An oxygen therapy control system

Abstract

The present invention relates to the field of medical detection technology, and in particular to a control method for an oxygen therapy system. The method comprises the following steps: presetting an initial flow rate; obtaining an EIT image and obtaining a target flow rate; using the initial flow rate value as a flow rate estimate value at a first moment, calculating a flow rate prediction value at a next moment based on the flow rate estimate value at a current moment, and calculating a flow rate estimate value at a current moment based on the flow prediction value at the current moment; calculating an error value between the flow prediction value at the next moment and the target flow rate at the current moment; calculating a flow adjustment amount based on the error value, and adjusting the oxygen therapy output flow rate. The present invention obtains the target output flow rate of oxygen therapy through an EIT image, thereby achieving real-time adjustment of the output flow rate of the device and improving the oxygen therapy effect. By using the difference between the prediction value and the target value as a reference for a control adjustment parameter, the control system responds more quickly, effectively reduces the control error, and thus achieves optimal control of the flow output.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, in particular to an oxygen therapy control system. Background Art

[0002] Oxygen therapy is a key treatment for respiratory diseases such as COPD and asthma. In traditional treatment practice, the oxygen therapy flow rate is usually set by medical staff based on experience and remains unchanged throughout the treatment cycle. However, this set oxygen therapy flow rate may not be suitable for all users. Inappropriate flow setting may not only fail to achieve the therapeutic effect, but may also cause additional harm to the user.

[0003] Dynamic and personalized oxygen therapy flow adjustment based on the user's specific situation is particularly important. Currently, most oxygen therapy devices adjust oxygen flow based on blood oxygen saturation, but this method has the following problems:

[0004] 1) If the blood oxygen saturation of a user with carbon dioxide retention is low, increasing the flow rate of the oxygen therapy device will reduce the user's respiratory excitability, leading to worsening carbon dioxide retention;

[0005] 2) A high oxygen therapy flow rate will reduce the gas support of the user's alveoli, which may lead to atelectasis;

[0006] 3) There is a certain measurement delay in monitoring blood oxygen saturation, and it cannot reflect the user's lung ventilation status.

[0007] Therefore, it is crucial for those skilled in the art to design an oxygen therapy control system that can promptly reflect the user's breathing condition and help doctors identify the user's lung ventilation problems at an early stage. Summary of the Invention

[0008] The technical problem to be solved by the embodiments of the present invention is to provide an oxygen therapy control system that can timely reflect the user's breathing conditions, so as to solve the defects in the existing technology.

[0009] The utility model discloses an oxygen therapy control system, which comprises: an EIT imaging unit, an oxygen therapy unit, and a control unit. The EIT imaging unit is used to collect user boundary voltage data to obtain the user's EIT image. The oxygen therapy unit is used to provide a gas source and a gas transmission channel. The control unit is connected to the EIT imaging unit and the oxygen therapy unit respectively to perform data calculation for the system. The control unit includes a fuzzy PID controller for calculating a flow adjustment amount according to an error value, a Kalman filter for calculating a flow prediction value and a flow estimation value, and a main controller. The oxygen therapy control system performs the following steps:

[0010] Preset initial flow rate;

[0011] The linear relationship between global impedance change, regional ventilation delay index and flow rate was obtained experimentally to obtain a characterization model;

[0012] Obtain the user's EIT image, calculate the impedance value and regional ventilation delay index corresponding to the pixel point in the EIT image, and obtain the flow rate corresponding to the impedance value and regional ventilation delay index in the characterization model as the target flow rate;

[0013] The initial flow value is used as the flow estimate value at the first moment, and the flow forecast value of the current moment to the next moment is calculated based on the flow estimate value at the current moment, and the flow estimate value of the current moment is calculated based on the flow forecast value of the previous moment to the current moment;

[0014] Calculate the error value based on the traffic prediction value at the next moment and the target traffic at the current moment;

[0015] The flow adjustment amount is calculated according to the error value, and the oxygen therapy output flow is adjusted according to the flow adjustment amount to make it approach the target flow value.

