An iterative optimization-based micro-pressure cabin adaptive pressure control method and system

Abstract

The present application relates to a kind of micro-pressure cabin adaptive pressure control method and system based on iterative optimization, belong to pressure control technical field, to solve the problems such as the existing micro-pressure cabin pressure control relies on artificial repeated debugging, low efficiency and cannot be self-adaptive optimization.This method includes: in the pressure stabilization stage of micro-pressure cabin, real-time monitoring pressure in cabin, when pressure exceeds the upper limit or lower limit of pre-set pressure interval, respectively, execute pressure stabilization crest section or trough section opening degree adjustment algorithm, to adjust the opening degree of electric exhaust valve.After single oxygen therapy process is ended, execute iterative optimization step: system automatically analyzes the pressure data of this pressure stabilization stage, and iteratively updates control parameters for next oxygen therapy process according to it.The present application realizes self-learning and evolution of control parameters by the closed-loop mechanism of real-time adjustment and review optimization, can quickly converge to optimal state within several runs, shorten the debugging cycle and improve the stability of pressure control.

Description

Technical Field

[0001] This invention relates to the field of pressure control technology, specifically to an adaptive pressure control method and system for a micro-pressure oxygen chamber based on iterative optimization. Background Technology

[0002] When administering oxygen therapy in a microbaroagulant chamber, the process typically involves three stages: pressurization, stabilization, and depressurization. The stabilization stage is the core component, requiring the chamber pressure to be precisely maintained within a preset target pressure range.

[0003] Currently, cabin pressure is primarily regulated by controlling the opening of the electric exhaust valve. However, due to differences in the physical characteristics, sealing properties, and environment of each oxygen chamber, finding the optimal opening value that stabilizes the pressure within the target range is challenging. Traditional pressure control methods rely on extensive manual testing and repeated adjustments by technicians, which is not only time-consuming and labor-intensive but also results in a poor oxygen therapy experience for users until the optimal parameters are found.

[0004] Therefore, there is an urgent need for a pressure control method that can automatically adapt, dynamically adjust, and self-optimize. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an adaptive pressure control method and system for micro-pressure oxygen chambers based on iterative optimization, so as to solve the problems of existing pressure control methods relying on a large amount of manual testing, low adjustment efficiency, and inability to adaptively optimize.

[0006] To address the aforementioned technical issues, this iterative optimization-based adaptive pressure control method for micro-pressure oxygen chambers involves real-time monitoring of the chamber pressure during the pressure stabilization phase. When the cabin pressure Exceeding the upper limit of the preset pressure range At that time, the pressure stabilization peak segment opening adjustment algorithm is executed to increase the opening of the electric exhaust valve; when the cabin pressure Below the lower limit of the preset pressure range At that time, the pressure trough segment opening adjustment algorithm is executed to reduce the opening of the electric exhaust valve; in order to maintain the cabin pressure pt at the lower pressure limit. and pressure limit Within a preset pressure range. The method further includes: after a single oxygen therapy session, performing an iterative optimization step, collecting and analyzing pressure data during the pressure stabilization phase of the current oxygen therapy session, and iteratively updating the control parameters for the next oxygen therapy session based on the pressure data analysis results.

[0007] Specifically, the control parameters include the initial opening value of the electric exhaust valve during the pressure stabilization phase. The base amount of peak adjustment used in the voltage stabilization peak segment opening adjustment algorithm and the valley adjustment base amount used for the voltage stabilization valley opening adjustment algorithm. .

[0008] Furthermore, the step of executing the voltage stabilization peak segment opening adjustment algorithm includes:

[0009] - After monitoring the pressure inside the cabin Exceeding the upper limit of the preset pressure range Then, wait for the preset time. and collect the preset duration Internal pressure change sequence;

[0010] - Determine the current pressure change trend based on the pressure change sequence;

[0011] - If the pressure change trend is upward, then increase the opening of the electric exhaust valve. If the trend is stable or fluctuating, increase the opening of the electric exhaust valve. The preset multiple.

