An intelligent ventilator operation monitoring system

Abstract

The present invention discloses an intelligent ventilator operation monitoring system, including a data acquisition module, a safety margin evaluation function definition module, a safety margin standardization module, an initial danger point calibration module, a risk direction deviation detection module, an adaptive step size update module, an iterative convergence determination module, a system training module and a ventilator operation monitoring module. The present invention belongs to the field of operation monitoring, and specifically refers to an intelligent ventilator operation monitoring system. This scheme is guided by gradients, continuously iteratively approaches danger points, and accurately locates risk peaks within a respiratory cycle; quantifies the angle between the real risk trajectory and the ideal trajectory through risk direction deviation detection, and captures transient nonlinear events of sudden airway obstruction; performs angle normalization curve amplification in the respiratory stable interval to accelerate the approach to the most dangerous point; performs linear convergence correction in the nonlinear mutation interval to avoid false alarms caused by short-term noise, thereby improving the operation monitoring effect.

Description

Technical Field

[0001] The present invention relates to the field of operation monitoring, and in particular to an intelligent ventilator operation monitoring system. Background Art

[0002] The ventilator operation monitoring system is an intelligent platform that integrates sensing, data processing, reliability analysis, and real-time warning. However, typical ventilator operation monitoring systems are prone to missing transient extreme points in the cycle, and fail to respond promptly to sudden risks such as transient airway obstruction and sudden changes in patient compliance, resulting in false oscillation alarms and poor operation monitoring accuracy. Typical ventilator operation monitoring systems also have a slow response to sudden changes, repeatedly oscillating in nonlinear local intervals, missing true changes in risk direction, and are prone to false alarms and underreporting, resulting in poor operation monitoring effectiveness. Summary of the Invention

[0003] To address the above-mentioned situation and overcome the shortcomings of the prior art, the present invention provides an intelligent ventilator operation monitoring system. This system addresses the problem that conventional ventilator operation monitoring systems are prone to missing transient extreme points within a cycle, failing to respond promptly to sudden risks of transient airway obstruction and patient compliance changes, resulting in false oscillation alarms and poor operation monitoring accuracy. This system uses a gradient-guided approach to iteratively approach the danger point, accurately locating the risk peak within the respiratory cycle. It uses risk direction deviation detection to quantify the angle between the true risk trajectory and the ideal trajectory, adjusting the step size in real time to capture transient nonlinear events such as sudden airway obstruction. This improves operation monitoring accuracy. Furthermore, conventional ventilator operation monitoring systems suffer from slow sudden change response, repeated oscillations in local nonlinear intervals, missing true risk direction changes, and prone to false alarms and missed alerts, resulting in poor operation monitoring performance. This system performs angle normalization curve amplification in the stable breathing interval to accelerate approach to the most dangerous point. It also performs linear convergence correction in the nonlinear sudden change interval to counteract oscillation divergence in the presence of severe nonlinearity and prevent missed or false alerts. Furthermore, it uses dual convergence judgment to avoid false alarms caused by short-term noise, thereby improving operation monitoring performance.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides an intelligent ventilator operation monitoring system, including a data acquisition module, a safety margin evaluation function definition module, a safety margin standardization module, an initial danger point calibration module, a risk direction deviation detection module, an adaptive step size update module, an iterative convergence determination module, a system training module and a ventilator operation monitoring module;

[0005] The data acquisition module collects historical operating data of the ventilator and constructs an operating monitoring sample set;

[0006] The safety margin evaluation function definition module obtains a safety margin evaluation function by calculating the standardized margin of deviation between each operation monitoring variable and its safety margin;

[0007] The safety margin normalization module maps the original operation monitoring variables to the standard normal space using the empirical distribution function;

[0008] The initial dangerous point calibration module takes the most dangerous point in the cycle as the starting point and performs the first iterative position update;

[0009] The risk direction deviation detection module analyzes and detects the direction of risk deviation;

[0010] The adaptive step size update module adjusts the step size based on the interval division;

[0011] The iterative convergence determination module performs iterative determination on the operation data within the cycle;

[0012] The system training module trains system parameters;

[0013] The ventilator operation monitoring module is connected in series with each system module to monitor the ventilator operation data collected in real time within a period.

[0014] Furthermore, the data acquisition module collects historical operating data of the ventilator; marks the operating status of the ventilator operating data within a cycle, and the operating status includes normal operation and abnormal operation; pre-processes the historical operating data of the ventilator to obtain an operation monitoring sample set; and sets a safety boundary for each parameter.