[0016] Optionally, the “calculation of the impedance value corresponding to the pixel point in the EIT image” performed by the oxygen therapy control system is specifically calculated by the following formula:

[0017]

[0018] Among them, GIV i is the impedance value corresponding to the i-th pixel, N is the number of breaths in the cycle, ΔZ i1 is the impedance value of the i-th pixel at the end of inspiration during the n-th breath, ΔZ i2 is the impedance value at the end of expiration of the i-th pixel during the n-th breath.

[0019] Optionally, the “calculation of the regional ventilation delay index corresponding to the pixel point in the EIT image” performed by the oxygen therapy control system is specifically calculated by the following formula:

[0020]

[0021] Among them, t j,40％ T is the time required for the jth pixel of the lung to reach 40% of its maximum inspiratory impedance value. 40％ is the inspiratory time of the global impedance.

[0022] Optionally, the oxygen therapy control system performs “calculating the flow prediction value at the current moment for the next moment based on the flow estimation value at the current moment” according to the following formula:

[0023]

[0024] in, is the traffic forecast value at time n for time n+1, is the estimated flow rate at time n, For PID control as a function of time t.

[0025] Optionally, the oxygen therapy control system performs the calculation of the estimated flow rate at the current moment based on the flow rate prediction value at the previous moment according to the following formula:

[0026]

[0027] in, K is the traffic forecast value at time n-1 for time n, n is the Kalman gain, Z n is the actual flow value at time n.

[0028] Optionally, the oxygen therapy control system further performs the following steps:

[0029] Collect the user's boundary voltage data and obtain the user's end-inhalation image and end-expiration image within a certain time period;

[0030] The EIT image is obtained based on the boundary voltage data, end-inspiratory image and end-expiratory image.

[0031] Optionally, the oxygen therapy control system further performs the following steps:

[0032] The boundary voltage data are summed to obtain a global impedance curve, and the peaks and valleys in the global impedance curve are identified by second-order differences;

[0033] The conductivity matrix is ​​calculated according to the formula S×(V1-V0), where S is the Jacobian matrix, V1 is the peak in the global impedance curve, and V0 is the trough in the global impedance curve;

[0034] The conductivity matrix is ​​converted into a pixel matrix through an image reconstruction algorithm to obtain an EIT image.

[0035] Compared with the prior art, the oxygen therapy control system provided by the embodiments of the present invention has the following beneficial effects: an oxygen therapy control system is designed, an EIT imaging unit is used to obtain an EIT image to obtain in real time the effective oxygen therapy time of the oxygen therapy unit at an initial flow rate, and the target output flow rate of the device is calculated by the EIT image, thereby achieving real-time adjustment of the output flow rate of the oxygen therapy unit and improving the accuracy of the output of the oxygen therapy unit; further, by introducing Kalman filtering technology, the difference between the predicted value and the target value is used as a reference for the control adjustment parameter, so that the control system responds more quickly, effectively reduces the control error, and thus achieves optimal control of the flow output. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments, in which:

[0037] Figure 1 This is the process flow of the oxygen therapy control system provided by the embodiment of the present invention. Figure 1 ;

[0038] Figure 2 This is the process flow of the oxygen therapy control system provided by the embodiment of the present invention. Figure 2 ;

[0039] Figure 3 This is the process flow of the oxygen therapy control system provided by the embodiment of the present invention. Figure 3 ;

[0040] Figure 4 This is the process flow of the oxygen therapy control system provided by the embodiment of the present invention. Figure 4 ;

[0041] Figure 5 This is a system block diagram of an oxygen therapy control system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. Now, in conjunction with the accompanying drawings, the preferred embodiments of the present invention will be described in detail.

[0043] like Figures 1 to 4 As shown, the present invention provides a specific embodiment of an oxygen therapy control system.

