Oxygen generator control method and system based on respiratory sensing feedback and blood oxygen detection

Abstract

This invention discloses an oxygen concentrator control method and system based on respiratory sensor feedback and blood oxygen detection. The method includes: synchronously collecting multi-dimensional respiratory correlation data such as respiratory rate and respiratory depth, along with real-time blood oxygen saturation monitoring data via a sensor module; extracting features to form calibration input parameters; dynamically matching the oxygen production rate benchmark value using an oxygen production rate closed-loop control model; solving for energy consumption and efficiency balance parameters using an oxygen production energy consumption optimization analytical algorithm; using a blood oxygen steady-state maintenance prediction model to predict blood oxygen change trends and correct parameters; and outputting control commands to the execution unit after integration by an oxygen production parameter optimization calculation platform. Through multi-unit collaboration, the system achieves deep linkage control of respiratory characteristics and blood oxygen status, as well as coordinated operation of oxygen production effect, energy consumption optimization, and blood oxygen prediction. This invention improves the adaptability, accuracy, and energy utilization rate of oxygen production control, meeting the dynamic oxygen production needs of different users.

Description

Technical Field

[0001] This invention relates to the field of oxygen concentrator control technology, and in particular to an oxygen concentrator control method and system based on respiratory sensor feedback and blood oxygen detection. Background Technology

[0002] In medical care and home health management, oxygen concentrators are crucial devices for maintaining vital signs and improving respiratory function in patients with hypoxia. Their control precision and adaptability directly impact their effectiveness. As users increasingly demand personalized oxygenation, traditional oxygenation modes relying on fixed parameters or single monitoring indicators are no longer sufficient to meet the dynamic needs of users with varying respiratory states and blood oxygen levels. Especially for individuals with significant fluctuations in respiratory rate and blood oxygen saturation, there is a need to establish a linkage control mechanism that can capture real-time changes in respiratory characteristics and blood oxygen levels. This mechanism should achieve precise matching between the oxygenation process and the body's respiratory rhythm and blood oxygen demand through multi-parameter coordinated regulation, while simultaneously optimizing oxygenation efficiency and energy consumption. This need has driven the research and application of oxygen concentrator control technologies based on respiratory sensor feedback and blood oxygen detection.

[0003] Existing oxygen concentrator control technologies have two significant drawbacks: First, they lack in-depth analysis of the linkage between respiratory characteristics and blood oxygen status. Most control methods adjust oxygen production parameters based on single monitoring data, failing to fully integrate the correlation between multi-dimensional respiratory information such as respiratory rate, respiratory depth, and respiratory cycle phase and changes in blood oxygen saturation. This results in insufficient adaptability of oxygen production rate adjustments to human respiratory rhythm and blood oxygen demand, making it difficult to achieve dynamic and precise control. Second, they lack a collaborative calculation system that balances oxygen production effect and energy consumption optimization. During the control process, they fail to comprehensively optimize oxygen production rate, operating energy consumption, and blood oxygen steady-state maintenance. They either excessively pursue blood oxygen targets while ignoring energy waste, or sacrifice oxygen production accuracy to reduce energy consumption. Furthermore, they lack the ability to predict future blood oxygen change trends and cannot adjust control parameters in advance to maintain blood oxygen steady-state. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of the existing technology, the present invention provides an oxygen generator control method and system based on respiratory sensor feedback and blood oxygen detection.

[0005] The technical solution adopted in this invention is an oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection, comprising the following steps: S1, collecting respiratory frequency, respiratory depth, inspiratory duration, and expiratory duration correlation data during the user's breathing process through a respiratory sensor module, and simultaneously acquiring real-time monitoring data of the user's arterial blood oxygen saturation through a blood oxygen detection module, and transmitting both types of data to an oxygen generation parameter optimization calculation platform; S2, the oxygen generation parameter optimization calculation platform extracts features from the received respiratory correlation data and blood oxygen monitoring data, and selects respiratory frequency fluctuation coefficient, blood oxygen saturation change rate, and blood oxygen response data corresponding to inspiratory peak as calibration input parameters; S3, calling the oxygen generation rate closed-loop control module. The system performs the following steps: S4, dynamically matching the oxygen production rate benchmark value based on the calibrated input parameters and adjusting the output amplitude of the oxygen production rate in conjunction with the respiratory cycle phase information; S5, initiating the oxygen production energy consumption optimization analysis algorithm, using the oxygen production rate benchmark value, target blood oxygen saturation range, and respiratory cycle duration as constraints, to calculate the balance parameters between the operating energy consumption and oxygen production efficiency of the oxygen production system; S6, using the blood oxygen steady-state maintenance prediction model to extrapolate the blood oxygen saturation change trend within a preset time period, and correcting the oxygen production rate adjustment amplitude and energy consumption balance parameters based on the extrapolation results; and S7, the oxygen production parameter optimization calculation platform sends the corrected oxygen production rate parameters and energy consumption control parameters to the oxygen concentrator execution unit for dynamic control of the oxygen production process.

[0006] Furthermore, the expression for the closed-loop control model of the oxygen production rate is:

[0007] ,

[0008] in, This refers to the real-time output rate of the oxygen concentrator. This is the blood oxygen deviation adjustment coefficient. The blood oxygen saturation value at time t is the monitored value. The target value for blood oxygen saturation. This is a respiratory rate correlation function. The factor representing the influence of respiratory depth is... This is a characteristic value of inhalation depth. This is the respiratory cycle phase factor.

[0009] Furthermore, the expression for the oxygen production energy consumption optimization analytical algorithm is as follows:

[0010] ,

[0011] in, To optimize the energy consumption of oxygen production, These are the basic power parameters for an oxygen concentrator. This refers to the real-time output rate of the oxygen concentrator. The energy efficiency coefficient of the oxygen production system. The energy consumption influencing factor of respiratory rate fluctuation. Real-time respiratory rate, This is the preset average respiratory rate.

[0012] Furthermore, the expression for the blood oxygen homeostasis maintenance prediction model is as follows:

[0013] ,

[0014] in, for Constantly monitor blood oxygen saturation. The blood oxygen saturation value at time t is the monitored value. The contribution coefficient of oxygen production rate to blood oxygenation. This refers to the real-time output rate of the oxygen concentrator. For predicting time intervals, The coefficient representing the influence of respiratory rate deviation on blood oxygenation. Real-time respiratory rate, This is the standard respiratory rate parameter.

[0015] Furthermore, the parameter optimization expression of the oxygen production parameter optimization calculation platform is as follows:

[0016] ,

[0017] Where Parafinal is the final output control parameter set. This is the weighting coefficient for oxygen production rate. This refers to the real-time output rate of the oxygen concentrator. To optimize the energy consumption weighting coefficient, To optimize the energy consumption of oxygen production, To predict the blood oxygen weighting coefficient, for Continuously predict blood oxygen saturation.