[0015] Furthermore, the safety margin evaluation function definition module defines a safety margin evaluation function To ensure the safety of all indicators at the same time, take the worst margin, for i running monitoring samples x i , the safety margin evaluation function is expressed as: ;in, is the safety boundary of the jth monitoring variable; is the jth monitoring variable; is the standard deviation of the jth monitoring variable; is the weight of the jth monitoring variable; The most dangerous dimension value within the corresponding sample; for the operation monitoring sample set, calculate the value of each operation monitoring sample , take the sample corresponding to the minimum value as the initial most dangerous point in a cycle.

[0016] Furthermore, the safety margin normalization module performs a normalization transformation on each variable, which is expressed as: ;in, is the standard normal inverse CDF; is the empirical distribution function of the i-th monitoring quantity; obtain the mapped vector u; rewrite the safety margin evaluation function as: ; Each vector u in the mapping space is mapped to a running monitoring sample .

[0017] Furthermore, the initial dangerous point calibration module determines the initial most dangerous point in the respiratory cycle in the standard normal space as , as the starting point of this cycle iteration, the first step length , location update: ;in, It is the most dangerous point position after the first iteration; is the safety margin evaluation function in The value at is the gradient.

[0018] Furthermore, the risk direction deviation detection module calculates for the kth iteration: ; ; ;in, and are the most dangerous point positions at the kth iteration and the k-1th iteration respectively; is the safety margin evaluation function in The value at is the ideal update vector; is the degree of alignment; is the angular deviation.

[0019] Furthermore, the adaptive step size update module sets the angle threshold , the value range is (0,90) degrees, for The stable interval of , by adjusting the step size through the curve, is expressed as: ; ; where t is the normalized angular deviation; is the step size; for The nonlinear mutation interval of , through linear convergence correction step, is expressed as: ; ; ; ;in, is the mutation auxiliary function; c is the balance coefficient; is the direction vector; is a smoothing term; take the minimum m so that ; ;in, is a control parameter with a value range of (0,1); T is a transpose operation, where the gradient vector is transposed.

[0020] Furthermore, the iterative convergence determination module updates the stable interval using ; Nonlinear mutation interval update: ; Convergence judgment, expressed as: ; Calculate reliability index , expressed as: ; ;in, is the most dangerous point position at the k+1th iteration; is the momentum coefficient, ranging from [0,1]; and is the convergence threshold, and its value range is [10 -3 ,10 -6 ]; a reliability index is obtained for each breathing cycle to quantify the safety margin; when When the breathing cycle is abnormal, it is judged that the operation is abnormal; otherwise, it is judged to be normal; is the alarm probability threshold, with a value range of (0,1); Cumulative distribution function of the standard normal distribution.

[0021] Furthermore, the system training module divides the operation monitoring sample set into a test set and a training set, trains the system parameters based on the training set, uses the cross entropy loss function, and sets a prediction threshold when the loss of the training set converges. When the prediction accuracy of the test set is higher than the prediction threshold, the system parameter training is completed.

[0022] Furthermore, the ventilator operation monitoring module collects the ventilator operation data within the cycle in real time, and inputs it into the safety margin standardization module, the initial danger point calibration module, the risk direction deviation detection module, the adaptive step size update module, and the iterative convergence judgment module in sequence. If it is finally determined that the operation is abnormal, an early warning process is performed.

[0023] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0024] (1) In view of the problem that general ventilator operation monitoring systems are prone to missing transient extreme points in the cycle, and are not quick enough to respond to sudden risks of transient airway obstruction and sudden changes in patient compliance, resulting in false oscillation alarms, which in turn leads to poor accuracy of operation monitoring, this solution is gradient-guided, continuously iteratively approaches the danger point, and accurately locates the risk peak within the respiratory cycle; quantifies the angle between the actual risk trajectory and the ideal trajectory through risk direction deviation detection, adjusts the step size in real time, and captures transient nonlinear events of sudden airway obstruction; thereby improving the accuracy of operation monitoring.

[0025] (2) In view of the problems that the general ventilator operation monitoring system has slow response to sudden changes, repeated oscillations in the nonlinear local range, missing the real risk direction change, prone to false alarms and missed reports, and poor operation monitoring effect, this scheme performs angle normalization curve amplification in the breathing stable range to speed up the approach to the most dangerous point; performs linear convergence correction in the nonlinear sudden change range, resists oscillation divergence in severe nonlinearity, and prevents missed reports or false reports; based on double convergence judgment, avoids false alarms caused by short-term noise, thereby improving the operation monitoring effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of an intelligent ventilator operation monitoring system provided by the present invention.

