Plateau oxygen production and health monitoring integrated system

Abstract

The invention provides a plateau oxygen generation and health monitoring integrated system, which comprises an oxygen generator, a sensor, an electromagnetic valve, a blood oxygen concentration detector, a data transmission system, a control system, a central machine room and a data large screen, and is characterized in that the oxygen generator provides oxygen for a school classroom, and the sensor monitors various parameters in the classroom in real time; the control system controls the electromagnetic valve and the oxygen generator to automatically adjust the oxygen supply amount according to sensor data, the data transmission system transmits the sensor data to the control system and the data platform, the blood oxygen concentration detector monitors the blood oxygen concentration of students in real time and transmits the data to the data platform, and the physical state of the students is judged through big data analysis. The central machine room is provided with a server which is responsible for storing and processing data, the software platform realizes management and remote control of the system, and the data large screen displays each piece of data. The system realizes intelligent adjustment of oxygen supply and real-time monitoring of student health conditions, and has higher integration level, intelligent degree and cost effectiveness.

Description

Technical Field

[0001] The invention belongs to the technical field of environmental control, and in particular relates to an integrated system of plateau oxygen production and health monitoring. Background Art

[0002] Due to the high altitude, thin air and low oxygen content in plateau areas, long-term exposure to low oxygen environment will have adverse effects on human health, especially for students in the growth and development stage. Low oxygen environment may cause students to experience symptoms such as dizziness, fatigue, and memory loss. In severe cases, it may even affect students' physical development and learning efficiency. In order to improve the learning environment of plateau schools and protect students' physical health, a system that can intelligently adjust oxygen supply and monitor students' health status in real time is urgently needed.

[0003] At present, schools in plateau areas usually use traditional ventilation equipment or simple oxygen cylinder oxygen supply methods, but these methods have many shortcomings. First, traditional ventilation equipment cannot effectively increase the oxygen concentration in the classroom, especially in plateau areas. The oxygen content of the air itself is low, and it is difficult to meet the oxygen needs of students by relying solely on ventilation. Secondly, although the oxygen cylinder oxygen supply method can provide oxygen, there are problems such as unstable oxygen supply, inconvenient management, and great safety hazards. In addition, the existing oxygen supply system lacks the function of real-time monitoring of students' health status, and cannot dynamically adjust the oxygen supply according to the students' physiological state. Summary of the invention

[0004] The technical problem solved by the present invention is to provide an integrated system of plateau oxygen production and health monitoring, which can realize intelligent adjustment of oxygen supply and real-time monitoring of students' health status, and solve the problem that the existing oxygen supply method lacks intelligent management and cannot intelligently adjust the oxygen supply according to real-time conditions.

[0005] The technical solution adopted by the present invention is: an integrated system of plateau oxygen production and health monitoring, including an oxygen generator, a sensor, a solenoid valve, a blood oxygen concentration detector, a data transmission system, a control system, a central computer room and a large data screen. The oxygen generator is used to provide oxygen to school classrooms. The sensor monitors various parameters in the classroom in real time, including oxygen concentration, carbon dioxide concentration, temperature and humidity. The control system controls the solenoid valve and the oxygen generator according to the sensor data to automatically adjust the oxygen supply to achieve intelligent oxygen supply. The data transmission system is a wired transmission network, which transmits sensor data to the control system and the data platform. The blood oxygen concentration detector monitors the blood oxygen concentration of students in real time, transmits data to the data platform via 4G, saves data to a database or directly calls an interface, and judges the student's physical condition through big data analysis. The central computer room is equipped with a server responsible for storing and processing data. The central computer room is equipped with a software platform to realize system management and remote control. The large data screen displays student information, classroom oxygen content and oxygen generator data.

[0006] Preferably, the oxygen generation capacity of the oxygen generator is calculated based on the classroom area, the number of students, the altitude, the oxygen consumption rate and the target oxygen concentration.

[0007] Preferably, the oxygen concentrator is located in a dedicated machine room and is connected to each classroom via a PVC pipeline, and a solenoid valve is provided on each classroom branch of the pipeline.

