamically generate targeted protection strategies. Moreover, group collaborative protection mechanisms are lacking, and protection strategies and risk assessment models have long relied on static design, making it difficult to correct parameters through execution logs, resulting in poor adaptability.

[0003] Current fire-fighting protective clothing technology has significant limitations: In terms of environmental perception, traditional methods rely on single thermal radiation detection and fail to integrate multi-dimensional data, resulting in limited risk assessment dimensions and insufficient real-time performance; in terms of physiological-environment linkage, there is a lack of causal correlation analysis between physiological abnormalities (such as decreased heart rate variability) and environmental risks (such as high temperature), making it impossible to trigger precise protective actions such as physical cooling and equipment activation; at the same time, the group defense response mechanism is lagging behind, failing to generate directional defense based on the group's location and the degree of environmental threat (such as tactile vibration prompting evacuation direction), resulting in low efficiency of coordination among firefighters and difficulty in adapting to the dynamic changes of complex fire scenes. Summary of the Invention

[0004] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution: a smart protection method for fire-fighting protective clothing based on impact mechanics analysis, comprising: S1: Acquire sound waves of building structure fracture, heat radiation distribution of fire scene, human impact force waveform and environmental impact waveform, and then quantify the sound wave main frequency energy value, heat radiation intensity value, human impact force vector and impact energy value, and fuse them to generate an environmental risk profile; S2: Based on the environmental risk profile, the different types of data within the environmental risk profile are classified and processed. Then, the human injury risk index, collapse risk index and secondary collapse probability are calculated by combining the weight coefficients. A collaborative threat classification table is generated by dividing the threat score and the level threshold. S3: Real-time monitoring of firefighters' physiological status data, causal correlation analysis of physiological abnormalities and environmental risks based on the collaborative threat classification table, triggering protective actions according to threat level and response priority, and dynamically generating physiological-environment linkage instruction sets; S4: Combining the collaborative threat classification table with the physiological-environment linkage instruction set, it detects high-risk locations and triggering conditions by mapping group topological coordinates to risk areas, generates targeted defense instructions and drives the tactile vibration array, and synchronously records the group protection execution log. S5: Based on the group protection execution log, analyze the command response efficiency, protection effectiveness and deviation rate, and dynamically correct the threat level threshold, linkage command strategy, tactile feedback parameters and threat index calculation accuracy in the threat classification table.

[0005] Furthermore, the method for generating the environmental risk profile includes: Acquire acoustic waves of building structure fracture, perform environmental noise separation and pre-emphasis processing, and then extract the characteristic frequencies of concrete fracture. The energy proportion of the frequency band corresponding to the characteristic frequency of concrete fracture is quantified to obtain the energy value of the dominant frequency of the sound wave; Real-time acquisition of fire thermal radiation distribution data, followed by data cleaning, and cluster analysis of the cleaned fire thermal radiation distribution data to obtain a set of high-temperature hotspot coordinates; The maximum radiative flux value of the high-temperature hotspot coordinate set is taken as the thermal radiation intensity value; Using a piezoelectric array sensor, the external force impact on the firefighter's body is detected in real time, and the impact force waveform is obtained. Sliding window analysis is performed on the impact force waveform to obtain the peak force and duration of the impact event. The three-axis components of the human body impact waveform from piezoelectric sensors of all parts of the human body are extracted simultaneously to obtain the overall impact force vector. The peak force, duration and overall impact force vector are integrated to form the human body impact force vector. Real-time acquisition of environmental impact waveforms and spectral analysis to obtain the impact spectrum of falling objects; The power spectral density of the impact frequency band of the falling object is integrated to obtain the total energy value, which is used as the impact energy value of the falling object. The system integrates the dominant frequency energy value of sound waves, the intensity value of thermal radiation, the vector of human body impact force, and the impact energy value of falling objects, and encapsulates them into an environmental risk profile.

[0006] Furthermore, the method for grading different types of data within the environmental risk profile includes: Based on environmental risk profiles, a three-level response priority is defined according to the degree of urgency, and the main frequency energy value of sound waves, thermal radiation intensity value, human body impact force vector, and falling object impact energy value are classified into the corresponding response priorities. Data with high response priority is always transmitted first, data with medium response priority is processed when high response priority data does not consume resources, and data with low response priority is processed asynchronously with minimal resource consumption.

[0007] Furthermore, the calculation methods for the human injury risk index, collapse risk index, and secondary collapse probability include: Based on different types of data after hierarchical processing, the peak force and duration of the human impact force vector are extracted, and a weighted fusion calculation is performed to obtain the human injury risk index. The collapse risk index is obtained by weighted fusion of thermal radiation energy value and sound wave dominant frequency energy value; The product of the impact energy of the falling object and the collapse risk index is taken as the probability of secondary collapse.

[0008] Furthermore, the generation method of the collaborative threat classification table includes: Define corresponding weighting coefficients for different response priorities; Human injury risk index, collapse risk index and secondary collapse probability are used as threat indices, and the weight coefficient corresponding to the data type with the highest response priority among the data required to calculate the threat index is used as the level weight of the threat index. The threat index is combined with the corresponding level weights to calculate the threat score; Threat level thresholds are defined based on threat scores, and then threat scores are divided into different threat levels. Based on the threat level, predefined protection strategies are matched, and the threat level and protection strategy are mapped to form a collaborative threat classification table.

[0009] Furthermore, the generation method of the physiological-environment linkage instruction set includes: Real-time monitoring of firefighters' physiological status data; threshold analysis to determine if there are any abnormalities in the physiological status data; if the physiological status data is normal, only the data is recorded and routine monitoring is maintained. If the physiological data is abnormal, then based on the collaborative threat classification table, a causal correlation analysis is performed between the firefighter's physiological abnormalities and the environmental risk profile to classify different types of physiological abnormalities. By mapping response priorities to threat levels and combining physiological anomaly types with environmental risk matching strategies, a physiological-environment linkage instruction set is dynamically generated.