[0044] An oxygen therapy control system, reference Figure 5 The oxygen therapy control system includes an EIT imaging unit 1, an oxygen therapy unit 2 and a control unit 3. The EIT imaging unit 1 is used to collect user boundary voltage data to obtain the user's EIT image. The oxygen therapy unit 2 is used to provide a gas source and a gas transmission channel. The control unit 3 is connected to the EIT imaging unit 1 and the oxygen therapy unit 2 respectively for data calculation of the system.

[0045] Specifically, refer to Figure 5 The EIT imaging unit 1, as the EIT imaging acquisition hardware of the system, can be composed of a pitaya development board and an expansion board; the oxygen therapy unit 2 is composed of a hose, a lung splint, a leakage branch, and a blower; the control unit 3 includes a fuzzy PID controller 31 for calculating the flow adjustment amount according to the error value, a Kalman filter 32 for calculating the flow prediction value and the flow estimation value, and a main controller 33.

[0046] refer to Figure 1, the oxygen therapy control system can perform the following steps:

[0047] S1. Preset the initial flow rate and perform oxygen therapy on the user at the initial flow rate;

[0048] S2. Monitor the user's EIT image and obtain the target flow rate of the user's oxygen therapy based on the EIT image;

[0049] S3. Using the initial flow value as the flow estimate value at the first moment, and calculating the flow prediction value from the current moment to the next moment based on the flow estimate value at the current moment, and calculating the flow estimate value at the current moment based on the flow prediction value from the previous moment to the current moment;

[0050] S4. Calculate the error value based on the flow rate prediction value at the next moment and the target flow rate at the current moment;

[0051] S5. Calculate a flow adjustment amount according to the error value, and adjust the oxygen therapy flow according to the flow adjustment amount to make it approach the target flow value.

[0052] Specifically, different initial oxygen therapy flow rates are set for users at different stages, and oxygen therapy is output at the preset initial flow rate. Since the initial oxygen therapy flow rate is pre-set, it is difficult to adapt to the needs of all users. If it remains unchanged throughout the entire treatment cycle, inappropriate oxygen therapy flow rate settings may not only fail to achieve the therapeutic effect, but may also cause additional harm to the user.

[0053] Therefore, during oxygen therapy, the oxygen therapy control system can obtain the user's EIT image through the EIT imaging device, and calculate the corresponding oxygen therapy flow rate based on the current EIT image as the user's oxygen therapy target flow rate, thereby realizing real-time oxygen therapy flow rate adjustment.

[0054] Furthermore, based on the target flow obtained by executing the above steps, in order to reduce control errors, the oxygen therapy control system also introduces the Kalman filtering method. By using the difference between the predicted value and the target value as the benchmark for the controller adjustment parameters, the control system responds more quickly. Under the premise of achieving real-time adjustment of the target value, the error is minimized, thereby achieving optimal control of oxygen therapy.

[0055] Specifically, the initial flow value is used as the flow estimation value at the first moment, and the flow prediction value from the current moment to the next moment is calculated based on the flow estimation value at the current moment, and the flow estimation value at the current moment is calculated based on the flow prediction value from the previous moment to the current moment; at the first moment, its flow estimation value is the initial flow value, and the flow prediction value from the first moment to the second moment is calculated by the initial flow value. When entering the second moment, the flow estimation value of the second moment can be calculated based on the flow prediction value from the first moment to the second moment, and the flow estimation value of the second moment can be calculated based on the flow prediction value from the second moment to the third moment. When entering the third moment, the flow estimation value of the third moment can be calculated using the same algorithm, and iterative calculation is performed to obtain the flow estimation value of the current moment and the flow prediction value of the current moment to the next moment in real time.

[0056] Furthermore, after obtaining the flow prediction value for the next moment at the current moment, the error value between the flow prediction value for the next moment at the current moment and the current target flow value can be calculated, and the error value can be used as the basis for the controller adjustment parameter. Specifically, the specific flow adjustment amount can be calculated according to the error value, and the oxygen therapy flow rate can be adjusted according to the flow adjustment amount, so that the output oxygen therapy flow rate is closer to the target flow rate, thereby providing the user with the best oxygen therapy flow rate.

