Oxygen supply pipeline state determination method and device for oxygen supply system, oxygen supply system and medium

Abstract

The application discloses an oxygen supply pipeline state determination method and device, an oxygen supply system and a medium, relates to the technical field of medical equipment, and provides the oxygen supply system, which comprises an oxygen supply pipeline, wherein the oxygen supply pipeline comprises a supply end and an output end; the method comprises the following steps: synchronously collecting the supply end pressure, the output end pressure and the oxygen flow signal of the oxygen supply pipeline at each sampling moment; constructing an equivalent circuit model taking the supply end pressure as an input voltage, the pipeline air resistance as a variable resistor and the output end air capacity as a capacitor; establishing a discretized state equation taking the output end pressure and the pipeline air resistance as state variables and an observation equation taking the output end pressure and the oxygen flow as observation quantities; taking the supply end pressure as an input and the output end pressure and the oxygen flow as observation quantities, and utilizing Kalman filtering recursion to recursively estimate the optimal value of the pipeline air resistance; and performing mutation direction detection on the optimal value, and distinguishing the blockage or shedding state according to the air resistance increment or decrement in a preset window. The two faults can be distinguished in real time only by using the pressure and flow signals of the pipeline itself.

Description

Technical Field

[0001] This invention relates to the field of medical equipment technology, and in particular to a method, device, oxygen supply system, and medium for determining the status of oxygen supply pipelines in an oxygen supply system. Background Technology

[0002] For critically ill, sedated, or unconscious patients undergoing MRI (Magnetic Resonance Imaging) examinations and during emergency ambulance transport, continuous oxygen supply is essential for maintaining vital signs. In such challenging environments, oxygen supply lines face risks such as bending, pressure, and accidental detachment. Interruption of oxygen supply can lead to irreversible hypoxic-ischemic brain injury within minutes. Furthermore, medical staff cannot directly observe the condition of the tubing during MRI scans, and the bumpy ride and confined spaces during ambulance transport further increase the likelihood of overlooking any abnormalities.

[0003] Currently, commonly used clinical methods for detecting tubing anomalies are typically based on flow thresholds. An alarm is triggered when the oxygen flow sensor reading consistently falls below a certain set limit, indicating a potential tubing malfunction. However, blockages caused by tubing bends also manifest as a sudden drop in flow. A single flow threshold cannot distinguish between blockages and detachments, two distinct fault types that require opposite clinical management: blockages require immediate relief from pressure or bends, while detachments require reconnection. Currently, after an alarm sounds, healthcare professionals need to spend extra time observing the patient's condition and the appearance of the tubing to make a correct diagnosis. This diagnostic delay can be fatal, especially in patients with already limited respiratory reserve. Furthermore, both flow threshold and pressure anomaly methods are lagging detection methods at the physical signal level, failing to provide a clear indication of the fault type immediately after an oxygen supply interruption.

[0004] In summary, how to distinguish between blockage and detachment of oxygen supply lines in real time and directly using the pressure and flow signals of the oxygen supply lines themselves, without relying on visual observation and secondary judgment by medical staff, is a problem that needs to be solved in this field. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a method, device, oxygen supply system, and medium for determining the status of oxygen supply pipelines in an oxygen supply system. This method, without relying on visual observation and secondary judgment by medical personnel, utilizes the pressure and flow signals of the oxygen supply pipeline itself to directly and in real time distinguish between two fault states: pipeline blockage and detachment. The specific solution is as follows: In a first aspect, the present invention discloses a method for determining the state of an oxygen supply pipeline in an oxygen supply system, comprising: The oxygen supply system includes an oxygen supply pipeline, which includes a supply end and an output end; the method includes: At each sampling time, the supply end pressure signal, output end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline are collected; An equivalent circuit model is constructed with the supply end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistor, and the output end air capacitance as the capacitor. Based on the equivalent circuit model, a discretized state equation with the output end pressure and the pipeline air resistance as state variables, and an observation equation with the output end pressure and oxygen flow rate as observation quantities are established. Using the supply-side pressure signal as the input to the discretized state equation, and the output-side pressure signal and the oxygen flow rate signal as the input to the observation equation, the Kalman filter algorithm is used to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time. The optimal estimated value of the pipeline air resistance is subjected to abrupt change direction detection, and the pipeline status of the oxygen supply pipeline is determined according to the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline status is a blocked state or a detached state.

[0006] Optionally, the construction of an equivalent circuit model with the supply-end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistance, and the output-end air capacitance as the capacitance, and the establishment of a discretized state equation with the output-end pressure and the pipeline air resistance as state variables, and an observation equation with the output-end pressure and oxygen flow rate as observation quantities based on the equivalent circuit model, includes: The hydrodynamic characteristics of the oxygen supply pipeline are mapped to a first-order RC equivalent circuit model; wherein, the supply end pressure is the constant pressure source, the pipeline air resistance of the oxygen supply pipeline is the variable resistor connected in series between the constant pressure source and the output end, the volume effect of the end of the oxygen supply pipeline and the compressible gas in the patient's mask is the capacitor connected in parallel between the output end and the reference ground, the gas consumption by the patient's spontaneous breathing is the leakage resistance connected in parallel across the capacitor, and the reference ground is the ambient atmospheric pressure; Based on Kirchhoff's current law, a continuous-time differential equation is established for the node where the capacitor is located; wherein, the continuous-time differential equation characterizes the quantitative relationship between the output pressure, pipeline gas resistance, supply pressure, oxygen flow rate, gas capacity, and leakage resistance. The continuous-time differential equation is discretized to obtain a discretized state equation with the output pressure and the pipeline air resistance as state variables. Based on the continuous-time differential equation and the relationship between oxygen flow rate and output pressure, an observation equation is established with output pressure and oxygen flow rate as the observed quantities.

[0007] Optionally, the step of using the supply-side pressure signal as input to the discretized state equation, and the output-side pressure signal and the oxygen flow rate signal as input to the observation equation, and using the Kalman filter algorithm to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time includes: At each sampling time, the supply end pressure signal at the current time is used as the input excitation of the discretized state equation, and the discretized state equation is recursively predicted to obtain the prior estimates of the output end pressure and the pipeline air resistance at the current time. Using the current output pressure signal and the current oxygen flow signal as the observed values, and inputting them into the observation equation, the residual between the prior estimate and the observed value is determined. The prior estimate is then weighted and corrected based on the residual to obtain the posterior estimate of the current output pressure and the pipeline air resistance. The posterior estimate of the pipeline air resistance obtained by recursion at each sampling time is determined as the optimal estimate of the pipeline air resistance at each sampling time.