[0018] Further, S2 includes the following sub-steps: S21, performing time series alignment on the respiratory rate, respiratory depth, inspiratory duration, and expiratory duration correlation data transmitted by the respiratory sensing module, and extracting feature point data within each respiratory cycle; S22, performing continuous sampling point screening on the real-time arterial blood oxygen saturation monitoring data acquired by the blood oxygen detection module, removing abnormal jump data points, and retaining continuous and stable monitoring data segments; S23, calculating the fluctuation coefficient of respiratory rate within a preset time window, and processing the blood oxygen saturation data using a moving average algorithm to obtain the rate of change; S24, associating and marking the respiratory rate fluctuation coefficient, the rate of change of blood oxygen saturation, and the blood oxygen response data corresponding to the inspiratory peak to form a calibration input parameter set.

[0019] Further, S3 includes the following sub-steps: S31, the oxygen generation parameter optimization calculation platform calls the oxygen generation rate closed-loop control model, and substitutes the blood oxygen saturation change rate and respiratory rate fluctuation coefficient in the calibrated input parameters into the model initial calculation; S32, the respiratory cycle phase information is determined according to the ratio of inspiratory duration to expiratory duration, and the oxygen generation rate adjustment weight under different phases is calculated; S33, the oxygen generation rate benchmark value is dynamically corrected by combining the deviation between the target blood oxygen saturation range and the real-time monitoring value; S34, the initial value of the oxygen generation rate output amplitude is calculated according to the corrected benchmark value and the phase adjustment weight.

[0020] Further, step S4 includes the following sub-steps: S41, starting the oxygen generation energy consumption optimization and analysis algorithm, importing the oxygen generation rate benchmark value, the blood oxygen saturation target interval boundary value, and real-time respiratory cycle duration data; S42, setting the constraint threshold for the operating energy consumption of the oxygen generation system and the minimum required value for oxygen generation efficiency, and constructing a balance objective function between energy consumption and efficiency; S43, iteratively calculating the oxygen generator operating power, gas compression ratio, and molecular sieve adsorption time parameters through the algorithm; S44, outputting the energy consumption balance parameters that meet the constraint conditions, which include the power adjustment coefficient and the ratio relationship of operating parameters.

[0021] Further, S5 includes the following sub-steps: S51, inputting the corrected oxygen production rate adjustment amplitude, energy consumption balance parameters, and current blood oxygen saturation data into the blood oxygen steady-state maintenance prediction model; S52, setting the future preset duration as multiple consecutive time segments, and respectively deriving the blood oxygen saturation change trend within each time segment; S53, comparing the deriving results of each time segment with the target blood oxygen saturation range, and determining the parameter type and correction direction that need to be corrected; S54, calculating the correction amount based on the degree of deriving deviation, and dynamically correcting the oxygen production rate adjustment amplitude and energy consumption balance parameters.

[0022] An oxygen concentrator control system based on respiratory sensor feedback and blood oxygen detection is applied to an oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection. The system includes: a respiratory sensor data acquisition unit, a blood oxygen saturation monitoring unit, an oxygen production parameter optimization calculation unit, an oxygen production rate closed-loop control model calculation unit, an oxygen production energy consumption optimization analysis unit, and an oxygen production execution control unit. The respiratory sensor data acquisition unit and the blood oxygen saturation monitoring unit are respectively connected to the oxygen production parameter optimization calculation unit via data transmission links, used to transmit the collected respiratory correlation data and blood oxygen monitoring data to the oxygen production parameter optimization calculation unit in real time. The parameter optimization calculation unit communicates bidirectionally with both the oxygen production rate closed-loop control model calculation unit and the oxygen production energy consumption optimization analysis unit, and integrates the calculation results of the two units. The oxygen production rate closed-loop control model calculation unit completes the oxygen production rate related calculations based on the received calibration input parameters, and the oxygen production energy consumption optimization analysis unit solves the balance parameters between energy consumption and efficiency. The oxygen production parameter optimization calculation unit sends the integrated and corrected control parameters to the oxygen production execution control unit. The oxygen production execution control unit dynamically adjusts the operating status of the oxygen generator according to the received parameters. All units work together to dynamically control the oxygen production process.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] This invention proposes an oxygen concentrator control method and system based on respiratory sensor feedback and blood oxygen detection. Through collaborative data acquisition by a respiratory sensor module and a blood oxygen detection module, combined with a closed-loop control model for oxygen generation rate, an oxygen generation energy consumption optimization algorithm, a blood oxygen steady-state maintenance prediction model, and an oxygen generation parameter optimization calculation platform, it achieves deep linkage and comprehensive control of multi-dimensional parameters, significantly improving the accuracy and adaptability of oxygen generation control. This method collects multi-dimensional respiratory-related data such as respiratory rate, respiratory depth, and respiratory cycle phase, and simultaneously acquires real-time blood oxygen saturation monitoring data. After feature extraction, calibration input parameters are formed, utilizing the oxygen generation rate... The closed-loop control model dynamically matches the oxygen production rate, enabling precise adjustments to oxygen production to align with the body's respiratory rhythm and blood oxygen changes, completely overcoming the limitations of single-parameter control. Through an oxygen production energy consumption optimization algorithm, the energy consumption and efficiency balance parameters are solved under the constraints of the oxygen production rate and target blood oxygen range. Combined with a blood oxygen steady-state maintenance prediction model, future blood oxygen change trends are extrapolated, and control parameters are corrected in advance. After integration and correction by the oxygen production parameter optimization calculation platform, control commands are output, ensuring both stable blood oxygen maintenance and avoiding energy waste. Simultaneously, the collaborative work of each unit forms a complete control link, achieving dynamic, personalized, and efficient control of the oxygen production process. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the overall process of the method of the present invention.

[0026] Figure 2This is a flowchart of method step S2 of the present invention;

[0027] Figure 3 This is a flowchart of method step S3 of the present invention;

[0028] Figure 4 This is a flowchart of method step S4 of the present invention;

[0029] Figure 5 This is a flowchart of step S5 of the method of the present invention;

[0030] Figure 6 This is a diagram showing the system unit composition of the present invention. Detailed Implementation

[0031] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] like Figure 1 As shown, the oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection includes the following steps:

[0033] S1 collects data on the user's breathing rate, breathing depth, inhalation duration and exhalation duration through the breathing sensor module, and simultaneously obtains real-time monitoring data of the user's arterial blood oxygen saturation through the blood oxygen detection module. Both types of data are transmitted to the oxygen generation parameter optimization calculation platform.