[0057] At present, most oxygen therapy devices mainly adjust the oxygen flow rate based on the user's blood oxygen saturation. This method is not suitable for all users. If only blood oxygen saturation is used to adjust for users in different situations, there will be many problems. For example, if the blood oxygen saturation of a user with carbon dioxide retention is low, the oxygen therapy device will increase the flow rate, which will reduce the user's respiratory excitability and cause carbon dioxide retention to worsen. A larger oxygen therapy flow rate will reduce the gas support of the user's alveoli, which may cause atelectasis. In addition, there is a certain measurement delay in monitoring blood oxygen saturation, and it cannot reflect the user's lung ventilation status.

[0058] In this embodiment, an oxygen therapy control system is designed. The oxygen therapy control system obtains the effective oxygen therapy time of the oxygen therapy unit at the initial flow rate in real time by acquiring EIT images, and calculates the target output flow rate of the device through the EIT images, thereby achieving real-time adjustment of the output flow rate of the oxygen therapy unit and improving the output accuracy of the oxygen therapy unit. Furthermore, by introducing Kalman filtering technology, the difference between the predicted value and the target value is used as the benchmark for controlling the adjustment parameters, making the control system respond more quickly, effectively reducing the control error, and thus achieving optimal control of the flow output.

[0059] In one embodiment, reference Figure 2 The oxygen therapy control system obtains the target flow rate of the user's oxygen therapy according to the EIT image, which specifically includes the following steps:

[0060] S21. Experimentally obtain the linear relationship between global impedance change, regional ventilation delay index, and flow rate to obtain a characterization model;

[0061] S22. Calculate the impedance value and regional ventilation delay index corresponding to the pixel point in the EIT image, and obtain the flow rate corresponding to the impedance value and regional ventilation delay index in the characterization model as the target flow rate.

[0062] Specifically, as shown by the changes in the existing 60-minute EIT data of oxygen therapy, the two evaluation indicators of global impedance change and regional ventilation delay show a strong correlation with the oxygen therapy trend, that is, there is a large correlation between the global impedance change, regional ventilation delay index and flow. Through experiments and recording a large amount of indicator data during oxygen therapy, the specific linear relationship between the global impedance change, regional ventilation delay index and flow can be obtained, and this linear relationship is used as a linear representation model between the oxygen therapy flow and the EIT image indicator, so as to facilitate the subsequent acquisition of the oxygen therapy flow value corresponding to different EIT image indicators based on the linear correlation between the global impedance change, regional ventilation delay index and flow.

[0063] The experiment shows that the ventilation ratio of the entire dorsal area is more reliable for the oxygen therapy trend, and the linear relationship between the EIT image index and the oxygen therapy flow rate is:

[0064] f (flow) =a(GIV d +RVD)+b

[0065] Among them, f (flow) is the oxygen therapy flow rate, GIV d is the end-inspiratory trend diagram of the EIT image, and RVD is the regional ventilation delay index.

[0066] The end-inspiratory trend graph in the EIT image represents the ventilation proportion of the entire dorsal area, and can effectively reflect the spatial distribution of regional lung ventilation. By analyzing the end-inspiratory trend graph and regional ventilation delay index in the EIT image and calculating the above-mentioned characterization model, the optimal oxygen therapy flow corresponding to this state can be determined as the target flow value for system flow control.

[0067] In one embodiment, the oxygen therapy control system calculates the impedance value corresponding to the pixel point in the EIT image, specifically by the following formula:

[0068]

[0069] Among them, GIV i is the impedance value corresponding to the i-th pixel, N is the number of breaths in the cycle, ΔZ i1is the impedance value of the i-th pixel at the end of inspiration during the n-th breath, ΔZ i2 is the impedance value at the end of expiration of the i-th pixel during the n-th breath.

