A pressure control parameter correction method, device, equipment and medium

Abstract

The application relates to the technical field of medical equipment control, and discloses a pressure control parameter correction method, device, equipment and medium, a first target pressure difference is calculated according to a first target pressure in an inhalation stage and a second target pressure in an exhalation stage, and a first actual pressure difference is calculated according to a first actual pressure in the inhalation stage and a second actual pressure in the exhalation stage; a first gain compensation value is determined according to the difference between the first target pressure difference and the first actual pressure difference; a first bias compensation value is determined by correcting a historical bias compensation value according to the first gain compensation value, the first target pressure and the first actual pressure or the second target pressure and the second actual pressure; and a current pressure control parameter is corrected according to the first gain compensation value and the first bias compensation value. In this way, adaptive online correction of the pressure control parameter is realized, and the pressure control precision and stability of a breathing machine are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of medical device control technology, and in particular to a method, apparatus, device and medium for pressure control parameter correction. Background Technology

[0002] In modern intensive care and respiratory therapy, ventilators achieve precise closed-loop control of airway pressure by dynamically adjusting the opening of the expiratory valve or the pump displacement. However, regardless of the electromechanical implementation method used (such as voice coil motors, stepper motors, piezoelectric valves, or solenoid valves), the pressure control system is inevitably affected by factors such as differences in hardware characteristics, component aging, and sensor drift.

[0003] Current technologies primarily rely on manual calibration at the factory or fixed compensation curves to calibrate the pressure control parameters of ventilators. This method not only increases manufacturing costs and testing cycles but also makes it difficult to track dynamic changes in hardware characteristics during equipment use, failing to achieve adaptive adjustments in pressure control and resulting in decreased pressure control accuracy. Summary of the Invention

[0004] To address the aforementioned technical problems, this application provides a pressure control parameter correction method, apparatus, device, and medium, which enables adaptive adjustment and online correction of pressure control, significantly improving the pressure control accuracy and stability of the ventilator.

[0005] In a first aspect, this application provides a method for correcting pressure control parameters, the method comprising: The first target pressure difference is calculated based on the first target pressure during the inhalation phase and the second target pressure during the exhalation phase, and the first actual pressure difference is calculated based on the first actual pressure during the inhalation phase and the second actual pressure during the exhalation phase. The first gain compensation value is determined based on the difference between the first target pressure difference and the first actual pressure difference; Based on the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, the historical bias compensation value is corrected to determine the first bias compensation value. The current pressure control parameters are corrected based on the first gain compensation value and the first bias compensation value.

[0006] In one possible implementation, the step of correcting the historical bias compensation value based on the first gain compensation value, the first target pressure, and the first actual pressure, or the second target pressure and the second actual pressure, to determine the first bias compensation value includes: If the first gain compensation value is greater than the lower limit of the preset gain limit range and less than the upper limit of the preset gain limit range, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value, and the updated bias compensation value is determined. If the first gain compensation value is greater than or equal to the upper limit of the preset gain limit range, or less than or equal to the lower limit of the preset gain limit range, the historical bias compensation value is corrected according to the second target pressure, the second actual pressure, and the historical gain compensation value to determine the updated bias compensation value. Based on the updated bias compensation value, a first bias compensation value is determined.

[0007] In one possible implementation, if the first gain compensation value is greater than the lower limit of the preset gain limiting range and less than the upper limit of the preset gain limiting range, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value to determine the updated bias compensation value, including: If the first gain compensation value is greater than the lower limit of the preset gain limiting range and less than the upper limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula:

[0008] in, The updated bias compensation value. This represents the historical bias compensation value. This represents the first gain compensation value. This indicates the first target pressure. This indicates the first actual pressure; If the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the historical bias compensation value is corrected based on the second target pressure, the second actual pressure, and the historical gain compensation value to determine the updated bias compensation value, including: If the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula:

[0009] in, The updated bias compensation value. This represents the historical bias compensation value. This indicates the second actual pressure.

[0010] In one possible implementation, the method further includes: The updated bias compensation value and the historical bias compensation value are weighted and fused to obtain a fused bias compensation value; the fused bias compensation value is then limited according to a preset bias limiting range to determine the first bias compensation value.

[0011] In one possible implementation, the method further includes: If the first bias compensation value reaches the upper limit of the preset bias limit range, and the current actual pressure is higher than the current target pressure, then the first gain compensation value is reduced. If the first bias compensation value reaches the lower limit of the preset bias limit range, and the current actual pressure is lower than the current target pressure, then the first gain compensation value is increased.

[0012] In one possible implementation, determining the first gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference includes: The updated gain compensation value is determined based on the difference between the first target pressure difference and the first actual pressure difference, as well as the historical gain compensation value. The updated gain compensation value and the historical gain compensation value are weighted and fused to obtain the fused gain compensation value; The first gain compensation value is determined based on the fusion gain compensation value.

[0013] In one possible implementation, the first target pressure is determined by averaging multiple target pressures acquired during the inhalation phase; the first actual pressure is determined by averaging multiple actual pressures acquired during the inhalation phase; the second target pressure is determined by averaging multiple target pressures acquired during the exhalation phase; and the second actual pressure is determined by averaging multiple actual pressures acquired during the exhalation phase.

