Biosensing-based fireman fire extinguishing protective clothing data acquisition method and system

Abstract

The invention belongs to the technical field of fire safety, and discloses a fireman fire extinguishing protective clothing data acquisition method and system based on biosensing, and the method comprises the steps: collecting fire-fighting environment data and personnel physiological data, and carrying out the sensing enhancement of the personnel physiological data, and obtaining enhanced physiological data; performing data decoupling on the enhanced physiological data to obtain physiological clear data; performing environment temperature calibration on the physiological clear data based on the fire-fighting environment data to obtain physiological calibration data, and performing micro-motion compensation on the physiological calibration data to obtain physiological compensation data; performing physiological evaluation on the physiological compensation data based on the constructed physiological evaluation model to obtain a health evaluation label of the firefighter, and performing corresponding safety early warning on the firefighter based on the health label; and the intelligent level and the safety performance of the fireman protective clothing are obviously improved.

Description

Technical Field

[0001] The present invention relates to the field of fire safety technology, and more specifically, to a method and system for collecting data of firefighters' firefighting protective clothing based on biosensors. Background Art

[0002] When performing firefighting tasks, firefighters usually need to enter extreme fire scenes. These environments are full of multiple dangerous factors such as high temperature, thick smoke and toxic gases. Long-term exposure to such an environment poses a great threat to the life safety of firefighters. Ensuring the health of firefighters and timely understanding the changes in their vital signs are crucial to ensuring the safety of firefighters. For this reason, biological data collection systems have emerged as the times require, becoming an important means of real-time monitoring of the physiological state of firefighters.

[0003] However, during the firefighting process, firefighters often need to enter extremely hot fire environments. High temperatures not only threaten the human body, but also bring challenges to the sensor systems in protective clothing. In particular, sensors based on traditional technologies are prone to quantum tunneling effects in high-temperature environments. The quantum tunneling effect refers to the fact that particles (such as electrons) can pass through energy barriers that they usually cannot pass through in quantum mechanics. This phenomenon can cause distortion of sensor signals or increase noise, thereby affecting the accuracy of data. In extreme environments, the physiological state of firefighters is often in drastic changes. Changes in multiple physiological parameters such as heart rate, body temperature and respiratory rate will produce complex chaotic signals, and these signals are coupled with each other and difficult to separate and process. Traditional biological data acquisition systems cannot effectively separate and extract various physiological signals, resulting in inaccurate monitoring results, which in turn affects the assessment of the physical state of firefighters. Firefighters often face extremely high temperatures and intense exercise in fires, which causes tiny relative movements between the sensor and the skin, thereby generating micro-currents. These micro-currents can cause signal distortion and affect the accuracy and reliability of the data acquisition system.

[0004] In view of this, the present invention proposes a firefighter firefighting protective clothing data collection method and system based on biosensing to solve the above problems. Summary of the invention

[0005] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for collecting data of firefighters' firefighting protective clothing based on biosensors, comprising: S1. Collect fire environment data and personnel physiological data, perform sensor enhancement on personnel physiological data, and obtain enhanced physiological data; S2, decoupling the enhanced physiological data to obtain clear physiological data; S3, performing environmental temperature calibration on the physiological clarity data based on the fire environment data to obtain physiological calibration data, and performing micro-motion compensation on the physiological calibration data to obtain physiological compensation data; S4. Perform physiological evaluation on the physiological compensation data based on the constructed physiological evaluation model, obtain the health evaluation label of the firefighter, and make corresponding safety warnings to the firefighter based on the health label; Furthermore, the fire environment data includes: ambient temperature; the personnel physiological data includes: respiratory rate, body temperature data, heart rate data and blood oxygen data.