[0010] Furthermore, the method for generating the targeted defense command includes: Real-time acquisition of firefighter group topology coordinates; marking corresponding risk areas according to the threat level in the collaborative threat classification table; overlaying firefighter coordinates with risk areas; marking firefighters located in risk areas as high-risk locations. The triggering conditions for mass defense response are defined by combining the probability of secondary collapse and the human injury risk index; The triggering conditions are: the probability of secondary collapse is greater than the preset collapse probability threshold and the firefighter is in a high-risk position, or the human injury risk index is greater than the preset human injury risk threshold. Once the triggering conditions are met, a targeted defense command is generated for the adjacent firefighters based on the threat level and the triggering condition type, and then sent to the adjacent firefighters.

[0011] Furthermore, the generation method of the group protection execution log includes: Based on targeted defense commands and a collaborative threat classification table, the parameters of the tactile vibration array are defined according to the threat level; By combining the vector direction of the risk area and the firefighter's coordinates, the activation area of ​​the vibration array is mapped to the corresponding position of the firefighter's body, and then vibration commands are sent to the tactile array equipment on the firefighter's equipment. It records triggered linkage commands and targeted defense commands, threat levels, executed actions, and tactile vibration parameters in real time, generating a group protection execution log.

[0012] Furthermore, the methods for forming closed-loop optimization include: Based on the group protection execution log, the system classifies and statistically analyzes command response efficiency, protection effectiveness, and tactile feedback response rate, detects command failure events, and adjusts the risk level threshold in the threat classification table according to the scenario in which the command failure events occur. Based on events where the causal link between physiological abnormality types and environmental risk profiles fails, update the physiological-environment linkage instruction strategy; The mapping rules for vibration frequency, intensity, and activation area are dynamically calibrated based on the firefighters' response efficiency to vibration. By calculating the deviation rate between the human injury risk index and the actual injury, and the deviation rate between the secondary collapse probability and the actual collapse event, the calculation accuracy of the human injury risk index and the secondary collapse probability is dynamically adjusted, and the accuracy of high-temperature hotspot coordinate identification is also adjusted.

[0013] Furthermore, an intelligent protection system for fire-fighting protective clothing based on impact mechanics analysis includes: Environmental perception module: acquires sound waves of building structure fracture, heat radiation distribution of fire scene, human impact force waveform and environmental impact waveform, and then quantifies the sound wave main frequency energy value, heat radiation intensity value, human impact force vector and impact energy value, and integrates them to generate an environmental risk profile; Threat Assessment Module: Based on the environmental risk profile, different types of data within the environmental risk profile are classified and processed. Then, the human injury risk index, collapse risk index and secondary collapse probability are calculated by combining weight coefficients. Through threat scoring and level threshold division, a collaborative threat classification table is generated. Physiological linkage unit: Real-time monitoring of firefighters' physiological status data, causal correlation analysis of physiological abnormalities and environmental risks based on the collaborative threat classification table, triggering protective actions according to threat level and response priority, and dynamically generating physiological-environment linkage instruction sets; Defense Feedback Module: Combining the collaborative threat classification table and the physiological-environment linkage instruction set, it detects high-risk locations and triggering conditions by mapping group topological coordinates to risk areas, generates targeted defense instructions and drives the tactile vibration array, and synchronously records the group protection execution log. Closed-loop optimization unit: Based on the group protection execution log, it analyzes the command response efficiency, protection effectiveness and deviation rate, and dynamically corrects the threat level threshold, linkage command strategy, tactile feedback parameters and threat index calculation accuracy in the threat classification table.

[0014] The technical effects and advantages of the intelligent protection method and system for fire extinguishing protective clothing based on impact mechanics analysis of this invention are as follows: This invention uses multi-source sensor fusion (building structure fracture sound waves, fire heat radiation distribution, human impact force waveforms, etc.) to quantify parameters such as sound wave main frequency energy, heat radiation intensity, and human impact force vector, and construct a dynamic environmental risk profile to achieve comprehensive perception of new risks such as secondary collapse and falling object impact. Secondly, the data is processed in a hierarchical manner, and the human injury risk index, collapse risk index and secondary collapse probability are calculated by combining weight coefficients. Threat scores and collaborative threat classification tables are generated. By mapping the threat level to the protection strategy, the risk assessment and protection actions are accurately matched, which significantly improves the response efficiency and accuracy of the protection strategy. Then, through physiological-environment linkage analysis (such as the correlation between HRV abnormality and high temperature), active protection actions such as physical cooling and equipment startup are dynamically triggered, breaking through the traditional static threshold judgment mode; Next, based on the group topological coordinates and threat level, directional defense commands are generated. Combined with the vector direction mapping of the tactile vibration array, firefighters are driven to respond synchronously, solving the problems of lagging group defense response and low command execution efficiency in traditional protection systems. Finally, based on the protection execution log, the threshold of the threat classification table, the tactile feedback parameters, and the risk profile generation logic are corrected in reverse to form a closed-loop optimization link and realize the continuous iteration of the system model. This invention solves the problems of limited environmental perception, insufficient physiological linkage, and delayed group response in existing technologies through an innovative mechanism, significantly improving the accuracy, real-time performance, and adaptability of firefighter protection, and providing an intelligent solution for life safety protection in complex fire environments. Attached Figure Description