[0014] Secondly, this application provides a pressure control parameter correction device, which is used to implement the method and function as described in the first aspect or any possible implementation of the first aspect. The device body includes: The pressure difference calculation unit is used to calculate the first target pressure difference based on the first target pressure during the inhalation phase and the second target pressure during the exhalation phase, and to calculate the first actual pressure difference based on the first actual pressure during the inhalation phase and the second actual pressure during the exhalation phase. The first gain compensation value determination unit is used to determine the first gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference. The first bias compensation value determination unit is used to correct the historical bias compensation value based on the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, and determine the first bias compensation value. The correction unit is used to correct the current pressure control parameters based on the first gain compensation value and the first bias compensation value.

[0015] In one possible implementation, the first bias compensation value determining unit is configured to: If the first gain compensation value is greater than the lower limit of the preset gain limit range and less than the upper limit of the preset gain limit range, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value to determine the updated bias compensation value. If the first gain compensation value is greater than or equal to the upper limit of the preset gain limit range, or less than or equal to the lower limit of the preset gain limit range, the historical bias compensation value is corrected according to the second target pressure, the second actual pressure, and the historical gain compensation value to determine the updated bias compensation value. Based on the updated bias compensation value, a first bias compensation value is determined.

[0016] In one possible implementation, the first bias compensation value determining unit is specifically used for: If the first gain compensation value is greater than the lower limit of the preset gain limiting range and less than the upper limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula:

[0017] in, The updated bias compensation value. This represents the historical bias compensation value. This represents the first gain compensation value. This indicates the first target pressure. This indicates the first actual pressure; The first bias compensation value determination unit is specifically used for: If the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula:

[0018] in, Update the bias compensation value. This represents the historical bias compensation value. This indicates the second actual pressure.

[0019] In one possible implementation, the device further includes: The weighted fusion unit is used to perform weighted fusion of the updated bias compensation value and the historical bias compensation value to obtain a fused bias compensation value; and to perform amplitude limiting processing on the fused bias compensation value according to a preset bias limiting range to determine the first bias compensation value.

[0020] In one possible implementation, the device further includes: The limit verification unit is used to reduce the first gain compensation value if the first bias compensation value reaches the upper limit of the preset bias limit range and the current actual pressure is higher than the current target pressure. If the first bias compensation value reaches the lower limit of the preset bias limit range, and the current actual pressure is lower than the current target pressure, then the first gain compensation value is increased.

[0021] In one possible implementation, the first gain compensation value determining unit includes: The updated gain compensation value determination unit is used to determine the updated gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference and the historical gain compensation value. A fusion gain compensation value determination unit is used to perform weighted fusion of the updated gain compensation value and the historical gain compensation value to obtain a fusion gain compensation value. The final determination unit is used to determine the first gain compensation value based on the fusion gain compensation value.

[0022] In one possible implementation, the first target pressure is determined by averaging multiple target pressures acquired during the inhalation phase; the first actual pressure is determined by averaging multiple actual pressures acquired during the inhalation phase; the second target pressure is determined by averaging multiple target pressures acquired during the exhalation phase; and the second actual pressure is determined by averaging multiple actual pressures acquired during the exhalation phase.

[0023] Thirdly, this application discloses a computer device, which includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the pressure control parameter correction method as described in the first aspect, according to the instructions in the program code.

[0024] Fourthly, this application discloses a computer-readable storage medium for storing a computer program, which, when executed by a processor, performs the pressure control parameter correction method as described in the first aspect.

[0025] This application provides a pressure control parameter correction method, apparatus, device, and medium. A first target pressure difference is calculated based on a first target pressure during the inhalation phase and a second target pressure during the exhalation phase. A first actual pressure difference is calculated based on a first actual pressure during the inhalation phase and a second actual pressure during the exhalation phase. Since the first target pressure difference reflects the expected pressure difference between the inhalation and exhalation phases, and the first actual pressure difference reflects the actual pressure difference between the inhalation and exhalation phases, comparing the first target pressure difference and the first actual pressure difference allows determination of the difference between the actual pressure difference and the target pressure difference. This allows for the determination of a first gain compensation value for this difference. Correction using the first gain compensation value makes the first actual pressure difference approach the first target pressure difference, thereby correcting system sensitivity variations caused by the dispersion or aging of air resistance elements. To further reduce the deviation between the actual pressure and the target pressure, based on a first gain compensation value determined according to the difference between the first target pressure difference and the first actual pressure difference, a historical bias compensation value is corrected according to the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, to determine a first bias compensation value. This bias compensation value is then used to correct the current pressure control parameters, making the actual pressure approach the target pressure, thereby compensating for the static zero-point deviation of the actuator. Finally, the current pressure control parameters are corrected based on the first gain compensation value and the first bias compensation value. In this way, the first gain compensation value reduces the difference between the first actual pressure difference and the first target pressure difference, and the first bias compensation value further reduces the deviation between the actual pressure and the target pressure, achieving adaptive adjustment and online correction of pressure control, significantly improving the pressure control accuracy and stability of the ventilator. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0027] Figure 1 A flowchart illustrating a pressure control parameter calibration method provided in this application embodiment; Figure 2 This is a schematic diagram of a ventilator pressure control structure provided in an embodiment of this application; Figure 3 A flowchart for calibrating ventilator pressure control parameters is provided in this application embodiment; Figure 4 A schematic diagram of a pressure control parameter correction algorithm provided in an embodiment of this application; Figure 5 A structural block diagram of a pressure control parameter correction device provided in an embodiment of this application; Figure 6 This is a structural block diagram of a computer device for pressure control parameter correction provided in an embodiment of this application. Detailed Implementation

[0028] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the specific embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0029] Many specific details are set forth in the following description in order to provide a full understanding of this application. However, this application may also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the spirit of this application. Therefore, this application is not limited to the specific embodiments disclosed below.