[0034] Specifically, the implementation process of step S1 is as follows: A data acquisition link is constructed using a high-precision respiratory sensing module and a medical-grade blood oxygen detection module. The respiratory sensing module continuously captures multi-dimensional data during the user's breathing process at a sampling frequency of 50 times per second, including respiratory rate (monitoring range of 8 to 40 breaths per minute), respiratory depth (quantified by the change in chest cavity displacement during breathing, with a detection accuracy of 0.1 mm), inspiratory duration and expiratory duration (time measurement accuracy of 0.01 seconds), and records the temporal correlation of each parameter within the respiratory cycle. The blood oxygen detection module obtains the user's arterial blood oxygen saturation data at a sampling frequency of 30 times per second through the dual-wavelength detection principle of infrared and red light, with a detection range covering 70% to 100% and an accuracy controlled within ±1%. The data collected by the two types of modules are converted from analog to digital and then transmitted to the oxygen production parameter optimization calculation platform via wired Ethernet or Bluetooth 5.0 wireless communication links. The transmission delay is controlled within 100 milliseconds to ensure data real-time performance and provide accurate and complete raw data support for subsequent control parameter calculations. This step breaks the limitations of single data acquisition and realizes synchronous monitoring of respiratory status and blood oxygen level, laying a data foundation for multi-dimensional collaborative regulation.

[0035] S2, the oxygen production parameter optimization calculation platform extracts features from the received respiratory correlation data and blood oxygen monitoring data, and selects the blood oxygen response data corresponding to the respiratory rate fluctuation coefficient, blood oxygen saturation change rate, and inspiratory peak as calibration input parameters;

[0036] Specifically, the implementation process of step S2 is as follows: After receiving the data, the oxygen production parameter optimization calculation platform starts the data feature extraction process. First, the respiratory correlation data is time-series normalized and divided into data segments according to the respiratory cycle. Each data segment corresponds to one complete inhalation and exhalation process. The respiratory rate fluctuation coefficient is calculated based on the sliding time window algorithm (the window length is set to 5 respiratory cycles). This coefficient is obtained by the ratio of the standard deviation to the mean of the respiratory rate within each window and is used to quantify the stability of the respiratory rate. For blood oxygen monitoring data, a continuous data segment screening strategy is adopted to remove jump data points caused by wearing offset during the sampling process (set jump). (The threshold is set to 5%). Stable data segments with more than 10 consecutive sampling points are retained. The rate of change of blood oxygen saturation is calculated using a linear fitting algorithm to reflect the dynamic trend of blood oxygen level. At the same time, the time node corresponding to the inspiratory peak in each respiratory cycle is located, and the blood oxygen data of 3 sampling points before and after the node are extracted as blood oxygen response data. Finally, the respiratory rate fluctuation coefficient, the rate of change of blood oxygen saturation, and the blood oxygen response data corresponding to the inspiratory peak are associated and labeled to form a calibration input parameter set. This step filters out key features directly related to oxygen production control from the original data, reduces redundant data interference, and improves the efficiency and accuracy of subsequent model calculations.

[0037] S3 calls the closed-loop control model of oxygen production rate, dynamically matches the baseline value of oxygen production rate based on the calibrated input parameters, and adjusts the output amplitude of oxygen production rate by combining respiratory cycle phase information.

[0038] Specifically, the implementation process of step S3 is as follows: The oxygen generation parameter optimization calculation platform calls the pre-stored closed-loop control model of oxygen generation rate. First, the blood oxygen saturation change rate and respiratory rate fluctuation coefficient in the calibration input parameters are input into the model. Combined with the preset initial range of oxygen generation rate (1 to 10 liters per minute), the baseline value of oxygen generation rate is dynamically matched. When the blood oxygen saturation change rate is positive and the respiratory rate fluctuation coefficient is less than 0.2, the baseline value is taken as the middle value of the initial range. When the blood oxygen saturation change rate is negative or the respiratory rate fluctuation coefficient is greater than 0.5, the baseline value is adjusted towards the upper limit of the range by a gradient of 5%. Subsequently, based on the inspiratory duration collected in step S1 and The ratio of exhalation duration to exhalation duration is calculated to determine the respiratory cycle phase information. The respiratory cycle is divided into six phases: early inhalation, mid-inhalation, late inhalation, early exhalation, mid-exhalation, and late exhalation. Each phase corresponds to a different oxygen production rate adjustment weight (the weight for mid-inhalation is set to 1.0, and the weight for late exhalation is reset to 0.3). Based on the phase information and adjustment weights, the baseline value of oxygen production rate is adjusted by amplitude to obtain the output amplitude of oxygen production rate for each phase. This step achieves precise synchronization between oxygen production rate and respiratory cycle, enabling dynamic matching between oxygen supply and user inhalation demand, and avoiding supply waste caused by misalignment between oxygen production timing and respiratory rhythm.

[0039] S4, start the oxygen generation energy consumption optimization analysis algorithm, and calculate the balance parameters between the oxygen generation system's operating energy consumption and oxygen generation efficiency with the oxygen generation rate benchmark value, blood oxygen saturation target range, and respiratory cycle duration as constraints.

[0040] Specifically, the implementation process of step S4 is as follows: The oxygen generation energy consumption optimization algorithm is started. First, the baseline value of oxygen generation rate determined in step S3, the preset target range of blood oxygen saturation (90% to 98%), and the respiratory cycle duration calculated in step S1 (ranging from 1.5 to 5 seconds) are imported, and these three are used as constraints for the algorithm. The constraint threshold of the oxygen generation system's operating energy consumption (based on 30% to 80% of the oxygen concentrator's rated power) and the minimum required value of oxygen generation efficiency (≥85%) are set, constructing an optimization objective function with the goal of minimizing energy consumption and constraints of oxygen generation efficiency and achieving the target blood oxygen level. The algorithm iteratively calculates... The algorithm optimizes key operating parameters of the oxygen generator, such as operating power, gas compression ratio (adjustable range 1.2 to 2.5), and molecular sieve adsorption time (adjustable range 10 to 30 seconds). Each iteration adjusts the parameters by 5% and the number of iterations is set to 20 until a parameter combination that satisfies all constraints is found. Finally, the algorithm outputs a balance parameter between the operating energy consumption and oxygen production efficiency of the oxygen generation system. This parameter includes the power adjustment coefficient and the ratio of each operating parameter. This step achieves optimal energy consumption while ensuring oxygen production effect, avoiding ineffective energy consumption and improving the operating economy of the oxygen generator.

[0041] S5 uses a blood oxygen steady state maintenance prediction model to predict the trend of blood oxygen saturation changes within a preset time period, and adjusts the oxygen production rate adjustment amplitude and energy consumption balance parameters based on the prediction results.

