CN-122006035-A - Self-adaptive algorithm-based intelligent parameter matching method for anesthesia respirator

CN122006035ACN 122006035 ACN122006035 ACN 122006035ACN-122006035-A

Abstract

The invention relates to the technical field of breathing machine control, in particular to an intelligent parameter matching method of an anesthesia breathing machine based on a self-adaptive algorithm, which comprises the following steps: executing inhalation blocking inversion static flow resistance coefficient at the initial starting stage of the anesthesia respirator, combining with real-time flow velocity mapping pressure drop and reconstructing real-time alveolus estimated pressure, integrating the flow velocity to obtain tidal volume to construct a pressure volume sequence and a dynamic linear compliance reference standard, quantifying track deviation, generating inhalation phase and exhalation phase nonlinear deviation total moment through trapezoidal integral operation, in the invention, by blocking inversion flow resistance coefficient mapping pipeline pressure drop, reconstructing signal isolation alveolus pressure to eliminate interference, and constructing a dynamic compliance reference, quantifying the deviation track by using the hysteresis moment, accurately identifying the state, and correcting the tidal volume by negative feedback, so as to realize ventilation self-adaptive matching and solve the problems of monitoring hysteresis and parameter mismatch.

Inventors

ZHANG YAO
WANG FENG
ZHOU YAYING
Peng Zufen
QIN XUE
Yuan Rumei
SHAO JIANLIANG
YOU YUEMEI
ZHANG LINGLIN

Assignees

中国人民解放军陆军军医大学第一附属医院

Dates

Publication Date: 20260512
Application Date: 20260325

Claims (10)