[0030] The inventors discovered through research that in modern intensive care and respiratory therapy, ventilators achieve precise closed-loop control of airway pressure by dynamically adjusting the opening of the expiratory valve or the pump displacement. However, regardless of the electromechanical implementation method used (such as voice coil motors, stepper motors, piezoelectric valves, or solenoid valves), the pressure control system is inevitably affected by factors such as differences in hardware characteristics, component aging, and sensor drift.

[0031] Specifically, various drive actuators are affected by coil tolerances, magnetic circuit assembly errors, and friction fluctuations, resulting in significant individual differences in their "input signal-output displacement / torque" conversion characteristics. Simultaneously, passive flow resistance elements in pipelines are subject to limitations in manufacturing consistency and the effects of dust accumulation and moisture buildup, causing irreversible drift in their damping characteristics. Both of these factors combined lead to a severe deviation of the system's flow-pressure transfer function from the preset model, resulting in poor pressure output consistency across batches of equipment.

[0032] Furthermore, during long-term, high-frequency operation, the diaphragm, sealing rings, and drive components of the ventilator undergo physical wear and fatigue aging, leading to mechanical zero-point drift and introducing hysteresis and nonlinear dead zones. Simultaneously, various sensors experience zero-point drift and temperature drift due to changes in temperature and humidity, as well as long-term use, causing measurement deviations in the system. This dual time-varying characteristic means that the factory calibration parameters gradually become ineffective as the equipment's lifespan progresses.

[0033] To address the aforementioned issues, existing technologies primarily rely on manual calibration at the factory or fixed compensation curves to calibrate the pressure control parameters of ventilators. This method not only increases manufacturing costs and testing cycles but also makes it difficult to track dynamic changes in hardware characteristics during equipment use. Once hardware drifts or ages, fixed control parameters cannot be adaptively adjusted, leading to decreased pressure control accuracy and even jeopardizing ventilation safety.

[0034] Based on the above technical problems, embodiments of this application provide a pressure control parameter correction method, apparatus, device, and medium. A first target pressure difference is calculated based on a first target pressure during the inhalation phase and a second target pressure during the exhalation phase, and a first actual pressure difference is calculated based on a first actual pressure during the inhalation phase and a second actual pressure during the exhalation phase. Since the first target pressure difference reflects the expected pressure difference between the inhalation and exhalation phases, and the first actual pressure difference reflects the actual pressure difference between the inhalation and exhalation phases, by comparing the first target pressure difference and the first actual pressure difference, the difference between the actual pressure difference and the target pressure difference can be determined, and thus a first gain compensation value can be determined for this difference. Correction using the first gain compensation value can make the first actual pressure difference approach the first target pressure difference, thereby correcting changes in system sensitivity caused by the dispersion or aging of the air resistance element. To further reduce the deviation between the actual pressure and the target pressure, based on a first gain compensation value determined according to the difference between the first target pressure difference and the first actual pressure difference, a historical bias compensation value is corrected according to the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, to determine a first bias compensation value. The current pressure control parameters are then corrected using this bias compensation value, making the actual pressure approach the target pressure, thereby compensating for the static zero-point deviation of the actuator. The current pressure control parameters are corrected based on the first gain compensation value and the first bias compensation value.

[0035] In this way, the difference between the first actual pressure difference and the first target pressure difference can be reduced by the first gain compensation value, and the deviation between the actual pressure and the target pressure can be further reduced by the first bias compensation value, realizing adaptive adjustment and online correction of pressure control, and significantly improving the pressure control accuracy and stability of the ventilator.

[0036] The following detailed description, in conjunction with the accompanying drawings, illustrates the specific implementation of a pressure control parameter correction method and related device provided in this application through embodiments.

[0037] refer to Figure 1 The diagram shown is a flowchart of a pressure control parameter correction method provided in an embodiment of this application, which may include the following steps.

[0038] S101, calculate the first target pressure difference based on the first target pressure during the inhalation phase and the second target pressure during the exhalation phase, and calculate the first actual pressure difference based on the first actual pressure during the inhalation phase and the second actual pressure during the exhalation phase.

[0039] In this embodiment, the ventilation cycle is divided into an inspiratory phase and an expiratory phase. The ventilation cycle refers to the time interval taken to complete one full breath; the inspiratory phase refers to the phase in which the ventilator delivers gas to the patient's airway; and the expiratory phase refers to the phase in which gas is expelled from the patient's lungs through the expiratory circuit.

[0040] The first target pressure during the inspiratory phase indicates the airway pressure that the ventilator aims to achieve during the inspiratory phase; the first actual pressure during the inspiratory phase indicates the actual airway pressure achieved by the ventilator during the inspiratory phase. The second target pressure during the expiratory phase indicates the airway pressure that the ventilator aims to achieve during the expiratory phase; the second actual pressure during the expiratory phase indicates the actual airway pressure achieved by the ventilator during the expiratory phase.

[0041] While acquiring the aforementioned pressure data, the ventilator can also acquire ventilation parameters such as ventilation flow rate, current ventilation mode, stage identifier of the inspiratory or expiratory phase, and respiratory cycle. Based on the stage identifier, the collected target pressure and actual pressure are divided into pressure data corresponding to the inspiratory phase and pressure data corresponding to the expiratory phase for separate storage and processing.

[0042] It should be noted that the first target pressure, the first actual pressure, the second target pressure, and the second actual pressure can be determined based on multiple pressure data collected during the corresponding ventilation phase, in order to reduce the impact of fluctuations in a single pressure data point on the differential pressure calculation results.