[0008] Optionally, the optimal estimate of the pipeline air resistance is subjected to abrupt change direction detection, and the pipeline status of the oxygen supply pipeline is determined based on the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline status is a blocked state or a detached state, including: Obtain the nominal air resistance value of the oxygen supply pipeline under normal operating conditions; At each sampling moment, the optimal estimated value of the pipeline air resistance corresponding to each sampling moment within the preset time window before the current moment is obtained, and the upward cumulative sum and downward cumulative sum are calculated based on the difference between each optimal estimated value and the nominal value of the air resistance. When the upward accumulation exceeds a first preset threshold, it is determined that the oxygen supply pipeline is blocked. When the downward accumulation exceeds the second preset threshold, it is determined that the oxygen supply pipeline is in a detached state.

[0009] Optionally, the step of acquiring the supply-end pressure signal, output-end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline at each sampling time includes: At each sampling time, the supply end pressure signal, output end pressure signal, and oxygen flow signal of the oxygen supply pipeline, as well as the respiratory waveform signal and blood oxygen saturation signal of the oxygen supply system, are collected. Accordingly, after determining the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window, the method further includes: The risk of asphyxiation in patients is predicted based on the status of the oxygen supply line, the respiratory status determined by the respiratory waveform signal, and the oxygenation status determined by the blood oxygen saturation signal.

[0010] Optionally, the step of acquiring the supply-end pressure signal, output-end pressure signal, and oxygen flow signal of the oxygen supply pipeline, as well as the respiratory waveform signal and blood oxygen saturation signal of the oxygen supply system at each sampling time includes: At each sampling time, the first raw signal of the oxygen supply pipeline and the second raw signal of the oxygen supply system are collected respectively; wherein, the first raw signal includes the raw supply end pressure signal, the raw output end pressure signal, and the raw oxygen flow signal, and the second raw signal includes the raw respiratory waveform signal and the raw blood oxygen saturation signal; A first discrete time series and a second discrete time series are constructed based on each of the first original signals and each of the second original signals, and the first discrete time series and the second discrete time series are time-aligned to obtain each first aligned sequence and each second aligned sequence. Each of the first aligned sequences is subjected to MRI electromagnetic interference filtering to obtain the filtered supply pressure signal, the filtered output pressure signal, and the filtered oxygen flow rate signal. Each of the second aligned sequences is filtered to obtain the filtered respiratory waveform signal and the filtered blood oxygen saturation signal.

[0011] Optionally, the step of predicting the patient's asphyxiation risk based on the status of the oxygen supply tubing, the respiratory status determined based on the respiratory waveform signal, and the oxygenation status determined based on the blood oxygen saturation signal includes: The physical state risk factor of the oxygen supply pipeline is determined based on its status. Specifically, when the oxygen supply pipeline is in normal working condition, the physical state risk factor is a first preset value; when the oxygen supply pipeline is blocked or detached, the physical state risk factor is a second preset value; and when the increase in the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed the first preset threshold, or when the decrease in the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed the second preset threshold, the physical state risk factor is a third preset value. The short-time energy and zero-crossing rate of the respiratory waveform signal within a sliding window are determined. If the short-time energy and the zero-crossing rate meet a preset condition, the respiratory state is determined to be apnea and the respiratory risk factor is set to a fourth preset value. If the short-time energy and the zero-crossing rate do not meet the preset condition, the respiratory frequency in the respiratory waveform signal is determined, and the respiratory risk factor is assigned a value between 0 and 1 based on the normalized distance of the respiratory frequency from the preset normal range. The preset condition is that the short-time energy is continuously lower than a preset energy lower limit and the zero-crossing rate is continuously lower than a preset zero-crossing rate lower limit for a period exceeding a preset apnea determination threshold. Determine the linear fitting slope of the blood oxygen saturation signal within a sliding window. When the linear fitting slope is negative and the absolute value of the linear fitting slope exceeds a preset rate of decline threshold, assign the oxygenation risk factor a value between 0 and 1 according to the linear mapping. The risk factors of the pipeline physical state, the respiratory risk factor, and the oxygenation risk factor are weighted and fused to obtain a comprehensive risk score; The patient's asphyxiation risk level is predicted based on the preset numerical range of the comprehensive risk score.

[0012] Secondly, the present invention discloses a device for determining the status of an oxygen supply pipeline in an oxygen supply system, wherein the oxygen supply system includes an oxygen supply pipeline, and the oxygen supply pipeline includes a supply end and an output end; the device includes: The signal acquisition module is used to acquire the supply end pressure signal, output end pressure signal and oxygen flow signal of the oxygen supply pipeline at each sampling time. The model equation construction module is used to construct an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistance, and the output end air capacitance as the capacitor. Based on the equivalent circuit model, a discretized state equation with the output end pressure and the pipeline air resistance as state variables is established, as well as an observation equation with the output end pressure and oxygen flow rate as observation quantities. The recursive estimation module is used to take the supply end pressure signal as the input of the discretized state equation, and the output end pressure signal and the oxygen flow signal as the input of the observation equation. It uses the Kalman filter algorithm to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time. The status determination module is used to detect the sudden change direction of the optimal estimated value of the pipeline air resistance, and determine the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline status is a blocked state or a detached state.

[0013] Thirdly, the present invention discloses an oxygen supply system, comprising: Oxygen supply pipeline, including the output end and the supply end connected to the oxygen supply equipment; A first pressure sensor installed at the supply end is used to collect the supply end pressure signal of the oxygen supply pipeline; The second pressure sensor, located at the output end, is used to collect the pressure signal at the output end of the oxygen supply pipeline. A flow sensor installed in the oxygen supply pipeline is used to collect the oxygen flow signal of the oxygen supply pipeline; Furthermore, the oxygen supply system also includes: Memory, used to store computer programs; A processor is used to execute the computer program to implement the steps of the aforementioned method for determining the state of the oxygen supply pipeline in an oxygen supply system.

[0014] Fourthly, the present invention discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned method for determining the state of the oxygen supply pipeline in an oxygen supply system.