[0012] Furthermore, the steps of executing the voltage stabilization trough segment opening adjustment algorithm specifically include:

[0013] - After monitoring the pressure inside the cabin Below the lower limit of the preset pressure range Then, wait for the preset time. and collect the preset duration Internal pressure change sequence;

[0014] - Determine the current pressure change trend based on the pressure change sequence;

[0015] If the pressure change trend is downward, then reduce the opening of the electric exhaust valve. If the trend is stable or fluctuating, reduce the opening of the electric exhaust valve. The preset multiple.

[0016] Furthermore, the iterative optimization step specifically includes:

[0017] -Based on the pressure data from the stabilization phase of this oxygen therapy procedure, calculate the average pressure change slope from the trough to the peak. and the slope of the average pressure change from the crest to the trough. ;

[0018] -Based on the slope of the average pressure change and Iteratively update the peak adjustment baseline quantity and the aforementioned trough adjustment base quantity ;

[0019] -Based on the initial pressure changes during the pressure stabilization phase of this oxygen therapy procedure, the initial opening value is iteratively updated. .

[0020] Furthermore, the step of determining the current pressure change trend based on the pressure change sequence includes:

[0021] - The slope of the pressure change sequence is calculated based on a linear regression algorithm. Calculate the overall percentage change of the pressure change sequence. Calculate the trend state of the pressure change sequence based on the moving average algorithm;

[0022] - Combining the linear regression slope The overall percentage change And the trend state, determine that the pressure change trend is one of four states: rising, falling, stable, or fluctuating.

[0023] This iteratively optimized adaptive pressure control system for the micro-hyperbaric oxygen chamber includes features for real-time monitoring of the chamber pressure. The system includes a pressure sensor, an electric exhaust valve for adjusting the amount of gas discharged from the chamber, and a controller for electrically connecting the pressure sensor and the electric exhaust valve, wherein the controller is configured to execute the above-described iteratively optimized micro-pressure oxygen chamber adaptive pressure control method.

[0024] This invention discloses an adaptive pressure control method and system for micro-barrier oxygen chambers based on iterative optimization. Through a closed-loop mechanism of real-time adjustment and post-event review and optimization, the control parameters achieve self-learning and evolution, and can quickly converge to the optimal state within a few runs. This significantly shortens the debugging cycle and improves the stability of pressure control and the user's oxygen therapy experience. Attached Figure Description

[0025] The adaptive pressure control method for a micro-hyperbaric oxygen chamber based on iterative optimization, as described below with reference to the accompanying drawings, is further explained in this invention:

[0026] Figure 1 This refers to the pressure stabilization stage of the micro-pressure oxygen chamber described in the implementation method. A schematic diagram showing how the cabin pressure changes over time;

[0027] Figure 2 This is a schematic diagram of the overall process of the adaptive pressure control method for micro-pressure oxygen chamber based on iterative optimization in the implementation method;

[0028] Figure 3This is a flowchart illustrating the pressure change trend algorithm of the adaptive pressure control method for micro-pressure oxygen chamber based on iterative optimization in Example 1.

[0029] Figure 4 This is a schematic diagram of the adaptive pressure control system for the micro-pressure oxygen chamber based on iterative optimization in Example 1.

[0030] In the picture:

[0031] 10 - Controller, 20 - Pressure sensor, 30 - Electric exhaust valve. Detailed Implementation

[0032] To make the technical means, features, and effects of this invention clear, the invention will be further described below in conjunction with the accompanying drawings, embodiments, and examples. The scope of protection of this invention is not limited to the following embodiments.