[0043] In one possible implementation, a ventilation cycle can be divided into an inspiratory phase and an expiratory phase, and the collected target pressure and actual pressure can be preprocessed for the inspiratory and expiratory phases respectively. The data preprocessing may include data cleaning, sliding accumulation, and effective sample statistics to obtain pressure data for subsequent pressure deviation calculation.

[0044] Specifically, during the inhalation phase, multiple target pressures and multiple actual pressures can be acquired according to a preset sampling period. The average of the acquired target pressures is calculated to obtain the first target pressure of the inhalation phase; the average of the acquired actual pressures is calculated to obtain the first actual pressure of the inhalation phase. In one possible implementation, data is collected during the inhalation phase under the conditions of meeting the inhalation duration target and the inhalation flow rate being within the effective ventilation range. After removing negative interference, the acquired target pressures and actual pressures are stored in a corresponding annular buffer of length L, and the target pressures within the buffer are accumulated by sliding to obtain the total inhalation target pressure. And by sliding and accumulating the actual pressure within the buffer zone, the total actual intake pressure is obtained. Simultaneously record the number of valid samples during the inhalation phase. The first target pressure is determined based on the sum of the inhalation target pressures and the number of effective samples during the inhalation phase. The first actual pressure is determined based on the sum of the actual inhalation pressures and the number of valid samples during the inhalation phase. .

[0045] During the exhalation phase, multiple target pressures and multiple actual pressures can be acquired according to a preset sampling period. The average of the acquired target pressures is calculated to obtain the second target pressure for the exhalation phase; the average of the acquired actual pressures is calculated to obtain the second actual pressure for the exhalation phase. In one possible implementation, a trigger delay mechanism is introduced after entering the exhalation phase. Specifically, when the ventilation process is detected to switch from the inhalation phase to the exhalation phase, the target pressure and actual pressure for the exhalation phase are collected after a preset delay. By setting a trigger delay, the impact of pressure oscillations or trigger interference generated during the switch between the inhalation and exhalation phases on the pressure data for the exhalation phase can be reduced. After the preset delay and the expiratory flow rate reaches a stable state, the acquired target pressure and actual pressure are stored in the corresponding buffer, and the target pressure and actual pressure are accumulated by sliding, while the number of valid samples in the exhalation phase is recorded. Based on the total target expiratory pressure The second target pressure was determined by the effective sample size during the exhalation phase. And based on the total actual expiratory pressure The second actual pressure is determined by the effective sample size during the exhalation phase. .

[0046] Further, calculate the first target pressure difference. and the first actual pressure difference .

[0047] In one possible implementation, to ensure the validity of the actual sampled data, validity verification can be performed. For example, it can be verified whether the first actual pressure difference is significant. Furthermore, it is important to ensure that the number of valid samples meets the minimum statistical requirements, so as to ensure that the subsequent parameter correction steps are activated only when an effective ventilation pressure difference is generated and the data confidence level is high, thus preventing miscorrection in the case of ineffective ventilation or micro-pressure difference.

[0048] S102, determine the first gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference.

[0049] Specifically, the first gain compensation value is used to correct for changes in the system flow-pressure transfer function sensitivity caused by batch dispersion of air resistance components, assembly errors, or long-term aging. This compensation value is dynamically calculated based on the pressure difference feedback during the inhalation and exhalation phases. For example, when the first actual pressure difference is less than the first target pressure difference, it indicates that the current system gain is too low, so the first gain compensation value is increased to improve the pressure response sensitivity; conversely, when the first actual pressure difference is greater than the first target pressure difference, the first gain compensation value is decreased to reduce sensitivity.

[0050] In one possible implementation, the first gain compensation value can be determined by the following method.

[0051] Specifically, it can be based on the first target pressure difference. and the first actual pressure difference The relative deviation is used to calculate the theoretical update gain compensation value required to eliminate the current system sensitivity drift.

[0052] in, This is the historical gain compensation value. It should be noted that when the first actual pressure difference... Greater than the first target pressure difference When the gain is too high, it indicates that the actual voltage difference is being excessively amplified, and the gain needs to be reduced to suppress overshoot; conversely, when the gain is too low, it indicates that the current system gain is too high, and the actual voltage difference is being excessively amplified, and the gain needs to be reduced to suppress overshoot; Less than If the signal is too strong, it indicates that the system gain is insufficient and the actual differential pressure response is weak. The gain needs to be increased to improve the sensitivity.

[0053] Furthermore, to avoid pressure control oscillations caused by sudden parameter changes, a weighted fusion strategy can be used to smoothly fuse the updated gain compensation value with the historical gain compensation value, resulting in a fused gain compensation value, as shown in the following formula:

[0054] in, α is the gain learning rate (0 < α < 1). Based on the number of valid samples ( + And dynamic adjustment of differential pressure stability (the larger the sample size or the more stable the differential pressure, the larger the value). For example, when the total number of valid samples is large, it indicates that the confidence level of the current statistical results is high, and the value will be adjusted accordingly. Setting α to a larger value allows the system to respond to deviations more quickly; when the number of samples is small, setting α to a smaller value ensures conservative updates and avoids incorrect adjustments due to accidental fluctuations.

[0055] In one possible implementation, the first gain compensation value can be directly taken as... The value of .