[0008] Preferably, the oxygen concentrators are arranged on a floor-by-floor basis, with one oxygen concentrator installed on each floor. The oxygen concentrators are connected to the classrooms on the floor via pipelines, and solenoid valves are provided on each classroom branch of the pipelines.

[0009] Preferably, the oxygen concentrators are arranged according to classrooms, and each classroom is equipped with an oxygen concentrator.

[0010] Preferably, four sensors are provided in each classroom, and are evenly spaced at the four corners of the classroom ceiling.

[0011] Preferably, the control system adopts a dynamic priority adaptive adjustment algorithm based on multimodal data fusion, specifically by fusing environmental data including oxygen concentration, carbon dioxide concentration, temperature and humidity and physiological data including students' blood oxygen saturation and heart rate, and combining classroom dynamic scenes including the number of people, time, and activity intensity, to construct a multimodal data fusion model, and introduce a dynamic priority mechanism and an adaptive adjustment strategy to achieve intelligent optimization control of oxygen supply.

[0012] Preferably, the algorithm steps of the control system are: Step 1: Data collection and preprocessing; the collected data include: environmental data, physiological data, classroom dynamic scene data, and the collected data is Kalman filtered to eliminate noise interference and normalized to obtain oxygen concentration O 2 、Carbon dioxide concentration CO 2 、Students’ physiological status SpO 2 The data is mapped to the interval [0, 1]; Step 2: Multimodal data fusion; obtaining the calculation result of the health environment comprehensive index HEI; HEI=α⋅(ω 1 ⋅O 2 +ω 2 ⋅(1−CO 2 ))+β⋅(ω 3 ⋅SpO 2 +ω 4 ⋅(1−HR norm )); Among them, α is the environmental data weight coefficient, and its initial value is 0.6; β is the physiological data weight coefficient, and its initial value is 0.4; ω 1 ,ω 2 ,ω 3 ,ω 4 is the sub-weight coefficient obtained through optimization of historical data; HR norm A heart rate normalized value that is dynamically adjusted based on the student's age and resting heart rate; Step 3: Set up a dynamic priority mechanism; set priorities and scenario rules, and divide the priorities into three types according to the comprehensive health environment index results obtained in step 2, namely, emergency mode, optimization mode, and energy-saving mode; scenario rules are divided into class mode, courseware mode, and high-intensity mode; Step 4: Adopt an adaptive oxygen supply adjustment strategy. The adaptive oxygen supply strategy is a nonlinear adjustment function in the form of a piecewise function. Different adjustment strategies are adopted according to different ranges of the health environment comprehensive index. Step 5: Feedback learning and parameter optimization: Determine whether to adjust the weight coefficient based on the comparison between the HEI change rate after each adjustment and the threshold, and adjust the weight coefficient when the HEI change rate is less than the threshold.

[0013] Preferably, the adaptive oxygen supply strategy of step 4 is that when in emergency mode, the target oxygen supply is equal to the maximum oxygen supply; when in optimization mode, the target oxygen supply is equal to the maximum oxygen supply. ,in is the basic oxygen supply, k is the adjustment gain coefficient, which is dynamically adjusted according to the carbon dioxide concentration. The higher the carbon dioxide concentration, the larger the k value, and the more sensitive the oxygen supply regulation is. The lower the carbon dioxide concentration, the smaller the k value, and the more stable the oxygen supply regulation is. When in energy-saving mode, the target oxygen supply is equal to the minimum oxygen supply.

[0014] The beneficial effects of the present invention are as follows: the present invention can realize intelligent regulation of oxygen supply and real-time monitoring of students' health status, with higher integration, intelligence and cost-effectiveness; it deeply integrates students' physiological status with environmental data for the first time through multi-modal data fusion, breaking through the limitation of single environmental control; it adopts dynamic priority mechanism to introduce scene parameters such as time, number of people, activity intensity, etc., to realize scene adaptation of oxygen supply strategy; the adaptive oxygen supply strategy adopts nonlinear function adjustment strategy, taking into account response speed and stability, avoiding the integral saturation problem of traditional PID; it has lightweight feedback learning ability, and through online optimization of weight parameters, the system gradually adapts to the characteristics of different classrooms without the need for complex machine learning models. DETAILED DESCRIPTION

[0015] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0016] The key technical points of the present invention cover multiple aspects such as intelligent oxygen supply control, health monitoring, data fusion, remote management, data security, sealing modification, data display, system integration, energy-saving selection and data analysis.