1. The intelligent parameter matching method for the anesthesia respirator based on the self-adaptive algorithm is characterized by comprising the following steps of: S1, executing inhalation blocking at the initial starting stage of an anesthesia respirator, collecting peak value and platform pressure of an air passage and blocking flow rate, executing differential pressure extraction on the peak value and the platform pressure, executing impedance inversion based on the blocking flow rate, and generating a static flow resistance coefficient; S2, collecting the real-time pressure and the real-time flow velocity of the air channel, performing pipeline pressure drop mapping on the real-time flow velocity and the static flow resistance coefficient, and performing signal reconstruction on the real-time pressure of the air channel based on a mapping result to generate real-time alveolus estimated pressure; s3, calling the real-time alveolus estimated pressure, performing integral transformation on the real-time flow velocity to obtain accumulated tidal volume, performing spatial mapping to construct a pressure volume sequence, extracting inspiration start-stop coordinates, and constructing a dynamic linear compliance reference standard; s4, performing nonlinear deviation degree quantification on the dynamic linear compliance reference standard and the real-time alveolus estimated pressure to obtain track deviation, and performing split-phase lag moment operation on the track deviation in the inhalation and exhalation phase by adopting a trapezoidal integral algorithm to generate nonlinear deviation total moment of inhalation phase and exhalation phase; and S5, judging the lung compliance state of the inhalation phase and exhalation phase nonlinear deviation total moment, and executing parameter negative feedback correction according to the judging result to generate a target tidal volume parameter.
2. The adaptive algorithm-based intelligent anesthesia respirator parameter matching method according to claim 1 wherein the static flow resistance coefficient comprises an airway viscosity resistance coefficient and an airway turbulence resistance coefficient, the real-time alveolus estimated pressure comprises a pulmonary elastic recoil pressure and an endogenous positive end expiratory pressure, the dynamic linear compliance reference comprises a compliance slope and a pressure volume intercept, the total non-linear deviation moment of the inspiratory and expiratory phases comprises an inspiratory filling hysteresis moment and an expiratory evacuation damping moment, and the target tidal volume parameter comprises a preset tidal volume and a circuit compliance compensation amount.
3. The intelligent anesthetic breathing apparatus parameter matching method based on the adaptive algorithm as claimed in claim 1, wherein the specific steps of S1 are as follows: s101, monitoring an initial starting state of an anesthesia respirator and controlling an inhalation valve to be closed to execute inhalation blocking, triggering a sensor to acquire an airway peak pressure value, a platform pressure value and a blocking flow rate value, establishing a time axis association mapping and packaging, and generating an airway mechanics basic parameter set; S102, extracting an airway peak pressure value and a platform pressure value based on the airway mechanics basic parameter set, performing difference operation by subtracting the platform pressure value from the airway peak pressure value, calculating a pressure difference value of the airflow from dynamic flow to static retention, and obtaining an airway pressure gradient value; S103, calling the blocking flow velocity value in the airway mechanics basic parameter set, executing impedance inversion by combining the airway pressure gradient value, constructing a linear flow resistance relation, and executing division operation on the blocking flow velocity value by utilizing the airway pressure gradient value to obtain a static flow resistance coefficient.
4. The intelligent anesthetic breathing apparatus parameter matching method based on the adaptive algorithm as claimed in claim 3, wherein the specific steps of S2 are as follows: S201, calling the static flow resistance coefficient, activating a high-frequency sampling port of a breathing machine gas circuit to collect a real-time pressure signal and a real-time flow rate signal of the gas channel, executing time axis alignment and abnormal rejection processing, and storing the aligned real-time pressure of the gas channel and a real-time flow rate numerical sequence in a correlated manner to establish a respiratory hydrodynamic monitoring data set; S202, extracting a real-time flow velocity numerical value sequence based on the respiratory fluid mechanics monitoring data set, constructing a linear resistance calculation relation by utilizing a static flow resistance coefficient, and performing multiplication operation on flow velocity sampling points in the real-time flow velocity numerical value sequence and the static flow resistance coefficient to generate a dynamic pipeline pressure drop sequence; And S203, performing numerical analysis on the dynamic pipeline pressure drop sequence and the respiratory hydrodynamic monitoring data set, extracting an airway real-time pressure numerical sequence, and subtracting the dynamic pipeline pressure drop sequence from the airway real-time pressure numerical sequence to obtain real-time alveolar estimated pressure.
5. The intelligent anesthetic breathing apparatus parameter matching method based on the adaptive algorithm as claimed in claim 4, wherein the specific step of S3 is as follows: S301, invoking the real-time alveolus estimated pressure, extracting a real-time flow velocity numerical sequence based on a respiratory hydrodynamic monitoring data set, setting an inhalation starting trigger point and an inhalation ending cut-off point as integral boundaries, executing cumulative summation operation, calculating the total gas capacity of a single inhalation process, and generating cumulative tidal volume; S302, performing multidimensional data space reconstruction based on the accumulated tidal volume and the real-time alveolus estimated pressure, establishing a two-dimensional Cartesian coordinate mapping system, mapping the accumulated tidal volume under the same sampling time stamp as a horizontal axis variable and the real-time alveolus estimated pressure as a vertical axis variable, and establishing a pressure volume sequence; s303, searching an inhalation starting zero point coordinate and an inhalation end peak value coordinate for the pressure volume sequence, constructing a linear reference line connecting the zero point coordinate and the peak value coordinate by using a two-point linear equation, and generating a dynamic linear compliance reference standard.
6. The intelligent matching method for parameters of an anesthesia respirator based on an adaptive algorithm according to claim 5, wherein the setting of the inspiration starting trigger point and the ending trigger point as integral boundaries means traversing the real-time flow velocity value sequence in time sequence, and when the flow velocity value is monitored to be greater than a preset inspiration trigger threshold, locking the current sampling moment as the inspiration starting trigger point, continuously monitoring the real-time flow velocity value sequence until the flow velocity value is attenuated and is smaller than or equal to a zero flow velocity baseline, and locking the current sampling moment as the ending trigger point.
7. The intelligent anesthetic breathing apparatus parameter matching method based on the adaptive algorithm as claimed in claim 5, wherein the specific step of S4 is as follows: S401, calling the dynamic linear compliance reference standard, extracting linear slope and intercept characteristic parameters, calculating a theoretical linear pressure value in the current volume state by combining the accumulated tidal volume, performing difference calculation on the real-time pulmonary alveolus estimated pressure and the theoretical linear pressure value, and generating a dynamic track deviation sequence according to a time sampling sequence; S402, based on the dynamic track deviation sequence, calling a real-time flow velocity numerical value sequence to identify a zero reversal position, and executing segmentation extraction of inhalation and exhalation time periods on the dynamic track deviation sequence according to positive and negative polarity characteristics of the flow velocity to construct an inhalation and exhalation split-phase deviation set; S403, performing discrete numerical integration on the inhalation and exhalation phase-splitting deviation set, selecting adjacent deviation data points as an upper bottom and a lower bottom, extracting volume increment between sampling points as high, calculating a micro-element trapezoidal area, and performing accumulation summation to generate nonlinear deviation total moment of inhalation phase and exhalation phase.
8. The intelligent matching method for parameters of an anesthesia respirator based on an adaptive algorithm according to claim 7, wherein the performing of the segmentation extraction of inspiration and expiration periods on the dynamic trajectory deviation sequence according to the positive and negative flow velocity characteristics refers to traversing each flow sampling point in the real-time flow velocity numerical value sequence, marking the data point in the dynamic trajectory deviation sequence corresponding to the moment as an inspiration attribute when the flow velocity numerical value at the current sampling moment is detected to be greater than zero, marking the data point in the dynamic trajectory deviation sequence corresponding to the moment as an expiration attribute when the flow velocity numerical value at the current sampling moment is detected to be less than zero, and marking the data point in the dynamic trajectory deviation sequence corresponding to the moment as an expiration attribute when the flow velocity numerical value at the current sampling moment is detected to be less than zero.
9. The intelligent anesthetic breathing apparatus parameter matching method based on the adaptive algorithm as claimed in claim 7, wherein the specific step of S5 is as follows: S501, calling nonlinear deviation total moment of the inhalation phase and the exhalation phase, comparing with a preset compliance linear tolerance threshold, dividing a nonlinear level interval according to the comparison difference amplitude, determining a deviation level of elastic deformation of lung tissue, mapping the deviation level to a digital code, and generating a lung compliance state discrimination index; S502, determining corresponding adjustment weight parameters based on a feedback adjustment gain coefficient table preset by a control loop of the lung compliance state discrimination index retrieval breathing machine, constructing a negative feedback operation formula, and performing multiplication operation on the weight parameters and nonlinear deviation total moment of inhalation phase and exhalation phase to obtain a tidal volume negative feedback correction quantity; S503, collecting a basic tidal volume set value of the current respiratory cycle according to the tidal volume negative feedback correction quantity, establishing a dynamic updating rule, adding the tidal volume negative feedback correction quantity to the set value, executing algebraic sum operation, and generating a target tidal volume parameter.
10. The adaptive algorithm-based intelligent anesthesia respirator parameter matching method according to claim 9, wherein the preset compliance linear tolerance threshold is determined by calculating the maximum orthogonal deviation distance of the pressure-volume hysteresis loop data relative to the mid-section linear regression fit line and superimposing a preset measurement noise tolerance coefficient based on the pressure-volume hysteresis loop data generated by the standard simulated lung under the constant flow ventilation test.