[0056] In another possible implementation, to ensure the feasibility of the first gain compensation value during execution, it can be based on a preset gain limiting range [ (The preset gain limiting range refers to a pre-set numerical range for limiting the fluctuation range of the system gain. This range has a lower threshold.) and upper limit threshold This is used to determine whether the current gain value is within the allowable fluctuation range, in order to decide whether to perform gain limiting. Limiting is performed on the fused gain compensation value to obtain... And the first gain compensation value can be directly taken as Specifically, when the fusion gain compensation value When the value is within the specified range, it indicates that the system gain adjustment capability is sufficient; when the fused gain compensation value... When the range is exceeded, it indicates that the pipeline operating conditions have reached their physical limits, and the current gain adjustment capability has reached the boundary of the preset adjustable range. The first gain compensation value is set to The value, The first gain compensation value can be set to The value of .

[0057] In this way, the gain compensation value is dynamically calculated by feedback of the pressure difference during the inhalation and exhalation phases. The target pressure difference to actual pressure difference ratio correction strategy is used to compensate for the impact of changes in system sensitivity. Compared with traditional fixed compensation control, the pressure tracking accuracy is significantly improved. At the same time, through weighted fusion smooth update and amplitude limiting safety verification, pressure oscillations caused by parameter mutations are prevented, and the gain is strictly constrained within the safe range of the actuator, ensuring that the correction process is stable and reliable.

[0058] S103, based on the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, the historical bias compensation value is corrected to determine the first bias compensation value.

[0059] In the embodiments of this application, the historical bias compensation value is used to characterize the historical compensation level corresponding to the static zero-point deviation of the execution component and the sensor drift.

[0060] The first bias compensation value is used to characterize the static zero-point deviation of the actuator and the real-time drift deviation caused by sensor drift.

[0061] It should be noted that the first gain compensation value is mainly used to reduce the difference between the first target pressure difference and the first actual pressure difference. However, when the actual pressure deviates from the target pressure, gain compensation alone is insufficient to eliminate this deviation. Therefore, the pressure also needs to be corrected using the first offset compensation value so that the actual pressure approaches the target pressure as the pressure difference approaches the target pressure.

[0062] In this embodiment, if the first gain compensation value is greater than the lower limit of the preset gain limiting range and less than the upper limit of the preset gain limiting range, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value to determine an updated bias compensation value; if the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the historical bias compensation value is corrected based on the second target pressure, the second actual pressure, and the historical gain compensation value to determine an updated bias compensation value; and a first bias compensation value is determined based on the updated bias compensation value.

[0063] Specifically, if the first gain compensation value is within the preset gain limit range, indicating sufficient gain adjustment capability, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value corresponding to the current inhalation phase, to determine the updated bias compensation value. For example, the updated bias compensation value can be determined using the following formula (corresponding to the combined inhalation and exhalation correction strategy):

[0064] in, Update the bias compensation value. This represents the historical bias compensation value. This represents the first gain compensation value. This indicates the pressure of the first target. This indicates the primary actual pressure.

[0065] It should be noted that although the above bias update formula directly uses the first target pressure and the first actual pressure during the inhalation phase, the first gain compensation value is determined based on the target pressure difference and the actual pressure difference between the inhalation and exhalation phases. Therefore, the bias determination process comprehensively utilizes the pressure data of the current inhalation and exhalation phases, which corresponds to the combined inhalation and exhalation correction strategy.

[0066] If the first gain compensation value is not within the preset gain limit range, it indicates that the pipeline operating condition has reached the physical limit and the current gain adjustment capability has reached the boundary of the preset adjustable range. Then, the historical bias compensation value is corrected according to the second target pressure, the second actual pressure, and the historical gain compensation value corresponding to the current exhalation stage, and the updated bias compensation value is determined.

[0067] Specifically, if the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the following formula (corresponding to the exhalation correction strategy) is used to determine the updated bias compensation value:

[0068] in, Update the bias compensation value. This represents the historical bias compensation value. This indicates the second actual pressure.

[0069] Understandably, when the gain adjustment capability reaches the above-mentioned boundary, in order to prevent alveolar collapse or shortness of breath, it is necessary to prioritize the accuracy of pressure control during the expiratory phase. Therefore, the bias determination process in this case uses data from the expiratory phase, i.e., the corresponding expiratory correction strategy.

[0070] It should be noted that, without performing any other processing on the updated bias compensation value, the first bias compensation value can be directly taken as [value missing]. The value of .

[0071] In one possible implementation, a weighted fusion strategy can be used to smoothly update the updated bias compensation value to obtain the fused bias compensation value. Then, the first bias compensation value can be determined based on the fused bias compensation value. The calculation formula is as follows:

[0072] in, For the bias update weights (0 < β < 1), the bias update weights This is used to control the update speed of the bias compensation value. When the value of β is large, the system responds faster to the currently calculated updated bias compensation value, which is suitable for scenarios with drastic changes in bias. When the value of β is small, the system relies more on historical bias values ​​and updates more conservatively, which is suitable for scenarios with large noise or slow changes in bias, and can effectively suppress the interference of random fluctuations on bias estimation.

[0073] It should be noted that the bias learning rate β can be the same as the aforementioned gain learning rate α, or it can be set independently. For example, it can be dynamically adjusted according to the sample quality during the exhalation phase, where sample quality includes the number of effective samples and data stability during the exhalation phase.

[0074] It should be noted that, without further processing of the fusion bias compensation value, the first bias compensation value can be directly taken as [value missing]. The value of .

[0075] This avoids stress oscillations caused by sudden changes in bias parameters and ensures the smoothness of bias updates.

[0076] In one possible implementation, it can also be based on a preset bias threshold range [ The fusion bias compensation value is obtained by limiting the amplitude. And the first bias compensation value is taken as The value is adjusted to avoid the bias compensation value from going out of bounds, thereby improving the stability and safety of the ventilation process.