[0015] The beneficial effects of this invention are as follows: The oxygen supply system of this invention includes an oxygen supply pipeline, which includes a supply end and an output end; the method includes: acquiring the supply end pressure signal, the output end pressure signal, and the oxygen flow rate signal of the oxygen supply pipeline at each sampling time; constructing an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance as the variable resistor, and the output end air capacitance as the capacitor; and establishing a discretized state equation with the output end pressure and the pipeline air resistance as state variables, and an observation equation with the output end pressure and the oxygen flow rate as observed quantities, based on the equivalent circuit model. The system employs a measurement equation; using the supply-end pressure signal as input to the discretized state equation, and the output-end pressure signal and the oxygen flow rate signal as input to the observation equation, a Kalman filter algorithm is used to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time; the optimal estimate of the pipeline air resistance is subjected to abrupt change direction detection, and the pipeline state of the oxygen supply pipeline is determined based on the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline state is either a blocked state or a detached state. Therefore, this invention, by collecting pressure and oxygen flow signals from the supply and output ends of the oxygen supply pipeline, constructs an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance as the variable resistance, and the output end air capacitance as the capacitance. Based on this, it establishes discretized state equations with output end pressure and pipeline air resistance as state variables, and observation equations with output end pressure and oxygen flow rate as observation quantities. This transforms the fluid dynamics of the oxygen supply pipeline into a parameter estimation problem of the circuit model, enabling the pipeline air resistance, which was originally impossible to measure directly, to be identified online using the Kalman filter algorithm, thereby obtaining the optimal estimate of the pipeline air resistance at each sampling time. When the pipeline is blocked, the cross-sectional area through which the fluid passes decreases, leading to an increase in air resistance. When the pipeline detaches, the output end connects to the atmosphere, causing a sudden drop in air resistance. The directions of air resistance change are diametrically opposed in these two fault modes. Therefore, by detecting the abrupt change direction of the optimal estimated value of the pipeline air resistance, the increase or decrease in air resistance within a preset time window can directly distinguish whether the oxygen supply pipeline is blocked or detached. This invention does not rely on a single determination of the flow rate threshold, nor does it rely on secondary judgment by medical personnel observing the output status and pipeline appearance. It can directly determine the fault type from a physical perspective when the oxygen supply pipeline malfunctions, providing a clear root cause for subsequent clinical treatment. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0017] Figure 1 This is a flowchart of a method for determining the status of an oxygen supply pipeline in an oxygen supply system, as disclosed in this invention. Figure 2 This is a schematic diagram of a specific equivalent circuit model disclosed in this invention; Figure 3 This is a schematic diagram of the structure of an oxygen supply pipeline status determination device in an oxygen supply system disclosed in this invention. Figure 4 This is a structural diagram of an oxygen supply system disclosed in this invention. Detailed Implementation

[0018] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] For critically ill, sedated, or unconscious patients undergoing MRI scans and during emergency ambulance transport, continuous oxygen supply is essential for maintaining vital signs. Oxygen supply lines face sudden risks such as bending, pressure, and accidental detachment in these challenging environments. If oxygen supply is interrupted, irreversible hypoxic-ischemic brain injury can occur within minutes. Furthermore, medical staff cannot directly observe the condition of the tubing during MRI scans, and the bumpy ride and confined spaces during ambulance transport further increase the likelihood of overlooking tubing abnormalities.

[0020] Currently, clinical methods for detecting tubing abnormalities typically rely on flow thresholds. An alarm is triggered when the oxygen flow sensor reading consistently falls below a certain set limit, indicating potential tubing detachment. However, tubing blockages caused by bends also manifest as a sudden drop in flow, and a single flow threshold cannot distinguish between these two distinct types of tubing malfunctions: blockage and detachment. The clinical treatment for these two malfunctions is opposite: blockage requires immediate relief from pressure or bends, while detachment requires reconnection. Currently, after an alarm sounds, healthcare professionals need to spend extra time observing the patient's condition and the appearance of the tubing to make a correct diagnosis. This diagnostic delay can be fatal, especially in patients with already limited respiratory reserve.

[0021] More importantly, both the flow threshold method and the pressure anomaly method are lag detection methods at the physical signal level. Clinically, it is well-established that there is a physiological lag window of 45 to 90 seconds between the interruption of oxygen supply and a noticeable decrease in pulse oxygen saturation (SpO2). Current technologies almost entirely rely on the drop in SpO2 as the final confirmation signal of patient asphyxiation, meaning that by the time medical staff receive a clear warning of a life-threatening situation, tissue hypoxia has often already persisted for about a minute. Therefore, this invention provides a corresponding scheme for determining the status of oxygen supply pipelines in an oxygen supply system. Without relying on visual observation and secondary judgment by medical staff, it uses the pressure and flow signals of the oxygen supply pipeline itself to directly and in real-time distinguish between two fault states: pipeline blockage and detachment.

[0022] See Figure 1 As shown in the figure, an embodiment of the present invention discloses a method for determining the state of an oxygen supply pipeline in an oxygen supply system. The oxygen supply system includes an oxygen supply pipeline, which includes a supply end and an output end. The method includes: Step S11: Collect the supply end pressure signal, output end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline at each sampling time.

[0023] The oxygen supply system includes an oxygen supply pipeline, which comprises a supply end and an output end. The supply end is connected to the oxygen supply equipment. Further, the system includes a first pressure sensor (i.e., the supply end pressure sensor), a second pressure sensor (i.e., the output end pressure sensor), and a flow sensor. The first pressure sensor is located at the supply end to collect the supply end pressure signal. The second pressure sensor is located at the output end, specifically near the patient mask or endotracheal intubation port, to collect the output end pressure signal. The flow sensor, which can be a non-magnetic variable area flow meter or a fiber optic flow sensor, is located within the oxygen supply pipeline to collect the oxygen flow signal. The supply end pressure signal, the patient end pressure signal (i.e., the output end pressure signal), and the oxygen flow signal are synchronously sampled at a uniform sampling frequency to obtain a discrete time series. The sampling clock is uniformly synchronized by the computer's NTP (Network Time Protocol) time server to ensure strict time alignment of the multi-channel data.

[0024] In this embodiment, the step of collecting the supply end pressure signal, output end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline at each sampling time includes: collecting the supply end pressure signal, output end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline, as well as the respiratory waveform signal and blood oxygen saturation signal of the oxygen supply system at each sampling time.

[0025] With a uniform sampling frequency Supply-side pressure signals Output pressure signal Oxygen flow signal Respiratory waveform signal and blood oxygen saturation signal Perform synchronous sampling, specifically... =100Hz, obtaining a discrete time series, can be represented as , , , , n = 0, 1, 2, ..., n represents the nth time.

[0026] Respiratory waveform signals are acquired non-invasively by fiber optic respiratory sensors attached to the patient's chest and abdomen; blood oxygen saturation signals are output after optical encoding by a fiber optic blood oxygen probe. All sensors are non-magnetic and non-metallic in design, and the optical signals output by the sensors are transmitted via fiber optic cables to a signal readout unit for conversion into digital electrical signals. In the 120 ambulance transport environment, the above sensors can also acquire signals via a portable fiber optic demodulator and a vehicle-mounted ruggedized computer. The physical meaning and measurement dimensions of each signal remain consistent in both environments, ensuring the algorithm has cross-environmental applicability. The sampling clock is uniformly synchronized by an NTP time server to ensure strict time alignment of multi-channel data.

[0027] In this embodiment, acquiring the supply-end pressure signal, output-end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline, as well as the respiratory waveform signal and blood oxygen saturation signal of the oxygen supply system at each sampling time includes: acquiring a first original signal of the oxygen supply pipeline and a second original signal of the oxygen supply system at each sampling time; wherein, the first original signal includes the original supply-end pressure signal, the original output-end pressure signal, and the original oxygen flow rate signal, and the second original signal includes the original respiratory waveform signal and the original blood oxygen saturation signal; constructing a first discrete-time series and a second discrete-time series based on each of the first original signal and each of the second original signal, and performing time alignment on the first discrete-time series and the second discrete-time series to obtain each of the first aligned sequences and each of the second aligned sequences; performing MRI electromagnetic interference filtering on each of the first aligned sequences to obtain the filtered supply-end pressure signal, the filtered output-end pressure signal, and the filtered oxygen flow rate signal; and performing filtering on each of the second aligned sequences to obtain the filtered respiratory waveform signal and the filtered blood oxygen saturation signal.