[0042] Specifically, the implementation process of step S5 is as follows: The oxygen production rate adjustment amplitude corrected in step S3, the energy consumption balance parameters obtained in step S4, and the current stable blood oxygen saturation data filtered in step S2 are input into the blood oxygen steady-state maintenance prediction model; the preset future duration is set to 60 seconds, which is divided into 12 consecutive 5-second time segments. Based on historical blood oxygen data and current oxygen production parameters, the model uses a time-series prediction method to extrapolate the blood oxygen saturation change trend within each time segment, fully considering the impact of respiratory rate fluctuations and oxygen production rate adjustments on blood oxygen levels during the prediction process; the extrapolation results for each time segment are compared with the preset blood oxygen saturation... The oxygen production rate is compared with the target range. If the calculated result exceeds the upper limit of the target range by more than 3%, the oxygen production rate adjustment amplitude needs to be lowered. If it is lower than the lower limit of the target range by more than 3%, the oxygen production rate adjustment amplitude needs to be increased and the energy consumption balance parameters need to be optimized. The specific correction amount is calculated according to the degree of deviation. For every 1% deviation, the oxygen production rate adjustment amplitude is corrected by 0.2 liters per minute, and the energy consumption balance parameters are corrected synchronously by 2%. The corrected oxygen production rate adjustment amplitude and energy consumption balance parameters are formed. This step predicts the blood oxygen change trend in advance, realizes the forward adjustment of oxygen production parameters, avoids large fluctuations in blood oxygen levels, and ensures the maintenance of blood oxygen steady state.

[0043] S6, the oxygen production parameter optimization calculation platform sends the corrected oxygen production rate parameters and energy consumption control parameters to the oxygen generator execution unit for dynamic control of the oxygen production process.

[0044] Specifically, the implementation process of step S6 is as follows: The oxygen generation parameter optimization calculation platform integrates and verifies the oxygen generation rate parameter and energy consumption control parameter corrected in step S5. The verification includes whether the oxygen generation rate parameter is within the preset safe range (0.5 to 10 liters per minute) and whether the energy consumption control parameter meets the hardware operating limits of the oxygen generator. If the parameter exceeds the range, it is corrected according to the limit value to ensure the feasibility of the parameter. After the verification is passed, the platform sends the control parameter to the oxygen generator execution unit in the form of a digital signal through the industrial bus or wireless communication module. The sending frequency is consistent with the data acquisition frequency, which is 30 times per second to ensure the real-time control. After receiving the control parameter, the oxygen generator execution unit controls the oxygen generator through the drive circuit. The oxygen concentrator monitors the operation of its core components, including the compressor, solenoid valves, and molecular sieve switching mechanism. The compressor adjusts its output pressure and flow rate based on oxygen production rate parameters, the solenoid valves control the gas flow path and switching timing, and the molecular sieve switching mechanism adjusts the adsorption and desorption cycles according to energy consumption control parameters. During operation, the execution unit feeds back its own operating status data to the oxygen production parameter optimization calculation platform in real time, forming a closed-loop control. The platform judges the execution effect of the control parameters based on the feedback data, providing a reference for the next round of parameter adjustments. This step achieves precise execution and dynamic feedback of control parameters, ensuring that the oxygen concentrator operates stably according to the optimized parameters, ultimately achieving the goal of precise oxygen production control based on respiratory sensor feedback and blood oxygen detection.

[0045] Preferably, the expression for the closed-loop control model of the oxygen production rate is:

[0046] ,

[0047] in, This refers to the real-time output rate of the oxygen concentrator. This is the blood oxygen deviation adjustment coefficient. The blood oxygen saturation value at time t is the monitored value. The target value for blood oxygen saturation. This is a respiratory rate correlation function. The factor representing the influence of respiratory depth is... This is a characteristic value of inhalation depth. This is the respiratory cycle phase factor.

[0048] Specifically, the closed-loop control model for oxygen production rate is pre-stored in the algorithm database of the oxygen production parameter optimization calculation platform. Upon startup, it first reads the real-time blood oxygen saturation monitoring value and the preset target blood oxygen saturation value from the calibration input parameters. The target value can be set between 90% and 98% according to the user's condition. Simultaneously, it extracts respiratory rate data and converts it into a respiratory rate correlation function value using a linear interpolation algorithm. This function ranges from 0.6 to 1.4. When the respiratory rate is within the normal range of 12 to 20 breaths per minute, the function value is 1.0; if it exceeds this range, it is adjusted linearly. The blood oxygen deviation adjustment coefficient in the model is set to 0.3 to 0.8, dynamically allocated according to the user's baseline blood oxygen level, with the upper limit used when the baseline blood oxygen value is low. The respiratory depth influence coefficient is set to 0.2 to 0.5, positively correlated with the respiratory depth characteristic value; the coefficient increases by 0.1 for every 0.5 mm increase in respiratory depth. The respiratory cycle phase factor is assigned values ​​for each of the six respiratory phases, ranging from 0.3 to 1.0, with a value of 1.0 for mid-inspiratory and 0.3 for end-expiratory. The implementation involves first calculating the blood oxygen deviation value, then multiplying it by the respiratory rate correlation function and then by the blood oxygen deviation adjustment coefficient to obtain the blood oxygen correlation adjustment amount. Simultaneously, the respiratory depth characteristic value is multiplied by the respiratory cycle phase factor and then multiplied by the respiratory depth influence coefficient to obtain the respiratory correlation adjustment amount. The sum of these two values ​​represents the real-time output rate of the oxygen concentrator. This model achieves coordinated regulation of the oxygen generation rate by blood oxygen status and respiratory characteristics, enabling the oxygen generation rate adjustment to respond to both blood oxygen deviation and respiratory rhythm, thus improving the accuracy and synchronization of oxygen supply.

[0049] Preferably, the expression for the oxygen production energy consumption optimization analytical algorithm is:

[0050] ,

[0051] in, To optimize the energy consumption of oxygen production, These are the basic power parameters for an oxygen concentrator. This refers to the real-time output rate of the oxygen concentrator. The energy efficiency coefficient of the oxygen production system. The energy consumption influencing factor of respiratory rate fluctuation. Real-time respiratory rate, This is the preset average respiratory rate.

[0052] Specifically, after the oxygen generation energy consumption optimization analysis algorithm is started, it first obtains the basic power parameters of the oxygen concentrator. These parameters are determined based on the rated power of the oxygen concentrator, ranging from 300 watts to 800 watts, and are pre-entered into the platform according to the oxygen concentrator model. The energy efficiency coefficient of the oxygen generation system is set to 0.7 to 0.95, determined by the hardware configuration of the oxygen concentrator. The higher the purity of the molecular sieve and the higher the efficiency of the compressor, the closer the coefficient is to the upper limit. The respiratory rate fluctuation energy consumption influence factor is set to 0.02 to 0.08, used to quantify the additional impact of respiratory rate fluctuation on energy consumption. The larger the fluctuation coefficient, the higher the value of this factor. During implementation, the real-time output rate of the oxygen concentrator determined in step S3 is first read and multiplied by the basic power parameters of the oxygen concentrator to obtain the basic energy consumption value. Then, the absolute value of the difference between the real-time respiratory rate and the preset average respiratory rate is calculated. The preset average respiratory rate is set to 16 breaths per minute. The difference is multiplied by the respiratory rate fluctuation energy consumption influence factor and then 1 is added to obtain the fluctuation correction coefficient. Finally, the basic energy consumption value is divided by the product of the oxygen generation system energy efficiency coefficient and the fluctuation correction coefficient to obtain the optimized oxygen generation energy consumption. The algorithm's iterative calculation step size is set to 5%, with 15 iterations. Each iteration updates the correction coefficient in real time based on respiratory rate fluctuations, ensuring dynamic matching between energy consumption calculations and respiratory status. This algorithm, while guaranteeing that the oxygen production rate meets demand, fully considers the impact of respiratory rate fluctuations on energy consumption, achieving dynamic optimization of energy consumption, avoiding increased ineffective energy consumption due to respiratory fluctuations, and improving the economic efficiency of the oxygen concentrator's operation.

