Wearable sensor based on printed carbon material

Abstract

The invention provides a wearable sensor based on a printed carbon material, and relates to the technical field of motion monitoring. Comprising a signal calibration module, a deformation identification module, a feature analysis module, a mode analysis module and a state monitoring module. According to the method, by means of dynamic environment compensation and multi-dimensional feature fusion, the stability of a signal baseline is enhanced, residual drift errors caused by temperature and humidity gradient mutation are reduced, the anti-interference capacity in a complex environment is improved, morphological correlation analysis of a deformation response curve and motion artifacts is adopted, the separation precision of physiological signals and interference components is optimized, and the reliability of the system is improved. The recognition accuracy of deformation characteristics is enhanced, the dynamic change characteristics of deformation signals are quantified through cooperative calculation of multi-dimensional characteristics, the decoupling efficiency of the breathing depth and the exercise intensity is improved, accurate capture of breathing parameters in a dynamic scene is achieved, and the recognition accuracy of the breathing mode characteristics and real-time fluctuation parameters is improved by combining the evaluation of the breathing mode characteristics and the real-time fluctuation parameters. And the accuracy of motion state recognition and monitoring is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of motion monitoring, and in particular to a wearable sensor based on printed carbon materials. Background Art

[0002] The field of motion monitoring technology encompasses a technology system for dynamically collecting and calculating human motion and physiological parameters using wearable devices. The core of this technology involves extracting effective characteristic parameters from raw biomechanical signals, including acceleration, angular velocity, pressure distribution, and electromyographic signals. This technology then uses time-frequency analysis and pattern recognition algorithms to implement gait analysis, heart rate variability monitoring, or respiratory rhythm estimation. This includes motion tracking using an inertial measurement unit combined with a Kalman filter, and analyzing physiological parameters using photoplethysmography combined with adaptive threshold detection.

[0003] Among them, a wearable sensor based on printed carbon material refers to a monitoring system that integrates a multimodal signal processing link. Its core function is to map the dynamic physical signals output by the carbon material sensing unit into human physiological parameters, covering multiple links from signal acquisition to parameter output. First, the deformation signals of different parts are synchronously acquired through a multi-channel parallel acquisition mechanism, and the adaptive baseline calibration technology is used to eliminate the signal drift caused by changes in ambient temperature and humidity. Secondly, the original signal is jointly analyzed in the time domain and frequency domain to extract characteristic waveforms related to heart rate, respiratory rhythm and muscle contraction intensity. Subsequently, a multi-source data fusion strategy is adopted to establish a correlation model between different sensing channels, and motion artifact interference is reduced through feature weight distribution. Finally, based on the dynamic threshold library trained with historical data, the matching mapping of physical signals and target physiological parameters is realized, including heart rate variability, apnea index, and muscle fatigue, to complete non-invasive continuous monitoring.

[0004] The traditional wearable sensor calibration process uses a fixed threshold or linear compensation model, which cannot adapt to sudden changes in temperature and humidity gradients or nonlinear drift scenarios in real time, resulting in incomplete signal baseline correction and residual drift errors in high temperature and high humidity environments. The joint analysis of time and frequency domains focuses on the energy distribution of frequency bands and ignores the dynamic correlation of deformation signals in time domain characteristics such as acceleration and amplitude. It is difficult to distinguish between the time domain overlapping signals of respiratory rhythm and limb movement, resulting in deviations in the estimation of respiratory cycle, which limits the monitoring stability and accuracy of existing technologies in dynamic environments and complex motion scenarios. Summary of the Invention

[0005] In order to solve the technical problems existing in the prior art, an embodiment of the present invention provides a wearable sensor based on printed carbon materials. The technical solution is as follows:

[0006] A wearable sensor based on printed carbon material is provided. The sensor includes: a signal calibration module that collects electrical signals from a carbon material sensor, obtains real-time data from temperature and humidity nodes on the sensor surface, and constructs an electrical signal compensation parameter table by analyzing the impact of temperature and humidity changes on the electrical signals; a deformation recognition module that uses the electrical signal compensation parameter table to perform baseline correction on the electrical signals, identifies and separates deformation signals from the electrical signals by analyzing the relationship between carbon material stress and deformation response curves, and generates a deformation signal dataset; a feature analysis module that extracts acceleration, amplitude, and deformation frequency of the deformation signal in a continuous time window based on the deformation signal dataset, calculates the transition smoothness of the deformation curve, and generates deformation feature parameters; a pattern analysis module that uses the deformation feature parameters to mark abnormal fluctuation segments based on deformation frequency and smoothness parameters, separates motion interference signals, compares the deformation features with known breathing patterns, extracts breathing cycle and breathing depth data, and generates breathing rhythm parameters; and a state monitoring module that inputs the breathing rhythm parameters, assesses the user's exercise intensity and breathing rhythm regularity based on the fluctuation and amplitude stability of the breathing cycle, identifies the user's exercise state, and generates an exercise state classification label.

[0007] Optionally, the electrical signal compensation parameter table specifically includes the temperature and humidity gradient change rate, the compensation weight factor, and the hysteresis effect correction amount; the deformation signal data set includes the deformation response amplitude, the stress distribution time series, and the baseline offset correction amount; the deformation characteristic parameters specifically refer to the deformation acceleration value, the deformation frequency fluctuation rate, and the transition smoothness; the respiratory rhythm parameters include the respiratory cycle time series, the amplitude stability coefficient, and the motion artifact separation threshold; and the motion state classification label specifically includes motion intensity data, motion state matching degree, and state identification label.

[0008] Optionally, the signal calibration module includes: a data acquisition submodule that collects electrical signals from carbon material sensors, obtains real-time temperature and humidity data of temperature and humidity nodes on the sensor surface in real time, and generates a sensor data set; a gradient analysis submodule that is based on the sensor data set, calculates the spatial gradient change rate of adjacent temperature and humidity nodes, analyzes the fluctuation amplitude and duration of temperature and humidity data over time, and generates a temperature and humidity gradient fluctuation rate; a compensation construction submodule that calls the temperature and humidity gradient fluctuation rate, analyzes the impact of temperature and humidity changes on electrical signals, identifies the baseline drift mapping relationship between temperature and humidity and electrical signals, and generates an electrical signal compensation parameter table.