[0027] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] In the description of the present invention, it should be understood that terms such as "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, they should not be understood as limiting the present invention.

[0030] Example 1, see Figure 1 The present invention provides an intelligent ventilator operation monitoring system, comprising a data acquisition module, a safety margin evaluation function definition module, a safety margin standardization module, an initial danger point calibration module, a risk direction deviation detection module, an adaptive step size update module, an iterative convergence determination module, a system training module and a ventilator operation monitoring module;

[0031] The data acquisition module collects historical operating data of the ventilator and constructs an operating monitoring sample set; and sends the data to the safety margin evaluation function definition module;

[0032] The safety margin evaluation function definition module obtains a safety margin evaluation function by calculating the normalized margin of deviation between each operation monitoring variable and its safety margin; and sends the data to the safety margin standardization module;

[0033] The safety margin standardization module maps the original operation monitoring variables to the standard normal space using the empirical distribution function; and sends the data to the initial danger point calibration module;

[0034] The initial danger point calibration module takes the most dangerous point in the cycle as the starting point, performs the first iterative position update, and sends the data to the risk direction deviation detection module;

[0035] The risk direction deviation detection module analyzes and detects the direction of risk deviation; and sends the data to the adaptive step size update module;

[0036] The adaptive step size update module adjusts the step size based on the interval division; and sends the data to the iterative convergence determination module;

[0037] The iterative convergence determination module iteratively determines the operating data within the cycle; and sends the data to the system training module;

[0038] The system training module trains the system parameters and sends the data to the ventilator operation monitoring module;

[0039] The ventilator operation monitoring module is connected in series with each system module to monitor the ventilator operation data collected in real time within a period.

[0040] Example 2, see Figure 1 This embodiment is based on the above embodiment. The data acquisition module collects historical operating data of the ventilator; the operating status of the ventilator operating data within a cycle is marked, and the operating status includes normal operation and abnormal operation; the historical operating data of the ventilator includes positive end-expiratory pressure, tidal volume, respiratory rate, end-tidal CO2 concentration, battery voltage, and oxygen pressure; the historical operating data of the ventilator is preprocessed to obtain an operation monitoring sample set; the preprocessing includes missing value and outlier processing, smoothing filtering and vector conversion; and a safety margin is set for each parameter.

[0041] Example 3, see Figure 1 This embodiment is based on the above embodiment. The safety margin evaluation function definition module defines the safety margin evaluation function , in order to ensure the safety of all indicators at the same time, take the worst margin, for i running monitoring samples x i , the safety margin evaluation function is expressed as: ;in, is the safety boundary of the jth monitoring variable; is the jth monitoring variable; is the standard deviation of the jth monitoring variable; is the weight of the jth monitoring variable, ranging from [0,1]; The most dangerous dimension value within the corresponding sample; for the operation monitoring sample set, calculate the value of each operation monitoring sample , take the sample corresponding to the minimum value as the initial most dangerous point in a cycle.

[0042] Example 4, see Figure 1 This embodiment is based on the above embodiment. The safety margin normalization module performs a normalization transformation on each variable, which is expressed as: ;in, is the standard normal inverse CDF; is the empirical distribution function of the i-th monitoring quantity; obtain the mapped vector u; rewrite the safety margin evaluation function as: ; Each vector u in the mapping space is mapped to a running monitoring sample .

[0043] Example 5, see Figure 1 This embodiment is based on the above embodiment. The initial dangerous point calibration module determines the initial most dangerous point in the respiratory cycle in the standard normal space as , as the starting point of this cycle iteration, the first step length , location update: ;in, It is the most dangerous point position after the first iteration; is the safety margin evaluation function in The value at is the gradient; T is the transpose operation, where the gradient vector is transposed.

[0044] Example 6, see Figure 1 This embodiment is based on the above embodiment. The risk direction deviation detection module calculates the k-th iteration: ; ; ;in, and are the most dangerous point positions at the kth iteration and the k-1th iteration respectively; is the safety margin evaluation function in The value at is the ideal update vector; is the degree of alignment; It is the angle deviation; it quantifies the deviation of the iteration direction from the ideal direction in real time, reflecting the risks brought by sudden changes in ventilator-patient compliance and transient nonlinearity of airway obstruction; once a large turning angle is detected, the step size can be adjusted immediately to prevent iterative oscillation or divergence.