[0033] Implementation method: As shown in Figure 2, the adaptive pressure control method for micro-pressure oxygen chambers based on iterative optimization is as follows: during the pressure stabilization phase of the micro-pressure oxygen chamber, the pressure inside the chamber is monitored in real time. When the cabin pressure Exceeding the upper limit of the preset pressure range At that time, the pressure stabilization peak segment opening adjustment algorithm is executed to increase the opening of the electric exhaust valve; when the cabin pressure Below the lower limit of the preset pressure range At that time, the pressure trough segment opening adjustment algorithm is executed to reduce the opening of the electric exhaust valve; in order to maintain the cabin pressure pt at the lower pressure limit. and pressure limit Within a preset pressure range. The method further includes: after a single oxygen therapy session, performing an iterative optimization step, collecting and analyzing pressure data during the pressure stabilization phase of the current oxygen therapy session, and iteratively updating the control parameters for the next oxygen therapy session based on the pressure data analysis results. Specifically, a complete oxygen therapy session is as follows: Figure 1 As shown, it can be divided into a boost stage. Stabilization phase and blood pressure reduction phase During the pressurization phase, the system activates the air pump and oxygen generator, while simultaneously setting the electric exhaust valve to a small opening, allowing the chamber pressure to rise from atmospheric pressure. Once the pressure sensor detects that the chamber pressure has entered the preset stabilization range... At this point, the system enters its core voltage stabilization phase. This method is applied during the voltage stabilization stage. It is divided into two levels. The first level is real-time adjustment within a single oxygen therapy session, ensuring that the pressure can be effectively controlled near the target range in any oxygen therapy session. The second level is iterative optimization across oxygen therapy sessions, which gives the system the ability to learn and evolve on its own.

[0034] The control parameters include the initial opening value of the electric exhaust valve during the pressure stabilization phase. The base amount of peak adjustment used in the voltage stabilization peak segment opening adjustment algorithm and the valley adjustment base amount used for the voltage stabilization valley opening adjustment algorithm. The three core parameters form the basis for the system's self-optimization: initial opening value. This parameter determines the base displacement when the system switches from the pressure boosting phase to the pressure stabilization phase, serving as the starting point for pressure control. Optimizing this parameter allows the pressure to stabilize more quickly; peak adjustment base displacement. and trough adjustment base quantity These represent the base step size for a single adjustment action when the pressure is too high or too low, respectively. Since the sealing performance, piping characteristics, and environment of each oxygen chamber differ, the optimal solutions for these three parameters also vary. This method, through continuous iterative optimization of these three parameters, enables the system to adapt more and more accurately to the physical characteristics of a specific oxygen chamber.

[0035] The steps of executing the pressure stabilization peak segment opening adjustment algorithm include: monitoring the cabin pressure Exceeding the upper limit of the preset pressure range Then, wait for the preset time. and collect the preset duration The pressure change sequence within the system is analyzed; the current pressure change trend is determined based on the pressure change sequence; if the pressure change trend is upward, the opening of the electric exhaust valve is increased. If the trend is stable or fluctuating, increase the opening of the electric exhaust valve. The preset multiplier. When the pressure is too high (e.g., Figure 1 In (At that moment), the system will not react immediately, but will wait. (e.g., 3-5 seconds) to collect a real pressure data segment, effectively avoiding sudden pressure changes caused by accidental factors such as minute deformation of the hatch or user movement inside the cabin, thus preventing misoperation. Subsequently, the system calls a pressure change trend algorithm to analyze this data. If the analysis result shows an upward trend, it indicates that the current exhaust valve opening is significantly too small, requiring a standard adjustment, i.e., increasing the opening by a base amount. If the analysis results show a stable or fluctuating trend, it indicates that the current opening is only slightly too small. In this case, a small adjustment is sufficient (such as increasing the opening). The preset multiplier here is 0.5.

[0036] The specific steps of executing the pressure stabilization trough section opening adjustment algorithm include: monitoring the cabin pressure... Below the lower limit of the preset pressure range Then, wait for the preset time. and collect the preset duration The pressure change sequence within the system is analyzed; the current pressure change trend is determined based on the pressure change sequence; if the pressure change trend is downward, the opening of the electric exhaust valve is reduced. If the trend is stable or fluctuating, reduce the opening of the electric exhaust valve. The preset multiplier. When the pressure is too low (e.g., Figure 1 In (Time) When pressure is lower At that time, the system also went through The waiting and observation period applies. If the analysis results show a downward trend, it indicates that the current exhaust valve opening is significantly too large and requires adjustment to the standard force, i.e., reducing the opening by a base amount. If the analysis results show a stable or fluctuating trend, it indicates that the current opening is only slightly too large. In this case, a small adjustment (such as reducing the opening) is sufficient. By combining coarse and fine adjustments, the pressure curve can converge faster and become smoother.