[0009] Optionally, the specific formula for the influence of the temperature and humidity changes on the electrical signal is:

[0010]

[0011] Calculate the correlation coefficient between temperature and humidity and electrical signals, and identify the baseline drift mapping relationship between temperature and humidity and electrical signals; where R XRepresents the correlation coefficient of the impact of temperature and humidity changes on electrical signals, X i' Represents the temperature or humidity value measured at the i'th time point, Represents the average value of temperature or humidity data at all time points, V i " represents the electrical signal value measured at the i'th time point, represents the average value of the electrical signal data at all time points, i' represents the i'th time point during the data acquisition process, and n' represents the total number of time sampling points.

[0012] Optionally, the deformation identification module includes: a baseline correction submodule calling the electrical signal compensation parameter table, correcting the original electrical signal, calculating the compensated electrical signal amplitude and timing characteristics, and generating a corrected electrical signal waveform; a response analysis submodule analyzing the correspondence between the carbon material stress and deformation response curve based on the corrected electrical signal waveform, analyzing the influence of the carbon material deformation on the electrical signal, calculating the sensitivity parameter of the electrical signal to the deformation, and generating a deformation response characteristic parameter; a signal separation submodule calling the deformation response characteristic parameter, identifying and separating the deformation signal in the electrical signal, and generating a deformation signal data set.

[0013] Optionally, the specific formula for the effect of the deformation of the carbon deposition material on the electrical signal is:

[0014]

[0015] Calculate the sensitivity parameter of the electrical signal to deformation; where SD represents the sensitivity parameter of the electrical signal to deformation, VDc q represents the measured value of the corrected electrical signal corresponding to the qth deformation variable, VDc0 represents the initial value of the corrected electrical signal when the deformation variable is zero, Xε q represents the qth deformation variable, Xε0 represents the deformation variable without external force, p represents the number of data sampling points, and q represents the sequence number of the currently calculated deformation variable.

[0016] Optionally, the feature analysis module includes: an acceleration calculation submodule calling the deformation signal data set, calculating the changing speed of the deformation signal in the continuous time window, identifying the deformation acceleration, and generating a deformation acceleration value; an amplitude frequency identification submodule using the deformation acceleration value, recording the fluctuation amplitude of the deformation signal, calculating the deformation frequency, and generating a deformation amplitude frequency parameter; a smoothness calculation submodule calling the deformation amplitude frequency parameter, analyzing the transition smoothness of the deformation curve, calculating the smoothness score, and combining the acceleration, amplitude, and deformation frequency of the signal to generate deformation feature parameters.

[0017] Optionally, the specific formula for calculating the smoothness score is:

[0018]

[0019] Calculate the smoothness score; where S ∈ represents the smoothness score, J ∈i represents the rate of change of the deformation signal at the i-th time point, represents the mean value of the deformation signal change rate, N represents the total number of time points in the deformation signal dataset, a ∈i represents the deformation acceleration at the i-th time point, represents the mean value of deformation acceleration, f ∈ represents the deformation signal frequency, Represents the mean value of the deformation signal frequency, and i represents the time point index of the current calculation.

[0020] Optionally, the pattern analysis module includes: an abnormal marking submodule calls the deformation feature parameters, uses the deformation frequency fluctuation rate and smoothness score, and calculates the statistical characteristics of the deformation frequency to identify and mark the abnormal fluctuation segment, and generate an abnormal fluctuation interval mark; a signal screening submodule extracts the amplitude data in the deformation signal based on the abnormal fluctuation interval mark, compares the amplitude threshold interval in the preset motion interference database, screens and separates the motion interference signal, and generates an interference signal separation result; a breathing extraction submodule calls the interference signal separation result, compares the processed deformation signal with the breathing pattern in the breathing pattern database, identifies the breathing pattern, and records the corresponding breathing cycle and breathing depth data to generate a breathing rhythm parameter.

[0021] Optionally, the state monitoring module includes: a fluctuation assessment submodule calling the respiratory rhythm parameters, extracting respiratory cycle timing data, evaluating the changing trend and volatility of the respiratory cycle, and generating a respiratory cycle fluctuation coefficient; an intensity analysis submodule extracting respiratory amplitude stability data based on the respiratory cycle fluctuation coefficient, identifying the user's exercise intensity, and generating an exercise intensity index; a state classification submodule calling the exercise intensity index, combining the changing characteristics of the respiratory cycle, and comparing with the data characteristics of multiple exercise states in a preset exercise pattern database to identify the user's exercise state and generate an exercise state classification label.

[0022] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0023] Through dynamic environment compensation and multi-dimensional feature fusion, the signal baseline stability is enhanced, the residual drift error caused by sudden changes in temperature and humidity gradients is reduced, and the anti-interference ability in complex environments is improved. The morphological correlation analysis of deformation response curves and motion artifacts is used to optimize the separation accuracy of physiological signals and interference components, and enhance the recognition accuracy of deformation features. The collaborative calculation of multi-dimensional features is used to quantify the dynamic change characteristics of deformation signals, improve the decoupling efficiency of breathing depth and exercise intensity, and achieve accurate capture of respiratory parameters in dynamic scenes. Combined with the evaluation of breathing pattern characteristics and real-time fluctuation parameters, the accuracy of motion state recognition and monitoring is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 It is a flow chart of the sensor of the present invention;

[0026] Figure 2 Schematic diagram of the sensor framework of the present invention;

[0027] Figure 3 This is a flow chart of the signal calibration module of the present invention;

[0028] Figure 4 This is a flow chart of the deformation recognition module of the present invention;

[0029] Figure 5 This is a flow chart of the feature analysis module of the present invention;

[0030] Figure 6 This is a flow chart of the pattern analysis module of the present invention;

[0031] Figure 7 This is a flow chart of the status monitoring module of the present invention. DETAILED DESCRIPTION

[0032] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0033] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0034] In the embodiments of the present invention, sometimes a subscript such as W1 may be written as a non-subscript such as W1. When the difference is not emphasized, the meanings to be expressed are the same.