[0077] S104, perform online correction of the current pressure control parameters based on the first gain compensation value and the first bias compensation value.

[0078] In the embodiments of this application, after determining the first gain compensation value and the first bias compensation value, the two can be applied together to the pressure control loop of the ventilator to achieve online correction of the current pressure control parameters.

[0079] In one possible implementation, the pressure can be corrected based on the first gain compensation value and the first bias compensation value. Specifically, the first gain compensation value can be used as a correction coefficient, and the first bias compensation value can be used as a bias value to correct the current pressure control parameters, resulting in the corrected pressure. For example, the corrected pressure can be determined according to the following relationship: P' = K × P + b. Where P' represents the corrected pressure, P represents the pressure before correction, K represents the correction coefficient corresponding to the first gain compensation value, and b represents the bias value corresponding to the first bias compensation value. Initially, the correction coefficient K can be 1, and the bias value b can be 0.

[0080] For ease of understanding, Figure 2The diagram shows a ventilator pressure control structure according to an embodiment of this application. It mainly includes an expiratory circuit and an exhaust port, air resistance, pressure sensor, flow sensor, diaphragm, and actuator disposed on the expiratory circuit. The pressure sensor and flow sensor are used to collect airway pressure and expiratory flow signals in the expiratory circuit in real time, respectively. The actuator is connected to the diaphragm and can respond to control commands and drive the diaphragm to change the effective flow area of ​​the expiratory circuit, thereby adjusting the exhaust flow and achieving precise control of airway pressure. The air resistance is disposed in the expiratory circuit to transform the patient's exhaled airflow from chaotic turbulence into a stable laminar flow. The stable pressure difference formed before and after the air resistance is used in conjunction with the flow sensor to calculate the expiratory flow rate. Simultaneously, the air resistance also plays a certain role in filtering and blocking, thereby achieving flow stabilization, measurement assistance, and protection. The exhaust port serves as the final outlet for gas discharge.

[0081] After obtaining the first gain compensation value and the first bias compensation value, the main control unit will correct the current pressure control parameters based on the first gain compensation value and the first bias compensation value, participate in pressure control based on the corrected control parameters, and generate control commands to send to the execution unit.

[0082] In one possible implementation, after completing one pressure control parameter calibration, the buffer data corresponding to the inspiratory and expiratory phases can be cleared, and the effective sample counts for the inspiratory and expiratory phases can be reset. Subsequently, the target pressure and actual pressure during the next ventilation process are re-acquired according to a preset cycle, and the above pressure control parameter calibration process is repeated. By continuously iteratively updating the first gain compensation value and the first bias compensation value, changes in pressure control characteristics caused by component aging, flow resistance changes, and sensor drift can be tracked online.

[0083] This enables adaptive adjustment and online correction of pressure control, significantly improving the accuracy and stability of ventilator pressure control.

[0084] In one possible implementation, to prevent pressure runaway due to parameter out-of-bounds errors, a closed-loop check can be performed after determining the first gain compensation value and the first bias compensation value. Specifically, it is determined whether the first bias compensation value reaches the upper or lower limit of a preset bias limiting range. If the first bias compensation value reaches the upper limit and the current actual pressure is higher than the target pressure, the first gain compensation value is reduced by a preset gain adjustment amount m to reduce the pressure output. If the first bias compensation value reaches the lower limit and the current actual pressure is lower than the corresponding target pressure, the first gain compensation value is increased by the preset gain adjustment amount m to increase the pressure output. If the first bias compensation value does not reach the upper or lower limit, the first gain compensation value remains unchanged. Thus, the first gain compensation value and the first bias compensation value can be coordinated for adjustment, preventing pressure control instability caused by the compensation parameters remaining at the limiting boundary for a long time.

[0085] To facilitate understanding, the pressure control parameter correction process described above is explained below with reference to the diagram. (Reference) Figure 3 The diagram shown is a flowchart of a ventilator pressure control parameter calibration method provided in an embodiment of this application. Specifically, relevant data during ventilation are first collected, and corresponding parameters for each ventilation stage (inspiratory and expiratory phase data) are constructed. The data for the inspiratory and expiratory phases are preprocessed separately, and then the pressure difference between the target pressure and the actual pressure is calculated.

[0086] Subsequently, the pressure deviation and collected data are validated for validity. If the validity validation fails, the parameter correction for this round will not be performed; if the validity validation passes, meaning there is an effective ventilation pressure difference and the data confidence level meets the requirements, the first gain compensation value is determined, and it is determined whether the first gain compensation value exceeds the preset gain limit range.

[0087] If the first gain compensation value exceeds the preset gain limit range, an exhalation correction strategy is used to determine the first bias compensation value; if the first gain compensation value does not exceed the preset gain limit range, a combined inhalation and exhalation correction strategy is used to determine the first bias compensation value. Then, a limit closed-loop verification is performed on the first gain compensation value and the first bias compensation value. The verified first gain compensation value and the first bias compensation value are converted into drive signals and sent to the actuator to correct the pressure, completing this correction process.

[0088] refer to Figure 4 The diagram shown is a schematic flowchart of a pressure control parameter correction algorithm provided in an embodiment of this application. Specifically, the algorithm first calculates the first target pressure during inhalation, the second target pressure during exhalation, the first actual pressure during inhalation, and the second actual pressure during exhalation. Based on these calculations, the algorithm calculates the first target pressure difference according to the first target pressure and the second target pressure, and then calculates the first actual pressure difference according to the first actual pressure and the second actual pressure.

