A multi-sensor helmet-based vital sign monitoring system and method

Abstract

The application discloses a kind of vital sign monitoring system and method based on multi-sensor helmet, it is related to safety helmet technical field, including data acquisition module, the data acquisition module includes sensor unit and data acquisition unit, the sensor unit specifically includes heart rate sensor: for real-time monitoring the instantaneous heart rate of wearer, temperature sensor: for real-time monitoring the temperature of wearer surface, respiratory rate sensor: for real-time monitoring the respiratory rate of wearer;According to the latest sensor data, recalculate dynamic baseline value according to the above calculation method once, the purpose of doing this is to make dynamic baseline can adapt to the change of physiological parameter in time, always keep accurate reflection to current physiological state, if the physiological parameter of wearer has changed in short time, these changes can be considered in time, update dynamic baseline, to provide more accurate reference for subsequent physiological state monitoring and analysis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of safety helmets, more particularly to a vital sign monitoring system and method based on a multi-sensor helmet. BACKGROUND

[0002] Intelligent safety helmets mainly focus on the intelligentization of site management, including real-name attendance, video monitoring, BIM and wisdom site integration functions. These safety helmets usually have basic head protection functions and realize simple environment monitoring and wearer state monitoring by integrating some sensors. Intelligent safety helmets are used in wisdom sites to improve engineering efficiency, ensure construction safety and optimize resource allocation.

[0003] However, in actual use, intelligent safety helmets mainly focus on site management functions such as attendance and video monitoring, and have limited health monitoring functions for wearers. They cannot monitor the vital signs of wearers such as heart rate, body temperature and respiratory rate in real time. The data processing capacity of existing intelligent safety helmets is limited, and they cannot realize localized data processing. They rely on cloud processing, resulting in high data processing delay and failing to meet real-time requirements.

[0004] Moreover, the working environment of a site is complex. The alarm mode of existing intelligent safety helmets is relatively single, usually only having sound and light alarms, which cannot ensure that wearers receive warning information in time in various environments. This may cause wearers to fail to notice alarm signals in time in noisy or insufficiently light environments. SUMMARY

[0005] To solve the above problems, the present application provides a vital sign monitoring system and method based on a multi-sensor helmet.

[0006] The present application provides a vital sign monitoring system based on a multi-sensor helmet, which comprises a data acquisition module. The data acquisition module comprises a sensor unit and a data acquisition unit. The sensor unit specifically comprises a heart rate sensor for monitoring the instantaneous heart rate of a wearer in real time, a body temperature sensor for monitoring the body surface temperature of a wearer in real time, a respiratory rate sensor for monitoring the respiratory rate of a wearer in real time, an electroencephalogram sensor for monitoring the fatigue state and abnormal brain activity of a wearer, and an oxygen saturation sensor for monitoring the oxygen saturation of a wearer in real time. The sensor unit also comprises a gas sensor, specifically including CO and H2S, for detecting the concentration of harmful gases in the site environment.

[0007] The system also comprises a temperature and humidity sensor for monitoring the temperature and humidity of the site environment in real time and a barometric pressure sensor for monitoring the barometric pressure of the site environment in real time.

[0008] The data acquisition unit is configured to receive parameter data of all sensors in the sensor unit, fuse the parameter data of all sensors, obtain processed sensor parameter data, and transmit the processed sensor parameter data.

[0009] The data analysis module is configured to receive the processed sensor parameter data of the data acquisition unit, identify a current state of the wearer according to the processed sensor parameter data, classify the current state of the wearer, obtain a classification result, and transmit the classification result.

[0010] The response module is configured to receive the classification result of the data analysis module, and implement different response strategies according to different classification results.

[0011] The data storage module is configured to store data fragments of the data acquisition module and the data analysis module in multiple nodes, and support data synchronization and recovery in an offline mode.

[0012] Preferably, the data acquisition unit has the following specific working steps:

[0013] The number M of each type of sensor and the current reading of each sensor are obtained, the average value of M sensor readings is calculated every other period, the average value is taken as the processed sensor parameter data, and the processed sensor parameter data is transmitted.

[0014] Preferably, the data acquisition unit is further configured to perform error analysis on the sensor readings of the sensor unit, and remove abnormal sensor readings, and the specific steps are as follows:

[0015] For each type of sensor in the sensor unit, the standard deviation σ of the sensor is calculated according to the formula wherein S i is the reading of the i-th sensor, and μ is the average value of the historical readings of the sensor of this type.

[0016] The value range [A, B] of each type of sensor in the sensor unit is calculated according to the formula Before calculating the average value of M sensor readings every other period, it is determined whether the M sensor readings are within the value range [A, B], if yes, the average value of M sensor readings is further calculated, and if no, it is determined that the sensor reading is abnormal, and an abnormal signal is generated and transmitted to the mobile terminal of the wearer.

[0017] Preferably, the data acquisition unit is further configured to adjust the average value of the corresponding sensor reading according to the environmental parameter, and the specific steps are as follows:

[0018] After obtaining the average value of M sensor readings, the ambient temperature T1, the ambient humidity T2 and the ambient pressure T3 of the current wearer are obtained every other period before transmission, so as to set an ambient temperature base value t1, an ambient humidity base value t2 and an ambient pressure base value t3;

[0019] For each sensor reading, according to the formula:

[0020] SX i =S i -[0.5*(T1-t1)+0.3*(T2-t2)+0.2*(T3-t3)]

[0021] The average value of the adjusted sensor readings is calculated and then transmitted to the data analysis module.

[0022] Preferably, the specific working steps of the data analysis module are as follows:

[0023] First, the average value of each sensor reading is obtained every other period, and the average value of each sensor reading is taken as the reading of the sensor in this period;

[0024] The reading Q1 of the heart rate sensor, the reading Q2 of the body temperature sensor, the reading Q3 of the respiration rate sensor and the reading Q4 of the blood oxygen saturation sensor are obtained.