[0006] Furthermore, the method of enhancing the sensing of the physiological data of the personnel includes: Each type of data in the physiological data is taken as the data to be enhanced, and the normalization algorithm is used to normalize the data to be enhanced to obtain the normalized data to be enhanced; a low-pass filter is preset, and low-frequency denoising is performed on the normalized data to be enhanced based on the low-pass filter to obtain denoised data; an initial enhancement scale factor is preset, and an enhancement transformation function is preset. The formula of the enhancement transformation function is: ;in, Represents the denoised data in The enhanced signal at all times, represents pi, Represents the denoised data in The value of the moment, represents the initial enhancement scale factor, represents the imaginary unit, Represents the time scale, represents infinity; for the enhanced signal under the initial enhancement scale factor, the signal amplitude and signal phase of the enhanced signal are statistically analyzed, and an enhancement evaluation function is constructed based on the signal amplitude and signal phase. The formula of the enhancement evaluation function is: ;in, represents the enhanced evaluation value, represents the signal amplitude, represents the imaginary unit, represents the signal phase, Represents the denoised signal amplitude; The enhanced evaluation value under the initial enhanced scale factor is recorded as the initial evaluation, the enhanced disturbance factor is preset, the disturbance multiple is selected by a random selection algorithm, the initial disturbance factor is disturbed based on the disturbance multiple, the product of the disturbance multiple and the enhanced disturbance factor is added to the initial enhanced scale factor to obtain the disturbance enhancement factor; the denoised data is enhanced by the disturbance enhancement factor, and the enhanced evaluation value corresponding to the disturbance enhancement factor is obtained based on the enhanced evaluation formula. When the enhanced evaluation value corresponding to the disturbance enhancement factor is greater than the initial evaluation, the disturbance enhancement factor is used as the new initial enhanced scale factor, and the enhanced evaluation value corresponding to the disturbance enhancement factor is used as the new initial evaluation. Repeat until the value of the initial evaluation no longer changes, and output the initial enhanced scale factor at this time as the optimal enhancement scale; substitute the optimal enhancement scale into the enhancement transformation function to perform an enhancement transformation on the denoised data to obtain the optimal enhanced signal. All optimal enhanced signals constitute enhanced physiological data.

[0007] Furthermore, the method of decoupling the enhanced physiological data includes: The spline analysis method is used to perform function analysis on each type of data in the enhanced physiological data to obtain the signal function of each type of data. A standard coordinate system is preset, and different signal functions are plotted in the standard coordinate system. The common intersection of all signal functions is the coupling point. The signal function is cut with the coupling point as the cutting point to obtain the function segment. The starting point and the end point of each function segment are both coupling points. For each function segment, the different signal functions in the function segment are coupled to obtain the coupling operator. For the A-th signal function, the coupling operator of other types of signal functions to the A-th signal function is calculated, and a coupling influence set is formed. Based on the coupling influence set, the coupling point at the end of each function segment is signal decoupled to obtain the decoupling value. For the coupling point of each type of data, the value at the coupling point is replaced by the decoupling value to obtain the complete data of each type of data. All complete data constitute physiological clear data.

[0008] Furthermore, the formula for coupling simulation of different signal functions in the function segment is: ;in, Representative The signal function of Coupling operators of signal-like functions, represents the coupling parameter, Represents the time scale, Represents the time span of the function segment, Representative Signal-like functions The value of the moment, Represents the d-type signal function in The value of the moment; The formula for signal decoupling at the coupling point at the end of each function segment is: ;in, Representative Decoupled values ​​of signal-like functions, represents the signal conversion function, represents the size of the coupling influence set, Representative The coupled influence set of signal-like functions, Representative A coupling operator, Represents the value of the coupling point.

[0009] Furthermore, the method of calibrating the physiological clarity data to the ambient temperature includes: Based on the constructed temperature calibration model, physiological clarity data and fire environment data are used as inputs of the temperature calibration model for calibration to obtain physiological calibration data.

[0010] Furthermore, the method of performing micro-motion compensation on the physiological calibration data includes: An energy level radius is preset, and a circle is drawn with the data collection point of each type of data in the physiological calibration data as the center and the energy level radius as the radius of the circle to obtain the energy level area. The energy level area is used as the data energy point, and an initial energy evaluation is performed on the data energy point to obtain the initial energy level. A vibration sensor is preset to collect vibration data in the energy level area, and the vibration data is aligned with the physiological calibration data in time series to obtain synchronous vibration data. Based on the synchronous vibration data, the initial energy level of each type of data in the physiological calibration data is evolved to obtain the time series energy level. Based on the time series energy level, compensation calculation is performed on each type of data in the physiological calibration data to obtain the micro-motion compensation factor. Based on the micro-motion compensation factor, micro-motion compensation is eliminated for the physiological calibration data, and the physiological compensation data is obtained by subtracting the corresponding micro-motion compensation factor from the value of the physiological calibration data at each moment.