[0015] Figure 1This is a schematic diagram of a smart protection method for fire extinguishing protective clothing based on impact mechanics analysis according to the present invention. Figure 2 This is a schematic diagram of the collaborative threat classification table generation process in the intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis of the present invention. Figure 3 This is a schematic diagram of the intelligent protection system for fire extinguishing protective clothing based on impact mechanics analysis according to the present invention. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example 1 Please see Figure 1 and Figure 2 As shown in the figure, this embodiment presents an intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis, comprising: S1: Acquire sound waves of building structure fracture, heat radiation distribution of fire scene, human impact force waveform and environmental impact waveform, and then quantify the sound wave main frequency energy value, heat radiation intensity value, human impact force vector and impact energy value, and fuse them to generate an environmental risk profile; S2: Based on the environmental risk profile, the different types of data within the environmental risk profile are classified and processed. Then, the human injury risk index, collapse risk index and secondary collapse probability are calculated by combining the weight coefficients. A collaborative threat classification table is generated by dividing the threat score and the level threshold. S3: Real-time monitoring of firefighters' physiological status data, causal correlation analysis of physiological abnormalities and environmental risks based on the collaborative threat classification table, triggering protective actions according to threat level and response priority, and dynamically generating physiological-environment linkage instruction sets; S4: Combining the collaborative threat classification table with the physiological-environment linkage instruction set, it detects high-risk locations and triggering conditions by mapping group topological coordinates to risk areas, generates targeted defense instructions and drives the tactile vibration array, and synchronously records the group protection execution log. S5: Based on the group protection execution log, analyze the command response efficiency, protection effectiveness and deviation rate, dynamically correct the threat level threshold, linkage command strategy, tactile feedback parameters and threat index calculation accuracy in the threat classification table, and form a closed-loop optimization. Using a high-sensitivity capacitive microphone or piezoelectric sensor array (which can be built into the helmet), acoustic features in the environment (such as concrete fracture, falling object impact, etc.) are captured. Then, high-frequency sound wave features related to structural damage (usually in the 20Hz-20kHz frequency response range) are extracted as the raw sound wave signal generated by the building structure fracture. Environmental noise separation is performed (noise interference can be reduced by double interpolation filtering) and pre-emphasis processing (i.e., high-pass filtering is applied to the signal (the cutoff frequency can be set to 500Hz) to enhance high-frequency features), thereby extracting the characteristic frequency of concrete fracture. The energy proportion of the frequency band corresponding to the characteristic frequency of concrete fracture is quantified to obtain the energy value of the dominant frequency of the sound wave; Specifically, an exemplary method for extracting the characteristic frequency of concrete fracture is as follows: the main frequency of concrete fracture is usually 35Hz, so a fourth-order Butterworth bandpass filter can be used, and then the cutoff frequencies are set to 30Hz (low frequency) and 40Hz (high frequency), retaining only the filtered signal of the 30-40Hz frequency band as the characteristic frequency of concrete fracture. The reason for using a fourth-order Butterworth bandpass filter is that it has a steep transition band and low phase distortion, which can ensure the integrity of the signal waveform. Then calculate the sum of squares of amplitude in the 35Hz±2Hz frequency band (i.e., 33Hz-37Hz, the typical characteristic frequency of concrete fracture), and then calculate the sum of squares of amplitude in the entire frequency band to obtain the proportion of the dominant frequency energy, which is used as the dominant frequency energy value of the sound wave. It should be noted that by focusing on the 35Hz±2Hz frequency band and reflecting the fracture strength through the energy ratio, the absolute amplitude can be avoided from being affected by the environmental distance. Infrared thermal radiation data (such as the 8-14μm band) of the fire scene is collected in real time by an infrared thermal imaging camera (which can be built into the helmet). Then, local temperature rise anomalies are detected in real time by infrared hotspot positioning to obtain accurate infrared thermal radiation data as the fire scene thermal radiation distribution data. Data cleaning is performed, including background noise suppression (i.e., smoothing ambient temperature fluctuations by using low-pass filtering (cutoff frequency 1Hz)) and invalid data removal (i.e., removing inter-frame duplicates or blurry images (which can be done through a sharpness detection algorithm)) to remove ambient temperature background noise. Cluster analysis was performed on the cleaned fire scene thermal radiation distribution data to obtain a set of high-temperature hotspot coordinates; Specifically, the fire thermal radiation distribution data is converted into a two-dimensional heat map and input into the DBSCAN clustering algorithm (exemplary parameters are set to eps=0.5m, min_samples=3). Then, a temperature threshold is set, such as 100℃, and the dense area of ​​high-temperature hotspots above 100℃ is output. The coordinates of each high-temperature hotspot are extracted to form a set of high-temperature hotspot coordinates. The maximum radiative flux value of the high-temperature hotspot coordinate set is taken as the thermal radiation intensity value; Using piezoelectric array sensors attached to key parts of the human body (such as the spine, limbs, and joints), the system detects the external impact force on the firefighter's body in real time, obtaining the impact force waveform. The waveform data collected by multiple piezoelectric sensors are aligned by timestamps, and then high-frequency noise (such as electromagnetic interference) is removed by a low-pass filter (the cutoff frequency can be set to 500Hz). Sliding window analysis is performed on the human body impact force waveform (the sliding window size can be set according to the typical duration of the impact event, such as 10ms, and a threshold is set for the measurement range of the piezoelectric sensors to filter out small fluctuations, such as 10% of the measurement range of the piezoelectric sensors). The waveform data is traversed, and when the maximum value in a certain sliding window exceeds the threshold, it is marked as a potential impact event. If multiple consecutive windows (such as 5, 10, or 20, which can be set according to practical experience) exceed the threshold, it is confirmed as a valid impact event. The peak force of the impact event (the maximum value of the impact event waveform) and the duration (the time difference from the start time to the waveform falling back below the threshold) are obtained, and the start time (the time point when the impact event waveform first exceeds the threshold) is recorded. The three-axis components of the human body impact waveform from piezoelectric sensors of all parts of the human body are extracted simultaneously to obtain the overall impact force vector. The peak force, duration and overall impact force vector are integrated to form the human body impact force vector. Specifically, the local coordinate system of the piezoelectric sensors for all parts of the human body is defined in advance (e.g., the x-axis of the piezoelectric sensor is aligned with the direction of the human arm). Then, the inertial measurement unit built into the piezoelectric sensor is used to obtain the real-time pose angle (e.g., through gyroscope and accelerometer data). Then, the impact force vector in the local coordinate system is converted into the three-axis components of the global coordinate system using the Euler angle method (through the rotation matrix (Roll / Pitch / Yaw angles)). Then, the converted triaxial components of all piezoelectric sensors are superimposed in the global coordinate system to obtain the overall impact force vector; By placing a plantar pressure sensor on the sole of the foot or deploying a vibration sensor on the ground or structural (building, obstacle) surface, the raw environmental impact waveform is collected in real time. Then, the environmental impact waveform data collected by multiple pressure or vibration sensors are aligned by timestamp, the sensor output is calibrated, zero-point drift is eliminated (e.g., baseline offset is removed by moving average filtering), and then high-frequency noise (e.g., electromagnetic interference) and low-frequency drift (e.g., slow ground deformation) are removed by using a bandpass filter (with cutoff frequencies set such as 80Hz (low frequency) and 120Hz (high frequency), which are typical mechanical vibration characteristics of falling object impacts). Spectral analysis is then performed to obtain the falling object impact spectrum. Specifically, the environmental impact waveform is converted into the frequency domain representation (i.e., power spectral density, PSD) of the impact signal through a fast Fourier transform (the window size can be adjusted according to the sampling rate, such as 256 points, and the overlap rate can be set to 50% to improve the spectral resolution), which serves as the impact spectrum of the falling object. The power spectral density of the impact frequency band (e.g., 80-120Hz) of the falling object is integrated to obtain the total energy value, which is used as the impact energy value of the falling object. The system integrates the main frequency energy value of sound waves, the thermal radiation intensity value, the human body impact force vector, and the impact energy value of falling objects, encapsulates them into a structured JSON, and adds a timestamp and spatial coordinates to create an environmental risk profile. Based on environmental risk profiles, a three-level response priority is defined according to the degree of urgency, and the main frequency energy value of sound waves, thermal radiation intensity value, human body impact force vector, and falling object impact energy value are classified into the corresponding response priorities. High-response-priority data is always transmitted first, medium-response-priority data is processed when high-response-priority data does not consume resources, and low-response-priority data is processed asynchronously with minimal resource consumption (with minimal consumption of computing resources (such