[0045] By performing the above operations, the general ventilator operation monitoring system is prone to missing the transient extreme points in the cycle, and does not respond promptly enough to the sudden risks of transient airway obstruction and sudden changes in patient compliance, resulting in false oscillation alarms, which in turn leads to poor operation monitoring accuracy. This solution is gradient-guided, continuously iteratively approaches the danger point, and accurately locates the risk peak within the respiratory cycle; through risk direction deviation detection, the angle between the actual risk trajectory and the ideal trajectory is quantified, and the step size is adjusted in real time to capture transient nonlinear events of sudden airway obstruction, thereby improving the accuracy of operation monitoring.

[0046] Example 7, see Figure 1 This embodiment is based on the above embodiment, and the adaptive step size update module sets the corner threshold ,for The stable interval of , by adjusting the step size through the curve, is expressed as: ; ; where t is the normalized angular deviation; is the step length; when the ventilator parameters fluctuate slightly, the step length is quickly enlarged to accelerate the search for the most dangerous point; the amount of calculation for each respiratory monitoring is greatly reduced to meet the real-time requirements; for The nonlinear mutation interval of , through linear convergence correction step, is expressed as: ; ; ; ;in, is the mutation auxiliary function; c is the balance coefficient; is the direction vector; is a smoothing term; take the minimum m so that ; ;in, is the control parameter; T is the transpose operation, where the gradient vector is transposed; in the event of severe nonlinearity such as sudden airway obstruction or a sharp change in patient compliance, it ensures that each step has sufficient descent; it is anti-oscillation and anti-divergence to prevent false alarms or missed alarms.

[0047] Example 8, see Figure 1 This embodiment is based on the above embodiment. The iterative convergence judgment module updates the stable interval using ; Nonlinear mutation interval update: ; Convergence judgment, avoids local jitter in nonlinearity and prevents missing drastic changes in directionality, expressed as: ; Calculate reliability index , expressed as: ; ;in, is the most dangerous point position at the k+1th iteration; is the momentum coefficient; and is the convergence threshold; a reliability index is obtained for each breathing cycle to quantify the safety margin; when When the breathing cycle is abnormal, it is judged that the operation is abnormal; otherwise, it is judged to be normal; is the alarm probability threshold; Cumulative distribution function of the standard normal distribution; for the stable interval where the difference between the previous and next periods is not much, the momentum term is used to speed up the search for the most dangerous point and reduce the repeated iterations of small noise.

[0048] By performing the above operations, in order to solve the problems of slow response to sudden changes in general ventilator operation monitoring systems, repeated oscillations in nonlinear local intervals, missing the real risk direction changes, prone to false alarms and missed alarms, and poor operation monitoring effects, this scheme performs angle normalization curve amplification in the stable breathing interval to speed up the approach to the most dangerous point; performs linear convergence correction in the nonlinear sudden change interval, resists oscillation divergence in severe nonlinearity, and prevents missed alarms or false alarms; based on double convergence judgment, avoids false alarms caused by short-term noise, thereby improving the operation monitoring effect.

[0049] Example 9, see Figure 1 This embodiment is based on the above embodiment. The system training module divides the running monitoring sample set into a test set and a training set. The safety boundary of each monitoring variable, the weight of the monitoring variable, the corner threshold, the alarm probability threshold, the balance coefficient, the initial smoothing term, the control parameter, and the convergence threshold are used as system parameters. The system parameters are trained based on the training set, and the cross entropy loss function is used. When the loss of the training set converges, the prediction threshold is set. When the prediction accuracy of the test set is higher than the prediction threshold, the system parameter training is completed.

[0050] Example 10, see Figure 1 This embodiment is based on the above embodiment. The ventilator operation monitoring module collects the ventilator operation data in real time during the cycle, and inputs it into the safety margin standardization module, the initial danger point calibration module, the risk direction deviation detection module, the adaptive step size update module, and the iterative convergence judgment module in sequence. If it is finally determined that the operation is abnormal, an early warning process is performed.

[0051] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that various changes, modifications, substitutions, and alterations can be made to the embodiments without departing from the principles and spirit of the invention.