[0017] An integrated system for plateau oxygen production and health monitoring includes an oxygen generator, a sensor, a solenoid valve, a blood oxygen concentration detector, a data transmission system, a control system, a central computer room and a data screen. The oxygen generator is used to provide oxygen to school classrooms. When the average value of the oxygen concentration measured by all sensors in the classroom is lower than the set value, the oxygen generator is started. The sensor monitors various parameters in the classroom in real time, including oxygen concentration, carbon dioxide concentration, temperature and humidity. The control system controls the solenoid valve and the oxygen generator according to the sensor data to automatically adjust the oxygen supply to realize intelligent oxygen supply. The data transmission system is a wired transmission network, which transmits the sensor data to the control system and the data platform. The blood oxygen concentration detector monitors the blood oxygen concentration of students in real time, transmits the data to the data platform through 4G, saves the data to the database or directly calls the interface, and judges the physical state of students through big data analysis. The central computer room is equipped with a server responsible for storing and processing data. The central computer room is equipped with a software platform to realize system management and remote control. The data screen displays student information, classroom oxygen content and oxygen generator data.

[0018] The preferred oxygen concentrator is the vspa oxygen concentrator. The oxygen concentrator is located in a dedicated machine room and is connected to each classroom through PVC pipes. Solenoid valves are installed on each classroom branch of the pipe.

[0019] As another embodiment, the oxygen concentrator can also be arranged by floor, with one oxygen concentrator installed on each floor. The oxygen concentrator is connected to the classrooms on the floor through pipelines, and solenoid valves are provided on each classroom branch of the pipeline.

[0020] As another embodiment, the oxygen concentrator may also be arranged in classrooms, with one oxygen concentrator installed in each classroom.

[0021] The oxygen production capacity of the oxygen concentrator is calculated based on the classroom area, number of students, altitude, oxygen consumption rate and target oxygen concentration. The classroom area determines the total volume of the classroom. The number of students determines the total amount of oxygen required. The altitude determines the oxygen content in the air. The target oxygen concentration usually hopes that the oxygen concentration in the classroom is close to the level of the plain area (about 20.9%). The oxygen consumption rate is the oxygen consumption of each person at rest.

[0022] Taking the example of an altitude of 4700 meters, a classroom area of ​​A = 45 square meters, a classroom height of h = 3 meters, and a number of students N = 30, the steps to calculate the required oxygen concentrator capacity are as follows: 1. Calculate the total volume of the classroom V = 45×3 = 135 cubic meters.

[0023] 2. Calculate the oxygen demand in the classroom: At an altitude of 4,700 meters, the oxygen content in the air is about 50% of that in the plains (about 10.5%). We hope to raise the oxygen concentration in the classroom to a level close to that in the plains (20.9%), so the amount of oxygen required is: Target oxygen concentration - current oxygen concentration = 20.9% - 10.5% = 10.4%; oxygen demand in the classroom Q O2 It can be calculated by the following formula: Q O2 = V×10.4% cubic meters / hour=135×10.4% = 14.04 cubic meters / hour.

[0024] 3. Consider students’ oxygen consumption: The oxygen consumption of each student at rest is about 0.005 cubic meters per hour. If there are 30 students in the classroom, the total oxygen consumption of the students is: Q students = 30×0.005 cubic meters / hour = 0.15 cubic meters / hour.

[0025] 4. Calculate total oxygen demand Total oxygen demand Q total It is the sum of the oxygen demand in the classroom and the oxygen consumption of the students: Q total = Q O2 + Q students= = 14.04 + 0.15 = 14.19 cubic meters per hour.

[0026] Therefore, the required oxygen concentrator capacity for the classroom is approximately 14.19 cubic meters per hour. In order to ensure that the system has a certain redundancy, a 15 cubic meter per hour oxygen concentrator is selected.