[0028] At each sampling time, the first original signal of the oxygen supply pipeline and the second original signal of the oxygen supply system are collected respectively. The first original signal is the original supply end pressure signal, the original output end pressure signal, and the original oxygen flow rate signal. The second original signal is the original respiratory waveform signal and the original blood oxygen saturation signal. The first discrete time series and the second discrete time series are constructed respectively. It can be understood that the first discrete time series includes the discrete time series of the original supply end pressure signal, the original output end pressure signal, and the original oxygen flow rate signal, respectively. The second discrete time series includes the discrete time series of the original respiratory waveform signal and the original blood oxygen saturation signal. The time alignment of the multi-channel data is completed by the NTP time server to obtain each first aligned sequence and each second aligned sequence.

[0029] The pressure and flow signals in the first aligned sequence were subjected to MRI electromagnetic interference filtering. The filtering method involved obtaining the gradient switching fundamental frequency of the current scan sequence from the MRI console. and its first M harmonic frequencies An adaptive notch filter is constructed to filter the signals from each sensor. The transfer function of the adaptive notch filter is shown below: ; in, Notch bandwidth control parameters ( In this embodiment, 0.95 is used. For unit delay operators, yes The second power of is the two-level unit delay operator, which satisfies This means that the signal will be sent. Delay by two sampling periods, =100Hz to eliminate periodic electromagnetic interference artifacts generated by gradient magnetic field switching and radio frequency pulses, and obtain the filtered supply pressure signal, the filtered output pressure signal, and the filtered oxygen flow signal.

[0030] For the respiratory waveform signal and blood oxygen saturation signal in the second aligned sequence, since their frequency band is much lower than the gradient switching frequency, a low-pass filter with a cutoff frequency of 10Hz is used to remove high-frequency spikes, resulting in the filtered respiratory waveform signal and the filtered blood oxygen saturation signal.

[0031] Step S12: Construct an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistor, and the output end air capacitance as the capacitor. Based on the equivalent circuit model, establish a discretized state equation with the output end pressure and the pipeline air resistance as state variables, and an observation equation with the output end pressure and oxygen flow rate as observation quantities.

[0032] In this embodiment, the construction of an equivalent circuit model with the supply-end pressure as the input voltage, the air resistance of the oxygen supply pipeline as a variable resistor, and the output-end gas capacitance as a capacitor, and the establishment of a discretized state equation with the output-end pressure and the air resistance of the pipeline as state variables, and an observation equation with the output-end pressure and oxygen flow rate as observation quantities based on the equivalent circuit model, includes: mapping the hydrodynamic characteristics of the oxygen supply pipeline to a first-order RC equivalent circuit model; wherein, the supply-end pressure is used as a constant pressure source, the air resistance of the oxygen supply pipeline is used as a variable resistor connected in series between the constant pressure source and the output end, and the volume effect of the terminal of the oxygen supply pipeline and the compressible gas in the patient mask is used as a variable resistor connected in parallel between the output end and the... The capacitance between reference grounds is represented by the leakage resistance connected in parallel across the capacitor, with the patient's spontaneous breathing consuming gas. The reference ground is the ambient atmospheric pressure. A continuous-time differential equation is established for the node containing the capacitor based on Kirchhoff's current law. This continuous-time differential equation characterizes the quantitative relationship between output pressure, pipeline air resistance, supply pressure, oxygen flow rate, gas capacity, and leakage resistance. The continuous-time differential equation is discretized to obtain a discretized state equation with output pressure and pipeline air resistance as state variables. Based on the continuous-time differential equation and the relationship between oxygen flow rate and output pressure, an observation equation is established with output pressure and oxygen flow rate as observed quantities.

[0033] like Figure 2 As shown, a lumped parameter equivalent circuit model of the oxygen supply pipeline is established, mapping the pipeline air resistance to resistance parameters. The gas capacitance of the pipeline is mapped to the capacitance parameter. Gas pressure is mapped to voltage U, and gas flow rate is mapped to current I; with supply-side pressure... Output pressure signal Oxygen flow signal As an observation, the Kalman filter algorithm is used to estimate the pipeline air resistance parameters online. .

[0034] The lumped-parameter equivalent circuit model is a first-order RC equivalent circuit model. Specifically, the mapping relationship is: the supply-side gas pressure output from the oxygen supply equipment... It is equivalent to a constant voltage source in a circuit (equivalent to a power supply voltage); the frictional resistance and local resistance encountered by the gas flowing in the pipeline are equivalent to a variable resistance. The compressibility of the gas in the cavity between the tube output end and the patient's face or endotracheal tube is equivalent to a capacitor connected to ground. (Equivalent to an energy storage element in a circuit); the process of oxygen consumption during the patient's spontaneous breathing is equivalent to a leakage resistor connected in parallel with the capacitor. (Equivalent to load resistance). The reference ground plane for all equivalent elements is the current ambient atmospheric pressure.

[0035] The supply side is a constant pressure source Gas through pipeline gas resistance The gas flows to the output end, and the output end gas capacity This represents the volumetric effect of the compressible gas at the pipeline terminal and within the mask, with the gas pressure at both ends being... The patient's spontaneous breathing consumes gas equivalent to a leakage air resistance. The flow rate through this air resistance can be used to approximate the patient's minute ventilation.

[0036] In the equivalent circuit model, the positive terminal of the constant voltage source passes through the variable resistor. Connected to a common node, at which the capacitor is also connected in parallel. and leakage resistance Both are connected to a reference ground at their other ends. The potential at this common node corresponds to the output pressure. .

[0037] According to Kirchhoff's current law (conservation of gas mass), for the gas-capacitor node at the output end, the continuous-time differential equation of the node containing the capacitor is established as follows: ; In the formula, When the patient's spontaneous breathing is stable, it can be considered a constant and estimated from the patient's average tidal volume and respiratory rate. For known system parameters, they can be pre-calibrated using pipeline volume and gas compressibility coefficient.

[0038] Oxygen flow signal measured by flow sensor The following relationship must be satisfied: .

[0039] air resistance parameters Consider it as the state variable to be estimated. Define the state vector of the system at any time t. for: ; in, The output pressure can be measured directly. These are the air resistance parameters to be identified.

[0040] Discretize the continuous-time differential equation and the sampling period. Assuming The dynamic model is a random walk process, whose changes are driven by process noise, resulting in the discrete-time state equation: ; ; In the formula, The process noise, representing the air resistance parameter, follows a zero-mean Gaussian distribution with a covariance of... The observation vector consists of two directly measurable signals: ; Where the superscript "meas" represents the sensor's measured value. The observation equation is: ; ; in, and Let the pressure measurement noise and flow measurement noise be uncorrelated, zero-mean Gaussian white noise, respectively. Their covariance matrices are: ; In the formula, This represents the covariance of the pressure measurement noise. This represents the covariance of the flow measurement noise.