as CPU, memory, network bandwidth), low-response-priority data is processed independently in the background, and other higher-response-priority data can be executed without waiting for it to complete), thereby ensuring real-time response of critical data and efficient utilization of system resources; Specifically, in fire scenarios, the human body impact force vector is classified as high response priority, the sound wave main frequency energy value and the falling object impact energy value are classified as medium response priority, and the thermal radiation intensity value is classified as low response priority. The human body impact force vector is propagated in the original waveform form, while a low-latency communication protocol (such as UDP+QoS response priority marking) is used to avoid data loss or delay, and the transmission delay is set to ≤10ms. It should be noted that human impact events (such as falling object impacts) must be responded to in the shortest possible time (e.g., transmission delay ≤ 10ms) to ensure that protective devices such as hydraulic airbags inside the fire-fighting protective suit respond immediately after the impact occurs, and to ensure that the physical response limits of protective devices such as hydraulic airbags are met, while the original waveform retains complete impact characteristics to facilitate the generation of subsequent linkage commands. The transmission delay limit for the dominant frequency energy value of sound waves and the impact energy value of falling objects is increased to ≤50ms; It should be noted that compressing the original acoustic wave signal into a sequence of acoustic wave dominant frequency energy values ​​and compressing the original environmental impact waveform into falling object impact energy values ​​(i.e., single-value frequency band energy values) is used to reduce transmission bandwidth requirements. Furthermore, the acoustic wave dominant frequency energy value (35Hz±2Hz) is a characteristic signal of concrete fracture and needs to be dynamically monitored to assess collapse risk and is used for calculating the collapse risk index. The falling object impact energy value (total energy value in the 80~120Hz frequency band) can characterize the impact intensity of the falling object and is used for calculating the probability of secondary collapse. The thermal radiation intensity value is mainly used for high temperature early warning. The transmission delay limit can be further increased to ≤100ms. The asynchronous processing mechanism can prevent the delay or abnormality of low response priority data from affecting the overall system response (such as the real-time performance of tactile vibration commands), avoid low response priority from occupying too many resources, and ensure the stable operation of high response priority. Based on different types of data after hierarchical processing, the peak force and duration of the human impact force vector are extracted, and a weighted fusion calculation is performed to obtain the human injury risk index. Specifically, the weighted fusion method is to calculate the product of peak force and peak force weight, then calculate the product of duration and duration weight, and add the two products together to obtain the human injury risk index. The specific allocation of peak force weights and duration weights can be obtained based on biomechanical models (such as Whiplash injury studies, such as 0.6 and 0.4). The collapse risk index is obtained by weighted fusion of thermal radiation energy value and sound wave dominant frequency energy value; Specifically, the dominant frequency energy value of the sound wave is used to reflect the fracture strength of concrete, while the thermal radiation energy value is used because high temperature may cause material failure. The weighted fusion method is the same as above, and the specific weight allocation can be based on the coupled analysis of structural mechanics and thermodynamics (such as the concrete strength degradation model in fire, with exemplary weights of 0.7 and 0.3). The product of the impact energy of the falling object and the collapse risk index is taken as the probability of secondary collapse; Specifically, the collapse risk index can be understood as structural stability, and energy multiplied by structural stability can be quantified as the probability of triggering a secondary collapse. Define corresponding weighting coefficients for different response priorities (e.g., 0.5 for high response priority, 0.3 for medium response priority, and 0.2 for low response priority; these can be set based on experience). Human injury risk index, collapse risk index and secondary collapse probability are used as threat indices, and the weight coefficient corresponding to the data type with the highest response priority among the data required to calculate the threat index is used as the level weight of the threat index. Specifically, for example, the human injury risk index is calculated using human impact vectors. Since it is calculated entirely from high response priority data without the need for other data fusion, the weight coefficient of high response priority is used as the level weight of the human injury risk index. The collapse risk index is calculated using the dominant frequency energy value of sound waves and the intensity value of thermal radiation. However, the dominant frequency energy value of sound waves is of medium response priority, which is higher. Therefore, the weighting coefficient of medium response priority is used as the level weight of the collapse risk index. The probability of secondary collapse is calculated using the impact energy of falling objects and the collapse risk index. Both are of medium response priority, so the weighting coefficient of medium response priority is used as the level weight of the probability of secondary collapse. The threat index is combined with the corresponding level weights to calculate the threat score; The specific calculation method for weight fusion is to multiply the human injury risk index, the collapse risk index, and the probability of secondary collapse by their respective level weights, and then add the results of the multiplication to obtain the threat score. For example, assuming the human injury risk index = 2.5468, the grade weight = 0.5, the collapse risk index = 185.92, the grade weight = 0.3, the secondary collapse probability = 5968.15, and the grade weight = 0.3, after weighted fusion, the threat score = 1847.495, which can be further normalized. The normalization process can limit the minimum value to 0 and the maximum value to 10000. After calculation using the normalization formula, we get 0.1847, which is within the range of 0-1. The threat score is normalized, and a threat level threshold is defined based on the normalized threat score, thereby classifying the threat score into different threat levels. Specifically, the threat level is divided into five levels. For example, the threat level thresholds can be divided into Lv0=[0.0,0.1], Lv1=[0.1,0.2], Lv2=[0.2,0.4], Lv3=[0.4,0.7], and Lv4=[0.7,1.0]. The logic for classifying threat levels is as follows: Lv0→0.0-0.1→No threat→System hibernation; Lv1→0.1-0.2→Low Risk (Warning)→Low Response Priority, Data Monitoring; Lv2→0.2-0.4→Medium risk (local protection)→Medium response priority, dynamic response; Lv3→0.4-0.7→High risk (emergency evacuation)→High response priority, triggering protection (such as hydraulic airbags); Lv4→0.7-1.0→Extremely high risk (complete evacuation)→High response priority + medium response priority, data-driven response; Based on the threat level, predefined protection strategies are matched, and the threat level and protection strategy are mapped to form a collaborative threat classification table (encapsulated as a JSON structure table). Example protection strategy: Lv0 → No protection required → System hibernation; Lv1 → Low-frequency sound wave warning (35Hz main frequency buzzer) → Mild reminder; Lv2 → Hydraulic airbag partial activation (activated only on the impact direction side) → Automatic protection; Lv3 → All-around hydraulic airbag activation + emergency lighting + audible and visual alarm → automatic + manual confirmation; Lv4 → Full evacuation command + shut down hazardous equipment + smoke dispersal → Automatic + remote control; The protection strategy is defined by the logic that for high-risk threat levels such as Lv3 and Lv4, it is necessary to directly associate it with high-response priority data (human impact force vector) to ensure that high-response priority data drives key protection actions. Levels Lv1-Lv2 focus on medium or low response priority data to avoid over-responding to low response priority threats. Real-time monitoring of firefighters' physiological status data (such as abnormal heart rate variability (HRV) and body temperature) is conducted. Threshold analysis is used to determine whether there are any abnormalities in the physiological status data. If the physiological status data is normal, only the data is recorded and routine monitoring is maintained. Specifically, a normal physiological state threshold (such as HRV threshold) is preset, and then the physiological state data is compared with the normal physiological state threshold. If the physiological state data does not meet the normal physiological state threshold, it is judged as abnormal (such as HRV < HRV threshold). If the physiological state meets the normal physiological state threshold, it is judged as normal (such as HRV ≥ HRV threshold). If the physiological data is abnormal, then based on the collaborative threat classification table, a causal correlation analysis is performed between the firefighter's physiological abnormalities (such as a decrease in HRV) and the environmental risk profile (thermal radiation, sound energy, impact force) to classify different types of physiological abnormalities. Specifically, for the heat radiation intensity value, if the heat radiation intensity value in the threat classification table is greater than the preset heat radiation threshold (e.g., >500W / m²), and the firefighter's real-time body temperature is greater than the preset body temperature threshold (e.g., >39℃), it is judged as high temperature causing HRV abnormality and marked as moderate abnormality; For the dominant frequency energy of sound waves, if the dominant frequency energy of sound waves is greater than the preset sound wave energy threshold (e.g., >90%) and the HRV is less than the HRV threshold (e.g., <80ms), it is judged as a noise-induced pressure-type HRV anomaly and marked as a high-level anomaly. For human body impact vector, if the peak force of the human body impact is greater than the preset peak threshold (e.g., >5kN) and the HRV is less than the HRV threshold, it is determined that the HRV is abnormal due to physical impact and is marked as extremely high anomaly. If the abnormal physiological state data is not caused by environmental risks, it is judged as a non-environmentally caused abnormality and marked as a low-level abnormality. The response priority is mapped according to the threat level, and the physiological anomaly type is matched