Medical atomizer salt mist concentration detection method and device
By combining the deep neural network model with the nebulizer control data and environmental monitoring data, the problem of uneven salt spray concentration in the nebulizer was solved, and low-cost detection of salt spray concentration and uniformity of drug absorption were achieved.
Patent Information
- Application Number
- CN202511159046.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-19
- Publication Date
- 2025-10-17
AI Technical Summary
Existing nebulizers have the problem of uneven salt spray concentration during the nebulization process, resulting in uneven drug absorption. In addition, low-cost nebulizers lack the salt spray concentration detection function and cannot accurately adjust their operation.
A deep neural network model is used to combine the atomizer control data, liquid parameters and atomization environment monitoring data. The target environmental state data is determined through the prediction model to indirectly measure the salt spray concentration.
The low-cost detection of the salt spray concentration of the nebulizer is realized, and the uniformity of drug absorption and the accuracy of detection are improved.
Smart Images
Figure CN120809134A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the field of medical devices, in particular to a medical nebulizer salt mist concentration detection method and device. BACKGROUND
[0002] In recent years, the incidence of respiratory diseases has increased in many parts of the country, and the demand for medical and health services has increased significantly. The demand for nebulization equipment in primary medical institutions is increasing. Nebulization therapy is a treatment method that uses nebulization devices to atomize liquid medicine into aerosol particles with a particle size of 0.1 to 10 microns, which are then inhaled into the airway and deposited in the lungs to prevent and treat diseases. Currently, the common nebulizer has a variety of factors that cause uneven salt mist concentration during atomization, and this uneven salt mist concentration can cause uneven drug absorption. Since low-cost nebulizers do not have a salt mist concentration detection function, it is not possible to determine the concentration of the salt mist, which makes it difficult for users to accurately adjust the operation of the nebulizer.
[0003] The above content is only used to assist in understanding the technical solutions of the present application and does not represent an acknowledgement of the above content as prior art. SUMMARY
[0004] The main purpose of the present application is to provide a medical nebulizer salt mist concentration detection method and device, which aims to detect the salt mist concentration of the nebulizer.
[0005] To achieve the above-mentioned purpose, the present application provides a medical nebulizer salt mist concentration detection method applied to an ultrasonic nebulization device, which comprises the following steps: Obtain the control data of the nebulizer at the current time, the liquid medicine parameters and the nebulization environment monitoring data, the control data including: nebulization power and working frequency, the liquid medicine parameters including: liquid medicine type and liquid medicine amount; Determine the target environment state data according to the control data, the liquid medicine parameters and the running parameter prediction model; Determine the salt mist concentration at the current time according to the target environment state data and the nebulization environment monitoring data.
[0006] Optionally, before the step of determining the running state data according to the control data, the liquid medicine parameters and the prediction model, the method further comprises: Record the historical control data, historical liquid medicine parameters and historical nebulization environment monitoring data of the nebulizer obtained at the same collection time before the current time; Train the deep neural network model according to the historical control data, historical liquid medicine parameters and historical nebulization environment monitoring data to obtain the running parameter prediction model.
[0007] Optionally, the step of training the deep neural network model according to the historical control data, the historical drug liquid parameters and the historical atomization environment monitoring data to obtain the operation parameter prediction model comprises: normalizing the historical control data, the historical drug liquid parameters and the historical atomization environment monitoring data, and grouping the historical control data, the historical drug liquid parameters and the historical atomization environment monitoring data into a training set and a test set according to a preset proportion; training a deep neural network model according to the training set to obtain an intermediate model to be tested; testing the intermediate model according to the test set to obtain a test result; when the test result reaches a preset training target, taking the intermediate model as the operation parameter prediction model.
[0008] Optionally, after the step of testing the intermediate model according to the test set to obtain a test result, the method further comprises: when the test result does not reach the preset training target, updating parameters of the deep neural network model, and returning to the step of training a deep neural network model according to the training set to obtain an intermediate model to be tested.
[0009] Optionally, the target environment state data comprises target temperature data, target humidity data and target salt mist concentration, the atomization environment monitoring data comprises temperature monitoring data and humidity monitoring data, and the step of determining the salt mist concentration according to the target environment state data and the atomization environment monitoring data comprises: when the target temperature data is equal to the temperature monitoring data and the target humidity data is equal to the humidity monitoring data, taking the target salt mist concentration as the salt mist concentration.