[0041] Step S13: Using the supply end pressure signal as the input to the discretized state equation, and the output end pressure signal and the oxygen flow rate signal as the input to the observation equation, the Kalman filter algorithm is used to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time.

[0042] In this embodiment, the step of using the supply-side pressure signal as the input to the discretized state equation, and the output-side pressure signal and the oxygen flow rate signal as the input to the observation equation, and using the Kalman filter algorithm to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time includes: at each sampling time, using the supply-side pressure signal at the current time as the input excitation of the discretized state equation, recursively predicting the discretized state equation to obtain the prior estimate of the output-side pressure and the pipeline air resistance at the current time; using the output-side pressure signal and the oxygen flow rate signal at the current time as the observation values ​​at the current time, and inputting them into the observation equation, determining the residual between the prior estimate and the observation value, and weighting and correcting the prior estimate based on the residual to obtain the posterior estimate of the output-side pressure and the pipeline air resistance at the current time; and determining the posterior estimate of the pipeline air resistance obtained recursively at each sampling time as the optimal estimate of the pipeline air resistance at each sampling time.

[0043] At each sampling time, the supply-side pressure signal at the current time is used as the input excitation for the discretized state equation. The discretized state equation is then recursively predicted to obtain the prior estimates of the output-side pressure and pipeline air resistance at the current time. The state vector in the discretized state equation consists of the output-side pressure and pipeline air resistance, and the process noise of the air resistance parameter follows a zero-mean Gaussian distribution.

[0044] Since the functional relationship between flow rate and state in the observation equation is nonlinear, an Extended Kalman Filter (EKF) is used for state estimation. The EKF recursive process is as follows: Prediction Step: ; That is, the prior state estimate is equal to the result of mapping the previous posterior estimate to the nonlinear state transition function f described by the discretized state equation, where, The nonlinear state transition function is defined for the discrete-time state equation. The prediction error covariance matrix is: ; In the formula, the state transition Jacobian matrix is: ; Expanding on this will yield the following: ; Process noise covariance matrix for: ; in, This is the variance of the output pressure process noise, used to absorb model errors. Update steps: The current output pressure signal and oxygen flow rate signal constitute the current two-dimensional observation vector, where the pressure measurement noise and flow rate measurement noise are assumed to be uncorrelated, zero-mean Gaussian white noise. The observation Jacobian matrix is: ; The expression for Kalman gain is: ; This gain determines the weighted correction magnitude of the residuals between the prior estimate and the observed value.

[0045] Then, a state update is performed, and the state update equation is: ; The posterior estimate of the state is calculated by adding the prior estimate to the Kalman gain and multiplying by the observation residual (the observed value minus the observed value predicted by the prior estimate).

[0046] The error covariance update equation is: ; Through the above recursive calculations, the optimal estimate of the pipeline air resistance parameter is obtained at each sampling time k. This estimate integrates complementary information from pressure and flow sensors, effectively suppressing measurement noise and MRI interference, and accurately reflecting the true physical state of pipeline air resistance.

[0047] Step S14: Detect the abrupt change direction of the optimal estimated value of the pipeline air resistance, and determine the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline status is a blocked state or a detached state.

[0048] In this embodiment, the step of detecting abrupt changes in the optimal estimated value of the pipeline air resistance and determining the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window includes: obtaining the nominal air resistance value of the oxygen supply pipeline under normal operating conditions; at each sampling time, obtaining the optimal estimated value of the pipeline air resistance corresponding to each sampling time within the preset time window before the current time, and calculating the upward cumulative sum and the downward cumulative sum based on the difference between each optimal estimated value and the nominal air resistance value; when the upward cumulative sum exceeds a first preset threshold, it is determined that the oxygen supply pipeline is in a blocked state; when the downward cumulative sum exceeds a second preset threshold, it is determined that the oxygen supply pipeline is in a detached state.

[0049] After obtaining the optimal estimate of the pipeline air resistance, the physical meaning of its direction of change is used to distinguish the type of pipeline fault. Under normal pipeline operation, the optimal estimate of the pipeline air resistance stabilizes at a nominal value related to the pipeline length, inner diameter, and gas viscosity. Nearby, when a blockage occurs, the local cross-section of the pipeline decreases, and the air resistance increases sharply (i.e., the optimal estimate of the pipeline air resistance tends to infinity). When a detachment occurs, the output end is directly connected to the atmosphere, and the air resistance almost disappears at the point of connection failure (i.e., the optimal estimate of the pipeline air resistance tends to zero).

[0050] To reliably detect such directional mutations, this embodiment employs a change point detection algorithm based on Cumulative Sum (CUSUM) to establish statistics for upward deviation (blockage) and downward deviation (detachment).

[0051] Assume the average air resistance under normal conditions is This value is updated online from historical data or preset, and the allowable small fluctuation range is [missing value]. This embodiment Take 0.1 Define upward cumulative sum and downward accumulation and Its expression is: ; ; initial value = =0, set the detection threshold h (0.5 in this embodiment). ),when When >h, a pipe blockage is determined; when When the value is greater than h, a pipe detachment is determined to have occurred. Once any alarm is triggered, the corresponding accumulation and reset to zero to prevent repeated triggering. This method achieves a precise distinction between blockage and detachment in terms of physical nature: blockage always causes a positive cumulative shift in the estimated air resistance value, while detachment always causes a negative cumulative shift. The CUSUM response paths for the two are completely independent, thus achieving the purpose of distinguishing between the two types of fault defects.

[0052] In this embodiment, after determining the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window, the method further includes: predicting the patient's risk of asphyxiation based on the status of the oxygen supply pipeline, the respiratory status determined based on the respiratory waveform signal, and the oxygenation status determined based on the blood oxygen saturation signal.

[0053] Accurate differentiation of the physical state of the tubing provides reliable fault diagnosis input. Based on this, cross-validation and fusion of the patient's spontaneous breathing status and oxygenation status can issue an asphyxiation risk warning before a significant drop in pulse oxygen saturation (SpO2), solving the inherent physiological delay lag problem of 45 to 90 seconds in SpO2 monitoring.