[0070] Specifically, the above formula is used to calculate the impedance value corresponding to the pixel point in electrical impedance tomography. The impedance value corresponding to the pixel point in electrical impedance tomography can be used to evaluate the user's lung ventilation during the respiratory cycle, thereby guiding the adjustment of the user's oxygen therapy flow; GIV i is the impedance value corresponding to the i-th pixel, which is the average value of the impedance change of the pixel during the respiratory cycle; N represents the number of breaths in the cycle, which is used to calculate the average value; ΔZ i1 is the impedance value of the i-th pixel at the end of inspiration during the n-th breath, ΔZ i2 is the impedance value of the i-th pixel at the end of expiration during the n-th breath, ΔZ i1 and ΔZ i2 The difference between the two values ​​is used to represent the impedance change of the pixel point during a respiratory cycle; by calculating the impedance value of each pixel point, the ventilation distribution map of the entire lung can be depicted, which can better understand the user's lung function. This quantitative evaluation method can be used to optimize oxygen therapy flow settings, monitor the user's lung ventilation status, and timely adjust the oxygen therapy target flow.

[0071] Among them, experiments have shown that the ventilation ratio of the entire dorsal area can more effectively reflect the spatial distribution of regional lung ventilation and is more reliable.

[0072] In one embodiment, the oxygen therapy control system calculates the regional ventilation delay index corresponding to the pixel point in the EIT image, specifically by the following formula:

[0073]

[0074] Among them, t j,40％ T is the time required for the jth pixel of the lung to reach 40% of its maximum inspiratory impedance value. 40％ is the inspiratory time of the global impedance.

[0075] Specifically, the regional ventilation delay index is an important indicator for evaluating lung ventilation conditions. In electrical impedance tomography, the regional ventilation delay index is usually used to describe the time delay between different regions during ventilation. It can reflect the asynchrony or abnormality of ventilation between different regions of the lungs and other regions. By calculating the regional ventilation delay index, the optimal oxygen therapy flow corresponding to the regional ventilation delay index can be found in the characterization model as the target flow.

[0076] In one embodiment, the oxygen therapy control system calculates the flow rate prediction value at the current moment for the next moment based on the flow rate estimation value at the current moment, specifically according to the following formula:

[0077]

[0078] in, is the traffic forecast value at time n for time n+1, is the estimated flow rate at time n, For PID control as a function of time t.

[0079] The estimated flow rate at the current moment is calculated based on the flow rate prediction value at the previous moment, specifically according to the following formula:

[0080]

[0081] in, K is the traffic forecast value at time n-1 for time n, n is the Kalman gain, Z n is the actual flow value at time n.

[0082] Specifically, by introducing the one-dimensional Kalman filter result as the coefficient K in the PID controller p , K i , K d The Kalman filter is an algorithm for state estimation of dynamic systems. By combining the dynamic model of the system and the actual measurement data, the algorithm can provide the optimal estimate of the system state. It first needs to establish a dynamic model of the system to describe how the system state evolves over time. It usually includes state equations and observation equations. The state equation is used to describe the evolution law of the system state, and the observation equation is used to describe the relationship between the system state and the measurement value.

[0083] In the step of calculating the flow prediction value of the next moment based on the flow estimation value at the current moment, which is the prediction step in the Kalman filter model, the dynamic model of the system and the previous state estimation are used, that is, through the formula And the flow estimation value at time n, predict the next state of the system. This step will produce the predicted state and the predicted state covariance; in the step of calculating the flow estimation value at the current moment based on the flow prediction value at the previous moment, it is the update step in the Kalman filter model, comparing the predicted state with the actual measured value, through the formula The actual flow value measured in the process is used to correct the system state, which will produce the optimal state estimation and state covariance.

[0084] Furthermore, the Kalman gain is used to weigh the information between the system model prediction value and the actual measurement value. Its calculation is based on the covariance of the system's state estimation error and the measurement error, so as to better integrate the information of the two in the update step. The Kalman gain is a matrix used to fuse the system's prediction value and the actual measurement value to obtain the optimal state estimate. The Kalman gain determines the degree of dependence of the system on the system model prediction and the actual measurement value in the update step. The larger the value of the gain matrix, the greater the influence of the system on the measurement value when updating the state estimate.