[0010] when the target temperature data is not equal to the temperature monitoring data or the target humidity data is not equal to the humidity monitoring data, determining the salt mist concentration according to the target temperature data, the target humidity data, the temperature monitoring data, the humidity monitoring data and the target salt mist concentration.
[0011] Optionally, the step of determining the salt mist concentration according to the target temperature data, the target humidity data, the temperature monitoring data, the humidity monitoring data and the target salt mist concentration comprises: according to the target temperature data, the target humidity data, the temperature monitoring data and the humidity monitoring data; determining the salt mist concentration according to the target salt mist concentration and a first mapping relationship.
[0012] Optionally, the step of acquiring the control data of the atomizer at the current time, the drug liquid parameter, and the atomization environment monitoring data comprises: acquiring the control data of the atomizer at the current time and the drug liquid parameter; when the control data is the same as the previous control data before the current time, collecting the atomization environment monitoring data; when the control data is not the same as the previous control data before the current time, collecting the atomization environment monitoring data after a preset time.
[0013] In addition, to achieve the above-mentioned purpose, the present application also provides a medical atomizer salt mist concentration detection device, characterized in that the medical atomizer salt mist concentration detection device comprises: an acquisition module, configured to acquire the control data of the atomizer at the current time, the drug liquid parameter, and the atomization environment monitoring data, wherein the control data comprises the atomization power and the working frequency, and the drug liquid parameter comprises the drug liquid type and the drug liquid amount; a prediction module, configured to determine the target environment state data according to the control data, the drug liquid parameter, and a running parameter prediction model; a calculation module, configured to determine the salt mist concentration at the current time according to the target environment state data and the atomization environment monitoring data.
[0014] In addition, to achieve the above-mentioned purpose, the present application also provides an ultrasonic atomization device, comprising a memory, a processor, and a medical atomizer salt mist concentration detection program stored on the memory and executable on the processor, wherein the medical atomizer salt mist concentration detection program is configured to implement the steps of the medical atomizer salt mist concentration detection method according to any one of the above-mentioned embodiments.
[0015] In addition, to achieve the above-mentioned purpose, the present application also provides a storage medium, wherein the storage medium stores a medical atomizer salt mist concentration detection program, and the medical atomizer salt mist concentration detection program, when executed by a processor, implements the steps of the medical atomizer salt mist concentration detection method according to any one of claims 1 to 7.
[0016] The present application provides a medical atomizer salt mist concentration detection method, which acquires the control data of the atomizer at the current time, the drug liquid parameter, and the atomization environment monitoring data, and determines the target environment state data according to the control data, the drug liquid parameter, and a running parameter prediction model, so as to predict the salt mist data based on the control data in the running process, and determine the salt mist concentration according to the predicted result and the target environment state data determined by the actually collected atomization environment monitoring data, thereby realizing the indirect measurement of the salt mist concentration and the low-cost measurement of the atomization data. BRIEF DESCRIPTION OF DRAWINGS
[0017] Figure 1 is a structural schematic diagram of the ultrasonic atomization device of the hardware running environment involved in the embodiment scheme of the present application. Figure 2 is a flowchart of the first embodiment of the salt mist concentration detection of the medical atomizer of the present application. Figure 3 is a flowchart of the second embodiment of the salt mist concentration detection of the medical atomizer of the present application. Figure 4 is a flowchart of the third embodiment of the salt mist concentration detection of the medical atomizer of the present application. Figure 5 is a flowchart of the fourth embodiment of the salt mist concentration detection of the medical atomizer of the present application.
[0018] The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION
[0019] It should be understood that the specific embodiments described herein are merely intended to explain the present application and are not intended to limit the present application.
[0020] Reference Figure 1 , Figure 1 is a structural schematic diagram of the ultrasonic atomization device of the hardware running environment involved in the embodiment scheme of the present application.