[0011] Furthermore, the formula for performing energy level evolution on the initial energy level of each type of data in the physiological calibration data is: ;in, Representative Physiological calibration data in The temporal energy level of the moment, Representative Initial energy levels of physiological calibration data, represents the attenuation coefficient, Represents synchronous vibration data in The value of the moment, Representative Physiological calibration data in The value of the moment, represents the frequency of the synchronous vibration data, Represents the time scale, Represents the phase of the synchronous vibration data; The formula for performing compensation calculation on each type of data in the physiological calibration data is: ;in Representative Physiological calibration data in Moment micro-motion compensation factor, represents the integral weight, represents the differential weight, Represents the time derivative of the temporal energy level.

[0012] Furthermore, the physiological assessment model is constructed in the following manner: A linear regression model is used as the initial model of the physiological assessment model. E group of training data is collected in advance. The training data includes historical physiological data and historical health labels. The training data is used as a training sample set. The linear regression model is trained using the training sample set. The historical physiological data and historical health labels are used as input data of the physiological assessment model, and the predicted health labels are used as output data of the physiological assessment model. Minimizing the error between the actual historical health labels and the health labels predicted by the physiological assessment model is used as the training goal. The recall rate function is used as the loss function of the physiological assessment model. When the loss function converges, the training is stopped to obtain the physiological assessment model.

[0013] Firefighters' firefighting protective clothing data acquisition system based on biosensing, including: Data acquisition and processing module: collects fire environment data and personnel physiological data, performs sensor enhancement on personnel physiological data, and obtains enhanced physiological data; Coupling separation module: decouples enhanced physiological data to obtain clear physiological data; Interference correction module: including a temperature calibration unit and a micro-motion compensation unit. The temperature calibration unit performs environmental temperature calibration on physiological clarity data based on fire environment data to obtain physiological calibration data. The micro-motion compensation unit performs micro-motion compensation on physiological calibration data to obtain physiological compensation data. Health assessment module: Conduct physiological assessment on physiological compensation data based on the constructed physiological assessment model, obtain the health assessment label of the firefighter, and make corresponding safety warnings to the firefighter based on the health label.

[0014] The technical effects and advantages of the firefighter firefighting protective clothing data collection method and system based on biosensor of the present invention are as follows: The present invention can effectively overcome the signal attenuation problem caused by the barrier of multi-layer protective clothing by performing sensor enhancement on the physiological data of personnel, further improve the strength and stability of the sensor signal, thereby enhancing the anti-interference ability of the data, reducing sensor errors and signal interference, and ensuring the accuracy and reliability of data acquisition; performing data decoupling on the enhanced physiological data can effectively separate the independent change trend of each type of physiological signal from the complex mixed signal, so that the interference between various types of physiological signals is minimized, and the independence and clarity of the data are improved; the environmental temperature calibration model is used to calibrate the physiological clarity data, and the physiological data can be corrected in real time according to the ambient temperature, eliminating the interference of the ambient temperature change on the physiological data, so that the evaluation result is more accurate; by performing micro-motion compensation on the physiological calibration data, the signal distortion caused by the tiny displacement and vibration between the skin and the sensor is effectively reduced, ensuring the accurate collection and real-time feedback of the physiological data, and avoiding the influence of micro-motion on the signal. Through the physiological evaluation model, the system can monitor the physiological state of the firefighters in real time, and provide timely safety warnings, reduce the risk of accidents caused by health problems, and provide scientific decision-making support for the safety protection of firefighters. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the data collection method of firefighters' firefighting protective clothing based on biosensing of the present invention; Figure 2 This is a schematic diagram of the biosensor-based firefighting protective clothing data acquisition system for firefighters of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example 1 See also Figure 1 As shown, the firefighting protective clothing data collection method for firefighters based on biosensing in this embodiment includes: S1, collecting firefighting environment data and personnel physiological data, performing sensor enhancement on the personnel physiological data, and obtaining enhanced physiological data; S2, decoupling the enhanced physiological data to obtain clear physiological data; S3, performing environmental temperature calibration on the physiological clarity data based on the fire environment data to obtain physiological calibration data, and performing micro-motion compensation on the physiological calibration data to obtain physiological compensation data; S4. Perform physiological assessment on the physiological compensation data based on the constructed physiological assessment model, obtain the health assessment label of the firefighter, and make corresponding safety warnings to the firefighter based on the health label.