[0027] The sensors are oxygen and carbon dioxide concentration sensors with high precision and high stability, which can accurately measure the oxygen and carbon dioxide content in the classroom. Currently, the R485 sensor is used for testing. Multiple sensors are installed in different locations in each classroom to ensure that the air environment in the classroom can be fully and accurately monitored. Sensors can be installed in the four corners, the middle position, and near the doors and windows of the classroom. For example, there are 4 sensors in each classroom, which are evenly spaced at the four corners of the classroom ceiling. At the same time, each student also wears a non-contact blood oxygen concentration detector. Currently, two types of smart bracelets are used for testing. The smart bracelet transmits data via 4G. The data acquisition URL is provided by the supplier, and the data can be saved to the database or the interface can be directly called. Students wear the bracelet 24 hours a day to monitor the blood oxygen concentration in real time, and the data will be automatically uploaded to the data platform.

[0028] At the same time, a stable and reliable wired transmission network is established to transmit sensor data to the control system and data platform. The security and privacy of the data are ensured, and the transmitted data is encrypted.

[0029] First, the client and the server establish a TLS connection: the client initiates a TLS handshake request; the server returns a certificate, and the client verifies the legitimacy of the certificate; ECDHE (Elliptic Curve Diffie-Hellman Key Exchange) is used for key exchange to generate a session key; the handshake is completed and an encrypted channel is established. Then, data is transmitted, and AES256GCM (symmetric encryption) is used to encrypt and protect the integrity of the data; the data is encrypted during transmission to prevent eavesdropping and tampering. After the transmission is completed, the connection is closed and the session key is destroyed to ensure forward secrecy.

[0030] The control system adopts a dynamic priority adaptive adjustment algorithm based on multimodal data fusion. Specifically, it integrates environmental data including oxygen concentration, carbon dioxide concentration, temperature and humidity and physiological data including students' blood oxygen saturation and heart rate, and combines classroom dynamic scenes including number of people, time, and activity intensity to build a multimodal data fusion model to quantify the comprehensive index of the healthy environment, and introduces a dynamic priority mechanism and adaptive adjustment strategy to achieve intelligent optimization control of oxygen supply. It can also perform lightweight feedback learning, optimize weight parameters through historical data, and improve system adaptability. The control system can automatically adjust the oxygen supply according to the preset algorithm to ensure that the oxygen content in the classroom remains within an appropriate range. When the oxygen concentration is too low, the control system will automatically open the solenoid valve to increase the oxygen supply; when the oxygen concentration is too high, the control system will automatically close the solenoid valve to reduce the oxygen supply. At the same time, the control system can be remotely controlled, and the management personnel can remotely control the oxygen generator through the software platform of the central computer room, including start-stop control, parameter adjustment and other operations, as well as remote control of the solenoid valve to adjust the oxygen supply. When the system fails or an abnormal situation occurs, the control system can send an alarm signal in time to remind the management personnel to deal with it. For example, when the oxygen generator fails, the sensor is abnormal, or the oxygen concentration is too low or too high, the control system will issue an audible and visual alarm.

[0031] The algorithm steps of the control system are: Step 1: Data collection and preprocessing; the collected data include: environmental data, physiological data, classroom dynamic scene data, and the collected data is Kalman filtered to eliminate noise interference and normalized to obtain oxygen concentration O 2 、Carbon dioxide concentration CO 2 、Students’ physiological status SpO 2 The data is mapped to the interval [0, 1]; Step 2: Multimodal data fusion; obtaining the calculation result of the health environment comprehensive index HEI; HEI=α⋅(ω 1 ⋅O 2 +ω 2 ⋅(1−CO 2 ))+β⋅(ω 3 ⋅SpO 2 +ω 4 ⋅(1−HR norm )); Among them, α is the environmental data weight coefficient, and its initial value is 0.6; β is the physiological data weight coefficient, and its initial value is 0.4; ω 1 ,ω 2 ,ω 3 ,ω 4 is the sub-weight coefficient obtained through optimization of historical data; HR norm It is a heart rate normalized value that is dynamically adjusted based on the student's age and resting heart rate. This value is used to quantify the student's heart rate status and is used as one of the important parameters in the comprehensive health environment index to dynamically adjust the oxygen supply strategy.