[0025] According to the formula:

[0026]

[0027] The dynamic baseline value G of the wearer is calculated i , wherein represents the reading of the i-th type of sensor at time t, W L is the first time interval, specifically 7, W S is the second time interval, specifically 8, and the baseline value G is recalculated every certain period of time i , i is 1 to 4, and there are four types of sensors in total, and the baseline value G corresponding to each parameter of heart rate, body temperature, respiration rate and blood oxygen saturation is calculated i , wherein G1 corresponds to the heart rate parameter, G2 corresponds to the body temperature parameter, G3 corresponds to the respiration rate parameter, and G4 corresponds to the blood oxygen saturation parameter;

[0028] Then, according to the formula:

[0029]

[0030] The compensation coefficient is calculated when i is equal to 1, 2 and 4, and the compensation coefficient is 1 when i is equal to 3, and the formula N i =Ki *G i [1±10%] to obtain the threshold range of each parameter N i It should be noted that, wherein AGE is the age of the wearer, BMI is the body mass index of the wearer, SM is the number of cigarettes smoked by the wearer in a single day divided by five and then rounded up to the nearest integer;

[0031] When the ratio of the wearer's heart rate to respiratory rate reaches 2.5, the body temperature threshold is multiplied by the corresponding compensation coefficient, and then multiplied by [1±15%] as the body temperature threshold range;

[0032] When the wearer's blood oxygen saturation parameter is less than 92%, and the body temperature is higher than the critical value, first, the baseline value G i is multiplied by the corresponding compensation coefficient, and then multiplied by [1±10%] to obtain the threshold range of blood oxygen saturation, and then subtracted to obtain the corrected threshold range of blood oxygen saturation, wherein G2 is the body temperature parameter of the wearer.

[0033] Preferably, if the wearer's heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters are all within the corresponding threshold range, the wearer is determined to be in a normal state;

[0034] If only the wearer's heart rate is not within the corresponding threshold range, further determine the reading of the wearer's brain wave sensor, whether the theta wave energy rises by more than 20%, if so, the wearer is determined to be in a mild fatigue state, if not, the wearer is determined to be in a normal state;

[0035] If any two or three of the wearer's heart rate, respiratory rate, and blood oxygen saturation are not within the corresponding threshold range, further determine the reading of the wearer's brain wave sensor, whether the theta wave energy rises by more than 20%, if so, the wearer is determined to be in a severe fatigue state;

[0036] If not, further determine whether the ambient pressure where the wearer is located is greater than 1000hpa, if so, the wearer is determined to be in a hypoxia warning state, if not, the wearer is determined to be in a normal state;

[0037] If the wearer's body temperature and heart rate are not within the corresponding threshold range at the same time, further determine whether the ambient temperature where the wearer is located is greater than 32℃, if so, the wearer is in a heatstroke risk state, if not, the wearer is determined to be in a normal state;

[0038] If the wearer's heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters are not within the corresponding threshold range, the wearer is determined to be in an emergency abnormal state;

[0039] The judgment result is taken as a classification result and is transmitted to the response module.

[0040] Preferably, the specific steps of the data analysis module further include the following:

[0041] The working time of the wearer is obtained.

[0042] The historical average working time V and the historical standard deviation σ of the wearer are obtained.

[0043] The critical working time V1 of the wearer is calculated according to the formula V1 = V + 1.05 * σ.

[0044] The current heart rate, body temperature, respiratory rate, blood oxygen saturation parameters of the wearer and the corresponding dynamic baseline value G of the wearer are obtained. i The difference values are normalized and added and then divided by 4 to obtain the total difference value J.

[0045] The critical working time V2 of the wearer is calculated according to the formula V2 = V1 - 0.1 * J.

[0046] If the working time of the current wearer is greater than V2, it is judged that the wearer is in a mild fatigue state.

[0047] The time and duration of the occurrence of fatigue are automatically recorded according to the formula, and if the number of times of mild fatigue state in 4 hours reaches 3 times, the judgment result is changed to a severe fatigue state even if the current classification result is still a mild fatigue state.

[0048] If any one of the heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters of the wearer fluctuates by more than 20% within 5 minutes, and the classification result is a mild fatigue state.

[0049] In the next 10 minutes, the data of the abnormal item is continuously monitored, and if the fluctuation amplitude of the abnormal item continues to increase or other abnormal physiological data appears, the classification result is immediately upgraded to a sudden abnormal state.

[0050] Preferably, the specific working steps of the response module are as follows:

[0051] If the classification result is normal, no alarm is triggered.

[0052] If the classification result is a mild fatigue state, a voice prompt is issued through the built-in speaker or earphone of the helmet.

[0053] If the classification result is a severe fatigue state, a vibration alarm is issued through the built-in vibration motor of the helmet.

[0054] If the classification result is an oxygen deficiency warning state, a vibration alarm is sent through the built-in vibration motor of the helmet, current state data and location information are sent to the monitoring center, and further measures are taken;

[0055] If the classification result is a heatstroke risk state, a vibration alarm is sent through the built-in vibration motor of the helmet, current state data and location information are sent to the monitoring center, and further measures are taken;

[0056] If the classification result is a sudden abnormal state, a vibration alarm is sent through the built-in vibration motor of the helmet, current state data and location information are sent to the monitoring center, further measures are taken, and an emergency rescue phone call is automatically dialed, and location information and current state data are sent.

[0057] Preferably, the specific steps of the data storage module are:

[0058] The data of the data acquisition module and the data analysis module are divided into multiple data subsets according to a preset sharding strategy, and the data subsets are stored on different nodes to complete storage.

[0059] Each helmet is provided with an RFID reader and a memory card, and the memory card stores physiological parameters of the data acquisition unit;

[0060] The data of the memory card of each helmet is connected through the Internet of Things;

[0061] The wearer wears an anti-disassembly electronic badge integrated with a passive RFID tag, and the helmet is uniformly stored, the wearer receives the helmet through the anti-disassembly electronic badge, and the helmet is returned to the original position when use is completed, when the wearer wears the helmet, the helmet reads the RFID of the badge, obtains a basic identity code, obtains the threshold range of each parameter corresponding to the wearer, and then performs monitoring.