[0053] Preferably, the expression for the blood oxygen homeostasis maintenance prediction model is:

[0054] ,

[0055] in, for Constantly monitor blood oxygen saturation. The blood oxygen saturation value at time t is the monitored value. The contribution coefficient of oxygen production rate to blood oxygenation. This refers to the real-time output rate of the oxygen concentrator. For predicting time intervals, The coefficient representing the influence of respiratory rate deviation on blood oxygenation. Real-time respiratory rate, This is the standard respiratory rate parameter.

[0056] Specifically, the prediction time interval of the blood oxygen steady-state maintenance prediction model is set to 5 to 15 seconds. The lower limit is used when the user's blood oxygen fluctuates significantly, and the upper limit is used when the fluctuation is small, to ensure the timeliness and effectiveness of the prediction. The blood oxygen contribution coefficient of oxygenation rate is set to 0.03% to 0.07%. This coefficient is calibrated through a large amount of clinical data. For every 1 liter per minute increase in oxygenation rate, the increase in blood oxygen saturation corresponds to the coefficient value. The influence coefficient of respiratory rate deviation from blood oxygen is set to 0.01% to 0.05%. It is used to quantify the inhibitory effect of respiratory rate deviation from the standard value on blood oxygen. The larger the deviation, the more significant the influence of this coefficient. The standard respiratory rate parameter is set to 16 breaths per minute as the benchmark value for respiratory rate deviation. The model first reads the blood oxygen saturation monitoring value at time t. Then, it calculates the product of the real-time output rate of the oxygen concentrator, the blood oxygen contribution coefficient of the oxygen production rate, and the prediction time interval to obtain the blood oxygen increase brought about by the oxygen production rate. Simultaneously, it calculates the difference between the real-time respiratory rate and the standard respiratory rate parameter, multiplies it by the blood oxygen influence coefficient of the respiratory rate deviation, and the prediction time interval to obtain the blood oxygen change caused by the respiratory deviation. Finally, it adds the blood oxygen increase to the blood oxygen saturation monitoring value at time t and subtracts the blood oxygen change caused by the respiratory deviation to obtain the predicted blood oxygen saturation at time t+Δt. The model recalculates every prediction time interval, continuously updating the prediction results. This model predicts blood oxygen change trends in advance, providing data support for proactive adjustments to oxygen production parameters, avoiding large fluctuations in blood oxygen levels, and ensuring steady-state blood oxygenation.

[0057] Preferably, the parameter optimization expression of the oxygen production parameter optimization calculation platform is:

[0058] ,

[0059] Where Parafinal is the final output control parameter set. This is the weighting coefficient for oxygen production rate. This refers to the real-time output rate of the oxygen concentrator. To optimize the energy consumption weighting coefficient, To optimize the energy consumption of oxygen production, To predict the blood oxygen weighting coefficient, for Continuously predict blood oxygen saturation.

[0060] Specifically, the parameter optimization implementation process of the oxygen generation parameter optimization calculation platform is as follows: The platform pre-sets the oxygen generation rate weight coefficient, the energy consumption optimization weight coefficient, and the predicted blood oxygen weight coefficient. The values ​​of all three range from 0.2 to 0.5, and their sum is 1.0. These can be dynamically adjusted according to user needs. When prioritizing steady-state blood oxygenation, the predicted blood oxygen weight coefficient is set to its upper limit; when prioritizing energy saving, the energy consumption optimization weight coefficient is also set to its upper limit. During implementation, firstly, the real-time output rate of the oxygen generator output in step S3 is read and multiplied by the oxygen generation rate weight coefficient to obtain the oxygen generation rate score. Then, the optimized oxygen generation energy consumption output in step S4 is read, normalized, and multiplied by the energy consumption optimization weight coefficient to obtain the energy consumption optimization score. Normalization converts the energy consumption value into a dimensionless value between 0 and 1; the lower the energy consumption, the higher the score. Finally, the predicted blood oxygen saturation at time t+Δt output in step S4 is read. The smaller the deviation from the target blood oxygen saturation value, the higher the score, and this is then multiplied by the predicted blood oxygen weight coefficient to obtain the predicted blood oxygen score. The three scores are then weighted and summed to obtain a comprehensive evaluation score. The platform sets a comprehensive evaluation threshold of 0.85. If the calculated comprehensive evaluation score is higher than this threshold, the current parameters are directly integrated into the final output control parameter set; if it is lower than this threshold, the input parameters are adjusted according to the weight coefficient ratio, and the calculation is repeated until the comprehensive evaluation score meets the standard. The response time of the parameter optimization process is controlled within 50 milliseconds to ensure real-time matching with data acquisition and model calculation. The platform's parameter optimization integrates three core indicators: oxygen generation rate, energy consumption optimization, and blood oxygen prediction, achieving multi-objective synergistic optimization, avoiding performance sacrifices caused by single-objective optimization, and ensuring the overall operating effect of the oxygen concentrator.

[0061] Preferred, such as Figure 2 As shown, step S2 includes the following sub-steps: S21, performing time series alignment on the respiratory frequency, respiratory depth, inspiratory duration, and expiratory duration correlation data transmitted by the respiratory sensing module, and extracting feature point data within each respiratory cycle; S22, performing continuous sampling point screening on the real-time arterial blood oxygen saturation monitoring data acquired by the blood oxygen detection module, removing abnormal jump data points, and retaining continuous and stable monitoring data segments; S23, calculating the fluctuation coefficient of respiratory frequency within a preset time window, and processing the blood oxygen saturation data using a moving average algorithm to obtain the rate of change; S24, associating and marking the respiratory frequency fluctuation coefficient, the rate of change of blood oxygen saturation, and the blood oxygen response data corresponding to the inspiratory peak to form a calibration input parameter set.