[0054] In this embodiment, the prediction of asphyxiation risk for the patient based on the state of the oxygen supply pipeline, the respiratory state determined based on the respiratory waveform signal, and the oxygenation state determined based on the blood oxygen saturation signal includes: determining a pipeline physical state risk factor based on the state of the oxygen supply pipeline; wherein, when the oxygen supply pipeline is in normal working condition, the pipeline physical state risk factor is a first preset value; when the oxygen supply pipeline is in a blocked or dislodged state, the pipeline physical state risk factor is a second preset value; when the increase of the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed the first preset threshold, or when the decrease of the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed the second preset threshold, the pipeline physical state risk factor is a third preset value; determining the short-time energy and zero-crossing rate of the respiratory waveform signal within a sliding window; if the short-time energy and the zero-crossing rate meet preset conditions, then respiratory asphyxiation is determined. The patient is in a state of apnea, and the respiratory risk factor is set to a fourth preset value. If the short-term energy and the zero-crossing rate do not meet preset conditions, the respiratory frequency in the respiratory waveform signal is determined, and the respiratory risk factor is assigned a value between 0 and 1 based on the normalized distance of the respiratory frequency deviating from the preset normal range. The preset conditions are that the short-term energy is continuously lower than the preset energy lower limit and the zero-crossing rate is continuously lower than the preset zero-crossing rate lower limit for a period exceeding a preset apnea judgment threshold. The linear fitting slope of the blood oxygen saturation signal within a sliding window is determined. When the linear fitting slope is negative and the absolute value of the linear fitting slope exceeds a preset rate of decline threshold, the oxygenation risk factor is assigned a value between 0 and 1 according to a linear mapping. The risk factors of the tubing physical state, the respiratory risk factor, and the oxygenation risk factor are weighted and fused to obtain a comprehensive risk score. The patient's asphyxia risk level is predicted based on the preset value range of the comprehensive risk score.

[0055] Determine the risk factor of the physical condition of the oxygen supply pipeline based on its condition. When the oxygen supply pipeline is in normal working condition The first preset value is 0, which is used when the oxygen supply pipeline is blocked or detached. The second preset value is 1. This occurs when the increase in the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed a first preset threshold, or when the decrease in the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed a second preset threshold. The third preset value is 0.5.

[0056] Determine the short-time energy of the respiratory waveform signal R[n] within the sliding window. and zero crossing rate The calculation formula is: ; ; in, This is the length of the sliding window (2 seconds in this example). The mean within the window. This is an indicator function; the function evaluates to 1 when the logical expression within the parentheses is true, and to 0 when the logical expression is false. Continuously below the preset energy limit and If the time spent below the preset zero-crossing rate threshold exceeds the apnea detection threshold (15 seconds in this embodiment), it is determined to be an apnea event, and the respiratory risk factor is set to the fourth preset value, i.e. Otherwise, a value between 0 and 1 is assigned based on the normalized distance of the respiratory rate from the normal range.

[0057] Determine the slope of the linear fit of the blood oxygen saturation signal SpO2[k] within the sliding window. The specific formula is as follows: ; in, The length of the trend assessment window (30 seconds in this example). Sampling time, and Representing the time within the window respectively The mean. When When the value is negative and its absolute value exceeds the preset rate of decline threshold, it indicates that the oxygenation status is deteriorating, and the oxygenation risk factor is... Values ​​are taken according to a linear mapping, even when Even if the absolute value is still above the 94% safety range, the trend of decompensation can be detected in advance.

[0058] The Analytic Hierarchy Process (AHP) was used to assign weights to the three risk dimensions. Clinical experts constructed a judgment matrix and calculated the tubing status weights. Respiratory state weights Oxygenation state weight The sum of the three weights is 1. In this embodiment, considering that the pipeline status directly reflects the risk of oxygen supply interruption, the pipeline status weight is... Respiratory state weights Oxygenation state weight The values ​​were set to 0.5, 0.3, and 0.2 respectively; then the overall risk score was calculated. ; The value range is [0, 1]. When the pipeline is blocked or detached ( And there is also apnea ( Even if SpO2 has not decreased significantly at this time ( ), It has reached the critical warning threshold and can issue a suffocation risk warning tens of seconds before a noticeable drop in SpO2 occurs.

[0059] Based on the comprehensive risk score The preset numerical range is used to predict the patient's risk level of asphyxiation, and a three-level warning threshold is set: Yellow alert (attention level): 0.3≤ <0.5; Orange alert (warning level): 0.5≤ <0.8; Red Alert (Critical Level): >0.8; When the tubing is blocked or dislodged and breathing apnea occurs simultaneously, even if SpO2 has not yet decreased significantly, It has reached the critical warning threshold and can issue a suffocation risk warning tens of seconds before a noticeable drop in SpO2 occurs.

[0060] Simultaneously, root cause diagnostic suggestions are output based on the combination of various risk factors, for example: Furthermore, the CUSUM message indicates "Pipe blockage, please check if the pipe is bent or under pressure." Furthermore, the CUSUM indicator triggers the message "Pipeline detached, please reconnect the oxygen supply line immediately"; And the tubing is normal. "The patient is experiencing respiratory arrest. Please assess the depth of sedation or airway patency." Early warning information is output to the MRI control room or transport monitoring terminal via a graphical interface and audible alarm, enabling medical staff to make quick decisions.

[0061] This embodiment uses the above method to simulate pipe blockage (gradually clamping the pipe) and pipe detachment (disconnecting the output terminal) experiments, and the extended Kalman filter estimates the air resistance parameters. Capable of tracking physical changes in real time: during congestion From nominal value The monotonicity rises to more than 5 times and triggers the CUSUM blockage alarm, when it detaches. The SpO2 signal drops instantly to near zero, triggering a detachment alarm. After both faults are introduced, the SpO2 signal shows a significant decrease only after a delay of approximately 60 to 80 seconds. In contrast, this method correctly distinguishes the tubing status and outputs an early warning within 3 seconds of the fault occurring, significantly outperforming existing clinical techniques that rely solely on the delayed detection of SpO2 decline.

[0062] The beneficial effects of this invention are as follows: The oxygen supply system of this invention includes an oxygen supply pipeline, which includes a supply end and an output end; the method includes: acquiring the supply end pressure signal, the output end pressure signal, and the oxygen flow rate signal of the oxygen supply pipeline at each sampling time; constructing an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance as the variable resistor, and the output end air capacitance as the capacitor; and establishing a discretized state equation with the output end pressure and the pipeline air resistance as state variables, and an observation equation with the output end pressure and the oxygen flow rate as observed quantities, based on the equivalent circuit model. The system employs a measurement equation; using the supply-end pressure signal as input to the discretized state equation, and the output-end pressure signal and the oxygen flow rate signal as input to the observation equation, a Kalman filter algorithm is used to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time; the optimal estimate of the pipeline air resistance is subjected to abrupt change direction detection, and the pipeline state of the oxygen supply pipeline is determined based on the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline state is either a blocked state or a detached state. Therefore, this invention, by collecting pressure and oxygen flow signals from the supply and output ends of the oxygen supply pipeline, constructs an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance as the variable resistance, and the output end air capacitance as the capacitance. Based on this, it establishes discretized state equations with output end pressure and pipeline air resistance as state variables, and observation equations with output end pressure and oxygen flow rate as observation quantities. This transforms the fluid dynamics of the oxygen supply pipeline into a parameter estimation problem of the circuit model, enabling the pipeline air resistance, which was originally impossible to measure directly, to be identified online using the Kalman filter algorithm, thereby obtaining the optimal estimate of the pipeline air resistance at each sampling time. When the pipeline is blocked, the cross-sectional area through which the fluid passes decreases, leading to an increase in air resistance. When the pipeline detaches, the output end connects to the atmosphere, causing a sudden drop in air resistance. The directions of air resistance change are diametrically opposed in these two fault modes. Therefore, by detecting the abrupt change direction of the optimal estimated value of the pipeline air resistance, the increase or decrease in air resistance within a preset time window can directly distinguish whether the oxygen supply pipeline is blocked or detached. This invention does not rely on a single determination of the flow rate threshold, nor does it rely on secondary judgment by medical personnel observing the output status and pipeline appearance. It can directly determine the fault type from a physical perspective when the oxygen supply pipeline malfunctions, providing a clear root cause for subsequent clinical treatment.