with the environmental risk to match the handling strategy. The physiological-environment linkage instruction set is dynamically generated, which includes the target device, action parameters and response priority, and is aligned with the protection requirements of the threat level (such as Lv4 forced evacuation). Specifically, threat levels are mapped and bound to response priorities, and then bound to different levels of anomalies; The thermal radiation intensity value is tied to Lv2 for low response priority, and then to medium anomaly. The acoustic wave dominant frequency energy is bound to Lv3 with medium response priority, and then bound to high-level anomalies; The human body impact vector is bound to Lv4 with high response priority, and then bound to an extremely high anomaly. Bind Lv0-Lv1 to low-level exceptions; Then, matching is performed using a pre-defined processing strategy library; For example: Lv0-Lv1 → HRV decrease (not caused by environmental factors) → Request medical support (such as remote ECG monitoring) and suggest rest; Lv2 → High temperature causes abnormal HRV → Activate cooling system (such as spray device), suspend operation in high temperature area, and provide fluid replenishment pack; Lv3 → Noise-induced HRV abnormality → Activate noise-canceling equipment (such as active noise-canceling headphones) and adjust the acoustic environment of the work area. Lv4 → Physical impact causes HRV abnormality → Activate hydraulic airbag buffer, evacuate to a safe area, and activate emergency lighting; Then, the matching processing strategy is converted into structured instructions and sent to the protection system and environmental control equipment, ensuring that the instructions are consistent with the protection strategy in the threat classification table; If multiple firefighters trigger the command at the same time, they will be ordered according to the threat level (e.g., Lv4 takes precedence over Lv3). If the threat level is Lv0-Lv1, the command priority is set to "low", and only data is recorded; If the protection strategy in the threat classification table conflicts with the current status of the fire-fighting protective clothing (e.g., hydraulic airbags are locked / abnormal / used / not installed), the system will automatically switch to the alternative strategy (e.g., activate emergency lighting). If the threat level drops from Lv4 to Lv2, terminate non-essential instructions (such as turning off emergency lighting). If the threat level remains at Lv4 but the HRV does not improve, upgrade the handling strategy (e.g., send an emergency order to call in a medical drone to deliver a first aid kit). Real-time topological coordinates of firefighter groups (obtainable via GPS / IMU fusion positioning) are acquired. Based on the threat level in the collaborative threat classification table, the location of the corresponding area is marked as a risk area. The firefighter coordinates are overlaid with the risk area. If a firefighter is located in a risk area, the firefighter coordinates are marked as a high-risk location. The triggering conditions for mass defense response are defined by combining the probability of secondary collapse and the human injury risk index; The triggering conditions are: if the probability of secondary collapse is greater than the preset collapse probability threshold (e.g., 70%) and the firefighter is in a high-risk position, it is determined that there is a risk of collapse and the triggering conditions are met; or if the human injury risk index is greater than the preset human injury risk threshold (e.g., 0.8, extremely high risk of injury), it is determined that there is a risk of injury and the triggering conditions are met. Once the triggering conditions are met, based on the threat level and the type of triggering conditions (such as collapse risk, damage risk), targeted defense instructions (such as evacuation routes, equipment activation) are generated for adjacent firefighters and sent to them. The core logic for generating directional defense commands is to prioritize commands based on the threat level, such as Lv4 over Lv3, and Lv3 over Lv2; directional commands are simultaneously sent to adjacent firefighters to ensure consistency in evacuation routes or protective measures. Example of a targeted defense command: When there is a risk of collapse, send an "emergency evacuation" order to adjacent firefighters and specify an avoidance route; When there is a risk of damage, send a "hydraulic airbag activation" command to the adjacent firefighters, and simultaneously activate emergency lighting and audible and visual alarms; If multiple firefighters trigger the command simultaneously and the threat level is Lv4, the evacuation command will be enforced, and non-essential equipment operations will be ignored. If the threat level decreases, the corresponding high-level instructions (such as turning off emergency lighting) that were executed when the threat level had not decreased will be terminated. Based on targeted defense commands and a collaborative threat classification table, the parameters of the tactile vibration array are defined according to the threat level, including vibration frequency, intensity, and activation area. The logic is defined as follows: the higher the threat level, the higher the vibration frequency (e.g., Lv4 is a high-frequency vibration of >200Hz), the greater the intensity (e.g., full-body array activation), and the longer the duration (e.g., 10 seconds). For example, Lv4 (extremely high risk), vibration frequency > 200Hz (high frequency), intensity = high intensity (100%), activation area = whole body array, duration = 10 seconds; Lv3 (high risk), vibration frequency 100-200Hz (medium frequency), intensity = medium intensity (70%), activation area = key parts of chest and back, duration = 8 seconds; Lv2 (medium risk), vibration frequency <100 Hz (low frequency), intensity = low intensity (50%), activation area = unilateral limb, duration = 5 seconds; Lv1 (Low Risk): Vibration frequency, intensity, activation area, and duration are not triggered. By combining the vector direction of the risk area and the firefighter's coordinates (e.g., the risk area is in the northwest direction of the firefighter), the activation area of ​​the vibration array is mapped to the corresponding position of the firefighter's body (e.g., the left shoulder area), and then a vibration command is sent to the tactile array equipment on the firefighter's equipment, prioritizing the activation of high-risk areas and simultaneously controlling the vibration mode of other parts to enhance the early warning effect. Example scenario description: A firefighter is located in a high-risk area of ​​collapse (impact direction is northwest), with a threat level of Lv4; The vibration command is defined as follows: Vibration module activation: high-frequency vibration (200 Hz) in the left shoulder area for 10 seconds; Full-body array: synchronous mid-frequency vibration (150 Hz) in other parts for 8 seconds; Upon receiving a command, the tactile feedback system immediately activates the corresponding vibration module; Real-time recording of triggered linkage commands and targeted defense commands, threat levels, executed actions, and tactile vibration parameters generates a group protection execution log; this data is encapsulated into standardized JSON logs, cached locally, and uploaded to the command center via a low-latency protocol (such as MQTT) to ensure rapid transmission of high-priority logs (such as Lv4 events); By mining the execution status (such as instruction completion rate), vibration feedback effectiveness (such as high-frequency vibration response rate), and threat level correlation in the logs, we can dynamically adjust tactile vibration parameters (such as optimizing frequency thresholds) and protection instruction priorities (such as upgrading equipment maintenance strategies). Based on the group protection execution log, the system is structured and classified according to command type, threat level, and execution status. Then, by analyzing response latency and threat level changes, the system classifies and statistically analyzes command response efficiency, protection effectiveness, and tactile feedback response rate. It detects command failure events and adjusts the risk level thresholds in the threat classification table according to the scenarios in which these events occur (i.e., updates the thresholds to match actual protection needs). By combining events where the causal link between physiological abnormality type and environmental risk profile fails, adjust the instruction execution rules (such as adding backup strategies) and the thresholds of physiological indicators (such as HRV abnormality thresholds) to update the physiological-environment linkage instruction strategy. Based on the firefighters' response efficiency to vibration, the dynamic calibration of vibration frequency, intensity, and active area mapping rules (such as pulsed vibration replacing high-frequency vibration). By calculating the deviation rate between the human injury risk index and the actual injury (calculating the difference between the human injury risk index and the average actual injury, and then comparing it with the average actual injury to obtain the deviation rate), and the deviation rate between the secondary collapse probability and the actual collapse event (if in a certain scenario the calculated secondary collapse probability is greater than the collapse threshold 10 times, and 6 collapses actually occur, with 2 false alarms and 2 missed alarms, then the deviation rate is 2+2=4, and then the ratio of 4 to 10 is calculated to obtain a deviation rate of 40%), the calculation accuracy of the human injury risk index and the secondary collapse probability is dynamically adjusted, and the accuracy of high temperature hotspot coordinate recognition is also adjusted. Specifically, if the deviation rate of the human injury risk index is greater than the preset injury deviation rate threshold, the weights in the human injury risk index calculation formula are adjusted (e.g., the weight of peak force is reduced from 0.6 to 0.55, and the weight of duration is increased from 0.4 to 0.45). If the deviation rate of the secondary collapse probability is greater than the preset collapse deviation rate threshold, adjust the weights in the collapse risk index calculation formula (e.g., reduce the weight of thermal radiation energy value by 0.7→0.6, and increase the weight of sound wave main frequency energy value by 0.3→0.4). If the coordinates of the high-temperature hotspot deviate from the actual collapse area by more than the preset deviation distance (e.g., 5 meters), adjust the spatial clustering radius of the thermal radiation intensity (e.g., from 3 meters to 5 meters), and dynamically update the thermal radiation threshold according to the deviation rate (e.g., change the original threshold from 500W / m² to 480W / m²). Finally, the optimization results are fed back into the environmental risk profile generation logic, threat classification table, linkage command strategy and haptic feedback unit to form a closed-loop iterative link.