[0062] Specifically, step S2 includes four sub-steps: S21 performs time series alignment on the respiratory rate, respiratory depth, inspiratory duration, and expiratory duration correlation data transmitted by the respiratory sensing module. Using the system clock as a reference, data from different sampling frequencies are uniformly calibrated to a standard sampling rate of 50 data points per second. Data segments are divided according to the respiratory cycle, with each data segment corresponding to one complete inspiratory and expiratory process to ensure data time sequence consistency; S22 performs continuous sampling point screening on the real-time arterial blood oxygen saturation monitoring data acquired by the blood oxygen detection module. A data jump threshold of 5% is set. When the difference in blood oxygen values ​​between two adjacent sampling points exceeds this threshold, it is determined to be an abnormal jump data point and is removed, retaining 10 or more consecutive sampling points. S23 calculates the fluctuation coefficient of respiratory rate within a preset time window of 5 respiratory cycles. This coefficient is obtained by comparing the standard deviation of respiratory rate with the mean within each window. Simultaneously, a moving average algorithm is used to process the stable blood oxygen saturation data segment, with a sliding step size of 3 sampling points, to calculate the rate of change in blood oxygen saturation and quantify the dynamic trend of blood oxygen changes. S24 associates and labels the respiratory rate fluctuation coefficient, the rate of change in blood oxygen saturation, and the blood oxygen response data corresponding to the inspiratory peak. The labeling is based on the synchronization of the data timestamps, ensuring a one-to-one correspondence between the characteristic parameters of each respiratory cycle and the corresponding blood oxygen response data, ultimately forming a calibration input parameter set. This step, through multi-dimensional data processing and feature filtering, extracts parameters that have a key impact on oxygen production control from the original collected data, eliminates redundant and abnormal data, and provides accurate and efficient input support for subsequent model calculations, improving the reliability and accuracy of the overall control process.

[0063] Preferred, such as Figure 3 As shown, S3 includes the following sub-steps: S31, the oxygen generation parameter optimization calculation platform calls the oxygen generation rate closed-loop control model and substitutes the blood oxygen saturation change rate and respiratory rate fluctuation coefficient in the calibrated input parameters into the model initial calculation; S32, the respiratory cycle phase information is determined according to the ratio of inspiratory duration to expiratory duration, and the oxygen generation rate adjustment weight under different phases is calculated; S33, the oxygen generation rate benchmark value is dynamically corrected by combining the deviation between the target blood oxygen saturation range and the real-time monitoring value; S34, the initial value of the oxygen generation rate output amplitude is calculated according to the corrected benchmark value and the phase adjustment weight.

[0064] Specifically, step S3 includes four sub-steps: S31 The oxygen generation parameter optimization calculation platform calls the oxygen generation rate closed-loop control model pre-stored in the algorithm database. First, the blood oxygen saturation change rate and respiratory rate fluctuation coefficient in the calibration input parameters are imported into the model. At the same time, the preset initial range of oxygen generation rate is read as 1 to 10 liters per minute, and the initial calculation process of the model is started to initially match the approximate range of the oxygen generation rate benchmark value; S32 Based on the inspiratory duration and expiratory duration collected in step S1, the ratio of the two is calculated to determine the respiratory cycle phase information. The respiratory cycle is accurately divided into six phases: early inspiratory phase, mid-inspiratory phase, late inspiratory phase, early expiratory phase, mid-expiratory phase, and late expiratory phase. Each phase corresponds to a different oxygen generation rate adjustment weight, where the weight of mid-inspiratory phase is set to 1.0, and the weight of late inspiratory phase is set to 1.0. The initial and final exhalation weights are reset to 0.7, the initial and mid-exhalation weights are set to 0.5, and the final exhalation weight is reset to 0.3, ensuring that the weight allocation aligns with the oxygen production needs of the respiratory process. In step S33, a deviation correction gradient is set based on the deviation between the preset target blood oxygen saturation range (90% to 98%) and the real-time monitored value. For every 1% deviation exceeding the target range, the oxygen production rate benchmark is adjusted by a 5% gradient; when blood oxygen is below the target range, the adjustment increases, and when it is above, the adjustment decreases, dynamically correcting the oxygen production rate benchmark. In step S34, based on the corrected benchmark and the corresponding adjustment weights for each phase, a weighted summation algorithm is used to calculate the initial value of the oxygen production rate output amplitude. The sum of the products of the weights and the benchmark value is the output amplitude for the corresponding phase, achieving differentiated allocation of oxygen production rates under different respiratory phases. This step, through precise step-by-step calculation and dynamic adjustment, ensures that the oxygen production rate responds to blood oxygen deviations and adapts to the phase characteristics of the respiratory cycle, achieving precise synchronization between oxygen supply and the human respiratory rhythm, avoiding supply waste or insufficiency caused by misalignment between oxygen production timing and respiratory demand.

[0065] Preferred, such as Figure 4 As shown, step S4 includes the following sub-steps: S41, start the oxygen generation energy consumption optimization analysis algorithm, and import the oxygen generation rate benchmark value, blood oxygen saturation target interval boundary value, and real-time respiratory cycle duration data; S42, set the constraint threshold for the operating energy consumption of the oxygen generation system and the minimum required value for oxygen generation efficiency, and construct a balance objective function between energy consumption and efficiency; S43, perform iterative calculations on the oxygen generator operating power, gas compression ratio, and molecular sieve adsorption time parameters through the algorithm; S44, output the energy consumption balance parameters that meet the constraint conditions, which include the power adjustment coefficient and the ratio relationship of operating parameters.

[0066] Specifically, step S4 includes four sub-steps: S41: Activate the oxygen generation energy consumption optimization algorithm. First, import the baseline value of oxygen generation rate determined in step S3, the preset target range boundary values ​​of blood oxygen saturation (lower limit 90%, upper limit 98%), and the respiratory cycle duration calculated in step S1 (range 1.5 to 5 seconds). Use these three as the core constraints of the algorithm to clarify the boundary range of oxygen generation energy consumption optimization; S42: Set the constraint threshold for the operating energy consumption of the oxygen generation system. This threshold is determined based on 30% to 80% of the rated power of the oxygen concentrator. At the same time, set the minimum requirement value for oxygen generation efficiency to be 85%. With the core objective of minimizing energy consumption, construct a balance objective function between energy consumption and efficiency to clarify the direction of algorithm optimization; S43: Through iterative calculation... The algorithm optimizes key operating parameters of the oxygen concentrator by combining parameters including operating power, gas compression ratio (adjustable range 1.2 to 2.5), and molecular sieve adsorption time (adjustable range 10 to 30 seconds). The iterative adjustment step size is set to 5%, and the number of iterations is set to 20. In each iteration, energy consumption and efficiency values ​​are calculated based on the current parameter combination and compared with the constraints. In step S44, when the parameter combination obtained from the iterative calculation meets the energy consumption constraint threshold and the minimum oxygen production efficiency requirement, the iteration stops and the balance parameters of the oxygen production system's operating energy consumption and oxygen production efficiency are output. These parameters include the power adjustment coefficient (range 0.3 to 0.9) and the ratio relationship of each operating parameter, clarifying the optimal combination of parameters under different oxygen production rates. This step, through step-by-step constraint setting, target construction, and iterative optimization, achieves dynamic optimization of oxygen production energy consumption while ensuring that the oxygen production rate meets blood oxygenation requirements, avoiding ineffective energy consumption and improving the economy and sustainability of the oxygen concentrator's operation.