[0063] See Figure 3 As shown in the figure, an embodiment of the present invention discloses a device for determining the status of an oxygen supply pipeline in an oxygen supply system. The oxygen supply system includes an oxygen supply pipeline, which includes a supply end and an output end. The device includes: The signal acquisition module 11 is used to acquire the supply end pressure signal, output end pressure signal and oxygen flow signal of the oxygen supply pipeline at each sampling time. The model equation construction module 12 is used to construct an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistance, and the output end air capacitance as the capacitance. Based on the equivalent circuit model, a discretized state equation with the output end pressure and the pipeline air resistance as state variables is established, as well as an observation equation with the output end pressure and oxygen flow rate as observation quantities. The recursive estimation module 13 is used to take the supply end pressure signal as the input of the discretized state equation, and the output end pressure signal and the oxygen flow signal as the input of the observation equation, and use the Kalman filter algorithm to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time. The status determination module 14 is used to detect the sudden change direction of the optimal estimated value of the pipeline air resistance, and determine the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window; wherein the pipeline status is a blocked state or a detached state.

[0064] Furthermore, this embodiment of the invention also provides an oxygen supply system. Figure 4 This is a structural diagram of an oxygen supply system 20 according to an exemplary embodiment. The contents of the diagram should not be construed as limiting the scope of the invention.

[0065] Figure 4 This is a schematic diagram of an oxygen supply system provided in an embodiment of the present invention. Specifically, it may include: an oxygen supply pipeline, including an output end and a supply end connected to an oxygen supply device; a first pressure sensor disposed at the supply end for collecting the supply end pressure signal of the oxygen supply pipeline; a second pressure sensor disposed at the output end for collecting the output end pressure signal of the oxygen supply pipeline; and a flow sensor disposed in the oxygen supply pipeline for collecting the oxygen flow signal of the oxygen supply pipeline. The oxygen supply system further includes: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the oxygen supply pipeline status determination method performed by the oxygen supply system in any of the foregoing embodiments.

[0066] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the oxygen supply system; the communication interface 24 can create a data transmission channel between the oxygen supply system and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this invention, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0067] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processor), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0068] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored on it include operating system 221, computer program 222 and data 223, etc., and the storage method can be temporary storage or permanent storage.

[0069] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the oxygen supply system, enabling the processor 21 to perform calculations and processing on the massive amounts of data 223 stored in the memory 22. The operating system can be Windows, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the oxygen supply pipeline status determination method executed by the oxygen supply system as disclosed in any of the aforementioned embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the oxygen supply system from external devices, as well as data collected by its own input / output interface 25.

[0070] Furthermore, the present invention also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned method for determining the state of the oxygen supply pipeline in an oxygen supply system. The specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0071] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0072] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the invention. The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly in hardware, software modules executed by a processor, or a combination of both. The software module may be located in random access memory (RAM), memory, read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, removable disks, CD-ROMs (Compact Disc Read-Only Memory), or any other form of storage medium known in the art.

[0073] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0074] The above provides a detailed description of the method, device, system, and medium for determining the state of an oxygen supply pipeline in an oxygen supply system provided by the present invention. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for determining the state of an oxygen supply pipeline in an oxygen supply system, characterized in that, The oxygen supply system includes an oxygen supply pipeline, which includes a supply end and an output end; the method includes: At each sampling time, the supply end pressure signal, output end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline are collected; An equivalent circuit model is constructed with the supply end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistor, and the output end air capacitance as the capacitor. Based on the equivalent circuit model, a discretized state equation with the output end pressure and the pipeline air resistance as state variables, and an observation equation with the output end pressure and oxygen flow rate as observation quantities are established. Using the supply-side pressure signal as the input to the discretized state equation, and the output-side pressure signal and the oxygen flow rate signal as the input to the observation equation, the Kalman filter algorithm is used to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time. The optimal estimated value of the pipeline air resistance is subjected to abrupt change direction detection, and the pipeline status of the oxygen supply pipeline is determined according to the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline status is a blocked state or a detached state.

2. The method for determining the state of oxygen supply pipelines in an oxygen supply system according to claim 1, characterized in that, The construction of an equivalent circuit model with the supply-end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistance, and the output-end air capacitance as the capacitance, and the establishment of a discretized state equation with the output-end pressure and the pipeline air resistance as state variables, and an observation equation with the output-end pressure and oxygen flow rate as observation quantities based on the equivalent circuit model, includes: The hydrodynamic characteristics of the oxygen supply pipeline are mapped to a first-order RC equivalent circuit model; wherein, the supply end pressure is the constant pressure source, the pipeline air resistance of the oxygen supply pipeline is the variable resistor connected in series between the constant pressure source and the output end, the volume effect of the end of the oxygen supply pipeline and the compressible gas in the patient's mask is the capacitor connected in parallel between the output end and the reference ground, the gas consumption by the patient's spontaneous breathing is the leakage resistance connected in parallel across the capacitor, and the reference ground is the ambient atmospheric pressure; Based on Kirchhoff's current law, a continuous-time differential equation is established for the node where the capacitor is located; wherein, the continuous-time differential equation characterizes the quantitative relationship between the output pressure, pipeline gas resistance, supply pressure, oxygen flow rate, gas capacity, and leakage resistance. The continuous-time differential equation is discretized to obtain a discretized state equation with the output pressure and the pipeline air resistance as state variables. Based on the continuous-time differential equation and the relationship between oxygen flow rate and output pressure, an observation equation is established with output pressure and oxygen flow rate as the observed quantities.

3. The method for determining the state of oxygen supply pipelines in an oxygen supply system according to claim 2, characterized in that, The process involves using the supply-side pressure signal as input to the discretized state equation, and the output-side pressure signal and the oxygen flow rate signal as input to the observation equation. A Kalman filter algorithm is used to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time. This includes: At each sampling time, the supply end pressure signal at the current time is used as the input excitation of the discretized state equation, and the discretized state equation is recursively predicted to obtain the prior estimates of the output end pressure and the pipeline air resistance at the current time. Using the current output pressure signal and the current oxygen flow signal as the observed values, and inputting them into the observation equation, the residual between the prior estimate and the observed value is determined. The prior estimate is then weighted and corrected based on the residual to obtain the posterior estimate of the current output pressure and the pipeline air resistance. The posterior estimate of the pipeline air resistance obtained by recursion at each sampling time is determined as the optimal estimate of the pipeline air resistance at each sampling time.