[0032] The calculation formula is: ; Among them, HR current The student’s current heart rate value; HR min The lower limit of resting heart rate for the student's age group; HR max The upper limit of resting heart rate for the student's age group.

[0033] The reference values ​​of resting heart rate range for different age groups are: 70-110 beats per minute for 6-10 years old; 60-100 beats per minute for 11-15 years old; 50-90 beats per minute for 16-20 years old. For example, a 12-year-old student has a current heart rate of 85 beats per minute. norm =(85-60) / (100-60)=0.625.

[0034] Step 3: Set up a dynamic priority mechanism; set priorities and scenario rules, and divide the priorities into three types according to the comprehensive health environment index results obtained in step 2, namely, emergency mode, optimization mode, and energy-saving mode; scenario rules are divided into class mode, courseware mode, and high-intensity mode; When HEI < 0.4, it is emergency mode: oxygen supply is maximized and audible and visual alarms are triggered. When 0.4 ≤ HEI<0.7, it is the optimization mode: the oxygen supply is adjusted according to the scene rules. When HEI ≥ 0.7, it is energy-saving mode: maintain minimum oxygen supply and give priority to reducing energy consumption. Scene Adaptive Rules: Class time (T=1): Priority should be given to ensuring HEI>0.6. During inter-class activities (T=0), short-term HEI fluctuations are allowed (0.5≤HEI<0.7). High number of people / high activity intensity (N≥30 or A=1): Improve oxygen supply response speed. Step 4: Adopt an adaptive oxygen supply regulation strategy. The adaptive oxygen supply strategy is a nonlinear regulation function in the form of a piecewise function. Different regulation strategies are adopted according to different ranges of the comprehensive health environment index. The design goal of this function is to achieve smooth regulation of oxygen supply while avoiding oscillation or instability that may be caused by traditional linear regulation.

[0035] The adaptive oxygen supply strategy is that when in emergency mode, the target oxygen supply is equal to the maximum oxygen supply; when in optimization mode, the target oxygen supply is equal to the maximum oxygen supply. ,in is the basic oxygen supply, k is the adjustment gain coefficient, which is dynamically adjusted according to the carbon dioxide concentration. The higher the carbon dioxide concentration, the larger the k value is, and the more sensitive the oxygen supply regulation is. The lower the carbon dioxide concentration, the smaller the k value is, and the more stable the oxygen supply regulation is. When in energy-saving mode, the target oxygen supply is equal to the minimum oxygen supply. Adjustment gain coefficient k=k base ⋅(1+μ⋅CO 2 ), where k base is the basic gain coefficient (the default is 1); μ is the carbon dioxide concentration influence factor (the default is 0.1); CO 2 is the carbon dioxide concentration.

[0036] Step 5: Feedback learning and parameter optimization: Determine whether to adjust the weight coefficient based on the comparison between the HEI change rate after each adjustment and the threshold, and adjust the weight coefficient when the HEI change rate is less than the threshold.

[0037] Among them, the learning rate γ and threshold are the key parameters for optimizing the weight coefficients.

[0038] The learning rate γ is used to control the step size of the weight coefficient update. During the feedback learning and parameter optimization process, the system will adjust the weight coefficient such as ω according to the difference between the actual HEI value and the target HEI value. 1 ,ω 2 ,ω 3 ,ω 4 The learning rate determines the magnitude of each adjustment: a larger value of γ means that the weights are updated faster, but may cause oscillation or instability. A smaller value of γ means that the weights are updated slower, but more stable. By default, the learning rate γ is set to 0.01, which is a small value suitable for stable optimization in most scenarios.

[0039] The learning rate γ may need to be adjusted in the following cases: 1. System response is too slow: If the weight coefficient is found to be updated too slowly, resulting in the system not being sensitive enough to the HEI value, γ can be appropriately increased (such as from 0.01 to 0.05).