[0089] Subsequently, based on the difference between the first target pressure difference and the first actual pressure difference, an updated gain compensation value is calculated, and the updated gain compensation value and the historical gain compensation value are weighted and fused to obtain a fused gain compensation value. Further, the first gain compensation value can be determined based on the fused gain compensation value.

[0090] After obtaining the first gain compensation value, it is determined whether the first gain compensation value exceeds a preset gain limit range. If the first gain compensation value does not exceed the preset gain limit range, a first bias compensation value is calculated according to the combined inhalation and exhalation correction strategy. Specifically, the historical bias compensation value can be corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value to determine the updated bias compensation value. If the first gain compensation value exceeds the preset gain limit range, the first bias compensation value is calculated according to the exhalation correction strategy. Specifically, the historical bias compensation value can be corrected based on the second target pressure, the second actual pressure, and the historical gain compensation value to determine the updated bias compensation value.

[0091] Then, the updated bias compensation value and the historical bias compensation value can be weighted and fused to obtain the fused bias compensation value, and the first bias compensation value can be determined based on the fused bias compensation value.

[0092] Further, it is determined whether the first bias compensation value reaches the upper or lower limit of the preset bias limiting range. If the first bias compensation value reaches the upper limit of the preset bias limiting range, and the current actual pressure is higher than the current target pressure, then the first gain compensation value is decreased by m to reduce the pressure output; if the first bias compensation value reaches the lower limit of the preset bias limiting range, and the current actual pressure is lower than the current target pressure, then the first gain compensation value is increased by m to increase the pressure output. If the first bias compensation value does not reach the upper or lower limit, then the first gain compensation value remains unchanged.

[0093] Finally, the determined first gain compensation value and first bias compensation value are used to correct the current pressure.

[0094] In this way, by calculating and correcting the gain compensation value and the bias compensation value in stages, the accuracy and stability of the pressure control parameter correction can be improved.

[0095] Based on the above pressure control parameter correction method, this application embodiment also provides a pressure control parameter correction device, referencing... Figure 5 The diagram shown is a structural block diagram of a pressure control parameter correction device provided in an embodiment of this application, comprising: The pressure difference calculation unit 501 is used to calculate the first target pressure difference based on the first target pressure during the inhalation phase and the second target pressure during the exhalation phase, and to calculate the first actual pressure difference based on the first actual pressure during the inhalation phase and the second actual pressure during the exhalation phase. The first gain compensation value determination unit 502 is used to determine the first gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference. The first bias compensation value determination unit 503 is used to correct the historical bias compensation value based on the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, and determine the first bias compensation value. The correction unit 504 is used to correct the current pressure control parameters based on the first gain compensation value and the first bias compensation value.

[0096] In one possible implementation, the first bias compensation value determining unit is specifically used for: If the first gain compensation value is greater than the lower limit of the preset gain limit range and less than the upper limit of the preset gain limit range, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value to determine the updated bias compensation value. If the first gain compensation value is greater than or equal to the upper limit of the preset gain limit range, or less than or equal to the lower limit of the preset gain limit range, the historical bias compensation value is corrected according to the second target pressure, the second actual pressure, and the historical gain compensation value to determine the updated bias compensation value. Based on the updated bias compensation value, a first bias compensation value is determined.

[0097] In one possible implementation, the first bias compensation value determining unit is specifically used for: If the first gain compensation value is greater than the lower limit of the preset gain limiting range and less than the upper limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula:

[0098] in, The updated bias compensation value. This represents the historical bias compensation value. This represents the first gain compensation value. This indicates the first target pressure. This indicates the first actual pressure; The first bias compensation value determination unit is used for: If the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula:

[0099] in, Update the bias compensation value. This represents the historical bias compensation value. This indicates the second actual pressure.

[0100] In one possible implementation, the device further includes: The weighted fusion unit is used to perform weighted fusion of the updated bias compensation value and the historical bias compensation value to obtain a fused bias compensation value; and to perform amplitude limiting processing on the fused bias compensation value according to a preset bias limiting range to determine the first bias compensation value.

[0101] In one possible implementation, the device further includes: The limit verification unit is used to reduce the first gain compensation value if the first bias compensation value reaches the upper limit of the preset bias limit range and the current actual pressure is higher than the current target pressure. If the first bias compensation value reaches the lower limit of the preset bias limit range, and the current actual pressure is lower than the current target pressure, then the first gain compensation value is increased.

[0102] In one possible implementation, the first gain compensation value determining unit includes: The updated gain compensation value determination unit is used to determine the updated gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference and the historical gain compensation value. A fusion gain compensation value determination unit is used to perform weighted fusion of the updated gain compensation value and the historical gain compensation value to obtain a fusion gain compensation value. The final determination unit is used to determine the first gain compensation value based on the fusion gain compensation value.

[0103] In one possible implementation, the first target pressure is determined by averaging multiple target pressures acquired during the inhalation phase; the first actual pressure is determined by averaging multiple actual pressures acquired during the inhalation phase; the second target pressure is determined by averaging multiple target pressures acquired during the exhalation phase; and the second actual pressure is determined by averaging multiple actual pressures acquired during the exhalation phase.

[0104] Please see Figure 6 , Figure 6This application provides a structural block diagram of a computer device for pressure control parameter correction. The computer device includes a processor 610 and a memory 620. The memory 620 is used to store program code and transmit the program code to the processor 610; The processor 610 is used to execute the pressure control parameter correction method described in any of the above implementations according to the instructions in the program code.