[0062] The application also provides a vital sign monitoring method based on a multi-sensor helmet, comprising the following steps:

[0063] Step 1: A plurality of sensors are installed at specific positions of a safety helmet to monitor physiological parameters of the wearer and construction site environment data in real time;

[0064] Step 2: The processed sensor parameter data is received, the current state of the wearer is identified through analysis, the state is classified, and a classification result is obtained;

[0065] Step 3: Different response strategies are adopted according to the classification result.

[0066] Beneficial effect: According to the latest sensor data, the dynamic baseline value is recalculated once according to the above calculation method, and the purpose of doing so is to make the dynamic baseline adapt to the changes of physiological parameters in time, always keep accurate reflection to the current physiological state, if the physiological parameters of the wearer have changed in a short time, these changes can be considered in time, update the dynamic baseline, so as to provide more accurate reference for subsequent physiological state monitoring and analysis;

[0067] In high-risk working environments such as construction sites, mines, etc., real-time monitoring of the physiological state of the wearer can timely discover risks such as fatigue, heatstroke, hypoxia, etc., improve the safety of workers, avoid the decline of work efficiency caused by fatigue by timely discovery and processing of fatigue state, and improve the overall work efficiency, and through long-term monitoring of the physiological state of the wearer, data support can be provided for health management, and potential health problems can be discovered in time. BRIEF DESCRIPTION OF DRAWINGS

[0068] Figure 1 is the flow chart of the system of the present application;

[0069] Figure 2 is the method step diagram of the present application. DETAILED DESCRIPTION

[0070] Application scenario: In the actual use process, the intelligent safety helmet mainly focuses on the site management function such as attendance and video monitoring, and the health monitoring function of the wearer is relatively limited, and it is unable to monitor the vital signs of the wearer in real time, such as heart rate, body temperature, respiratory rate, etc., the data processing capacity of the existing intelligent safety helmet is limited, and it is unable to realize localized data processing, and it relies on cloud processing, resulting in high data processing delay and unable to meet the real-time requirement;

[0071] For example, Figure 1The multi-sensor helmet-based vital sign monitoring system comprises a data acquisition module, which comprises a sensor unit and a data acquisition unit, and the sensor unit specifically comprises a heart rate sensor for monitoring the real-time heart rate of the wearer, a body temperature sensor for monitoring the real-time body temperature of the wearer, a respiratory rate sensor for monitoring the real-time respiratory rate of the wearer, an electroencephalogram sensor for monitoring the fatigue state and abnormal brain activity of the wearer, an oxygen saturation sensor for monitoring the real-time oxygen saturation of the wearer, and a gas sensor specifically comprising CO and H2S for detecting the concentration of harmful gases in the construction site environment. It should be noted that the heart rate sensor can be installed on the inner lining of the safety helmet, closely attached to the forehead or temple position of the wearer, so as to accurately capture the heart rate signal. The body temperature sensor can be distributed on multiple parts of the safety helmet lining in contact with the skin of the head, such as the forehead, temple, etc., to improve the accuracy of measurement. The respiratory rate sensor can be installed on the lower jaw or neck position of the safety helmet, and the respiratory rate is monitored by detecting the breathing action of the wearer. The electroencephalogram sensor can be installed on the inner lining of the safety helmet, closely attached to the forehead or top of the head of the wearer, so as to accurately capture the electroencephalogram signal. The oxygen saturation sensor can be installed on the inner lining of the safety helmet, closely attached to the earlobe or finger position of the wearer, so as to accurately measure the oxygen saturation. The gas sensor can be installed on the top or front of the safety helmet, so as to detect the concentration of harmful gases in the construction site environment in real time.

[0072] The number of each type of sensor is at least two, and the specific number is adjusted according to the actual situation and installed on the above-mentioned positions.

[0073] It also comprises a temperature and humidity sensor for monitoring the temperature and humidity of the construction site environment in real time, and a barometric pressure sensor for monitoring the barometric pressure of the construction site environment in real time. It should be noted that the temperature and humidity sensor can be installed on the top or front of the safety helmet, so as to accurately capture the changes in environmental temperature and humidity. The barometric pressure sensor can be installed on the top or side of the safety helmet, so as to accurately measure the changes in environmental barometric pressure.

[0074] The data acquisition unit is used to receive the parameter data of all sensors in the sensor unit, fuse the parameter data of all sensors, obtain the processed sensor parameter data, and transmit it.

[0075] The data analysis module is used to receive the processed sensor parameter data of the data acquisition unit, identify the current state of the wearer according to the processed sensor parameter data, classify the current state of the wearer, obtain the classification result, and transmit it.

[0076] The response module is used to receive the classification result of the data analysis unit, and implement different response strategies according to the different classification results.

[0077] a data storage module, which stores data fragments of the data collection module and the data analysis module in multiple nodes and supports data synchronization and recovery in offline mode.

[0078] As an optional embodiment, the specific working steps of the data collection unit are as follows:

[0079] The installation number M of each sensor and the current reading of each sensor are obtained, the average value of M sensor readings is calculated every other period, the average value is taken as the processed sensor parameter data, and is transmitted. It should be noted that the information obtained by different sensors is complementary, a single sensor may be disturbed by various factors during measurement, resulting in measurement error, and multi-sensor data fusion can reduce the error of a single sensor by comprehensive analysis of the data of multiple sensors, improve the reliability of the measurement result, when one of the sensors fails or the data is abnormal, the data of other sensors can be used as a supplement to ensure the normal operation of the system, this redundancy can improve the reliability and stability of the system, and reduce the risk of system failure caused by failure of a single sensor;

[0080] It should be noted that the period is a fixed time interval set in advance, which is 2 seconds in this embodiment.