[0018] Firefighting environment data includes: ambient temperature; personnel physiological data includes: respiratory rate, body temperature data, heart rate data and blood oxygen data; ambient temperature is obtained through a temperature sensor installed on the outside of the firefighter's protective clothing; respiratory rate is obtained through an airflow sensor installed in the mouth and nose area of ​​the firefighter's protective clothing, body temperature data is obtained through a body temperature sensor, heart rate data is obtained through an optical heart rate sensor close to the firefighter's chest, and blood oxygen data is obtained through a blood oxygen sensor.

[0019] Ways to enhance the sensing of personnel physiological data include: Each type of data in the physiological data is taken as the data to be enhanced, and the normalization algorithm is used to normalize the data to be enhanced to obtain the normalized data to be enhanced. Common normalization algorithms include the maximum and minimum normalization algorithm and the zero score normalization algorithm; a low-pass filter is preset, and low-frequency denoising is performed on the normalized data to be enhanced based on the low-pass filter to obtain denoised data; an initial enhancement scale factor is preset, and the value range of the initial enhancement scale factor is , preset enhanced transformation function, the formula of enhanced transformation function is: ;in, Represents the denoised data in The enhanced signal at all times, represents pi, Represents the denoised data in The value of the moment, Represents the initial enhancement scale factor, which is used to control the degree of enhancement transformation. represents the imaginary unit, Represents the time scale, represents infinity; for the enhanced signal under the initial enhancement scale factor, the signal amplitude and signal phase of the enhanced signal are statistically analyzed, and an enhancement evaluation function is constructed based on the signal amplitude and signal phase. The formula of the enhancement evaluation function is: ;in, represents the enhanced evaluation value, represents the signal amplitude, represents the signal phase, represents the denoised signal amplitude (signal amplitude of denoised data); Record the enhanced evaluation value under the initial enhanced scale factor as the initial evaluation, preset the enhanced disturbance factor, select the disturbance multiple by a random selection algorithm, disturb the initial disturbance factor based on the disturbance multiple, increase the product of the disturbance multiple and the enhanced disturbance factor to the initial enhanced scale factor, and obtain the disturbance enhancement factor; perform an enhancement transformation on the denoised data with the disturbance enhancement factor, and obtain the enhanced evaluation value corresponding to the disturbance enhancement factor based on the enhanced evaluation formula; when the enhanced evaluation value corresponding to the disturbance enhancement factor is greater than the initial evaluation, use the disturbance enhancement factor as the new initial enhanced scale factor, and use the enhanced evaluation value corresponding to the disturbance enhancement factor as the new initial evaluation, repeat until the value of the initial evaluation no longer changes, and output the initial enhanced scale factor at this time as the optimal enhancement scale; substitute the optimal enhancement scale into the enhancement transformation function to perform an enhancement transformation on the denoised data to obtain the optimal enhanced signal, and all optimal enhanced signals constitute enhanced physiological data; The sensor signal is attenuated due to the obstruction of multiple layers of protective clothing. By sensing the physiological data of the personnel, the strength of the sensor signal is restored, the robustness of the sensor signal is enhanced, the data is made more resistant to interference, and the accuracy and reliability of the data are improved.