[0105] This application also discloses a computer-readable storage medium for storing a computer program, which, when executed by a processor, performs the pressure control parameter correction method described in any of the above embodiments.

[0106] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that all or part of the steps in the methods of the above embodiments can be implemented by means of software plus a general-purpose hardware platform. Based on this understanding, the technical solution of this application can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as a read-only memory (ROM) / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network communication device such as a router) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0107] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the 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.

[0108] It should also 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.

[0109] The above description is merely a preferred embodiment of this application. Although this application has disclosed preferred embodiments above, it is not intended to limit this application. Any person skilled in the art can make many possible variations and modifications to the technical solutions of this application using the methods and techniques disclosed above, or modify them into equivalent embodiments with equivalent changes, without departing from the scope of the technical solutions of this application. Therefore, any simple modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of this application without departing from the content of the technical solutions of this application shall still fall within the protection scope of the technical solutions of this application.

Claims

1. A method for calibrating pressure control parameters, characterized in that, include: The first target pressure difference is calculated based on the first target pressure during the inhalation phase and the second target pressure during the exhalation phase, and the first actual pressure difference is calculated based on the first actual pressure during the inhalation phase and the second actual pressure during the exhalation phase. The first gain compensation value is determined based on the difference between the first target pressure difference and the first actual pressure difference; Based on the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, the historical bias compensation value is corrected to determine the first bias compensation value. The current pressure control parameters are corrected based on the first gain compensation value and the first bias compensation value.

2. The method according to claim 1, characterized in that, Based on the first gain compensation value, the first target pressure, and the first actual pressure, or the second target pressure and the second actual pressure, the historical bias compensation value is corrected to determine the first bias compensation value, including: If the first gain compensation value is greater than the lower limit of the preset gain limit range and less than the upper limit of the preset gain limit range, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value, and the updated bias compensation value is determined. If the first gain compensation value is greater than or equal to the upper limit of the preset gain limit range, or less than or equal to the lower limit of the preset gain limit range, the historical bias compensation value is corrected according to the second target pressure, the second actual pressure, and the historical gain compensation value to determine the updated bias compensation value. Based on the updated bias compensation value, a first bias compensation value is determined.

3. The method according to claim 2, characterized in that, If the first gain compensation value is greater than the lower limit of the preset gain limiting range and less than the upper limit of the preset gain limiting range, the historical bias compensation value is corrected based on the first target pressure, the first actual pressure, the historical gain compensation value, and the first gain compensation value to determine the updated bias compensation value, including: If the first gain compensation value is greater than the lower limit of the preset gain limiting range and less than the upper limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula: in, The updated bias compensation value. This represents the historical bias compensation value. This represents the first gain compensation value. This indicates the first target pressure. This indicates the first actual pressure; If the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the historical bias compensation value is corrected based on the second target pressure, the second actual pressure, and the historical gain compensation value to determine the updated bias compensation value, including: If the first gain compensation value is greater than or equal to the upper limit of the preset gain limiting range, or less than or equal to the lower limit of the preset gain limiting range, the updated bias compensation value is determined using the following formula: in, The updated bias compensation value. This represents the historical bias compensation value. This indicates the second actual pressure.

4. The method according to claim 2, characterized in that, The method further includes: The updated bias compensation value and the historical bias compensation value are weighted and fused to obtain the fused bias compensation value; The first bias compensation value is determined by limiting the fusion bias compensation value according to the preset bias limiting range.

5. The method according to claim 4, characterized in that, The method further includes: If the first bias compensation value reaches the upper limit of the preset bias limit range, and the current actual pressure is higher than the current target pressure, then the first gain compensation value is reduced. If the first bias compensation value reaches the lower limit of the preset bias limit range, and the current actual pressure is lower than the current target pressure, then the first gain compensation value is increased.

6. The method according to claim 1, characterized in that, The step of determining the first gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference includes: The updated gain compensation value is determined based on the difference between the first target pressure difference and the first actual pressure difference, as well as the historical gain compensation value. The updated gain compensation value and the historical gain compensation value are weighted and fused to obtain the fused gain compensation value; The first gain compensation value is determined based on the fusion gain compensation value.

7. The method according to any one of claims 1-6, characterized in that, The first target pressure is determined by averaging multiple target pressures acquired during the inhalation phase; the first actual pressure is determined by averaging multiple actual pressures acquired during the inhalation phase; the second target pressure is determined by averaging multiple target pressures acquired during the exhalation phase; and the second actual pressure is determined by averaging multiple actual pressures acquired during the exhalation phase.

8. A pressure control parameter correction device, characterized in that, include: The pressure difference calculation unit is used to calculate the first target pressure difference based on the first target pressure during the inhalation phase and the second target pressure during the exhalation phase, and to calculate the first actual pressure difference based on the first actual pressure during the inhalation phase and the second actual pressure during the exhalation phase. The first gain compensation value determination unit is used to determine the first gain compensation value based on the difference between the first target pressure difference and the first actual pressure difference. The first bias compensation value determination unit is used to correct the historical bias compensation value based on the first gain compensation value, the first target pressure and the first actual pressure, or the second target pressure and the second actual pressure, and determine the first bias compensation value. The correction unit is used to correct the current pressure control parameters based on the first gain compensation value and the first bias compensation value.

9. A computer device, characterized in that, The computer device includes a processor and memory: The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the pressure control parameter correction method according to any one of claims 1-7 according to the instructions in the program code.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program, which, when executed by a processor, is used to perform the pressure control parameter correction method according to any one of claims 1-7.

Images