[0081] As an optional embodiment, the data collection unit is also used for error analysis of the sensor readings of the sensor unit, and abnormal sensor readings are removed, and the specific steps are as follows:

[0082] For each type of sensor of the sensor unit, the standard deviation σ of the sensor readings of this type of sensor is calculated according to the formula S i is the reading of the i-th sensor, and μ is the average value of the historical readings of this type of sensor;

[0083] The value range [A, B] of each type of sensor of the sensor unit is calculated according to the formula Before calculating the average value of M sensor readings every other period, it is judged whether the M sensor readings are within the value range [A, B], if yes, the average value of M sensor readings is further calculated, if no, it is judged that the sensor reading is abnormal, and an abnormal signal is generated and transmitted to the mobile terminal of the wearer;

[0084] It should be noted that by comparing the data of multiple sensors, the failure or abnormal condition of the sensor can be found in time. If the data of a certain sensor is significantly different from the data of other sensors, it indicates that the sensor has a problem and needs to be maintained or replaced. This fault detection capability can improve the self-diagnosis and self-repairing capability of the system, further enhancing the reliability of the system.

[0085] It should be further noted that the generation of the abnormal signal is transmitted to the mobile terminal of the wearer to inform the wearer that the sensor is abnormal, so that the wearer can maintain or replace the sensor subsequently.

[0086] As an optional embodiment, the data acquisition unit is further configured to adjust the average value of the corresponding sensor reading according to the environmental parameters, and the specific steps are as follows:

[0087] After obtaining the average value of the M sensor readings, the environmental temperature T1, the environmental humidity T2 and the environmental pressure T3 of the current wearer are obtained every other period before transmission, so as to set an environmental temperature base value t1, an environmental humidity base value t2 and an environmental pressure base value t3.

[0088] For each sensor reading, the formula is:

[0089] SX i = S i -[0.5*(T1-t1)+0.3*(T2-t2)+0.2*(T3-t3)]

[0090] The adjusted average value of the sensor reading is calculated and then transmitted to the data analysis module.

[0091] It should be noted that the base values of the environmental temperature, the environmental humidity and the environmental pressure are 25℃, 50% and 1000hpa respectively. It should be further noted that the environmental sensor data is used to calibrate the physiological signal in real time, reducing environmental interference. For example, the body temperature sensor dynamically adjusts the baseline value according to the environmental temperature to avoid false positives. Through the self-calibration function, the accuracy of the physiological signal can be significantly improved, and the error caused by environmental interference can be reduced. The self-calibration function can ensure the stability and reliability of the data, which can adapt to the wearer in various complex environments such as high temperature, high humidity and high altitude.

[0092] As an optional embodiment, the specific working steps of the data analysis module are as follows:

[0093] First, the average value of each sensor reading is obtained every other period, and the average value of each sensor reading is taken as the reading of the sensor in this period.

[0094] The reading Q1 of the heart rate sensor, the reading Q2 of the body temperature sensor, the reading Q3 of the respiratory frequency sensor, and the reading Q4 of the blood oxygen saturation sensor are obtained.

[0095] According to the formula:

[0096]

[0097] The dynamic baseline value G of the wearer is calculated i , wherein represents the reading of the i-th type of sensor at time t, W L is the first time interval, specifically 7, W S is the second time interval, specifically 8, and the baseline value G is recalculated every certain period of time i , i is 1 to 4, and there are four types of sensors in total, and the baseline value G corresponding to each parameter of heart rate, body temperature, respiratory frequency, and blood oxygen saturation is calculated i , wherein G1 corresponds to the heart rate parameter, G2 corresponds to the body temperature parameter, G3 corresponds to the respiratory frequency parameter, and G4 corresponds to the blood oxygen saturation parameter.

[0098] It should be noted that the time period is 4 hours in this embodiment, the first time interval is used to collect the average physiological parameter of the wearer in the previous week, so the value is 7 days, and the second time interval is used to collect the average physiological parameter of the wearer in the previous day in the actual use process. Because the state of the wearer is different every day, in actual use, not only the historical data of the wearer in the previous week is considered, but also the data of the wearer on the current day is considered, and the dynamic baseline value G of the wearer is obtained by comprehensively considering the two groups of data i , wherein t1 is the average parameter of the i-th type of sensor in the t1 time period, and t2 is the average parameter of the i-th type of sensor in the t2 time period. The unit of t1 is day, and the unit of t2 is hour.

[0099] Then, according to the formula:

[0100]

[0101] The compensation coefficient is calculated when i is equal to 1, 2, and 4, and the compensation coefficient is 1 when i is equal to 3. The threshold range N of each parameter is obtained through the formula N i = K i *G i *[1±10%]。 i It should be noted that AGE is the age of the wearer, BMI is the body mass index of the wearer, and SM is the number of cigarettes smoked by the wearer per day divided by five and rounded up.

[0102] For the first time wearing or wearing time not more than seven days of the wearer, get all the wearer history heart rate recorded average value q1, the average value q2 of body temperature, the average value q3 of respiratory rate, the average value q4 of blood oxygen saturation;

[0103] The wearer's heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters are all in the threshold range of the corresponding historical average value ± 10%. The first time wearing the wearer cannot identify the special nature of his personal physiological parameters, so the average value of other wearers is used to reference the threshold range;

[0104] It should be noted that in the use process, each wearer has different personal conditions, as the helmet is mainly used for the construction site, the wearer is mainly the worker, and the number of wearers is large. The self-condition and current physiological parameters of each wearer are different. If a fixed threshold range is used for judgment, the judgment may be wrong. The technical solution combines the periodic law of the wearer's parameters, and means that the dynamic baseline value is not fixed, but is updated over time. Every 4 hours, the dynamic baseline value is recalculated according to the latest sensor data according to the above calculation method. The purpose of this is to make the dynamic baseline adapt to the changes in physiological parameters in time, and always accurately reflect the current physiological state. If the physiological parameters of the wearer change in a short time (such as physiological fluctuations caused by exercise, sleep, and eating), the baseline value is recalculated every 4 hours, which can consider these changes in time and update the dynamic baseline, thereby providing more accurate reference for subsequent physiological state monitoring and analysis.