[0020] Ways to decouple data from augmented physiological data include: The spline analysis method is used to perform function analysis on each type of data in the enhanced physiological data to obtain the signal function of each type of data. The standard coordinate system is preset, and different signal functions are plotted into the standard coordinate system. The common intersection of all signal functions is the coupling point. The signal function is cut with the coupling point as the cutting point of the signal function to obtain the function segment. The starting point and the end point of each function segment are both coupling points. For each function segment, the different signal functions in the function segment are coupled and simulated. The formula for coupling simulation is: ;in, Representative The signal function of Coupling operators of signal-like functions, represents the coupling parameter, Represents the time scale, Represents the time span of the function segment, Representative Signal-like functions The value of the moment, Represents the d-type signal function in The value at the moment; for the A-th signal function, the coupling operators of other types of signal functions to the A-th signal function are calculated, and a coupling influence set is formed. Based on the coupling influence set, the signal decoupling is performed on the coupling point at the end of each function segment. The formula for signal decoupling is: ;in, Representative Decoupled values ​​of signal-like functions, Represents the signal conversion function. Common signal conversion functions include the Hilbert transform function. represents the size of the coupling influence set, Representative The coupled influence set of signal-like functions, Representative A coupling operator, Represents the value of the coupling point; for each type of data at the coupling point, the value at the coupling point is replaced by the decoupling value to obtain the complete data of each type of data, and all the complete data constitute the physiological clear data; By decoupling the enhanced physiological data, these complex chaotic signals can be effectively separated, making the changing trend of each type of physiological signal clearer and independent, significantly improving the accuracy and efficiency of signal processing, ensuring the reliability of monitoring data, and thus improving the accuracy of firefighters' physical condition assessment.

[0021] Ways to calibrate physiological clarity data to ambient temperature include: Collect historical physiological data, historical calibration data and historical fire environment data of group B, the data type of the historical physiological data is consistent with that of the physiological data of the personnel, and the historical calibration data is based on data obtained by technical personnel in this field through corresponding experiments; based on the historical physiological data, historical calibration data and historical fire environment data, use the historical physiological data and historical fire environment data as input of the temperature calibration model, use the predicted physiological calibration data as output of the temperature calibration model, use the actual historical calibration data as the prediction target of the temperature calibration model to perform model training, and construct a temperature calibration model, the temperature calibration model is a ridge regression model, the target loss function of the temperature calibration model is a mean square error function, and minimize the value of the target loss function as the training target, and obtain a temperature calibration model with the minimum value of the target loss function; Based on the constructed temperature calibration model, physiological clarity data and fire environment data are used as inputs of the temperature calibration model for calibration to obtain physiological calibration data.

[0022] Ways to compensate for micro-motion in physiological calibration data include: The energy level radius is preset, and the data collection point of each type of data in the physiological calibration data is used as the center. The energy level radius is used as the radius of the circle to draw a circle to obtain the energy level area. The energy level area is used as the data energy point, and the data energy point is initially evaluated for energy. The formula for initial energy evaluation is: ;in, Representative Initial energy levels of physiological calibration data, represents Planck's constant, The effective mass of electrons representing the energy level region is an intrinsic property of the material and is obtained through the Hall effect experiment. Represents the energy level radius; a vibration sensor is preset to collect vibration data in the energy level area, and the vibration data is aligned with the physiological calibration data in time series to obtain synchronous vibration data; based on the synchronous vibration data, the initial energy level of each type of data in the physiological calibration data is evolved, and the formula for energy level evolution is: ;in, Representative Physiological calibration data in The temporal energy level of the moment, Representative Initial energy levels of physiological calibration data, Represents the attenuation coefficient, which is used to simulate the signal attenuation caused by micro-motion. Represents synchronous vibration data in The value of the moment, Representative Physiological calibration data in The value of the moment, represents the frequency of the synchronous vibration data, Represents the time scale, Represents the phase of the synchronous vibration data; based on the time series energy level, each type of data in the physiological calibration data is compensated and calculated. The formula for the compensation calculation is: ;in Representative Physiological calibration data in Moment micro-motion compensation factor, Represents the integral weight, which is used to balance the proportion of the integral term to the micro-motion compensation factor. Represents the differential weight, which is used to balance the proportion of the differential term to the micro-motion compensation factor. Represents the derivative of the time series energy level with respect to time, indicating the rate at which the time series energy level changes with time, and is used to capture rapidly changing signal components; based on the micro-motion compensation factor, the physiological calibration data is subjected to micro-motion compensation elimination, and the physiological compensation data is obtained by subtracting the corresponding micro-motion compensation factor from the value of the physiological calibration data at each moment; By performing micro-motion compensation on the physiological calibration data, the signal distortion caused by micro-motion current is effectively reduced, and the signal deviation caused by the tiny displacement between the skin and the sensor is accurately identified and compensated, thereby improving the accuracy and stability of the physiological data, quickly responding to and correcting signal errors caused by micro-motion, reducing delays and errors, and ensuring that the sensor can still stably output reliable data in extreme environments.