[0035] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0036] The embodiment of the present invention provides a wearable sensor based on printed carbon materials, please refer to Figures 1 to 2 The present invention provides a wearable sensor based on printed carbon material, comprising: a signal calibration module that collects electrical signals from a carbon material sensor, obtains real-time data of temperature and humidity nodes on the sensor surface, and constructs an electrical signal compensation parameter table by analyzing the influence of temperature and humidity changes on the electrical signals; a deformation recognition module that calls the electrical signal compensation parameter table, performs baseline correction on the electrical signals, identifies and separates deformation signals from the electrical signals by analyzing the relationship between the stress and deformation response curve of the carbon material, and generates a deformation signal data set; a feature analysis module that extracts the acceleration, amplitude, and deformation frequency of the deformation signal in a continuous time window based on the deformation signal data set, calculates the transition smoothness of the deformation curve, and generates deformation feature parameters; a pattern analysis module that calls the deformation feature parameters, marks abnormal fluctuation segments based on deformation frequency and smoothness parameters, separates motion interference signals, compares the deformation features with known breathing patterns, extracts breathing cycle and breathing depth data, and generates breathing rhythm parameters; a state monitoring module that inputs the breathing rhythm parameters, evaluates the user's exercise intensity and the regularity of the breathing rhythm based on the fluctuation and amplitude stability of the breathing cycle, identifies the user's exercise state, and generates an exercise state classification label. The electrical signal compensation parameter table specifically includes the temperature and humidity gradient change rate, compensation weight factor, and hysteresis effect correction amount. The deformation signal data set includes the deformation response amplitude, stress distribution time series, and baseline offset correction amount. The deformation characteristic parameters specifically refer to the deformation acceleration value, deformation frequency fluctuation rate, and transition smoothness. The respiratory rhythm parameters include respiratory cycle time series, amplitude stability coefficient, and motion artifact separation threshold. The motion state classification label specifically includes motion intensity data, motion state matching degree, and state identification label.

[0037] See also Figure 2 and Figure 3 , the signal calibration module includes:

[0038] The data acquisition submodule collects the electrical signals of the carbon material sensor, obtains the real-time temperature and humidity data of the temperature and humidity nodes on the sensor surface in real time, and generates a sensor data set;

[0039] The data acquisition submodule collects electrical signals from carbon material sensors. First, multiple carbon material sensors are deployed within the monitoring area. Each sensor has an independent electrical signal acquisition unit and temperature and humidity sensing terminal. To ensure data integrity, the placement of sensors must take environmental factors into consideration. For example, in areas with drastic temperature and humidity fluctuations, more sensors should be deployed, while in areas with more stable environments, the number of sensors should be reduced appropriately to optimize data acquisition efficiency and cost. The sensor electrical signal acquisition unit uses a high-precision analog-to-digital conversion chip to convert the sensor's resistance signal into a voltage signal. The main control unit periodically reads the data and adds a timestamp to each sampling point to ensure data timing. Once acquired, the data must be stored in an EEPROM or SD card to prevent data loss. To ensure real-time data transmission, the system uses wireless communication technologies such as LRa or Wi-Fi to periodically send data to the server. On the server side, data is stored in CSV format. Each row of data contains fields such as a timestamp, electrical signal value, temperature value, and humidity value. The server then parses the raw voltage output of the sensor and calculates the temperature value based on the calibration coefficient provided by the sensor. The temperature calculation method is as follows: T = A·V + B.

[0040] Where T is the currently measured temperature (°C), V is the voltage output by the sensor (V), and A and B are the factory calibration coefficients of the sensor.

[0041] Calculation example: Assuming the sensor's factory calibration coefficients are A = 50, B = -25, and the currently collected voltage signal is V = 0.7V, the calculated temperature is: T = 50 × 0.7 - 25 = 10°C;

[0042] After storage and analysis, all collected data enters the data preprocessing phase, including abnormal data removal and data interpolation to ensure the integrity of the sensor data set. Based on the sensor data set, the gradient analysis submodule calculates the spatial gradient change rate of adjacent temperature and humidity nodes, analyzes the fluctuation amplitude and duration of temperature and humidity data over time, and generates the temperature and humidity gradient fluctuation rate;

[0043] The gradient analysis submodule calculates the temperature and humidity gradient change rate of adjacent sensors at the same time point based on the sensor data set. First, the data of all measurement points are sorted in chronological order to construct a time series data matrix. Then, a spatial temperature and humidity distribution matrix is established based on the location of the sensor layout. Each matrix element represents the temperature or humidity value at a specific location. When calculating the spatial temperature and humidity gradient, the finite difference method is used to calculate the data of adjacent measurement points. Taking the temperature gradient as an example, the temperature change rate between adjacent measurement points is calculated as follows:

[0044]

[0045] Among them, G Tis the temperature gradient (°C / m), T2 is the temperature measurement value of the adjacent sensor (°C), T1 is the temperature measurement value of the previous sensor (°C), and d is the distance between the two sensors (m).

[0046] Calculation example: Assuming that the temperature measurement values of adjacent sensors in a certain area are T2 = 30°C and T1 = 25°C, and the sensor spacing d = 2m, the calculated temperature gradient is:

[0047] In addition, to analyze the temporal rate of change of temperature and humidity, a sliding window technique is used on the time series. The window length is set to 10 minutes, the difference between the maximum and minimum temperature and humidity values within the window is calculated, and the duration of the change exceeding the threshold is counted. For example, when the temperature change exceeds 2°C and lasts for more than 5 minutes, the time period is marked as a significant temperature fluctuation area. Finally, the gradient analysis submodule combines the spatial gradient and the temporal volatility to generate a temperature and humidity gradient volatility data table.

[0048] The compensation construction submodule calls the temperature and humidity gradient fluctuation rate, analyzes the impact of temperature and humidity changes on electrical signals, identifies the mapping relationship between temperature and humidity and baseline drift of electrical signals, and generates an electrical signal compensation parameter table;

[0049] The specific formula for the effect of temperature and humidity changes on electrical signals is:

[0050]

[0051] Calculate the correlation coefficient between temperature and humidity and electrical signals, and identify the baseline drift mapping relationship between temperature and humidity and electrical signals;

[0052] Among them, R X Represents the correlation coefficient of the impact of temperature and humidity changes on electrical signals, X i' Represents the temperature or humidity value measured at the i'th time point, Represents the average value of temperature or humidity data at all time points, V i " represents the electrical signal value measured at the i'th time point, represents the average value of the electrical signal data at all time points, i' represents the i'th time point during the data acquisition process, and n' represents the number of time points during the data acquisition process.