[0040] 2. System oscillation or instability: If it is found that the weight coefficient is updated too quickly, resulting in large fluctuations in the HEI value, γ can be appropriately reduced (for example, from 0.01 to 0.005).

[0041] 3. Changes in data distribution: If the distribution of environmental data or student health data changes significantly (such as sudden climate changes in plateau areas), γ may need to be readjusted to adapt to the new data characteristics.

[0042] The learning rate γ is set directly into the program as a parameter. At each weight update, the system adjusts the weight coefficient according to the following formula: ; is the updated weight coefficient; is the weight coefficient before updating; is the preset target value; is the current calculated value.

[0043] The threshold is used to determine whether the change in the HEI value is significant. If the rate of change of the HEI value is less than the threshold, it is considered that the system has reached a stable state and no further adjustment of the weight coefficient is required.

[0044] The threshold is usually a fixed value, which is set according to actual needs. For example: If you want the system to be more sensitive to changes in HEI values, you can set the threshold to a smaller value (such as 0.01).

[0045] If you want the system to be more lenient with changes in HEI values, you can set the threshold to a larger value (such as 0.05).

[0046] The hardware equipment in the central computer room includes servers, storage devices, network equipment and monitoring equipment: high-performance servers are selected as the core equipment of the central computer room to store and process system data. The server should have high reliability, high availability and high scalability to meet the long-term operation requirements of the system. Equipped with large-capacity storage devices, such as hard disk arrays, tape libraries, etc., to store the system's historical data and backup data. Storage devices should have high reliability and high security to ensure data integrity and availability. Network equipment includes switches, routers, firewalls and other equipment to build the network environment of the central computer room. Network equipment should have high bandwidth, low latency and high reliability to ensure the speed and stability of data transmission. Install surveillance cameras, environmental monitoring equipment, etc. to monitor the operating environment of the central computer room in real time. Monitoring equipment should have high definition, high reliability and remote monitoring functions to facilitate management personnel to discover and handle problems in a timely manner.

[0047] The system also includes a large data screen, and a high-definition, large-size LCD or LED display screen is selected as the display device of the large data screen. The display device should have the characteristics of high brightness, high contrast and wide viewing angle, and can clearly display real-time student information, classroom oxygen content, oxygen concentrator data, etc. in different environments.

[0048] Data collection and processing: The data screen connects to the server in the central computer room through the network to collect system data in real time. After data collection, it is analyzed and processed to generate intuitive charts and reports. According to the content and needs of the display, a reasonable layout of the data screen is designed to facilitate management personnel and teachers to view and understand, and provide decision support for management personnel. Management personnel can remotely access the data screen through the network to understand the operation of the system anytime and anywhere.

[0049] The above are specific embodiments of the present invention and the technical principles used. Any modifications and equivalent changes based on the technical solution of the present invention should be included in the protection scope of the present invention.

Claims

1. A plateau oxygen production and health monitoring integrated system, characterized by: It includes an oxygen concentrator, a sensor, a solenoid valve, a blood oxygen concentration detector, a data transmission system, a control system, a central computer room and a large data screen. The oxygen concentrator is used to provide oxygen for school classrooms. The sensor monitors various parameters in the classroom in real time, including oxygen concentration, carbon dioxide concentration, temperature and humidity. The control system controls the solenoid valve and the oxygen concentrator according to the sensor data to automatically adjust the oxygen supply to achieve intelligent oxygen supply. The data transmission system is a wired transmission network, which transmits sensor data to the control system and the data platform. The blood oxygen concentration detector monitors the students' blood oxygen concentration in real time, and transmits the data to the data platform via 4G. The data is saved in the database or the interface is directly called. The physical condition of the students is judged through big data analysis. The central computer room is equipped with a server responsible for storing and processing data. The central computer room is equipped with a software platform to realize system management and remote control. The large data screen displays student information, classroom oxygen content and oxygen concentrator data.

2. The integrated system of plateau oxygen production and health monitoring according to claim 1 is characterized in that: The oxygen generation capacity of the oxygen generator is calculated based on the classroom area, the number of students, the altitude, the oxygen consumption rate and the target oxygen concentration.