[0085] Among them, the Kalman filter algorithm is an iterative process. By continuously repeating the prediction step and the update step, the estimation of the system state can be gradually optimized, that is, by continuously calculating the flow prediction value of the current moment to the next moment based on the flow estimation value at the current moment, and calculating the flow estimation value at the current moment based on the flow prediction value of the previous moment to the current moment, the estimation of the system state can be gradually optimized.

[0086] In the initial state, set an initial value of the Kalman gain, that is, the filter coefficient. Take K0 = 0.5 as an example. In the 0th iteration calculation, set K0 = 0.5. Before oxygen therapy, the doctor sets an initial oxygen therapy flow rate based on experience. After the flow rate stabilizes, start the initial oxygen therapy flow rate. For oxygen therapy for users, the system sets the core flow target value q0 according to the indicators on the EIT image, and further predicts the flow rate at the next moment The error between the predicted value and the target value is set to The fuzzy PID controller adjusts the oxygen therapy flow rate according to the error value e0.

[0087] In the first iteration calculation, the current oxygen therapy flow measurement value is measured, recorded as Z1, and the current estimated value is calculated using the state update equation, that is, through the formula The current estimate Compared with previous estimates Compare them. If the difference between the two is large, adjust the Kalman gain according to the specific size, and set a new oxygen therapy target flow value q1 according to the EIT index. Further, predict the flow at the next moment The error between the predicted value and the target value is set to The fuzzy PID controller adjusts the oxygen therapy flow rate according to the error value e1, and so on in subsequent iterative calculations.

[0088] In one embodiment, reference Figure 3 The oxygen therapy control system monitors the user's EIT image including the following steps:

[0089] S201, collecting user boundary voltage data, obtaining the end-inhalation image and end-expiration image of the user within a time period;

[0090] S202 : Obtain an EIT image based on the user boundary voltage data, the end-inspiratory image, and the end-expiratory image.

[0091] Specifically, for users at different stages, the doctor will set different initial oxygen therapy flow rates, and record the initial oxygen therapy flow rate given by the doctor as the initial flow rate value. At the same time, the EIT imaging module begins to collect the user's boundary voltage data, and uses the user's boundary voltage data to solve the image of the user at the end of inhalation during oxygen therapy to form a global impedance curve, and perform second-order difference identification on the peaks and troughs that appear in the voltage and global impedance curves, and calculate the conductivity matrix. Finally, the conductivity matrix is ​​converted into a pixel matrix through the image reconstruction algorithm and updated to the video memory on the display screen of the EIT imaging module.

[0092] In one embodiment, reference Figure 4 The iterative process of obtaining the EIT image based on the user boundary voltage data, the end-inspiratory image, and the end-expiratory image performed by the oxygen therapy control system includes the following steps:

[0093] S2021. Sum the boundary voltage data to obtain a global impedance curve, and identify peaks and valleys in the voltage and global impedance curves by second-order difference.

[0094] S2022. Calculate the conductivity matrix according to the formula S×(V1-V0), where S is the Jacobian matrix, V1 is the peak in the global impedance curve, and V0 is the trough in the global impedance curve;

[0095] S2023. Convert the conductivity matrix into a pixel matrix through an image reconstruction algorithm to obtain an EIT image.

[0096] Specifically, a large amount of boundary voltage data will be collected during a breathing cycle. By summing the collected boundary voltage data, a global impedance curve representing the overall resistance change of the system can be obtained to show the overall change of impedance in the system. Second-order difference is a method for processing time series data. By performing two differential operations on the boundary voltage data, the extreme points in the data, i.e., the peaks and troughs in the global impedance curve, can be identified. The peaks and troughs in the global impedance curve are calculated based on the conductivity matrix, specifically by inferring the conductivity distribution of the user's lungs through the measured voltage data, so as to establish the relationship between the measured data and the conductivity distribution, and then reconstruct the conductivity distribution image. In the EIT image reconstruction process, the conductivity matrix is ​​used to perform an image reconstruction algorithm to convert it into a pixel matrix to obtain an EIT image.