[0053] formula:

[0054]

[0055] Detailed explanation of the formula and the formula calculation process: The formula is used to calculate the correlation coefficient of the impact of temperature and humidity changes on the electrical signal. The result is used to determine the degree of influence of temperature or humidity on the sensor's electrical signal;

[0056] Parameter meaning and setting value: Xi' is the temperature (°C) or humidity (%RH) measured at the i'th time point, assuming that temperature is selected as the parameter, 24.1°C, 24.3°C, 24.5°C, 24.7°C, 25.0°C;

[0057] is the average value of temperature data at all time points, V i ” is the electrical signal value (V) measured at the i'th time point, assuming it is 1.12V, 1.18V, 1.20V, 1.25V, and 1.30V; is the average value of the electrical signal data at all time points, n' is the total number of time sampling points, assuming it is 5;

[0058] Substitute the parameters into the formula for calculation:

[0059]

[0060]

[0061] Correlation coefficient R X =0.215 indicates that there is a certain positive correlation between temperature and electrical signals, and the result is used to compensate and correct the electrical signals.

[0062] See also Figure 2 and Figure 4 , the deformation recognition module includes:

[0063] The baseline correction submodule calls the electric signal compensation parameter table to correct the original electric signal, calculates the compensated electric signal amplitude and timing characteristics, and generates the corrected electric signal waveform; the baseline correction submodule calls the electric signal compensation parameter table to correct the original electric signal. First, the system loads the compensation parameter table and performs time series analysis on the original electric signal obtained by the sensor, extracts the electric signal amplitude at the corresponding time point, and adjusts the baseline of the original signal according to the temperature and humidity gradient correction item in the compensation parameter table. The compensation calculation adopts the linear correction method to calculate the corrected electric signal value. The specific calculation formula is as follows: V c =V r -ΔV;

[0064] Among them, V c is the corrected electrical signal amplitude (V), V r is the original electrical signal amplitude (V), ΔV is the compensation value calculated based on the temperature and humidity gradient (V), and the compensation value comes from the search result of the compensation parameter table. The setting of the compensation parameter is based on historical data statistics, and the drift value in each temperature and humidity gradient interval is measured by experimental calibration. For example, when the temperature gradient G T=2.5℃ / m, humidity gradient G H =3, the experimentally measured electrical signal drift ΔV = 0.014V, and the corrected electrical signal is calculated as follows:

[0065] V c =2.0V-0.014V=1.986V;

[0066] After the corrected electrical signal amplitude is calculated, the system sorts the signal data according to the timestamp to ensure the temporal continuity of the data. Subsequently, the baseline correction submodule uses the sliding window method to process the signal curve, calculates the rate of change of the corrected signal within each window, and removes abnormal signal points. For example, within a 10ms window, the rate of change R between adjacent sampling points is calculated:

[0067] Among them, V c2 and V c1 is the corrected electrical signal value (V) at adjacent time points, and Δt is the time interval (s). If the calculated result exceeds the set threshold, for example, |R|>0.05V / ms, the point is considered an outlier, and interpolation correction is performed. All corrected electrical signal data are stored in the database, and finally the corrected electrical signal waveform is generated.

[0068] The response analysis submodule analyzes the corresponding relationship between the stress and deformation response curve of the carbon material based on the corrected electrical signal waveform, analyzes the influence of the carbon material deformation on the electrical signal, calculates the sensitivity parameter of the electrical signal to the deformation, and generates the deformation response characteristic parameter;

[0069] The specific formula for the effect of the deformation of the carbon deposition material on the electrical signal is:

[0070] Calculate the sensitivity parameter of the electrical signal to deformation; where SD represents the sensitivity parameter of the electrical signal to deformation, VDc q represents the measured value of the corrected electrical signal corresponding to the qth deformation variable, VDc0 represents the initial value of the corrected electrical signal when the deformation variable is zero, Xε q represents the qth deformation variable, Xε0 represents the deformation variable without external force, p represents the number of data sampling points, and q represents the sequence number of the currently calculated deformation variable.

[0071] formula:

[0072] Detailed explanation of the formula and the formula calculation derivation process: The formula is used to calculate the sensitivity parameter of the electrical signal to deformation. The obtained results are used to characterize the amplitude of the electrical signal change of the carbon material under different deformation amounts and are used in the subsequent signal separation process;

[0073] Parameter meaning and setting value: SD is the sensitivity parameter of electrical signal to deformation, which represents the influence of carbon material deformation on electrical signal; VDc q is the measured value of the corrected electrical signal corresponding to the qth deformation variable, assuming that the corrected electrical signal value corresponding to the 1st deformation variable is 1.95V, the corrected electrical signal value corresponding to the 2nd deformation variable is 1.92V, the corrected electrical signal value corresponding to the 3rd deformation variable is 1.89V, the corrected electrical signal value corresponding to the 4th deformation variable is 1.85V, the corrected electrical signal value corresponding to the 5th deformation variable is 1.82V, the corrected electrical signal value corresponding to the 6th deformation variable is 1.78V, the corrected electrical signal value corresponding to the 7th deformation variable is 1.74V, the corrected electrical signal value corresponding to the 8th deformation variable is 1.71V, the corrected electrical signal value corresponding to the 9th deformation variable is 1.67V, and the corrected electrical signal value corresponding to the 10th deformation variable is 1.63V; VDc0 is the initial value of the corrected electrical signal when the deformation variable is zero, assuming it is 2.0V; Xε q is the qth deformation variable, the first deformation variable is 0.001ε, the second deformation variable is 0.002ε, the third deformation variable is 0.003ε, the fourth deformation variable is 0.004ε, the fifth deformation variable is 0.005ε, the sixth deformation variable is 0.006ε, the seventh deformation variable is 0.007ε, the eighth deformation variable is 0.008ε, the ninth deformation variable is 0.009ε, and the tenth deformation variable is 0.01ε; Xε0 is the deformation variable without external force, which is assumed to be 0, indicating the strain of the material in a static state; p is the total number of data sampling points; q is the sequence number of the deformation variable currently calculated;

[0074] Substitute the parameters into the formula for calculation:

[0075]

[0076] The results show that the sensitivity parameter of the electrical signal to deformation is SD = 37.09V / ε, which means that when the carbon material produces a unit deformation of 1ε, the electrical signal changes by an average of 37.09V. This value is used in subsequent deformation signal separation calculations to identify the electrical signal characteristics of carbon materials under different loads, and can be used to distinguish the signal change trends caused by different deformations.