[0052] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An intelligent ventilator operation monitoring system, characterized by: The system includes a data acquisition module, a safety margin evaluation function definition module, a safety margin standardization module, an initial danger point calibration module, a risk direction deviation detection module, an adaptive step size update module, an iterative convergence determination module, a system training module, and a ventilator operation monitoring module; The data acquisition module collects historical operating data of the ventilator and constructs an operating monitoring sample set; The safety margin evaluation function definition module obtains a safety margin evaluation function by calculating the standardized margin of deviation between each operation monitoring variable and its safety margin; The safety margin normalization module maps the original operation monitoring variables to the standard normal space using the empirical distribution function; The initial dangerous point calibration module takes the most dangerous point in the cycle as the starting point and performs the first iterative position update; The risk direction deviation detection module analyzes and detects the direction of risk deviation; The adaptive step size update module adjusts the step size based on the interval division; The iterative convergence determination module performs iterative determination on the operation data within the cycle; The system training module trains system parameters; The ventilator operation monitoring module is connected in series with each system module to monitor the ventilator operation data collected in real time within the cycle; The safety margin evaluation function definition module defines the safety margin evaluation function To ensure the safety of all indicators at the same time, take the worst margin, for i running monitoring samples x i , the safety margin evaluation function is expressed as: ;in, is the safety boundary of the jth monitoring variable; is the jth monitoring variable; is the standard deviation of the jth monitoring variable; is the weight of the jth monitoring variable; The most dangerous dimension value within the corresponding sample; for the operation monitoring sample set, calculate the value of each operation monitoring sample , take the sample corresponding to the minimum value as the initial most dangerous point in a cycle; The safety margin normalization module performs a normalization transformation on each variable, which is expressed as: ;in, is the standard normal inverse CDF; is the empirical distribution function of the i-th monitoring quantity; obtain the mapped vector u; rewrite the safety margin evaluation function as: ; Each vector u in the mapping space is mapped to a running monitoring sample .

2. The intelligent ventilator operation monitoring system according to claim 1, characterized in that: The initial dangerous point calibration module is used to determine the initial most dangerous point in the respiratory cycle in the standard normal space as , as the starting point of this cycle iteration, the first step length , location update: ;in, It is the most dangerous point position after the first iteration; is the safety margin evaluation function in The value at is the gradient; T is the transpose operation, where the gradient vector is transposed.

3. The intelligent ventilator operation monitoring system according to claim 2, characterized in that: The risk direction deviation detection module calculates for the kth iteration: ; ; ;in, and are the most dangerous point positions at the kth iteration and the k-1th iteration respectively; is the safety margin evaluation function in The value at is the ideal update vector; is the degree of alignment; is the angular deviation.

4. The intelligent ventilator operation monitoring system according to claim 3, characterized in that: The adaptive step size update module sets the angle threshold ,for The stable interval of , by adjusting the step size through the curve, is expressed as: ; ; where t is the normalized angular deviation; is the step size; for The nonlinear mutation interval of , through linear convergence correction step, is expressed as: ; ; ; ;in, is the mutation auxiliary function; c is the balance coefficient; is the direction vector; is a smoothing term; take the minimum m so that ; ;in, is the control parameter; T is the transpose operation, where the gradient vector is transposed.

5. The intelligent ventilator operation monitoring system according to claim 4, characterized in that: The iterative convergence determination module updates the stable interval using ; Nonlinear mutation interval update: ; Convergence judgment, expressed as: ; Calculate reliability index , expressed as: ; ;in, is the most dangerous point position at the k+1th iteration; is the momentum coefficient; and is the convergence threshold; a reliability index is obtained for each breathing cycle to quantify the safety margin; when When the breathing cycle is abnormal, it is judged that the operation is abnormal; otherwise, it is judged to be normal; is the alarm probability threshold; Cumulative distribution function of the standard normal distribution.

6. The intelligent ventilator operation monitoring system according to claim 5, characterized in that: The data acquisition module collects historical operating data of the ventilator; marks the operating status of the ventilator operating data within a cycle, and the operating status includes normal operation and abnormal operation; pre-processes the historical operating data of the ventilator to obtain an operation monitoring sample set; and sets a safety boundary for each parameter.

7. The intelligent ventilator operation monitoring system according to claim 6, characterized in that: The system training module divides the operation monitoring sample set into a test set and a training set, trains the system parameters based on the training set, uses the cross entropy loss function, and sets the prediction threshold when the loss of the training set converges. When the prediction accuracy of the test set is higher than the prediction threshold, the system parameter training is completed.

8. The intelligent ventilator operation monitoring system according to claim 7, characterized in that: The ventilator operation monitoring module collects ventilator operation data in real time during the cycle, and inputs it into the safety margin standardization module, the initial danger point calibration module, the risk direction deviation detection module, the adaptive step size update module, and the iterative convergence judgment module in sequence. If it is finally determined that the operation is abnormal, an early warning process is performed.

Images