12 results about "Flow waveform" patented technology

The present application relates to the technical field of medical apparatus and instruments, in particular to a ventilation trigger recognition method and system of an anesthesia machine and the anesthesia machine. The method comprises the following steps: step 1: collecting airway pressure waveform data and flow waveform data of the anesthesia machine; step 2: converting the collected airway pressure waveform data and flow waveform data into matrix data; step 3: inputting the matrix data into a trained convolutional neural network, and the convolutional neural network outputs a probability value based on the input matrix data; step 4: comparing the probability value with a threshold value, and determining whether the ventilation trigger condition is met; if the trigger condition is met, the anesthesia machine starts ventilation support. The present application can more accurately determine the trigger condition by analyzing the shape of the ventilation curve through the convolutional neural network, so as to realize more accurate and safe anesthesia ventilation control.

The invention provides a method for extracting water flow time-lag data based on historical scheduling data. The method comprises the following steps: firstly, establishing an ex-warehouse flow waveform library by using historical ex-warehouse flow of an upstream power station; then, for each warehouse-out flow waveform, generating a corresponding warehouse-in flow waveform library by setting different time offsets; then, through an improved dynamic time warping algorithm, considering the flow value difference and the morphological trend similarity of a flow hydrograph at the same time, and quantifying the similarity of an ex-warehouse flow waveform and an in-warehouse flow waveform; and finally, according to the optimal matching result, extracting the water flow time lag of the corresponding warehouse-out flow. By applying the method, the limitation of a traditional fixed time-lag model can be effectively overcome, and high-precision dynamic water flow time-lag information can be obtained. Therefore, a dispatcher can grasp the water flow propagation characteristics in the changing process in time, the accuracy of cascade hydropower station reservoir flow forecasting and dispatching decision making is remarkably improved, and a core data guarantee is provided for safe and efficient operation of the hydropower station.

This invention discloses a non-invasive method for estimating central aortic pressure (PWV) driven by a vascular tree network, relating to the field of cardiovascular hemodynamic modeling. The method includes: collecting clinical data and scaling the vessel length and reference area; calculating the flow waveforms of the aorta and its branches based on the 4D-Flow MRI velocity field to determine the blood flow distribution ratio; constructing an eight-branch vascular tree network model based on the pressure propagation path from the aorta to the brachial artery; selecting a section on the descending aorta's central axis to calculate the flow waveform and inversely calculating PWV; constructing a dataset using sensitivity analysis and one-dimensional positive problem simulation to pre-train the neural network; performing PINN patient-specific fine-tuning on the model; extracting the aortic pressure waveform using the fine-tuned model, calculating the central aortic pressure value, and outputting patient-specific parameters and distribution results. The input waveform constructed based on non-invasive clinical data in this invention can adapt to different patient-specific differences, significantly improving the model's individualization and clinical compatibility.

The application discloses a model-driven arterial hemodynamics measurement method and device, equipment and a computer readable storage medium, and the method comprises the following steps: collecting arterial blood pressure waveform time series data in a preset cardiac cycle; inputting the arterial blood pressure waveform time series data into a preset aortic hemodynamics coupling model to obtain aortic hemodynamics waveform characteristic parameters; and determining cardiac output according to the aortic hemodynamics waveform characteristic parameters; wherein the preset aortic hemodynamics coupling model is formed by coupling a one-dimensional blood flow dynamics model simulating aortic blood vessel transmission characteristics and a zero-dimensional multi-elastic cavity model simulating peripheral arterial circulation impedance characteristics. The one-dimensional model in the coupling model can accurately depict the blood flow in the aorta and the pulse wave propagation and reflection phenomenon, and realize high-precision solution of blood pressure, flow velocity and flow waveform; the zero-dimensional model simulates the blood flow process of the peripheral artery and serves as a boundary condition of the one-dimensional model, so that the overall blood flow simulation is more in line with the real physiological state.

The invention discloses a fault monitoring method and system for a separate injection water distributor, electronic equipment and a storage medium, and relates to the technical field of oil field automation control. The method comprises the following steps: comprehensively monitoring multi-dimensional data such as pressure inside and outside an oil pipe, liquid flow and the like, and combining data threshold comparison and dynamic trend analysis to comprehensively evaluate the running state of the water distributor, and effectively judging whether a dropping-fishing core is stuck or not by utilizing a wireless communication state between a wireless positioning short section and an external pressure short section; the abnormal initial judgment result is subjected to matching and binary coding by means of a preset fault logic model, and fault information is uploaded to a ground system in a pressure-flow wave form through wave code signal conversion, so that the reliability and the operation and maintenance efficiency of a separate injection process are improved, various faults can be recognized in time, injection stop of a water injection well caused by fault expansion is avoided, and the injection efficiency is improved. The number of times of non-planned well repair operation is greatly reduced, the maintenance cost is reduced, and key technical support is provided for intelligent and fine management of the separated layer water injection process.