[0077] The signal separation submodule calls the deformation response characteristic parameters to identify and separate the deformation signal in the electrical signal and generate a deformation signal data set. The signal separation submodule calls the deformation response characteristic parameters to identify and separate the deformation signal in the electrical signal. First, the spectrum analysis of the corrected electrical signal waveform is performed to extract the low-frequency component as the deformation signal characteristic value. The deformation response characteristic parameters are used for matching, and the electrical signal changes under different deformation amounts are distinguished. The deformation contribution value in the electrical signal component is calculated as follows: V ∈ =S·∈;

[0078] Among them, V ∈ is the deformation signal amplitude (V), S is the sensitivity of the electrical signal to deformation (V / ε), ∈ is the measured deformation (ε), if the deformation ∈ = 0.003ε, the sensitivity S = 4V / ε, then the deformation signal amplitude is calculated as follows: V ∈ =4×0.003=0.012V;

[0079] After the calculation is completed, the deformation component in the electrical signal is separated from other interference signals, and the frequency domain filtering method is used to remove high-frequency noise to obtain pure deformation signal data, and finally generate a deformation signal data set.

[0080] See also Figure 2 and Figure 5 , the feature analysis module includes:

[0081] The acceleration calculation submodule calls the deformation signal data set, calculates the changing speed of the deformation signal within the continuous time window, identifies the deformation acceleration, and generates the deformation acceleration value. The acceleration calculation submodule calls the deformation signal data set, calculates the changing speed of the deformation signal within the continuous time window. First, the system extracts the deformation variables of consecutive time points from the deformation signal data set, arranges them in chronological order, and calculates the deformation variables of adjacent time points to obtain the rate of change of the deformation variables, that is, the deformation velocity. The deformation velocity is calculated as follows:

[0082] Among them, v ∈ is the deformation speed (ε / s), ∈ t2 is the deformation variable (ε) at time t2, ∈ t1 is the deformation at time t1 (ε), Δt is the interval between two time points (s), for example, at t1 = 1s, the deformation ∈ t1 =0.002ε, at t2=2s, the deformation variable ∈ t2 =0.006ε, then the deformation velocity is calculated as follows:

[0083]

[0084] Subsequently, a sliding window method was used to calculate the deformation velocity at different time periods in the entire deformation signal dataset. The window length was set to 10ms. The mean deformation velocity was calculated within each window to reduce the influence of transient noise. Based on the calculated deformation velocity data, the deformation acceleration, that is, the rate of change of the deformation velocity, was calculated as follows:

[0085] Among them, a ∈ is the deformation acceleration (ε / s2), v ∈2 is the deformation velocity at time t2 (ε / s), v ∈1is the deformation velocity at time t1 (ε / s), for example, if v ∈1 =0.004ε / s, v ∈2 =0.008ε / s, and time interval Δt=2s, the deformation acceleration is calculated as follows:

[0086] Finally, the system traverses the entire deformation signal data set, calculates the deformation acceleration values at all time points, stores them in the database, and generates deformation acceleration values.

[0087] The amplitude frequency identification submodule uses the deformation acceleration value to record the fluctuation amplitude of the deformation signal, calculate the deformation frequency, and generate the deformation amplitude frequency parameter; the amplitude frequency identification submodule uses the deformation acceleration value to record the fluctuation amplitude of the deformation signal and calculate the deformation frequency. First, the system extracts time series data from the deformation acceleration data set, calculates the maximum and minimum values of the deformation acceleration, and obtains the complete fluctuation amplitude. The calculation method is as follows: A ∈ =|a ∈max -a ∈min |;

[0088] Among them, A ∈ is the amplitude of deformation acceleration fluctuation (ε / s 2 ), a ∈max is the maximum deformation acceleration (ε / s 2 ), a ∈min is the minimum value of deformation acceleration (ε / s 2 ), for example, within a certain period of time, the maximum deformation acceleration measured is a ∈max =0.008ε / s 2 , the minimum deformation acceleration is a ∈min =-0.004ε / s 2 , then the fluctuation range is calculated as follows: A ∈ =|0.008-(-0.004)|=0.012ε / s 2 ;

[0089] Next, the system calculates the frequency of the deformation signal through the zero-crossing detection method, that is, the number of periodic changes of the deformation signal in unit time is counted. Whenever the deformation acceleration signal changes from negative to positive (or vice versa), a zero crossing is counted and the average time interval T between adjacent zero crossings is calculated. ∈ (s), the deformation frequency is calculated as follows:

[0090] Among them, f ∈ is the deformation frequency (Hz), T ∈ is the time interval of a complete cycle (s). For example, in the measured data, the average period T of the deformation signal is calculated. ∈=0.5s, then the deformation frequency is calculated as follows:

[0091]

[0092] All calculated fluctuation amplitude and deformation frequency data are stored in the database and used for subsequent deformation feature analysis, ultimately generating deformation amplitude frequency parameters. The smoothness calculation submodule calls the deformation amplitude frequency parameters, analyzes the transition smoothness of the deformation curve, calculates the smoothness score, and generates deformation feature parameters by combining the signal's acceleration, amplitude, and deformation frequency.

[0093] The specific formula for calculating the smoothness score is:

[0094]

[0095] Calculate the smoothness score; where S ∈ represents the smoothness score, J ∈i represents the rate of change of the deformation signal at the i-th time point, represents the mean value of the deformation signal change rate, N represents the total number of time points in the deformation signal dataset, a ∈i represents the deformation acceleration at the i-th time point, represents the mean value of deformation acceleration, f ∈ represents the deformation signal frequency, Represents the mean value of the deformation signal frequency, and i represents the time point index of the current calculation.

[0096] formula:

[0097] Detailed explanation of the formula and the formula calculation derivation process: The formula is used to calculate the smoothness score of the deformation signal. The result is used to measure the degree of change of the signal in the time series, providing a reference for further analysis of the deformation signal characteristics.