[0067] Preferred, such as Figure 5 As shown, step S5 includes the following sub-steps: S51, inputting the corrected oxygen production rate adjustment amplitude, energy consumption balance parameters, and current blood oxygen saturation data into the blood oxygen steady-state maintenance prediction model; S52, setting the future preset duration as multiple consecutive time segments, and predicting the blood oxygen saturation change trend in each time segment; S53, comparing the prediction results of each time segment with the target blood oxygen saturation range to determine the parameter type and correction direction that need to be corrected; S54, calculating the correction amount based on the degree of prediction deviation, and dynamically correcting the oxygen production rate adjustment amplitude and energy consumption balance parameters.

[0068] Specifically, step S5 includes four sub-steps: S51 inputs the oxygen production rate adjustment amplitude corrected in step S3, the energy consumption balance parameters obtained in step S4, and the current stable blood oxygen saturation data filtered in step S2 into the blood oxygen steady-state maintenance prediction model to ensure the integrity and accuracy of the model input data and provide a reliable basis for prediction calculation; S52 sets the future preset duration to 60 seconds and divides it evenly into 12 consecutive 5-second time segments. The model adopts a time-series prediction method, based on the blood oxygen data within the past 30 seconds and the current oxygen production parameters, to deduce the blood oxygen saturation change trend in each time segment. The deduction process fully incorporates the influence factors of respiratory rate fluctuations and oxygen production rate adjustment on blood oxygen levels; S53 inputs the deduction results of each time segment into the model. The results are compared one by one with the preset target range for blood oxygen saturation (90% to 98%). If the predicted result exceeds the upper limit of the target range by 3% or more, it is determined that the oxygen rate adjustment amplitude needs to be lowered. If it is lower than the lower limit of the target range by 3% or more, it is determined that the oxygen rate adjustment amplitude needs to be increased and the energy consumption balance parameters are optimized simultaneously, clarifying the type and direction of parameter correction. S54 calculates the specific correction amount based on the degree of deviation in the prediction and sets the deviation correction ratio. For every 1% deviation exceeding the target range, the oxygen rate adjustment amplitude is corrected by 0.2 liters per minute, and the energy consumption balance parameters are corrected simultaneously at a ratio of 2%. After correction, the prediction results are re-verified until the predicted blood oxygen values ​​for all time segments are within the target range, forming the final corrected oxygen rate adjustment amplitude and energy consumption balance parameters. The core significance of this step is that by predicting, comparing, and correcting in steps, the trend of blood oxygen change can be predicted in advance, enabling proactive adjustment of oxygenation parameters, avoiding large fluctuations in blood oxygen levels, ensuring the continuous maintenance of the user's blood oxygen steady state, and improving the stability and predictability of oxygenation control.

[0069] like Figure 6As shown, an oxygen concentrator control system based on respiratory sensor feedback and blood oxygen detection is characterized in that the system is applied to the oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection as described in claim 1, comprising: a respiratory sensor data acquisition unit, a blood oxygen saturation monitoring unit, an oxygen production parameter optimization calculation unit, an oxygen production rate closed-loop control model calculation unit, an oxygen production energy consumption optimization analysis unit, and an oxygen production execution control unit; the respiratory sensor data acquisition unit and the blood oxygen saturation monitoring unit are respectively connected to the oxygen production parameter optimization calculation unit through a data transmission link, for transmitting the collected respiratory correlation data and blood oxygen monitoring data to the oxygen production parameter optimization unit in real time. The calculation unit includes two-way communication with the oxygen production rate closed-loop control model calculation unit and the oxygen production energy consumption optimization analysis unit, respectively, to integrate the calculation results of the two units. The oxygen production rate closed-loop control model calculation unit completes the oxygen production rate related calculations based on the received calibration input parameters, and the oxygen production energy consumption optimization analysis unit solves the balance parameters between energy consumption and efficiency. The oxygen production parameter optimization calculation unit sends the integrated and corrected control parameters to the oxygen production execution control unit, which dynamically adjusts the operating status of the oxygen generator according to the received parameters. All units work together to dynamically control the oxygen production process.

[0070] The oxygen concentrator control method and system based on respiratory sensor feedback and blood oxygen detection synchronously collects multi-dimensional respiratory-related data such as respiratory rate, respiratory depth, inspiratory and expiratory duration, and respiratory cycle phase through a dedicated sensing module. Simultaneously, it accurately acquires real-time monitoring data of arterial blood oxygen saturation, and after feature extraction, forms comprehensive calibration input parameters. Utilizing a closed-loop control model for the oxygen generation rate, it dynamically matches the baseline value of the oxygen generation rate based on the calibration input parameters and adjusts the output amplitude in conjunction with respiratory cycle phase information. This ensures that the oxygen generation process precisely responds to the human respiratory rhythm and blood oxygen changes, completely overcoming the limitations of traditional single-parameter control. It significantly improves the adaptability and accuracy of oxygen generation control, ensuring that users with different respiratory states and blood oxygen levels can receive oxygen supply tailored to their individual needs.

[0071] This method and system construct a synergistic system combining oxygen generation effect, energy consumption optimization, and blood oxygen prediction, successfully solving the problems of existing technologies that fail to balance oxygen generation effect and energy consumption, and lack blood oxygen prediction capabilities. Through an oxygen generation energy consumption optimization analytical algorithm, with oxygen generation rate, target blood oxygen range, and respiratory cycle duration as constraints, it solves for the balance parameters between energy consumption and oxygen generation efficiency in the oxygen generation system, avoiding excessive pursuit of blood oxygen targets leading to energy waste or sacrificing oxygen generation accuracy to reduce energy consumption. Simultaneously, a blood oxygen steady-state maintenance prediction model is used to extrapolate the trend of blood oxygen saturation changes within a preset time period, pre-correcting the adjustment amplitude of the oxygen generation rate and energy consumption balance parameters. After integration and correction by the oxygen generation parameter optimization calculation platform, control commands are output. All units work together to form a complete control link, achieving dynamic, personalized, and efficient control of the oxygen generation process, ensuring blood oxygen steady-state while maximizing the utilization rate of oxygen generation energy.