[0105] When the ratio of the wearer's heart rate to the respiratory rate reaches 2.5, the body temperature threshold is multiplied by the corresponding compensation coefficient, and then multiplied by [1±15%] as the body temperature threshold range. It should be noted that under normal circumstances, there is a certain proportional relationship between heart rate and respiratory rate. When the ratio exceeds 2.5, it means that the correlation between the two is abnormal, which may be caused by certain physiological or pathological factors;

[0106] There is a certain physiological correlation between heart rate and respiratory rate. When the ratio is abnormal, it may be caused by certain specific physiological or pathological states. At this time, the body temperature threshold is relaxed, which can avoid misjudgment due to slight fluctuations in body temperature, and more accurately reflects the true state of the body. For example, after intense exercise, the heart rate and respiratory rate will increase, and the heart rate / respiratory ratio may temporarily exceed the normal range. However, if the body temperature also rises slightly at this time, relaxing the body temperature threshold can avoid misjudgment of this normal physiological response as an abnormal condition such as fever;

[0107] If the fixed body temperature threshold is strictly followed, unnecessary interventions may be made due to a slight increase in body temperature, such as the use of antipyretics, in cases of abnormal heart rate / respiration ratio. Relaxing the body temperature threshold can reduce such over-intervention and avoid unnecessary harm and burden to the wearer.

[0108] Physiological parameters such as heart rate, respiratory rate and body temperature vary among individuals. Fixed thresholds may not be applicable to all individuals. By dynamically adjusting the body temperature threshold based on abnormalities in the heart rate / respiration ratio, it is possible to better adapt to individual differences and provide more personalized diagnosis and treatment plans for each wearer.

[0109] When the wearer's blood oxygen saturation parameter is less than 92% and body temperature is higher than the critical value, the baseline value G corresponding to the blood oxygen saturation is first used. i Multiply by the corresponding compensation coefficient, then multiply by [1±10%] to obtain the threshold range of blood oxygen saturation, and then subtract... The corrected threshold range for blood oxygen saturation is obtained, where G2 is the wearer's body temperature parameter; The normal body temperature is 37°C in this embodiment. The threshold value is the threshold value when the wearer's body temperature is higher than the normal range, which is 37.5°C in this embodiment. Based on the final blood oxygen threshold, the blood oxygen threshold is reduced according to the degree to which the body temperature exceeds 37.0°C. This means that when the body temperature increases by 1°C, the blood oxygen threshold is reduced by 0.5 percentage points. The reason is that considering that an increase in body temperature may affect the measurement of blood oxygen and actual needs, by reducing the blood oxygen threshold, the blood oxygen status in the case of fever can be more accurately assessed, avoiding misjudgment of severe hypoxia due to the relative decrease in blood oxygen caused by fever.

[0110] It should be noted that when blood oxygen is low and body temperature is high, it indicates that the body may be in a relatively serious pathological state, such as infection or inflammation. By urgently correcting the blood oxygen threshold, this potential risk can be detected more promptly.

[0111] If the wearer's heart rate, body temperature, respiratory rate, and blood oxygen saturation are all within the corresponding threshold range, then the wearer is considered to be in a normal state.

[0112] If the wearer's heart rate is not within the corresponding threshold range, the reading of the wearer's EEG sensor is further judged to see if the theta wave energy rises by more than 20%. If so, the wearer is judged to be in a state of mild fatigue; if not, the wearer is judged to be in a normal state.

[0113] If any two or all of the wearer's heart rate, respiratory rate and blood oxygen saturation are not within the corresponding threshold range, further determine whether the wearer's brain wave sensor reading, theta wave energy rise, exceeds 20%, if so, determine that the wearer is in a severe fatigue state;

[0114] If not, further determine whether the ambient pressure in which the wearer is located is greater than 1000hpa, if so, determine that the wearer is in a hypoxia warning state, if not, determine that the wearer is in a normal state;

[0115] If the wearer's body temperature and heart rate are not within the corresponding threshold range at the same time, further determine whether the ambient temperature in which the wearer is located is greater than 32℃, if so, it indicates that the wearer is in a heatstroke risk state, if not, determine that the wearer is in a normal state;

[0116] If the wearer's heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters are not within the corresponding threshold range, determine that the wearer is in an emergency abnormal state;

[0117] The above determination result is taken as a classification result and transmitted to the response module;

[0118] If the gas sensor reading indicates that the CO concentration is between 30-50ppm and the H2S concentration is between 5-10ppm, it is determined to be a first-level dangerous environment;

[0119] If the CO concentration is between 50-100ppm and the H2S concentration is between 10-20ppm, it is determined to be a second-level dangerous environment;

[0120] If the CO concentration is greater than 100ppm and the H2S concentration is greater than 20ppm, it is determined to be a third-level dangerous environment, and the determination result is also transmitted as a classification result. It should be noted that in high-risk working environments such as construction sites and mines, real-time monitoring of the wearer's physiological state can timely detect fatigue, heatstroke, hypoxia and other risks, improve the safety of workers, and through timely detection and handling of fatigue, it can avoid the decline in work efficiency caused by fatigue, improve overall work efficiency, and through long-term monitoring of the wearer's physiological state, it can provide data support for health management and timely detection of potential health problems.

[0121] As an optional embodiment, the specific steps of the data analysis module further include the following:

[0122] The working time of the wearer is obtained. The specific way to obtain the working time is to automatically time the helmet when the wearer wears it until the current time;

[0123] The historical average working time V and the historical standard deviation σ of the wearer are obtained; it should be noted that if it is the first time to wear, the average data of the construction site is used; the personalized fatigue threshold is adjusted according to the difference between the current physiological parameters and the dynamic baseline, thereby helping to more accurately manage the fatigue level of the subject;

[0124] The critical working time V1 of the wearer is calculated according to the formula V1=V+1.05*σ; it should be noted that the historical working time data of the wearer can be approximately obtained through the historical average working time and the historical standard deviation, and the initial critical working time V1 is obtained through the historical working time data of the wearer;

[0125] The current heart rate, body temperature, respiratory rate, blood oxygen saturation parameters of the wearer and the corresponding dynamic baseline value G of the wearer are obtained i The difference between the current heart rate, body temperature, respiratory rate, blood oxygen saturation parameters of the wearer and the corresponding dynamic baseline value G of the wearer is obtained, and all the differences are normalized and added and then divided by 4 to obtain the total difference value J;

[0126] The critical working time V2 of the wearer is calculated according to the formula V2=V1-0.1*J

[0127] If the working time of the current wearer is greater than V2, it is judged that the wearer has a mild fatigue state;

[0128] According to the formula, the time and duration of the occurrence of fatigue are also automatically recorded, and if the number of times of mild fatigue state in 4 hours reaches 3 times, even if the current classification result is still mild fatigue state, the judgment result is changed to severe fatigue state;

[0129] If any one of the heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters of the wearer fluctuates by more than 20% within 5 minutes, and the classification result is mild fatigue state;

[0130] In the next 10 minutes, the data of the abnormal item is continuously monitored, and if the fluctuation range of the abnormal item continues to increase or other abnormal physiological data appears, the classification result is immediately upgraded to a sudden abnormal state.