[0097] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0098] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0099] It should be understood that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Those skilled in the art may modify the technical solutions described in the above embodiments, or replace some of the technical features therein with equivalents; and all these modifications and replacements should fall within the scope of protection of the claims attached to the present invention.

Claims

1. An oxygen therapy control system, characterized in that: include: An EIT imaging unit, an oxygen therapy unit, and a control unit, wherein the EIT imaging unit is used to collect user boundary voltage data to obtain the user's EIT image, the oxygen therapy unit is used to provide a gas source and a gas transmission channel, and the control unit is connected to the EIT imaging unit and the oxygen therapy unit respectively for system data calculation; the control unit includes a fuzzy PID controller for calculating a flow adjustment amount according to an error value, a Kalman filter for calculating a flow prediction value and a flow estimation value, and a main controller; wherein the oxygen therapy control system performs the following steps: Preset initial flow rate; The linear relationship between global impedance change, regional ventilation delay index and flow rate was obtained experimentally to obtain a characterization model; Obtain the user's EIT image, calculate the impedance value and regional ventilation delay index corresponding to the pixel point in the EIT image, and obtain the flow rate corresponding to the impedance value and regional ventilation delay index in the characterization model as the target flow rate; The initial flow value is used as the flow estimate value at the first moment, and the flow prediction value of the current moment to the next moment is calculated based on the flow estimate value at the current moment, and the flow estimate value of the current moment is calculated based on the flow prediction value of the previous moment to the current moment; Calculate the error value based on the traffic prediction value at the next moment and the target traffic at the current moment; The flow adjustment amount is calculated according to the error value, and the oxygen therapy output flow is adjusted according to the flow adjustment amount to make it approach the target flow value.

2. The oxygen therapy control system according to claim 1, characterized in that: The calculation of the impedance value corresponding to the pixel point in the EIT image performed by the oxygen therapy control system is specifically calculated by the following formula: Among them, GIV i is the impedance value corresponding to the i-th pixel, N is the number of breaths in the cycle, ΔZ i1 is the impedance value of the i-th pixel at the end of inspiration during the n-th breath, ΔZ i2 is the impedance value at the end of expiration of the ith pixel during the nth breath.

3. The oxygen therapy control system according to claim 1, characterized in that: The calculation of the regional ventilation delay index corresponding to the pixel point in the EIT image performed by the oxygen therapy control system is specifically calculated by the following formula: Among them, t j,40％ T is the time required for the jth pixel of the lung to reach 40% of its maximum inspiratory impedance value. 40％ is the inspiratory time of the global impedance.

4. The oxygen therapy control system according to claim 1, characterized in that: The oxygen therapy control system performs the calculation of the flow rate prediction value at the current moment for the next moment based on the flow rate estimation value at the current moment according to the following formula: in, is the traffic forecast value at time n for time n+1, is the estimated flow rate at time n, For PID control as a function of time t.

5. The oxygen therapy control system according to claim 1, characterized in that: The oxygen therapy control system performs the calculation of the estimated flow rate at the current moment based on the flow rate prediction value at the previous moment according to the following formula: in, K is the traffic forecast value at time n-1 for time n, n is the Kalman gain, Z n is the actual flow value at time n.

6. The oxygen therapy control system according to claim 1, characterized in that: The oxygen therapy control system further performs the following steps: Collecting user boundary voltage data to obtain the user's end-inhalation image and end-expiration image at the current moment; The EIT image is obtained based on the boundary voltage data, end-inspiratory image and end-expiratory image.

7. The oxygen therapy control system according to claim 6, characterized in that: The oxygen therapy control system further performs the following steps: The boundary voltage data are summed to obtain a global impedance curve, and the peaks and valleys in the global impedance curve are identified by second-order differences; The conductivity matrix is ​​calculated according to the formula S×(V1-V0), where S is the Jacobian matrix, V1 is the peak in the global impedance curve, and V0 is the trough in the global impedance curve; The conductivity matrix is ​​converted into a pixel matrix through an image reconstruction algorithm to obtain an EIT image.

Images