[0018] Example 2 Please see Figure 3 As shown, for parts not described in detail in this embodiment, please refer to the description in Embodiment 1. A smart protective system for fire extinguishing protective clothing based on impact mechanics analysis is provided, including: Environmental perception module: acquires sound waves of building structure fracture, heat radiation distribution of fire scene, human impact force waveform and environmental impact waveform, and then quantifies the sound wave main frequency energy value, heat radiation intensity value, human impact force vector and impact energy value, and integrates them to generate an environmental risk profile; Threat Assessment Module: Based on the environmental risk profile, different types of data within the environmental risk profile are classified and processed. Then, the human injury risk index, collapse risk index and secondary collapse probability are calculated by combining weight coefficients. Through threat scoring and level threshold division, a collaborative threat classification table is generated. Physiological linkage unit: Real-time monitoring of firefighters' physiological status data, causal correlation analysis of physiological abnormalities and environmental risks based on the collaborative threat classification table, triggering protective actions according to threat level and response priority, and dynamically generating physiological-environment linkage instruction sets; Defense Feedback Module: Combining the collaborative threat classification table and the physiological-environment linkage instruction set, it detects high-risk locations and triggering conditions by mapping group topological coordinates to risk areas, generates targeted defense instructions and drives the tactile vibration array, and synchronously records the group protection execution log. Closed-loop optimization unit: Based on the group protection execution log, it analyzes the command response efficiency, protection effectiveness and deviation rate, and dynamically corrects the threat level threshold, linkage command strategy, tactile feedback parameters and threat index calculation accuracy in the threat classification table.