[0037] The iterative optimization steps specifically include: calculating the average pressure change slope from the trough to the peak based on the pressure data during the pressure stabilization phase of this oxygen therapy process. and the slope of the average pressure change from the crest to the trough. According to the slope of the average pressure change and Iteratively update the peak adjustment baseline quantity and the aforementioned trough adjustment base quantity Based on the initial pressure changes during the pressure stabilization phase of this oxygen therapy procedure, the initial opening value is iteratively updated. At the end of one oxygen therapy session (e.g., upon arrival) After a certain point in time, the system performs a review. It retrieves and analyzes... The pressure data stored throughout the entire stabilization phase is used to calculate all pressure rise stages (such as...). The average pressure change slope and all pressure drop phases (such as The average pressure change slope The two slope values ​​intuitively reflect the system's response characteristics under the current parameters. In this embodiment, if the system detects... If the value is too large, it means that the pressure is rising too quickly, which can easily lead to overshoot. In this case, the system will appropriately reduce the base amount of the trough adjustment to be used in the next cycle, based on a preset update strategy (such as a proportional decay function). This makes the next descent adjustment smoother. Similarly, for... It will also be updated. In addition, the system will review the initial state when it first entered the voltage stabilization phase (…). The direction of pressure (around a certain time) indicates the initial opening degree. If the pressure rises rapidly and then falls back, it suggests that the initial opening degree was... The current size is small; the system will increase it appropriately upon the next startup. The initial value is determined by a specific mathematical model. Specifically, the iterative optimization step is implemented using a particular mathematical model. After the controller calculates the average pressure change slope during this stabilization phase, the control parameters for the next cycle can be iteratively updated using the following formula:

[0038] (1) Calculate the average slope from the trough to the peak of the pressure curve during the stabilization phase according to Formula 1. :

[0039]

[0040] in: For the first The time difference (in seconds) between the trough and the peak of the wave. For the first The pressure difference between the trough and the crest of the wave (in kPa). .

[0041] (2) Calculate the average slope from peak to trough in the pressure curve during the stabilization phase according to Formula 2. :

[0042]

[0043] in: For the first The time difference between the peak and the trough (in seconds). For the first The pressure difference between the crest and trough of the wave (in kPa). .

[0044] (3) Based on the slope Iterative update of trough adjustment base quantity :

[0045]

[0046] in: for Impact factor.

[0047] (4) Based on the slope Iterative update of peak adjustment baseline quantity :

[0048]

[0049] Note:

[0050] (5) Iteratively update the initial opening value based on the initial pressure change. :

[0051]

[0052] in: , This refers to the pressure value corresponding to the first peak or trough during the pressure stabilization phase. for The corresponding time point, for The corresponding time point.

[0053] That is, in formulas 1 to 5 above, For the first Secondary pressure sampling value, For the first The time point for the second pressure sampling; This represents the total number of sampling points; The influencing factor of the basic quantity of trough regulation. The influence factor of the basic quantity of peak adjustment; The influencing factor of the initial opening value; This is the first pressure peak (or trough) after entering the stabilization phase. This represents the lower limit of pressure during the stabilization phase. for The corresponding time point, This is the point in time when the voltage stabilizes.

[0054] The step of determining the current pressure change trend based on the pressure change sequence includes: calculating the slope of the pressure change sequence based on a linear regression algorithm. Calculate the overall percentage change of the pressure change sequence. Calculate the trend of the pressure change sequence based on the moving average algorithm; and combine the linear regression slope. The overall percentage change And based on the aforementioned trend state, determine whether the pressure change trend is one of four states: rising, falling, stable, or fluctuating. The process is as follows: Figure 3 As shown, in order to accurately determine the pressure trend over a short period of time, this method comprehensively utilizes three algorithms to form a triple confirmation mechanism: linear regression slope Used to determine the overall direction from a macro perspective; overall percentage change. The moving average algorithm is used to judge the severity of changes in magnitude; it is used to smooth data, eliminate noise interference, and observe micro-trend states. By weighting or logically judging the analysis results of the three dimensions, the system can draw more reliable conclusions about rising, falling, stabilizing, or fluctuating pressures than a single algorithm, thus providing a precise decision-making basis for the aforementioned adjustment actions of adjusting the opening degree during the peak and trough periods of the pressure stabilization wave. Specifically, the triple confirmation mechanism is achieved through quantitative calculation of the pressure change sequence, and its core judgment criteria and calculation methods are as follows:

[0055] (1) In the voltage stabilization peak section opening adjustment algorithm, the adjustment amount is calculated as follows:

[0056]

[0057] in: for Regulation factor, judgment Sequence. If the trend is upward, then If the trend is stable, then If the trend is fluctuating, then If the trend is downward, then .

[0058] (2) In the voltage stabilization trough section opening adjustment algorithm, the adjustment amount is calculated as follows:

[0059]

[0060] in: for Adjustment factor. If the trend is downward, then If it is stable, then If it is a fluctuation, then If it is an upward trend, then .

[0061] That is, in formulas 6 to 9 above, The amount by which the opening is increased for a single adjustment. The amount by which the opening is reduced in a single adjustment; and These are the basic quantities for peak and trough adjustments, respectively; These are all preset adjustment coefficients, with values ​​greater than 1, used to achieve more precise fine-tuning.

[0062] Example: This iteratively optimized micro-pressure oxygen chamber adaptive pressure control system includes features for real-time monitoring of chamber pressure. The system comprises a pressure sensor, an electric exhaust valve for adjusting the amount of gas discharged from the chamber, and a controller for electrically connecting the pressure sensor and the electric exhaust valve. The controller is configured to execute the iterative optimization-based adaptive pressure control method for micro-pressure oxygen chambers described in this embodiment. That is, this iterative optimization-based adaptive pressure control system for micro-pressure oxygen chambers is the physical carrier for implementing the iterative optimization-based adaptive pressure control method in this embodiment. The pressure sensor is the signal acquisition end of the system, responsible for continuously sensing changes in chamber pressure; the electric exhaust valve is the action execution end of the system, responsible for accurately executing opening adjustment commands; and the controller (such as an embedded system's MCU, CPU, etc.) is the intermediate control end of the system. The firmware program burned into the controller implements all the logical steps of the iterative optimization-based adaptive pressure control method for micro-pressure oxygen chambers described in this embodiment (including real-time monitoring, trend judgment, opening adjustment, and most importantly, the iterative optimization algorithm), thereby directing the entire system to automatically and intelligently complete pressure control and self-optimization.

[0063] This iterative optimization-based adaptive pressure control method and system for micro-hyperbaric oxygen chambers achieves self-learning and evolution of control parameters through a closed-loop mechanism of real-time adjustment and post-event review and optimization. It can quickly converge to the optimal state within a few runs, significantly shortening the debugging cycle and improving the stability of pressure control and the user's oxygen therapy experience. Specifically,

[0064] (1) Self-learning and evolution are achieved: This invention introduces an iterative optimization mechanism, which can review and summarize experience after each oxygen therapy session, and automatically optimize the initial control parameters for the next oxygen therapy session. This enables the control system to learn and evolve on its own, and the control effect tends to be optimal as the number of uses increases.

[0065] (2) Improved adjustment efficiency: Through adaptive algorithms and iterative optimization, the present invention can converge quickly and find near-optimal control parameters in a very small number of runs, which greatly shortens the long manual debugging cycle required by traditional methods.

[0066] (3) Improved user experience: With the continuous optimization of control parameters, the pressure fluctuation during the stabilization phase gradually decreases and the pressure curve becomes smoother, providing users with a more stable, comfortable and effective oxygen therapy environment.