[0131] As an optional embodiment, the specific steps of the data analysis module further include the following

[0132] Each helmet is built-in RFID reader and memory card, and the memory card stores the physiological parameters of the data acquisition unit;

[0133] The memory card data of each helmet is connected through the Internet of Things;

[0134] The wearer wears an anti-disassembly electronic badge integrated with a passive RFID tag, and the helmet is uniformly stored, so that the wearer can obtain the helmet through the anti-disassembly electronic badge, and put it back to the original position when use is finished. When the wearer wears the helmet, the helmet reads the RFID of the badge, obtains a basic identity code, obtains the threshold range of each parameter corresponding to the wearer, and then performs monitoring. It should be noted that each wearer and helmet are bound, and if the wearer wears the helmet of others, the data is not shared. The technical solution allows the helmet to identify through the tag, so that even if the wearer wears the helmet of others, the historical physiological parameters of the wearer can be identified.

[0135] As an optional embodiment, the specific working steps of the response module are as follows:

[0136] If the classification result is a normal state, no alarm is triggered;

[0137] If the classification result is a mild fatigue state, a voice prompt is issued through the built-in speaker or earphone of the helmet;

[0138] If the classification result is a severe fatigue state, a vibration alarm is issued through the built-in vibration motor of the helmet, and whether any one of the heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters of the wearer is within the corresponding average value ± 10% range is detected. If yes, the current state data and position information are sent to the monitoring center for further measures, and if no, the judgment result is upgraded to a sudden abnormal state;

[0139] If the classification result is an oxygen deficiency warning state, a vibration alarm is issued through the built-in vibration motor of the helmet, and the current state data and position information are sent to the monitoring center for further measures;

[0140] If the classification result is a heatstroke risk state, a vibration alarm is issued through the built-in vibration motor of the helmet, and the current state data and position information are sent to the monitoring center for further measures;

[0141] If the classification result is a sudden abnormal state, a vibration alarm is issued through the built-in vibration motor of the helmet, the current state data and position information are sent to the monitoring center for further measures, and an emergency rescue phone call is automatically dialed to send the position information and the current state data. It should be noted that the monitoring center is a control room of the construction site, which is responsible for receiving and processing physiological state data and alarm information from each wearer, and according to different classification results, the monitoring center can take the following further measures:

[0142] For a mild fatigue state, the direct supervisor or safety management personnel of the wearer are notified, and the wearer is suggested to rest properly. The current state data is recorded in a health log and marked as "mild fatigue". The state of the wearer is checked regularly to ensure that the wearer returns to a normal state;

[0143] Severe fatigue state, notify the wearer's direct supervisor or safety manager, suggest the wearer to rest immediately, arrange other personnel to replace the wearer's work, record the current state data to the health log, mark as "severe fatigue", regularly check the wearer's state, ensure the wearer to recover to normal state, and evaluate whether further medical examination is needed.

[0144] Hypoxia warning state, notify the wearer's direct supervisor or safety manager, suggest the wearer to leave the current environment immediately, and provide necessary oxygen supply, record the current state data to the health log, mark as "hypoxia warning", regularly check the wearer's state, ensure the wearer to recover to normal state, and evaluate whether further medical examination is needed.

[0145] Heatstroke risk state, notify the wearer's direct supervisor or safety manager, suggest the wearer to stop work immediately and take cooling measures such as drinking water, resting, etc., record the current state data to the health log, mark as "heatstroke risk", regularly check the wearer's state, ensure the wearer to recover to normal state, and evaluate whether further medical examination is needed.

[0146] Sudden abnormal state, immediately notify the emergency rescue team, provide the specific location and current state data of the wearer, automatically dial the emergency rescue phone, send the location information and current state data, record the current state data to the health log, mark as "sudden abnormality", keep in touch with the emergency rescue team to ensure the wearer to get timely medical assistance, and record the whole rescue process.

[0147] If the classification result is a first-level dangerous environment, send the current environment data and location information to the monitoring center through the built-in vibration motor in the helmet, and take further measures.

[0148] If the classification result is a second-level dangerous environment, send the current environment data and location information to the monitoring center through the built-in vibration motor in the helmet, and take further measures.

[0149] If the classification result is a third-level dangerous environment, send the current environment data and location information to the monitoring center through the built-in vibration motor in the helmet, and take further measures.

[0150] It should be noted that for the first-level dangerous environment, the wearer's direct supervisor or safety manager is notified, the wearer is advised to pay attention to ventilation and avoid long-term exposure, the current state data is recorded to the health log, marked as "first-level dangerous environment", and the wearer's state is regularly checked to ensure safety.

[0151] For a secondary dangerous environment: notify the direct supervisor or safety manager of the wearer, recommend the wearer to evacuate the current environment immediately, record the current state data into the health log and mark it as "secondary dangerous environment", check the state of the wearer regularly and ensure his safety;

[0152] For a tertiary dangerous environment, immediately notify the emergency rescue team, provide the specific location and current state data of the wearer, automatically dial an emergency rescue phone, send the location information and current state data, record the current state data into the health log and mark it as "tertiary dangerous environment", keep in touch with the emergency rescue team to ensure that the wearer receives timely medical assistance, and record the entire rescue process.

[0153] As an optional embodiment, the specific steps of the data storage module are:

[0154] The data of the data acquisition module and the data analysis module are divided into multiple data subsets according to a preset sharding strategy, and the data subsets are stored on different nodes to complete the storage.