[0098] Parameter meaning and setting value: J ∈i is the rate of change of the deformation signal at the i-th time point, and the set values are 0.002, 0.004, 0.005, 0.003, and 0.004ε / s 3 ; is the mean value of the deformation signal change rate; N is the total number of time points in the deformation signal data set, and the set value is 5; a ∈i is the deformation acceleration at the i-th time point, and the set values are 0.006, 0.008, 0.007, 0.005, and 0.006ε / s 2 ; is the mean value of deformation acceleration; f ∈ is the deformation signal frequency, the set value is 2.5Hz; is the mean value of the deformation signal frequency, and the set value is 2.4 Hz.

[0099] Substitute the parameters into the formula for calculation:

[0100]

[0101]

[0102] The calculated result of 0.1019 reflects the smoothness score of the deformation signal. The lower the value, the smoother the signal. This result indicates that the current signal has a certain degree of volatility, but is generally stable. Further combined with the acceleration, amplitude, and frequency of the deformation signal, it can be used to analyze deformation characteristics.

[0103] See also Figure 2 and Figure 6 , the pattern parsing module includes:

[0104] The abnormal marking submodule calls the deformation feature parameters, uses the deformation frequency fluctuation rate and smoothness score, and calculates the statistical characteristics of the deformation frequency to identify and mark the abnormal fluctuation segment, generating an abnormal fluctuation interval mark; the abnormal marking submodule calls the deformation feature parameters, uses the deformation frequency fluctuation rate and smoothness score, and calculates the statistical characteristics of the deformation frequency to identify and mark the abnormal fluctuation segment. First, the system extracts the deformation frequency fluctuation rate data from the deformation feature parameter set, arranges them in chronological order, calculates the mean deformation frequency in each time window, and analyzes its change over time. The deformation frequency mean is calculated as follows:

[0105] Among them, F avg is the mean deformation frequency (Hz), F j is the deformation frequency at the jth time point (Hz), N f is the number of sampling points in the time window. For example, if the deformation frequency data F = 1.8, 2.0, 2.2, 1.9, 2.1 Hz are measured at 5 time points, the mean deformation frequency is calculated as follows:

[0106] After the calculation is completed, the system further calculates the standard deviation of the deformation frequency to measure its fluctuation degree. The standard deviation is calculated as follows:

[0107] Among them, σ F is the standard deviation of deformation frequency fluctuation (Hz), if σ is calculated F Exceeding a set threshold, such as σ F If the frequency is >0.5Hz, the time period is marked as an abnormal fluctuation interval and stored in the database, and an abnormal fluctuation interval mark is finally generated.

[0108] The signal screening submodule extracts the amplitude data in the deformation signal based on the abnormal fluctuation interval mark, compares the amplitude threshold interval in the preset motion interference database, screens and separates the motion interference signal, and generates an interference signal separation result; the signal screening submodule extracts the amplitude data in the deformation signal based on the abnormal fluctuation interval mark, compares the amplitude threshold interval in the preset motion interference database, screens and separates the motion interference signal. First, the system extracts the deformation signal amplitude data from the abnormal fluctuation interval and calculates its maximum and minimum value range. The deformation signal amplitude calculation method is as follows: A def =|D max -D min |;

[0109] Among them, A def is the amplitude of the deformation signal (ε), D max is the maximum deformation of the deformation signal (ε), D min is the minimum deformation variable (ε) of the deformation signal. For example, within a certain period of time, the maximum deformation variable measured is D max =0.006ε, the minimum deformation is D min =0.002ε, then the amplitude is calculated as follows:

[0110] A def =|0.006-0.002|=0.004ε;

[0111] Then, the system extracts the amplitude threshold range of different types of motion interference from the preset motion interference database and compares it with the currently calculated amplitude. For example, if the amplitude range of running interference set in the database is 0.003≤A def ≤0.007ε, and the deformation signal amplitude A obtained in this calculation def =0.004ε, it is determined that the deformation signal may be caused by motion interference, and it is marked and separated. All the filtered motion interference signals are stored in the database, and finally the interference signal separation result is generated.

[0112] The breathing extraction submodule calls the interference signal separation result, compares the processed deformation signal with the breathing pattern in the breathing pattern database, identifies the breathing pattern, and records the corresponding breathing cycle and breathing depth data to generate breathing rhythm parameters; the breathing extraction submodule calls the interference signal separation result, compares the processed deformation signal with the breathing pattern in the breathing pattern database, identifies the breathing pattern, and records the corresponding breathing cycle and breathing depth data. First, the system extracts periodic signal segments from the deformation signal data set from which the interference signal has been separated, and calculates its average breathing cycle. The calculation method is as follows:

[0113] Among them, T bris the average respiratory period (s), T k is the duration of the kth respiratory cycle (s), N T is the number of respiratory cycles measured. For example, if the durations of the five respiratory cycles measured are 4.8, 5.0, 5.2, 4.9, and 5.1 s, respectively, the average respiratory cycle is calculated as follows:

[0114] Next, the system calculates the breathing depth data, that is, the amplitude variation range of the deformation signal during breathing, and the calculation method is as follows: A br =|D br,max -D br,min |;

[0115] Among them, A br is the amplitude of the respiratory deformation signal (ε), D br,max is the maximum deformation of the respiratory signal (ε), D br,min is the minimum deformation of the respiratory signal (ε), if the maximum deformation in a certain respiratory cycle is D br,max =0.005ε, the minimum deformation is D br,min =0.002ε, then calculate the breathing depth as follows: A br =|0.005-0.002|=0.003ε;

[0116] After the calculation is completed, the system compares the currently measured breathing cycle and breathing depth data with different patterns in the breathing pattern database. For example, the amplitude threshold of the deep breathing pattern in the database is set to A. br >0.004ε, the threshold of shallow breathing pattern is A br <0.002ε, if the calculated respiratory amplitude A br =0.003ε, then the breathing pattern does not belong to deep breathing or shallow breathing, and the system marks it as a normal breathing pattern and stores it in the database, and finally generates the breathing rhythm parameters.