[0067] The foregoing description illustrates the main features, basic principles, and advantages of the present invention. It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments or examples described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the above embodiments or examples should be considered exemplary and not restrictive. The scope of the present invention is defined by the appended claims rather than the foregoing description, and therefore all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0068] Furthermore, it should be understood that although this specification describes embodiments, not every embodiment contains only one independent technical solution. This narrative style is merely for clarity. Those skilled in the art should consider the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

Claims

1. An adaptive pressure control method for micro-pressure oxygen chambers based on iterative optimization, characterized in that: Real-time monitoring of internal pressure during the pressure stabilization phase of the micro-pressure oxygen chamber , When the pressure inside the chamber Exceeding the upper limit of the preset pressure range At that time, the pressure stabilization peak segment opening adjustment algorithm is executed to increase the opening of the electric exhaust valve; when the cabin pressure Below the lower limit of the preset pressure range At that time, the pressure trough segment opening adjustment algorithm is executed to reduce the opening of the electric exhaust valve; in order to maintain the cabin pressure pt at the lower pressure limit. and pressure limit Within the preset pressure range; Control parameters include the initial opening value of the electric exhaust valve during the pressure stabilization phase. The base amount of peak adjustment used in the voltage stabilization peak segment opening adjustment algorithm and the valley adjustment base amount used for the voltage stabilization valley opening adjustment algorithm. Both the pressure stabilization peak segment opening adjustment algorithm and the pressure stabilization trough segment opening adjustment algorithm include a step of determining the current pressure change rise and fall trend based on the collected pressure change sequence. This step of determining the current pressure change rise and fall trend based on the pressure change sequence includes... - The slope of the pressure change sequence is calculated based on a linear regression algorithm. Calculate the overall percentage change of the pressure change sequence. Calculate the trend state of the pressure change sequence based on the moving average algorithm; -Comprehensive linear regression slope The overall percentage change And the trend state, determine that the pressure change trend is one of four states: rising, falling, stable, or fluctuating; The method further includes: after a single oxygen therapy session, performing an iterative optimization step, collecting and analyzing pressure data during the pressure stabilization phase of the current oxygen therapy session, and iteratively updating the control parameters for the next oxygen therapy session based on the pressure data analysis results; The iterative optimization steps specifically include: -Based on the pressure data from the stabilization phase of this oxygen therapy procedure, calculate the average pressure change slope from the trough to the peak. and the slope of the average pressure change from the crest to the trough. ; -Based on the slope of the average pressure change and Iteratively update the peak adjustment baseline quantity and the aforementioned trough adjustment base quantity ; -Based on the initial pressure changes during the pressure stabilization phase of this oxygen therapy procedure, the initial opening value is iteratively updated. .

2. The adaptive pressure control method for micro-pressure oxygen chambers based on iterative optimization according to claim 1, characterized in that: The steps of executing the voltage stabilization peak segment opening adjustment algorithm include: - After monitoring the pressure inside the cabin Exceeding the upper limit of the preset pressure range Then, wait for the preset time. and collect the preset duration Internal pressure change sequence; - Determine the current pressure change trend based on the pressure change sequence; - If the pressure change trend is upward, then increase the opening of the electric exhaust valve. ; If the trend is stable or fluctuating, increase the opening of the electric exhaust valve. The preset multiple.

3. The adaptive pressure control method for micro-pressure oxygen chambers based on iterative optimization according to claim 1, characterized in that: The specific steps of executing the voltage stabilization trough segment opening adjustment algorithm include: - After monitoring the pressure inside the cabin Below the lower limit of the preset pressure range Then, wait for the preset time. and collect the preset duration Internal pressure change sequence; - Determine the current pressure change trend based on the pressure change sequence; If the pressure change trend is downward, then reduce the opening of the electric exhaust valve. ; If the trend is stable or fluctuating, reduce the opening of the electric exhaust valve. The preset multiple.

4. An adaptive pressure control system for a micro-pressure oxygen chamber based on iterative optimization, characterized by: Including for real-time monitoring of cabin pressure The system includes a pressure sensor 20, an electric exhaust valve 30 for regulating the amount of gas discharged from the cabin, and a controller 10 for electrically connecting the pressure sensor 20 and the electric exhaust valve 30. The controller 10 is configured to perform the iterative optimization-based adaptive pressure control method for micro-barrier oxygen chambers as described in any one of claims 1 to 3.

Images