[0023] The physiological assessment model is constructed in the following ways: A linear regression model is used as the initial model of the physiological assessment model, and E groups of training data are collected in advance. The training data includes historical physiological data and historical health labels. The training data is used as a training sample set. The linear regression model is trained using the training sample set. The historical physiological data and historical health labels are used as input data of the physiological assessment model, and the predicted health labels are used as output data of the physiological assessment model. Minimizing the error between the actual historical health labels and the health labels predicted by the physiological assessment model is used as the training goal, and the recall function is used as the loss function of the physiological assessment model. When the loss function reaches convergence, the training is stopped to obtain the physiological assessment model. Based on the trained physiological assessment model, a physiological assessment is performed on the physiological compensation data to obtain the firefighter's health assessment label, and corresponding safety warnings are given to the firefighter based on the health label.

[0024] This embodiment can effectively overcome the signal attenuation problem caused by the barrier of multi-layer protective clothing by performing sensor enhancement on the physiological data of personnel, further improve the strength and stability of the sensor signal, thereby enhancing the anti-interference ability of the data, reducing sensor errors and signal interference, and ensuring the accuracy and reliability of data acquisition; decoupling the enhanced physiological data can effectively separate the independent change trend of each type of physiological signal from the complex mixed signal, minimize the interference between various types of physiological signals, and improve the independence and clarity of the data; the temperature calibration model is used to calibrate the physiological clarity data to the ambient temperature, and the physiological data can be corrected in real time according to the ambient temperature, eliminating the interference of the ambient temperature change on the physiological data, so that the evaluation result is more accurate; by performing micro-motion compensation on the physiological calibration data, the signal distortion caused by the tiny displacement and vibration between the skin and the sensor is effectively reduced, ensuring the accurate collection and real-time feedback of the physiological data, and avoiding the influence of micro-motion on the signal. Through the physiological evaluation model, the system can monitor the physiological state of the firefighters in real time, and provide timely safety warnings, reduce the risk of accidents caused by health problems, and provide scientific decision-making support for the safety protection of firefighters.

[0025] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and a firefighter firefighting protective clothing data acquisition system based on biosensor is provided, including: Data acquisition and processing module: collects fire environment data and personnel physiological data, performs sensor enhancement on personnel physiological data, and obtains enhanced physiological data; Coupling separation module: decouples enhanced physiological data to obtain clear physiological data; Interference correction module: including a temperature calibration unit and a micro-motion compensation unit. The temperature calibration unit performs environmental temperature calibration on physiological clarity data based on fire environment data to obtain physiological calibration data. The micro-motion compensation unit performs micro-motion compensation on physiological calibration data to obtain physiological compensation data. Health assessment module: Perform physiological assessment on physiological compensation data based on the constructed physiological assessment model, obtain the health assessment label of the firefighter, and make corresponding safety warnings to the firefighter based on the health label; The modules are connected to each other via wired and / or wireless means to achieve data transmission between modules.

[0026] 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, the operation mode of the above-mentioned biosensor-based firefighting protective clothing data collection method for firefighters is implemented.

[0027] Since the electronic device introduced in this embodiment is an electronic device used to implement the firefighter firefighting protective clothing data collection method based on biosensors in the embodiment of this application, based on the firefighter firefighting protective clothing data collection method based on biosensors introduced in the embodiment of this application, the technical personnel of this field can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as the technical personnel of this field implement the electronic device used by the firefighter firefighting protective clothing data collection method based on biosensors in the embodiment of this application, it belongs to the scope of protection of this application.