[0155] It should be noted that the hash sharding algorithm is selected, the ID of the data is used as the sharding key, the hash value is calculated, and the data is distributed to the corresponding node according to the calculated hash value.

[0156] For example, node 0 stores data with a hash value of 0, node 1 stores data with a hash value of 1, and so on; each node is configured with storage resources and access interfaces;

[0157] It should be noted that by data sharding storage, the data is distributed to multiple nodes, improving the efficiency and scalability of data storage.

[0158] The present application also proposes a vital sign monitoring method based on a multi-sensor helmet, comprising the following steps:

[0159] Step one: multiple sensors are installed at specific positions of the safety helmet to monitor the physiological parameters of the wearer and the construction site environment data in real time;

[0160] Step two: receive the processed sensor parameter data, analyze and identify the current state of the wearer, classify the state and obtain the classification result;

[0161] Step three: adopt different response strategies according to the classification result.

[0162] Working principle:

[0163] The data acquisition module comprises a sensor unit and a data acquisition unit, and the sensor unit specifically comprises a heart rate sensor for monitoring the real-time heart rate of the wearer, a body temperature sensor for monitoring the body surface temperature of the wearer in real time, a respiratory rate sensor for monitoring the respiratory rate of the wearer in real time, an electroencephalogram sensor for monitoring the fatigue state and abnormal brain activity of the wearer, a blood oxygen saturation sensor for monitoring the blood oxygen saturation of the wearer in real time, and a gas sensor, specifically comprising CO and H2S, for detecting the concentration of harmful gases in the construction site environment;

[0164] The temperature and humidity of the construction site environment are monitored in real time, and a barometric pressure sensor is used to monitor the barometric pressure of the construction site environment in real time.

[0165] The data acquisition unit is used to receive the parameter data of all sensors in the sensor unit, fuse the parameter data of all sensors, obtain processed sensor parameter data, and transmit the processed sensor parameter data.

[0166] The data analysis module is used to receive the processed sensor parameter data of the data acquisition unit, identify the current state of the wearer according to the processed sensor parameter data, classify the current state of the wearer, obtain a classification result, and transmit the classification result.

[0167] The response module is used to receive the classification result of the data analysis unit, and implement different response strategies according to different classification results.

[0168] The above is only a preferred embodiment of the present application, and the protection scope of the present application is not limited to the above-mentioned embodiments. Any technical solution falling within the scope of the present application is also within the protection scope of the present application. It should be noted that for ordinary technical personnel in the technical field, some improvements and refinements without departing from the principles of the present application are also considered to be within the protection scope of the present application.

Claims

1. A vital signs monitoring system based on a multi-sensor helmet, characterized in that, The system includes a data acquisition module, which comprises a sensor unit and a data acquisition unit. The sensor unit specifically includes a heart rate sensor for real-time monitoring of the wearer's instantaneous heart rate, a body temperature sensor for real-time monitoring of the wearer's body surface temperature, a respiratory rate sensor for real-time monitoring of the wearer's respiratory rate, an electroencephalogram (EEG) sensor for monitoring the wearer's fatigue state and abnormal brain activity, a blood oxygen saturation sensor for real-time monitoring of the wearer's blood oxygen saturation, and a gas sensor. It also includes a temperature and humidity sensor for real-time monitoring of the temperature and humidity of the construction site environment, and an air pressure sensor for real-time monitoring of the air pressure of the construction site environment. The data acquisition unit is used to receive parameter data from all sensors in the sensor unit, perform fusion processing on the parameter data of all sensors to obtain processed sensor parameter data, and transmit it. The data analysis module is used to receive sensor parameter data processed by the data acquisition unit, identify the wearer's current state based on the processed sensor parameter data, classify the wearer's current state, obtain the classification result, and transmit it. A response module is used to receive the classification results from the data analysis unit and implement different response strategies based on the different classification results. The data storage module stores data fragments from the data acquisition module and the data analysis module across multiple nodes and supports data synchronization and recovery in offline mode. The data acquisition unit is also used to perform error analysis on the sensor readings of the sensor unit and remove abnormal sensor readings. The specific steps are as follows: For each type of sensor in the sensor unit, according to the formula The standard deviation of this type of sensor is calculated. ,in Let be the reading of the i-th sensor. This represents the average historical readings of this type of sensor. According to the formula The value range of each type of sensor in the sensor unit is calculated. Before calculating the average of the M sensor readings at each cycle, it is determined whether the M sensor readings are within the range of values. If the reading is within the range, the average value of the M sensor readings is calculated; otherwise, the sensor reading is determined to be abnormal, and an abnormal signal is generated and transmitted to the wearer's mobile phone terminal. The data acquisition unit is also used to adjust the average value of the corresponding sensor readings according to environmental parameters, and the specific steps are as follows: After obtaining the average value of M sensor readings, before transmission, the ambient temperature T1, ambient humidity T2 and ambient air pressure T3 of the current wearer are obtained every cycle, so as to set an ambient temperature base value t1, ambient humidity base value t2 and ambient air pressure base value t3. For the reading of each sensor, according to the formula: The average value of the adjusted sensor readings is calculated and then transmitted to the data analysis module. The specific working steps of the data analysis module are as follows: First, at each cycle, the average value of the readings of each sensor is obtained, and the average value of the readings of each sensor is taken as the reading of that sensor in that cycle; The readings of the heart rate sensor (Q1), body temperature sensor (Q2), respiratory rate sensor (Q3), and blood oxygen saturation sensor (Q4) are obtained. According to the formula; The wearer's dynamic baseline value was calculated. ,in This represents the reading of the i-th type of sensor at time t. For the first time interval, The second time interval is used to recalculate the baseline value at regular intervals. The value of i ranges from 1 to 4. There are four types of sensors in total. The baseline values ​​for each parameter, namely heart rate, body temperature, respiratory rate, and blood oxygen saturation, are calculated. , where the corresponding For heart rate parameters, For body temperature parameters, For respiratory rate parameters, This refers to the blood oxygen saturation parameter. Then, according to the formula: The compensation coefficients for i equal to 1, 2, and 4 are calculated. For i equal to 3, the compensation coefficient is 1, obtained using the formula... To obtain the threshold range for each parameter ; When the wearer's heart rate to respiratory rate ratio reaches 2.5, the body temperature threshold is multiplied by the corresponding compensation coefficient, and then multiplied by [1±15%] to obtain the body temperature threshold range. When the wearer's blood oxygen saturation parameter is less than 92% and body temperature is higher than the critical value, the baseline value corresponding to blood oxygen saturation will be used first. Multiply by the corresponding compensation coefficient, then multiply by [1±10%] to obtain the threshold range of blood oxygen saturation, and then subtract... The corrected threshold range for blood oxygen saturation is obtained, where This refers to the wearer's body temperature.