[0019] Example 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the operation mode of the intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis provided above.

[0020] Since the electronic device described in this embodiment is the electronic device used to implement the intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis in the embodiments of this application, those skilled in the art can understand the specific implementation method and various variations of the electronic device in this embodiment based on the intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis described in the embodiments of this application. Therefore, how the electronic device implements the method in the embodiments of this application will not be described in detail here. Any electronic device used by those skilled in the art to implement the intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis in the embodiments of this application falls within the scope of protection of this application.

[0021] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0022] The above description is merely a preferred embodiment of the present invention, and the scope of protection of the present invention is not limited to the above embodiments. All technical solutions falling within the scope of the present invention's concept are within the scope of protection of the present invention. It should be noted that for users of ordinary technical skills, any improvements and modifications made without departing from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A smart protection method for fire extinguishing protective clothing based on impact mechanics analysis, characterized in that, include: S1: Acquire sound waves of building structure fracture, heat radiation distribution of fire scene, human impact force waveform and environmental impact waveform, and then quantify the sound wave main frequency energy value, heat radiation intensity value, human impact force vector and falling object impact energy value, and fuse them to generate an environmental risk profile; S2: Based on the environmental risk profile, the different types of data within the environmental risk profile are classified and processed. Then, the human injury risk index, collapse risk index and secondary collapse probability are calculated by combining the weight coefficients. A collaborative threat classification table is generated by dividing the threat score and the level threshold. S3: Real-time monitoring of firefighters' physiological status data, causal correlation analysis of physiological abnormalities and environmental risks based on the collaborative threat classification table, triggering protective actions according to threat level and response priority, and dynamically generating physiological-environment linkage instruction sets; S4: Combining the collaborative threat classification table with the physiological-environment linkage instruction set, it detects high-risk locations and triggering conditions by mapping group topological coordinates to risk areas, generates targeted defense instructions and drives the tactile vibration array, and synchronously records the group protection execution log. S5: Based on the group protection execution log, analyze the command response efficiency, protection effectiveness and deviation rate, and dynamically correct the threat level threshold, linkage command strategy, tactile feedback parameters and threat index calculation accuracy in the threat classification table.

2. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 1, characterized in that, The methods for generating the environmental risk profile include: Acquire acoustic waves of building structure fracture, perform environmental noise separation and pre-emphasis processing, and then extract the characteristic frequencies of concrete fracture. The energy proportion of the frequency band corresponding to the characteristic frequency of concrete fracture is quantified to obtain the energy value of the dominant frequency of the sound wave; Real-time acquisition of fire thermal radiation distribution data, followed by data cleaning, and cluster analysis of the cleaned fire thermal radiation distribution data to obtain a set of high-temperature hotspot coordinates; The maximum radiative flux value of the high-temperature hotspot coordinate set is taken as the thermal radiation intensity value; Using a piezoelectric array sensor, the external force impact on the firefighter's body is detected in real time, and the impact force waveform is obtained. Sliding window analysis is performed on the impact force waveform to obtain the peak force and duration of the impact event. The three-axis components of the human body impact waveform from piezoelectric sensors of all parts of the human body are extracted simultaneously to obtain the overall impact force vector. The peak force, duration and overall impact force vector are integrated to form the human body impact force vector. Real-time acquisition of environmental impact waveforms and spectral analysis to obtain the impact spectrum of falling objects; The power spectral density of the impact frequency band of the falling object is integrated to obtain the total energy value, which is used as the impact energy value of the falling object. The system integrates the dominant frequency energy value of sound waves, the intensity value of thermal radiation, the vector of human body impact force, and the impact energy value of falling objects, and encapsulates them into an environmental risk profile.

3. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 2, characterized in that, The methods for classifying and processing different types of data within the environmental risk profile include: Based on environmental risk profiles, a three-level response priority is defined according to the degree of urgency, and the main frequency energy value of sound waves, thermal radiation intensity value, human body impact force vector, and falling object impact energy value are classified into the corresponding response priorities. Data with high response priority is always transmitted first, data with medium response priority is processed when high response priority data does not consume resources, and data with low response priority is processed asynchronously with minimal resource consumption.

4. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 3, characterized in that, The calculation methods for the human injury risk index, collapse risk index, and secondary collapse probability include: Based on different types of data after hierarchical processing, the peak force and duration of the human impact force vector are extracted, and a weighted fusion calculation is performed to obtain the human injury risk index. The collapse risk index is obtained by weighted fusion of thermal radiation energy value and sound wave dominant frequency energy value; The product of the impact energy of the falling object and the collapse risk index is taken as the probability of secondary collapse.

5. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 4, characterized in that, The collaborative threat classification table is generated in the following ways: Define corresponding weighting coefficients for different response priorities; Human injury risk index, collapse risk index and secondary collapse probability are used as threat indices, and the weight coefficient corresponding to the data type with the highest response priority among the data required to calculate the threat index is used as the level weight of the threat index. The threat index is combined with the corresponding level weights to calculate the threat score; Threat level thresholds are defined based on threat scores, and then threat scores are divided into different threat levels. Based on the threat level, predefined protection strategies are matched, and the threat level and protection strategy are mapped to form a collaborative threat classification table.

6. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 5, characterized in that, The generation methods of the physiological-environment linkage instruction set include: Real-time monitoring of firefighters' physiological status data; threshold analysis to determine if there are any abnormalities in the physiological status data; if the physiological status data is normal, only the data is recorded and routine monitoring is maintained. If the physiological data is abnormal, then based on the collaborative threat classification table, a causal correlation analysis is performed between the firefighter's physiological abnormalities and the environmental risk profile to classify different types of physiological abnormalities. By mapping response priorities to threat levels and combining physiological anomaly types with environmental risk matching strategies, a physiological-environment linkage instruction set is dynamically generated.

7. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 6, characterized in that, The methods for generating the targeted defense commands include: Real-time acquisition of firefighter group topology coordinates; marking corresponding risk areas according to the threat level in the collaborative threat classification table; overlaying firefighter coordinates with risk areas; marking firefighters located in risk areas as high-risk locations. The triggering conditions for mass defense response are defined by combining the probability of secondary collapse and the human injury risk index; The triggering conditions are: the probability of secondary collapse is greater than the preset collapse probability threshold and the firefighter is in a high-risk position, or the human injury risk index is greater than the preset human injury risk threshold. Once the triggering conditions are met, a targeted defense command is generated for the adjacent firefighters based on the threat level and the triggering condition type, and then sent to the adjacent firefighters.

8. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 7, characterized in that, The methods for generating the group protection execution log include: Based on targeted defense commands and a collaborative threat classification table, the parameters of the tactile vibration array are defined according to the threat level; By combining the vector direction of the risk area and the firefighter's coordinates, the activation area of ​​the vibration array is mapped to the corresponding position of the firefighter's body, and then vibration commands are sent to the tactile array equipment on the firefighter's equipment. It records triggered linkage commands and targeted defense commands, threat levels, executed actions, and tactile vibration parameters in real time, generating a group protection execution log.

9. The intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis according to claim 8, characterized in that, The methods for forming closed-loop optimization include: Based on the group protection execution log, the system classifies and statistically analyzes command response efficiency, protection effectiveness, and tactile feedback response rate, detects command failure events, and adjusts the risk level threshold in the threat classification table according to the scenario in which the command failure events occur. Based on events where the causal link between physiological abnormality types and environmental risk profiles fails, update the physiological-environment linkage instruction strategy; The mapping rules for vibration frequency, intensity, and activation area are dynamically calibrated based on the firefighters' response efficiency to vibration. By calculating the deviation rate between the human injury risk index and the actual injury, and the deviation rate between the secondary collapse probability and the actual collapse event, the calculation accuracy of the human injury risk index and the secondary collapse probability is dynamically adjusted, and the accuracy of high-temperature hotspot coordinate identification is also adjusted.

10. An intelligent protection system for fire extinguishing protective clothing based on impact mechanics analysis, implemented based on the intelligent protection method for fire extinguishing protective clothing based on impact mechanics analysis as described in any one of claims 1 to 9, characterized in that, include: Environmental perception module: acquires sound waves of building structure fracture, heat radiation distribution of fire scene, human impact force waveform and environmental impact waveform, and then quantifies the sound wave main frequency energy value, heat radiation intensity value, human impact force vector and falling object impact energy value, and integrates them to generate an environmental risk profile; Threat Assessment Module: Based on the environmental risk profile, different types of data within the environmental risk profile are classified and processed. Then, the human injury risk index, collapse risk index and secondary collapse probability are calculated by combining weight coefficients. Through threat scoring and level threshold division, a collaborative threat classification table is generated. Physiological linkage unit: Real-time monitoring of firefighters' physiological status data, causal correlation analysis of physiological abnormalities and environmental risks based on the collaborative threat classification table, triggering protective actions according to threat level and response priority, and dynamically generating physiological-environment linkage instruction sets; Defense Feedback Module: Combining the collaborative threat classification table and the physiological-environment linkage instruction set, it detects high-risk locations and triggering conditions by mapping group topological coordinates to risk areas, generates targeted defense instructions and drives the tactile vibration array, and synchronously records the group protection execution log. Closed-loop optimization unit: Based on the group protection execution log, it analyzes the command response efficiency, protection effectiveness and deviation rate, and dynamically corrects the threat level threshold, linkage command strategy, tactile feedback parameters and threat index calculation accuracy in the threat classification table.

Images