[0072] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," "link," and "fix" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0073] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection, characterized in that, Includes the following steps: S1 collects data on the user's breathing rate, breathing depth, inhalation duration and exhalation duration through the breathing sensor module, and simultaneously obtains real-time monitoring data of the user's arterial blood oxygen saturation through the blood oxygen detection module. Both types of data are transmitted to the oxygen generation parameter optimization calculation platform. S2, the oxygen production parameter optimization calculation platform extracts features from the received respiratory correlation data and blood oxygen monitoring data, and selects the blood oxygen response data corresponding to the respiratory rate fluctuation coefficient, blood oxygen saturation change rate, and inspiratory peak as calibration input parameters; S3 calls the closed-loop control model of oxygen production rate, dynamically matches the baseline value of oxygen production rate based on the calibrated input parameters, and adjusts the output amplitude of oxygen production rate by combining respiratory cycle phase information. S4, start the oxygen generation energy consumption optimization analysis algorithm, and calculate the balance parameters between the oxygen generation system's operating energy consumption and oxygen generation efficiency with the oxygen generation rate benchmark value, blood oxygen saturation target range, and respiratory cycle duration as constraints. S5 uses a blood oxygen steady state maintenance prediction model to predict the trend of blood oxygen saturation changes within a preset time period, and adjusts the oxygen production rate adjustment amplitude and energy consumption balance parameters based on the prediction results. S6, the oxygen production parameter optimization calculation platform sends the corrected oxygen production rate parameters and energy consumption control parameters to the oxygen generator execution unit for dynamic control of the oxygen production process.

2. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, The expression for the closed-loop control model of oxygen production rate is: ,in, This refers to the real-time output rate of the oxygen concentrator. This is the blood oxygen deviation adjustment coefficient. The blood oxygen saturation value at time t is the monitored value. The target value for blood oxygen saturation. This is a respiratory rate correlation function. The factor representing the influence of respiratory depth is... This is a characteristic value of inhalation depth. This is the respiratory cycle phase factor.

3. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, The expression for the oxygen production energy consumption optimization analytical algorithm is as follows: ,in, To optimize the energy consumption of oxygen production, These are the basic power parameters for an oxygen concentrator. This refers to the real-time output rate of the oxygen concentrator. The energy efficiency coefficient of the oxygen production system. The energy consumption influencing factor of respiratory rate fluctuation. Real-time respiratory rate, This is the preset average respiratory rate.

4. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, The expression for the blood oxygen homeostasis maintenance prediction model is as follows: ,in, for Constantly monitor blood oxygen saturation. The blood oxygen saturation value at time t is the monitored value. The contribution coefficient of oxygen production rate to blood oxygenation. This refers to the real-time output rate of the oxygen concentrator. For predicting time intervals, The coefficient representing the influence of respiratory rate deviation on blood oxygenation. Real-time respiratory rate, This is the standard respiratory rate parameter.

5. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, The parameter optimization expression of the oxygen production parameter optimization calculation platform is as follows: Where Parafinal is the final output control parameter set. This is the weighting coefficient for oxygen production rate. This refers to the real-time output rate of the oxygen concentrator. To optimize the energy consumption weighting coefficient, To optimize the energy consumption of oxygen production, To predict the blood oxygen weighting coefficient, for Continuously predict blood oxygen saturation.

6. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, S2 includes the following sub-steps: S21, performing time series alignment on the respiratory rate, respiratory depth, inspiratory duration, and expiratory duration correlation data transmitted by the respiratory sensing module, and extracting feature point data within each respiratory cycle; S22, performing continuous sampling point screening on the real-time arterial blood oxygen saturation monitoring data acquired by the blood oxygen detection module, removing abnormal jump data points, and retaining continuous and stable monitoring data segments; S23, calculating the fluctuation coefficient of respiratory rate within a preset time window, and processing the blood oxygen saturation data using a moving average algorithm to obtain the rate of change; S24, associating and marking the respiratory rate fluctuation coefficient, the rate of change of blood oxygen saturation, and the blood oxygen response data corresponding to the inspiratory peak to form a calibration input parameter set.

7. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, S3 includes the following steps: S31, the oxygen generation parameter optimization calculation platform calls the oxygen generation rate closed-loop control model and substitutes the blood oxygen saturation change rate and respiratory rate fluctuation coefficient from the calibrated input parameters into the model for initial calculation; S32, the respiratory cycle phase information is determined based on the ratio of inspiratory duration to expiratory duration, and the oxygen generation rate adjustment weights under different phases are calculated; S33, the oxygen generation rate benchmark value is dynamically corrected based on the deviation between the target blood oxygen saturation range and the real-time monitoring value; S34, the initial value of the oxygen generation rate output amplitude is calculated based on the corrected benchmark value and the phase adjustment weights.

8. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, S4 includes the following sub-steps: S41, start the oxygen generation energy consumption optimization analysis algorithm, and import the oxygen generation rate benchmark value, blood oxygen saturation target interval boundary value, and real-time respiratory cycle duration data; S42, set the constraint threshold for the operating energy consumption of the oxygen generation system and the minimum required value for oxygen generation efficiency, and construct a balance objective function between energy consumption and efficiency; S43, iteratively calculate the oxygen generator operating power, gas compression ratio, and molecular sieve adsorption time parameters through the algorithm; S44, output the energy consumption balance parameters that meet the constraint conditions, which include the power adjustment coefficient and the ratio relationship of operating parameters.

9. The oxygen concentrator control method based on respiratory sensor feedback and blood oxygen detection according to claim 1, characterized in that, S5 includes the following sub-steps: S51, inputting the corrected oxygen production rate adjustment amplitude, energy consumption balance parameters, and current blood oxygen saturation data into the blood oxygen steady-state maintenance prediction model; S52, setting the future preset duration as multiple consecutive time segments, and predicting the blood oxygen saturation change trend in each time segment; S53, comparing the prediction results of each time segment with the target blood oxygen saturation range to determine the type and direction of parameters that need to be corrected; S54, calculating the correction amount based on the degree of prediction deviation, and dynamically correcting the oxygen production rate adjustment amplitude and energy consumption balance parameters.

10. An oxygen concentrator control system based on respiratory sensor feedback and blood oxygen detection, characterized in that, include: The unit includes a respiratory sensor data acquisition unit, a blood oxygen saturation monitoring unit, an oxygen production parameter optimization calculation unit, an oxygen production rate closed-loop control model calculation unit, an oxygen production energy consumption optimization analysis unit, and an oxygen production execution control unit. The respiratory sensor data acquisition unit and the blood oxygen saturation monitoring unit are connected to the oxygen production parameter optimization calculation unit through a data transmission link, which is used to transmit the collected respiratory correlation data and blood oxygen monitoring data to the oxygen production parameter optimization calculation unit in real time. The oxygen production parameter optimization calculation unit communicates bidirectionally with the oxygen production rate closed-loop control model calculation unit and the oxygen production energy consumption optimization analysis unit, respectively, and integrates the calculation results of the two types of units. The oxygen production rate closed-loop control model calculation unit completes the oxygen production rate related calculations based on the received calibration input parameters, and the oxygen production energy consumption optimization analysis unit solves the balance parameters between energy consumption and efficiency. The oxygen generation parameter optimization calculation unit sends the integrated and corrected control parameters to the oxygen generation execution control unit. The oxygen generation execution control unit dynamically adjusts the operating status of the oxygen generator based on the received parameters. All units work together to dynamically control the oxygen generation process.

Images