2. The vital signs monitoring system based on a multi-sensor helmet according to claim 1, characterized in that, The specific working steps of the data acquisition unit are as follows: Obtain the number M of each type of sensor installed and the current reading of each sensor. Every cycle, calculate the average value of the M sensor readings, use the average value as the processed sensor parameter data, and transmit it.

3. The vital signs monitoring system based on a multi-sensor helmet according to claim 1, characterized in that, If the wearer's heart rate, body temperature, respiratory rate, and blood oxygen saturation are all within the corresponding threshold range, then the wearer is considered to be in a normal state. If the wearer's heart rate is not within the corresponding threshold range, the reading of the wearer's EEG sensor is further judged to see if the theta wave energy rises by more than 20%. If so, the wearer is judged to be in a state of mild fatigue; if not, the wearer is judged to be in a normal state. If any two or three of the wearer's heart rate, respiratory rate, and blood oxygen saturation are outside the corresponding threshold range, the readings of the wearer's EEG sensor will be further assessed to determine whether the theta wave energy rises by more than 20%. If so, the wearer will be judged to be in a state of severe fatigue. If not, then it is further determined whether the ambient air pressure of the wearer's environment is greater than 1000 hpa. If so, it is determined that the wearer is in a state of hypoxia warning. If not, it is determined that the wearer is in a normal state. If the wearer's body temperature and heart rate are both outside the corresponding threshold range, it is further determined whether the ambient temperature of the wearer is greater than 32℃. If it is greater, it indicates that the wearer is at risk of heatstroke. If not, it is determined that the wearer is in a normal state. If the wearer's heart rate, body temperature, respiratory rate, and blood oxygen saturation parameters are all outside the corresponding threshold range, the wearer is judged to be in a sudden abnormal state. The above judgment result is used as the classification result and transmitted to the response module.

4. The vital signs monitoring system based on a multi-sensor helmet according to claim 1, characterized in that, The specific steps of the data analysis module also include the following: To obtain the wearer's working hours; Obtain the wearer's historical average working hours (V) and historical standard deviation. ; According to the formula The critical working time V1 of the wearer is calculated and obtained; The wearer's current heart rate, body temperature, respiratory rate, blood oxygen saturation parameters, and corresponding dynamic baseline values ​​are obtained. The difference is calculated by normalizing all the differences, summing them, and then dividing by 4 to obtain the total difference value J. According to the formula The wearer's critical working time V2 was calculated. If the current wearer's working hours are greater than If so, it can be determined that the wearer is in a state of mild fatigue; The formula will also automatically record the time and duration of each instance of fatigue. If the cumulative number of mild fatigue states reaches 3 times within 4 hours, the judgment will be changed to severe fatigue state, even if the current classification result is still mild fatigue state. If any of the wearer's heart rate, body temperature, respiratory rate, or blood oxygen saturation parameters fluctuate by more than 20% within 5 minutes, and the classification result is mild fatigue; Over the next 10 minutes, continuously monitor the data for the abnormal item. If the fluctuation range of the abnormal item's data continues to increase or other abnormal physiological data appears, immediately upgrade the classification result to a sudden abnormal state.

5. A vital signs monitoring system based on a multi-sensor helmet according to claim 1, characterized in that, The specific working steps of the response module are as follows: If the classification result is normal, no alarm will be triggered; If the classification result is mild fatigue, a voice prompt will be issued through the helmet's built-in speaker or headphones; If the classification result is severe fatigue, a vibration alarm will be triggered by the built-in vibration motor in the helmet. If the classification result indicates an oxygen deficiency warning state, a vibration alarm will be triggered by the built-in vibration motor in the helmet, and the current status data and location information will be sent to the monitoring center for further measures. If the classification result is a heatstroke risk status, a vibration alarm will be issued through the built-in vibration motor of the helmet, and the current status data and location information will be sent to the monitoring center for further measures. If the classification result is a sudden abnormal state, the helmet's built-in vibration motor will issue a vibration alarm, send the current status data and location information to the monitoring center, take further measures, and automatically dial the emergency rescue number, sending the location information and current status data.

6. A vital signs monitoring system based on a multi-sensor helmet according to claim 1, characterized in that, The specific steps of the data storage module are as follows: The data from the data acquisition module and the data analysis module are divided into multiple data subsets according to a preset sharding strategy, and these data subsets are stored on different nodes to complete the storage. Each helmet has a built-in RFID reader and memory card, with the memory card storing the physiological parameters of the data acquisition unit; The memory card data in each helmet is connected via the Internet of Things; Wearers wear tamper-proof electronic name tags that integrate passive RFID tags. The helmets are stored together. Wearers retrieve their helmets using the tamper-proof electronic name tags and return them to their original locations when finished using them. When a wearer is wearing a helmet, the helmet reads the RFID tag to obtain a basic identification code and then obtains the threshold range for each parameter corresponding to the wearer, which is then monitored.

7. A method for monitoring vital signs based on a multi-sensor helmet, applicable to the vital signs monitoring system based on a multi-sensor helmet as described in any one of claims 1 to 6, characterized in that, Includes the following steps: Step 1: Multiple sensors are installed in specific locations on the safety helmet to monitor the wearer's physiological parameters and construction site environmental data in real time; Step 2: Receive the processed sensor parameter data, analyze and identify the wearer's current state, classify the state, and obtain the classification result; Step 3: Adopt different response strategies based on the classification results.

Images