[0117] See also Figure 2 and Figure 7 , the status monitoring module includes:

[0118] The fluctuation assessment submodule calls the respiratory rhythm parameters, extracts the respiratory cycle time series data, evaluates the change trend and volatility of the respiratory cycle, and generates a respiratory cycle fluctuation coefficient. The fluctuation assessment submodule calls the respiratory rhythm parameters, extracts the respiratory cycle time series data, and evaluates the change trend and volatility of the respiratory cycle. First, the system extracts the respiratory cycle data of consecutive time points from the respiratory rhythm parameter set, arranges them in chronological order, and calculates the mean of the respiratory cycle in multiple time windows. The calculation method is as follows:

[0119]

[0120] Among them, T mean is the average respiratory period (s), T bp,m is the mth respiratory cycle (s), N bp is the total number of cycles. For example, if the measured 6 respiratory cycles are [4.8, 5.1, 4.9, 5.0, 5.2, 4.7] s, the average respiratory cycle is calculated as follows:

[0121] After the calculation is completed, the system calculates the respiratory cycle volatility, that is, the degree of deviation of each respiratory cycle from the mean. The fluctuation coefficient is calculated as follows:

[0122] Among them, C bp is the respiratory cycle fluctuation coefficient, σ bp is the respiratory cycle standard deviation (s), and the standard deviation is calculated as follows:

[0123] For example, if we calculate σ bp = 0.18s, and T mean =4.95s, then the fluctuation coefficient is calculated as follows:

[0124]

[0125] The system defines intervals based on the range of the fluctuation coefficient, for example, C bp <0.05 is stable, 0.05≤C bp <0.1 indicates moderate fluctuation, C bp ≥0.1 indicates high fluctuation, and the respiratory cycle fluctuation coefficient is finally generated. The intensity analysis submodule extracts the respiratory amplitude stability data based on the respiratory cycle fluctuation coefficient, identifies the user's exercise intensity, and generates an exercise intensity index; the intensity analysis submodule extracts the respiratory amplitude stability data based on the respiratory cycle fluctuation coefficient, identifies the user's exercise intensity. First, the system extracts the respiratory amplitude in multiple time windows from the respiratory signal data set and calculates the amplitude mean. The calculation method is as follows:

[0126]

[0127] Among them, A mean is the mean respiratory amplitude (ε), A br,n is the respiratory amplitude (ε) in the nth time window, N amp is the total number of time windows. For example, if the respiratory amplitudes in the five time windows are measured as [0.0035, 0.0038, 0.0040, 0.0036, 0.0037]ε, the average respiratory amplitude is calculated as follows:

[0128]

[0129] After the calculation is completed, the system calculates the respiratory amplitude stability, that is, the amplitude deviation degree in each time window, and the calculation method is as follows:

[0130] Among them, S amp is the respiratory amplitude stability coefficient (dimensionless), σ amp is the amplitude standard deviation (ε), which is calculated as follows:

[0131] For example, if we calculate σ amp =0.0002ε, and A mean =0.00372ε, then the amplitude stability is calculated as follows:

[0132] The system calculates the exercise intensity index based on the amplitude stability and respiratory cycle fluctuation coefficient. The calculation method is as follows: I act =w1C bp +w2S amp ;

[0133] Among them, I act is the exercise intensity index (dimensionless), w1 and w2 are weight coefficients, for example, if w1 = 0.6, w2 = 0.4, calculate I act As follows: I act =0.6×0.036+0.4×0.0538=0.0436;

[0134] The system divides the intervals according to the exercise intensity index, for example, I act <0.05 is mild exercise, 0.05≤I act <0.15 is moderate exercise, I act ≥0.15 is considered high-intensity exercise, and the exercise intensity index is finally generated.

[0135] The state classification submodule calls the motion intensity index, combines the changing characteristics of the respiratory cycle, and compares it with the data characteristics of multiple motion states in the preset motion pattern database to identify the user's motion state and generate a motion state classification label; the state classification submodule calls the motion intensity index, combines the changing characteristics of the respiratory cycle, and compares it with the data characteristics of multiple motion states in the preset motion pattern database to identify the user's motion state. First, the system extracts the respiratory rhythm parameters corresponding to different motion states from the motion pattern database, including the respiratory cycle, amplitude mean, fluctuation coefficient, and motion intensity index, and matches them with the currently measured data. For example, the motion state characteristics defined in the database are as follows:

[0136] Table 1 Correspondence between movement state and respiratory rhythm parameters

[0137] Movement status respiratory cycle Amplitude mean Volatility coefficient Exercise intensity index Rest 5.0-6.5 0.0025-0.004 <0.05 <0.05 light exercise 4.0-5.0 0.003-0.005 0.05-0.1 0.05-0.15 moderate exercise 3.0-4.0 0.004-0.006 0.1-0.2 0.15-0.3 high-intensity exercise 2.0-3.0 >0.005 >0.2 >0.3

[0138] Refer to Table 1, if the current measured T mean =4.95s, A mean =0.00372ε, C bp =0.036, I act =0.0436, the matching result falls into the light motion state, the system stores it in the database, and finally generates a motion state classification label.

[0139] The above embodiments can be implemented in whole or in part through software, hardware (such as circuits), firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired method (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, or magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0140] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0141] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0142] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0145] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0146] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A wearable sensor based on printed carbon material, characterized in that: The sensor comprises: The signal calibration module collects the electrical signals of the carbon material sensor, obtains the real-time data of the temperature and humidity nodes on the sensor surface, analyzes the impact of temperature and humidity changes on the electrical signals, and constructs an electrical signal compensation parameter table; The deformation recognition module calls the electric signal compensation parameter table, performs baseline correction on the electric signal, identifies and separates the deformation signal from the electric signal by analyzing the relationship between the stress and deformation response curve of the carbon material, and generates a deformation signal data set; The feature analysis module extracts the acceleration, amplitude, and deformation frequency of the deformation signal in the continuous time window based on the deformation signal data set, calculates the transition smoothness of the deformation curve, and generates deformation feature parameters; The pattern analysis module calls the deformation feature parameters, marks abnormal fluctuation segments through deformation frequency and smoothness parameters, separates motion interference signals, compares the deformation features with known breathing patterns, extracts breathing cycle and breathing depth data, and generates breathing rhythm parameters; The state monitoring module inputs the respiratory rhythm parameters, evaluates the user's exercise intensity and the regularity of the respiratory rhythm according to the fluctuation and amplitude stability of the respiratory cycle, identifies the user's exercise state, and generates an exercise state classification label.