3. The integrated system of plateau oxygen production and health monitoring according to claim 1 is characterized by: The oxygen concentrator is located in a dedicated machine room and is connected to each classroom via a PVC pipeline. A solenoid valve is provided on each classroom branch of the pipeline.

4. The integrated system of plateau oxygen production and health monitoring according to claim 1 is characterized in that: The oxygen concentrators are arranged on a floor-by-floor basis, with one oxygen concentrator installed on each floor. The oxygen concentrators are connected to the classrooms on the floor through pipelines, and electromagnetic valves are arranged on the branches of each classroom of the pipelines.

5. The integrated system of plateau oxygen production and health monitoring according to claim 1 is characterized in that: The oxygen concentrators are arranged according to the classrooms, and each classroom is equipped with an oxygen concentrator.

6. The integrated system of plateau oxygen production and health monitoring according to claim 1 is characterized in that: Each classroom is provided with four sensors, which are evenly spaced at the four corners of the classroom ceiling.

7. The integrated system of plateau oxygen production and health monitoring according to claim 1 is characterized by: The control system adopts a dynamic priority adaptive adjustment algorithm based on multimodal data fusion. Specifically, it builds a multimodal data fusion model by integrating environmental data including oxygen concentration, carbon dioxide concentration, temperature and humidity and physiological data including students' blood oxygen saturation and heart rate, and combining dynamic classroom scenes including the number of people, time, and activity intensity. It also introduces a dynamic priority mechanism and an adaptive adjustment strategy to achieve intelligent optimization control of oxygen supply.

8. The integrated system of plateau oxygen production and health monitoring according to claim 7 is characterized in that: The algorithm steps of the control system are: Step 1, data collection and preprocessing; the collected data include: environmental data, physiological data, classroom dynamic scene data, and the collected data is subjected to Kalman filtering to eliminate noise interference, and the oxygen concentration O2, carbon dioxide concentration CO2, and student physiological status SpO2 data are normalized and mapped to the [0, 1] interval; Step 2: Multimodal data fusion; obtaining the calculation result of the health environment comprehensive index HEI; HEI=α⋅(ω1⋅O2+ω2⋅(1−CO2))+β⋅(ω3⋅SpO2+ω4⋅(1−HR) norm )); Among them, α is the environmental data weight coefficient, and its initial value is 0.6; β is the physiological data weight coefficient, and its initial value is 0.4; ω1, ω2, ω3, and ω4 are sub-weight coefficients obtained through optimization of historical data; HR norm A heart rate normalized value that is dynamically adjusted based on the student's age and resting heart rate; Step 3: Set up a dynamic priority mechanism; set priorities and scenario rules, and divide the priorities into three types according to the comprehensive health environment index results obtained in step 2, namely, emergency mode, optimization mode, and energy-saving mode; scenario rules are divided into class mode, courseware mode, and high-intensity mode; Step 4: Adopt an adaptive oxygen supply adjustment strategy. The adaptive oxygen supply strategy is a nonlinear adjustment function in the form of a piecewise function. Different adjustment strategies are adopted according to different ranges of the health environment comprehensive index. Step 5: Feedback learning and parameter optimization: Determine whether to adjust the weight coefficient based on the comparison between the HEI change rate after each adjustment and the threshold, and adjust the weight coefficient when the HEI change rate is less than the threshold.

9. The integrated system of plateau oxygen production and health monitoring according to claim 8, characterized in that: The adaptive oxygen supply strategy of step 4 is specifically that when in emergency mode, the target oxygen supply is equal to the maximum oxygen supply; when in optimization mode, the target oxygen supply is equal to the maximum oxygen supply. ,in is the basic oxygen supply, k is the adjustment gain coefficient, which is dynamically adjusted according to the carbon dioxide concentration. The higher the carbon dioxide concentration, the larger the k value, and the more sensitive the oxygen supply regulation is. The lower the carbon dioxide concentration, the smaller the k value, and the more stable the oxygen supply regulation is. When in energy-saving mode, the target oxygen supply is equal to the minimum oxygen supply.