4. The method for determining the state of oxygen supply pipelines in an oxygen supply system according to claim 3, characterized in that, The optimal estimated value of the pipeline air resistance is subjected to abrupt change direction detection, and the pipeline status of the oxygen supply pipeline is determined based on the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline status is a blocked state or a detached state, including: Obtain the nominal air resistance value of the oxygen supply pipeline under normal operating conditions; At each sampling moment, the optimal estimated value of the pipeline air resistance corresponding to each sampling moment within the preset time window before the current moment is obtained, and the upward cumulative sum and downward cumulative sum are calculated based on the difference between each optimal estimated value and the nominal value of the air resistance. When the upward accumulation exceeds a first preset threshold, it is determined that the oxygen supply pipeline is blocked. When the downward accumulation exceeds the second preset threshold, it is determined that the oxygen supply pipeline is in a detached state.

5. The method for determining the state of oxygen supply pipelines in an oxygen supply system according to any one of claims 1 to 4, characterized in that, The acquisition of the supply-end pressure signal, output-end pressure signal, and oxygen flow rate signal of the oxygen supply pipeline at each sampling time includes: At each sampling time, the supply end pressure signal, output end pressure signal, and oxygen flow signal of the oxygen supply pipeline, as well as the respiratory waveform signal and blood oxygen saturation signal of the oxygen supply system, are collected. Accordingly, after determining the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window, the method further includes: The risk of asphyxiation in patients is predicted based on the status of the oxygen supply line, the respiratory status determined by the respiratory waveform signal, and the oxygenation status determined by the blood oxygen saturation signal.

6. The method for determining the state of oxygen supply pipelines in an oxygen supply system according to claim 5, characterized in that, The acquisition of the supply-end pressure signal, output-end pressure signal, and oxygen flow signal of the oxygen supply pipeline, as well as the respiratory waveform signal and blood oxygen saturation signal of the oxygen supply system at each sampling time includes: At each sampling time, the first raw signal of the oxygen supply pipeline and the second raw signal of the oxygen supply system are collected respectively; wherein, the first raw signal includes the raw supply end pressure signal, the raw output end pressure signal, and the raw oxygen flow signal, and the second raw signal includes the raw respiratory waveform signal and the raw blood oxygen saturation signal; A first discrete time series and a second discrete time series are constructed based on each of the first original signals and each of the second original signals, and the first discrete time series and the second discrete time series are time-aligned to obtain each first aligned sequence and each second aligned sequence. Each of the first aligned sequences is subjected to MRI electromagnetic interference filtering to obtain the filtered supply pressure signal, the filtered output pressure signal, and the filtered oxygen flow rate signal. Each of the second aligned sequences is filtered to obtain the filtered respiratory waveform signal and the filtered blood oxygen saturation signal.

7. The method for determining the state of oxygen supply pipelines in an oxygen supply system according to claim 5, characterized in that, The method of predicting the risk of asphyxiation in patients based on the status of the oxygen supply pipeline, the respiratory status determined based on the respiratory waveform signal, and the oxygenation status determined based on the blood oxygen saturation signal includes: The physical state risk factor of the oxygen supply pipeline is determined based on its status. Specifically, when the oxygen supply pipeline is in normal working condition, the physical state risk factor is a first preset value; when the oxygen supply pipeline is blocked or detached, the physical state risk factor is a second preset value; and when the increase in the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed the first preset threshold, or when the decrease in the optimal estimated value of the pipeline air resistance exceeds a preset warning threshold but does not exceed the second preset threshold, the physical state risk factor is a third preset value. The short-time energy and zero-crossing rate of the respiratory waveform signal within a sliding window are determined. If the short-time energy and the zero-crossing rate meet a preset condition, the respiratory state is determined to be apnea and the respiratory risk factor is set to a fourth preset value. If the short-time energy and the zero-crossing rate do not meet the preset condition, the respiratory frequency in the respiratory waveform signal is determined, and the respiratory risk factor is assigned a value between 0 and 1 based on the normalized distance of the respiratory frequency from the preset normal range. The preset condition is that the short-time energy is continuously lower than a preset energy lower limit and the zero-crossing rate is continuously lower than a preset zero-crossing rate lower limit for a period exceeding a preset apnea determination threshold. Determine the linear fitting slope of the blood oxygen saturation signal within a sliding window. When the linear fitting slope is negative and the absolute value of the linear fitting slope exceeds a preset rate of decline threshold, assign the oxygenation risk factor a value between 0 and 1 according to the linear mapping. The risk factors of the pipeline physical state, the respiratory risk factor, and the oxygenation risk factor are weighted and fused to obtain a comprehensive risk score; The patient's asphyxiation risk level is predicted based on the preset numerical range of the comprehensive risk score.

8. A device for determining the status of an oxygen supply pipeline in an oxygen supply system, characterized in that, The oxygen supply system includes an oxygen supply pipeline, which includes a supply end and an output end; the device includes: The signal acquisition module is used to acquire the supply end pressure signal, output end pressure signal and oxygen flow signal of the oxygen supply pipeline at each sampling time. The model equation construction module is used to construct an equivalent circuit model with the supply end pressure as the input voltage, the pipeline air resistance of the oxygen supply pipeline as the variable resistance, and the output end air capacitance as the capacitor. Based on the equivalent circuit model, a discretized state equation with the output end pressure and the pipeline air resistance as state variables is established, as well as an observation equation with the output end pressure and oxygen flow rate as observation quantities. The recursive estimation module is used to take the supply end pressure signal as the input of the discretized state equation, and the output end pressure signal and the oxygen flow signal as the input of the observation equation. It uses the Kalman filter algorithm to recursively estimate the discretized state equation and the observation equation to obtain the optimal estimate of the pipeline air resistance at each sampling time. The status determination module is used to detect the sudden change direction of the optimal estimated value of the pipeline air resistance, and determine the pipeline status of the oxygen supply pipeline based on the increase or decrease of the pipeline air resistance within a preset time window; wherein, the pipeline status is a blocked state or a detached state.

9. An oxygen supply system, characterized in that, include: Oxygen supply pipeline, including the output end and the supply end connected to the oxygen supply equipment; A first pressure sensor installed at the supply end is used to collect the supply end pressure signal of the oxygen supply pipeline; The second pressure sensor, located at the output end, is used to collect the pressure signal at the output end of the oxygen supply pipeline. A flow sensor installed in the oxygen supply pipeline is used to collect the oxygen flow signal of the oxygen supply pipeline; Furthermore, the oxygen supply system also includes: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the steps of the method for determining the state of an oxygen supply pipeline in an oxygen supply system as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the method for determining the state of the oxygen supply pipeline in an oxygen supply system as described in any one of claims 1 to 7.

Images