Description

Self-adaptive algorithm-based intelligent parameter matching method for anesthesia respirator Technical Field The invention relates to the technical field of breathing machine control, in particular to an intelligent parameter matching method for an anesthesia breathing machine based on a self-adaptive algorithm. Background The technical field of ventilator control relates to monitoring and adjusting of the operation state of mechanical ventilation equipment, airflow delivery and respiratory physiological parameters of a patient, and covers a complete technical system from sensor data acquisition and ventilation mode selection to closed-loop feedback control, and the key point is that the normal alveolar ventilation function of the patient is maintained and the oxygenation state is improved by adjusting the core indexes of inspiratory pressure, positive end expiratory pressure, tidal volume and respiratory frequency, so that the ventilator control system is widely applied to intensive care, emergency resuscitation and surgical anesthesia medical scenes. The traditional anesthesia respirator parameter intelligent matching method is characterized in that the breathing support requirement of a patient in an anesthesia state in the operation process is indicated, the process of calculating and setting initial values of tidal volume, respiratory frequency and respiratory ratio is combined with a clinically preset ventilation formula or standard parameter comparison table according to physiological characteristic data of the patient, and medical staff manually adjusts a ventilation parameter knob or a touch screen input interface according to partial pressure of carbon dioxide at end of expiration and monitoring values of airway pressure in operation so as to correct the limit value of the ventilation volume and the airway pressure. The existing anesthesia respirator parameter matching depends on the fixed physiological characteristics and a preset formula of a patient, individual differences and dynamic evolution of mechanical characteristics of the lung under anesthesia are ignored, the intra-operative regulation is only carried out by the total airway pressure monitoring, the airflow resistance pressure drop of a pipeline cannot be stripped to acquire the actual alveolar pressure, the lung compliance evaluation distortion is caused, hysteresis exists in manual correction, the respiratory physiological state transient is difficult to respond finely, the ventilation parameter is mismatched with the actual alveolar demand, the air pressure injury or insufficient ventilation is easily caused by misjudgment of the pressure, and the regulation precision is low and the potential safety hazard exists. Disclosure of Invention In order to solve the technical problems that the parameter matching of the existing anesthesia respirator depends on the fixed physiological characteristics and a preset formula of a patient, individual differences and dynamic evolution of mechanical properties of the lung under anesthesia are ignored, the intra-operative adjustment is only carried out by the total airway pressure monitoring, the airflow resistance pressure drop of a pipeline cannot be stripped to acquire the actual alveolar pressure, the evaluation distortion of the lung compliance is caused, the hysteresis exists in manual correction, the transient of the respiratory physiological state is difficult to respond finely, the ventilation parameter is mismatched with the actual alveolar demand, the air pressure injury or insufficient ventilation is easily caused by misjudgment of the pressure, and the regulation precision is low and the potential safety hazard exists, the embodiment of the invention provides an intelligent parameter matching method of the anesthesia respirator based on a self-adaptive algorithm. In order to achieve the purpose, the invention adopts an intelligent parameter matching method of the anesthesia respirator based on an adaptive algorithm, and the method comprises the following steps: S1, executing inhalation blocking at the initial starting stage of an anesthesia respirator, collecting peak value and platform pressure of an air passage and blocking flow rate, executing differential pressure extraction on the peak value and the platform pressure, executing impedance inversion based on the blocking flow rate, and generating a static flow resistance coefficient; S2, collecting the real-time pressure and the real-time flow velocity of the air channel, performing pipeline pressure drop mapping on the real-time flow velocity and the static flow resistance coefficient, and performing signal reconstruction on the real-time pressure of the air channel based on a mapping result to generate real-time alveolus estimated pressure; s3, calling the real-time alveolus estimated pressure, performing integral transformation on the real-time flow velocity to obtain accumulated tidal volume, performing spatial mapping to cons