2. The wearable sensor based on printed carbon material according to claim 1, characterized in that The electrical signal compensation parameter table specifically includes the temperature and humidity gradient change rate, compensation weight factor, and hysteresis effect correction amount. The deformation signal data set includes the deformation response amplitude, stress distribution time series, and baseline offset correction amount. The deformation characteristic parameters specifically refer to the deformation acceleration value, deformation frequency fluctuation rate, and transition smoothness. The respiratory rhythm parameters include respiratory cycle time series, amplitude stability coefficient, and motion artifact separation threshold. The motion state classification label specifically includes motion intensity data, motion state matching degree, and state identification label.

3. The wearable sensor based on printed carbon material according to claim 1, characterized in that The signal calibration module includes: The data acquisition submodule collects the electrical signals of the carbon material sensor, obtains the real-time temperature and humidity data of the temperature and humidity nodes on the sensor surface in real time, and generates a sensor data set; The gradient analysis submodule calculates the spatial gradient change rate of adjacent temperature and humidity nodes based on the sensor data set, analyzes the fluctuation amplitude and duration of the temperature and humidity data over time, and generates the temperature and humidity gradient fluctuation rate; The compensation construction submodule calls the temperature and humidity gradient fluctuation rate, analyzes the impact of temperature and humidity changes on electrical signals, identifies the baseline drift mapping relationship between temperature and humidity and electrical signals, and generates an electrical signal compensation parameter table.

4. The wearable sensor based on printed carbon material according to claim 3, characterized in that The specific formula for the effect of temperature and humidity changes on electrical signals is: Calculate the correlation coefficient between temperature and humidity and electrical signals, and identify the baseline drift mapping relationship between temperature and humidity and electrical signals; Among them, R X Represents the correlation coefficient of the impact of temperature and humidity changes on electrical signals, X i' Represents the temperature or humidity value measured at the i'th time point, Represents the average value of temperature or humidity data at all time points, V i " represents the electrical signal value measured at the i'th time point, represents the average value of the electrical signal data at all time points, i' represents the i'th time point during the data acquisition process, and n' represents the total number of time points during the data acquisition process.

5. The wearable sensor based on printed carbon material according to claim 1, characterized in that The deformation recognition module includes: The baseline correction submodule calls the electric signal compensation parameter table, corrects the original electric signal, calculates the amplitude and timing characteristics of the compensated electric signal, and generates a corrected electric signal waveform; The response analysis submodule analyzes the corresponding relationship between the stress and deformation response curve of the carbon material based on the corrected electrical signal waveform, analyzes the influence of the carbon material deformation on the electrical signal, calculates the sensitivity parameter of the electrical signal to the deformation, and generates the deformation response characteristic parameter; The signal separation submodule calls the deformation response characteristic parameters, identifies and separates the deformation signal in the electrical signal, and generates a deformation signal data set.

6. The wearable sensor based on printed carbon material according to claim 5, characterized in that The specific formula for the effect of the deformation of the carbon deposition material on the electrical signal is: Calculate the sensitivity parameters of electrical signals to deformation; Among them, SD represents the sensitivity parameter of electrical signal to deformation, VDc q represents the measured value of the corrected electrical signal corresponding to the qth deformation variable, VDc0 represents the initial value of the corrected electrical signal when the deformation variable is zero, Xε q represents the qth deformation variable, Xε0 represents the deformation variable without external force, p represents the number of data sampling points, and q represents the sequence number of the currently calculated deformation variable.

7. The wearable sensor based on printed carbon material according to claim 6, characterized in that The feature analysis module includes: The acceleration calculation submodule calls the deformation signal data set, calculates the changing speed of the deformation signal in the continuous time window, identifies the deformation acceleration, and generates the deformation acceleration value; The amplitude-frequency identification submodule uses the deformation acceleration value to record the fluctuation amplitude of the deformation signal, calculates the deformation frequency, and generates deformation amplitude-frequency parameters; The smoothness calculation submodule calls the deformation amplitude frequency parameters, analyzes the transition smoothness of the deformation curve, calculates the smoothness score, and generates deformation feature parameters by combining the acceleration, amplitude, and deformation frequency of the signal.

8. The wearable sensor based on printed carbon material according to claim 7, characterized in that The specific formula for calculating the smoothness score is: Calculate smoothness score; Among them, S ∈ represents the smoothness score, J ∈i represents the rate of change of the deformation signal at the i-th time point, represents the mean value of the deformation signal change rate, N represents the total number of time points in the deformation signal dataset, a ∈i represents the deformation acceleration at the i-th time point, represents the mean value of deformation acceleration, f ∈ represents the deformation signal frequency, Represents the mean value of the deformation signal frequency, and i represents the time point index of the current calculation.

9. The wearable sensor based on printed carbon material according to claim 1, characterized in that The pattern parsing module includes: The abnormal marking submodule calls the deformation feature parameters, uses the deformation frequency fluctuation rate and smoothness score, calculates the statistical characteristics of the deformation frequency, identifies and marks the abnormal fluctuation segment, and generates the abnormal fluctuation interval mark; The signal screening submodule extracts the amplitude data from the deformation signal based on the abnormal fluctuation interval mark, compares the amplitude threshold interval in the preset motion interference database, screens and separates the motion interference signal, and generates an interference signal separation result; The breathing extraction submodule calls the interference signal separation result, identifies the breathing pattern by comparing the processed deformation signal with the breathing pattern in the breathing pattern database, and records the corresponding breathing cycle and breathing depth data to generate breathing rhythm parameters.

10. The wearable sensor based on printed carbon material according to claim 1, characterized in that The status monitoring module includes: The fluctuation evaluation submodule calls the respiratory rhythm parameters, extracts respiratory cycle time series data, evaluates the change trend and volatility of the respiratory cycle, and generates a respiratory cycle fluctuation coefficient; The intensity analysis submodule extracts the respiratory amplitude stability data based on the respiratory cycle fluctuation coefficient, identifies the user's exercise intensity, and generates an exercise intensity index; The state classification submodule calls the exercise intensity index, combines the change characteristics of the breathing cycle, and compares it with the data characteristics of multiple exercise states in the preset exercise pattern database to identify the user's exercise state and generate an exercise state classification label.

Images