The invention provides a method, equipment and a system for determining an intravascular blood flow velocity field. The method for determining the blood flow velocity field in the blood vessel comprises the following steps: calculating a specific flow curve of a patient relative to an average blood flow waveform under the condition of keeping the blood flow in each blood vessel unchanged so as to determine a time weight coefficient of each to-be-detected cardiac moment; according to a cross-frame image in a sliding window based on a cardiac cycle, a cross-frame blood flow velocity field calculation result is obtained by using an optical flow method, and a cross-frame optical flow guide item energy function is constructed; constructing a time coupling term energy function for constraining the blood flow acceleration according to the multiple groups of adjacent frame images in the sliding window; and determining the blood flow velocity field of the current frame in the sliding window according to the time weight coefficient, the cross-frame optical flow guide item energy function and the time coupling item energy function.

This invention discloses a parameter identification method for a lumped parameter model of systemic circulation, belonging to the field of lumped parameter model technology. The method includes: constructing the state equation of the lumped parameter model of systemic circulation based on Kirchhoff's voltage and current laws to obtain the systemic circulation control equation; calculating the duration ratio of systolic to diastolic phases and stroke volume based on routine clinical measurement data, constructing classic aortic pressure and flow waveforms, and performing registration processing; calculating central venous pressure and flow based on routine clinical measurement data; and using the registered aortic inlet pressure and flow, central venous pressure and flow, and systemic circulation control equations to calculate the values ​​of each parameter in the parameter model. This invention, by periodically stretching the classic reference waveform, matches the waveform extreme values ​​with the patient's measured blood pressure and cardiac output, indirectly reconstructing the aortic inlet pressure and flow curve reflecting individual characteristics under non-invasive conditions, significantly improving the model's individualization and clinical compatibility.

The present disclosure generally relates to systems and methods for delivery of therapeutic gas to patients, using techniques to compensate for disruptions in breathing gas flow measurement, such as when breathing gas flow measurement is unavailable or unreliable. Such techniques include using historical breathing gas flow rate data, such as moving average flow rates, moving median flow rates and / or flow waveforms. At least some of these techniques can be used to ensure that interruption in therapeutic gas delivery is minimized or eliminated.

The invention discloses a visual laryngeal mask ventilation state monitoring and air leakage early warning system and method based on artificial intelligence, and the system comprises a multi-mode data sensing and collection module which synchronously collects the video stream, pressure waveform and flow waveform data of a laryngeal mask; the data preprocessing and feature engineering module is used for processing video data to obtain position-related visual features and processing pressure flow data to obtain ventilation-related physiological features; the deep learning-based multi-time-sequence feature fusion and air leakage risk prediction module is used for fusing multi-modal features and predicting an air leakage risk level through a deep learning model; the man-machine interaction and multi-level early warning feedback module is used for starting multi-level visualization and auditory early warning according to the risk level; and the cloud model collaborative updating module is used for collaborating with the multi-center data optimization model through a federated learning framework. According to the invention, the air leakage risk is early warned in advance, and the air passage safety management level is improved.

Described herein are systems and methods for synchronizing electrical activity monitored by a plurality of external electrodes with supplemental cardiac data for assessing a patient's cardiac condition and configuring cardiac therapy. The supplemental cardiac data can include one or more markers indicative of a cardiac event occurrence and / or representative of at least one of a cardiac electrical signal, a heart sound, a cardiac pressure, a blood flow, and an estimated instantaneous flow waveform provided by a left ventricular assist device.

The application discloses a kind of based on reinforcement learning and fuzzy control's ultrasonic actuator pump lung control method, it is related to extracorporeal membrane oxygenation field, including the following steps: according to expert system knowledge, construct the fuzzy rule between basic vital signs and pulsation frequency, obtain fuzzy controller, adjust average flow;According to the flow field condition of oxygenation device, construct the interactive environment of agent;The state space and action space of agent control strategy are constructed, and the movement of motor is kept stable;Establish and train the blood pump control strategy model based on deep reinforcement learning, obtain blood flow waveform curve and blood pump control strategy;Intelligent control is carried out to motor by extracting trained model, and the control performance of strategy model is evaluated.The application finds optimal flow waveform using deep reinforcement learning, regulates and controls blood flow field, significantly improves oxygenation efficiency without complex oxygenator design conditions, and different agents can be obtained according to different oxygenator structures, with strong portability.

A control circuit for a sensorless implantable blood pump configured to determine mitral regurgitation includes processing circuitry configured to generate an estimated blood flow waveform from the sensorless implantable blood pump and generate an alert if a measured amplitude of the estimated blood flow waveform does not include an inflection point between end diastole and initial systole.