[0028] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0029] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A firefighter firefighting protective clothing data collection method based on biosensing, characterized in that: include: S1. Collect fire environment data and personnel physiological data, perform sensor enhancement on personnel physiological data, and obtain enhanced physiological data; S2, decoupling the enhanced physiological data to obtain clear physiological data; S3, performing environmental temperature calibration on the physiological clarity data based on the fire environment data to obtain physiological calibration data, and performing micro-motion compensation on the physiological calibration data to obtain physiological compensation data; S4. Perform physiological assessment on the physiological compensation data based on the constructed physiological assessment model, obtain the health assessment label of the firefighter, and make corresponding safety warnings to the firefighter based on the health label.

2. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 1 is characterized in that: The fire environment data includes: ambient temperature; the personnel physiological data includes: respiratory rate, body temperature data, heart rate data and blood oxygen data.

3. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 2 is characterized in that: The method of enhancing the sensing of the physiological data of the personnel includes: Each type of data in the physiological data is taken as the data to be enhanced, and the normalization algorithm is used to normalize the data to be enhanced to obtain the normalized data to be enhanced; a low-pass filter is preset, and low-frequency denoising is performed on the normalized data to be enhanced based on the low-pass filter to obtain denoised data; an initial enhancement scale factor is preset, and an enhancement transformation function is preset. The formula of the enhancement transformation function is: ;in, Represents the denoised data in The enhanced signal at all times, represents pi, Represents the denoised data in The value of the moment, represents the initial enhancement scale factor, represents the imaginary unit, Represents the time scale, represents infinity; for the enhanced signal under the initial enhancement scale factor, the signal amplitude and signal phase of the enhanced signal are statistically analyzed, and an enhancement evaluation function is constructed based on the signal amplitude and signal phase. The formula of the enhancement evaluation function is: ;in, represents the enhanced evaluation value, represents the signal amplitude, represents the signal phase, Represents the denoised signal amplitude; The enhanced evaluation value under the initial enhanced scale factor is recorded as the initial evaluation, the enhanced disturbance factor is preset, the disturbance multiple is selected by a random selection algorithm, the initial disturbance factor is disturbed based on the disturbance multiple, the product of the disturbance multiple and the enhanced disturbance factor is added to the initial enhanced scale factor to obtain the disturbance enhancement factor; the denoised data is enhanced by the disturbance enhancement factor, and the enhanced evaluation value corresponding to the disturbance enhancement factor is obtained based on the enhanced evaluation formula. When the enhanced evaluation value corresponding to the disturbance enhancement factor is greater than the initial evaluation, the disturbance enhancement factor is used as the new initial enhanced scale factor, and the enhanced evaluation value corresponding to the disturbance enhancement factor is used as the new initial evaluation. Repeat until the value of the initial evaluation no longer changes, and output the initial enhanced scale factor at this time as the optimal enhancement scale; substitute the optimal enhancement scale into the enhancement transformation function to perform an enhancement transformation on the denoised data to obtain the optimal enhanced signal. All optimal enhanced signals constitute enhanced physiological data.

4. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 3 is characterized in that: The method of decoupling the enhanced physiological data includes: The spline analysis method is used to perform function analysis on each type of data in the enhanced physiological data to obtain the signal function of each type of data. A standard coordinate system is preset, and different signal functions are plotted in the standard coordinate system. The common intersection of all signal functions is the coupling point. The signal function is cut with the coupling point as the cutting point to obtain the function segment. The starting point and the end point of each function segment are both coupling points. For each function segment, the different signal functions in the function segment are coupled to obtain the coupling operator. For the A-th signal function, the coupling operator of other types of signal functions to the A-th signal function is calculated, and a coupling influence set is formed. Based on the coupling influence set, the coupling point at the end of each function segment is signal decoupled to obtain the decoupling value. For the coupling point of each type of data, the value at the coupling point is replaced by the decoupling value to obtain the complete data of each type of data. All complete data constitute physiological clear data.

5. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 4 is characterized in that: The formula for coupling simulation of different signal functions in the function segment is: ;in, Representative The signal function of Coupling operators of signal-like functions, represents the coupling parameter, Represents the time scale, Represents the time span of the function segment, Representative Signal-like functions The value of the moment, Represents the d-type signal function in The value of the moment; The formula for signal decoupling at the coupling point at the end of each function segment is: ;in, Representative Decoupled values ​​of signal-like functions, represents the signal conversion function, represents the size of the coupling influence set, Representative The coupled influence set of signal-like functions, Representative A coupling operator, Represents the value of the coupling point.

6. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 5 is characterized in that: The method of calibrating the physiological clarity data to the ambient temperature includes: Based on the constructed temperature calibration model, physiological clarity data and fire environment data are used as inputs of the temperature calibration model for calibration to obtain physiological calibration data.

7. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 6 is characterized in that: The method of performing micro-motion compensation on physiological calibration data includes: An energy level radius is preset, and a circle is drawn with the data collection point of each type of data in the physiological calibration data as the center and the energy level radius as the radius of the circle to obtain the energy level area. The energy level area is used as the data energy point, and an initial energy evaluation is performed on the data energy point to obtain the initial energy level. A vibration sensor is preset to collect vibration data in the energy level area, and the vibration data is aligned with the physiological calibration data in time series to obtain synchronous vibration data. Based on the synchronous vibration data, the initial energy level of each type of data in the physiological calibration data is evolved to obtain the time series energy level. Based on the time series energy level, compensation calculation is performed on each type of data in the physiological calibration data to obtain the micro-motion compensation factor. Based on the micro-motion compensation factor, micro-motion compensation is eliminated for the physiological calibration data, and the physiological compensation data is obtained by subtracting the corresponding micro-motion compensation factor from the value of the physiological calibration data at each moment.

8. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 7 is characterized in that: The formula for performing energy level evolution on the initial energy level of each type of data in the physiological calibration data is: ;in, Representative Physiological calibration data in The temporal energy level of the moment, Representative Initial energy levels of physiological calibration data, represents the attenuation coefficient, Represents synchronous vibration data in The value of the moment, Representative Physiological calibration data in The value of the moment, represents the frequency of the synchronous vibration data, Represents the time scale, Represents the phase of the synchronous vibration data; The formula for performing compensation calculation on each type of data in the physiological calibration data is: ;in Representative Physiological calibration data in Moment micro-motion compensation factor, represents the integral weight, represents the differential weight, Represents the time derivative of the temporal energy level.

9. The method for collecting data of firefighters' firefighting protective clothing based on biosensing according to claim 8 is characterized in that: The physiological assessment model is constructed in the following manner: A linear regression model is used as the initial model of the physiological assessment model. E group of training data is collected in advance. The training data includes historical physiological data and historical health labels. The training data is used as a training sample set. The linear regression model is trained using the training sample set. The historical physiological data and historical health labels are used as input data of the physiological assessment model, and the predicted health labels are used as output data of the physiological assessment model. Minimizing the error between the actual historical health labels and the health labels predicted by the physiological assessment model is used as the training goal. The recall rate function is used as the loss function of the physiological assessment model. When the loss function converges, the training is stopped to obtain the physiological assessment model.

10. A firefighter firefighting protective clothing data acquisition system based on biosensors, which is used to implement the firefighter firefighting protective clothing data acquisition method based on biosensors as described in any one of claims 1 to 9, characterized in that: include: Data acquisition and processing module: collects fire environment data and personnel physiological data, performs sensor enhancement on personnel physiological data, and obtains enhanced physiological data; Coupling separation module: decouples enhanced physiological data to obtain clear physiological data; Interference correction module: including a temperature calibration unit and a micro-motion compensation unit. The temperature calibration unit performs environmental temperature calibration on physiological clarity data based on fire environment data to obtain physiological calibration data. The micro-motion compensation unit performs micro-motion compensation on physiological calibration data to obtain physiological compensation data. Health assessment module: Conduct physiological assessment on physiological compensation data based on the constructed physiological assessment model, obtain the health assessment label of the firefighter, and make corresponding safety warnings to the firefighter based on the health label.

Images