[0021] As shown in Figure 1 , the ultrasonic atomization device can include a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to realize the connection and communication between these components. The interactive device 1003 can include a display screen (Display) and an input unit such as a keyboard (Keyboard). The optional interactive device 1003 can also be connected with the communication bus through a standard wired interface and a wireless interface. The network interface 1004 can optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 1005 can be a high-speed random access memory (Random Access Memory, RAM) memory or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a magnetic disk memory. The memory 1005 can also be an independent storage device from the aforementioned processor 1001.
[0022] Those skilled in the art can understand that Figure 1The structure shown in the figure does not constitute a limitation on the ultrasonic atomization device, and can include more or fewer components than the figure, or combine certain components, or different component arrangements.
[0023] As shown in Figure 1 The memory 1005 as a storage medium can include an operating system, a data storage module, a network communication module, a user interface module, and a medical atomizer salt mist concentration detection program.
[0024] In the ultrasonic atomization device shown in Figure 1 The network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the ultrasonic atomization device can be arranged in the ultrasonic atomization device, and the medical atomizer salt mist concentration detection program stored in the memory 1005 is called by the processor 1001, and the medical atomizer salt mist concentration detection method provided by the embodiment of the application is executed.
[0025] The embodiment of the application provides a medical atomizer salt mist concentration detection method, which refers to Figure 2 , Figure 2 The flowchart of a first embodiment of a medical atomizer salt mist concentration detection method of the application.
[0026] In this embodiment, the gateway-based computing power allocation method comprises: Step S1, acquiring the control data of the atomizer, the liquid medicine parameter and the atomization environment monitoring data at the current time, the control data comprising: atomization power and working frequency, the liquid medicine parameter comprising: liquid medicine type and liquid medicine amount; For the atomizer can be selected by the user different working gear, different working gear generated by the salt fog concentration is not the same, at the same time due to different liquid parameters, will also affect the concentration of salt fog in a certain extent. In this embodiment, the working frequency here refers to the oscillation frequency of the ultrasonic atomizer, and the atomization power here refers to the power consumed by the atomizer when working. Because the corresponding properties of different types of liquid medicine are different, for example: the viscosity and surface tension of the liquid medicine will be different, because the maximum capacity of the atomizing cup is generally 10 milliliters and there is generally 1 milliliter of remaining medicine, therefore, the amount of liquid medicine is generally 1 milliliter to 10 milliliters. The corresponding capacity of different atomizing cups is actually not the same. The atomization environment monitoring data here refers to the physical parameters in the environment of generating atomized particles: for example: temperature, humidity, air pressure, etc. The physical parameters in the environment of generating atomized particles here do not include the salt fog concentration. This is because the traditional salt fog concentration detection method often needs to set up a scattering-based optical acquisition system, by measuring the light intensity of the scattered light, through the calculation formula of light intensity and salt fog concentration, to calculate the concentration of the salt fog generated by the atomizer. The type of control data is not limited, and optionally, the running time, i.e. the continuous running time of the atomizer, and the working mode can also be included. The liquid medicine parameter can also be the height of the liquid medicine. Because the atomization is carried out by ultrasonic vibration, the atomization process actually generates tiny drug particles through the vibration of the liquid surface, and thus the height of the liquid medicine will affect the running effect of the atomizer.
[0027] Step S2, determining target environment state data according to the control data, the liquid medicine parameter and the running parameter prediction model; In this embodiment, specifically, the control data and the liquid medicine parameter are input into the running parameter prediction model, and the running parameter prediction model outputs target environment state data. The target environment state data here refers to the physical data inside the atomizer predicted under the current control data and the current liquid medicine parameter. The running parameter prediction model is used to predict more than one parameter, rather than only one parameter.
[0028] Step S3, determining the salt fog concentration at the current time according to the target environment state data and the atomization environment monitoring data.
[0029] In the embodiment, whether the target environment state data is accurate is determined according to the target environment state data and the atomization environment monitoring data actually detected, specifically, whether each data in the target environment state data is in a reasonable interval is determined by using the atomization environment monitoring data respectively, when it is identified that the temperature and the humidity of the atomization environment monitoring data are equal to the data actually detected, it is determined that the atomization environment monitoring data is accurate, so that the target salt mist concentration in the atomization environment monitoring data is taken as the salt mist concentration. It should be noted that the target environment state data is predicted data, therefore, when it is identified that the error between the temperature and the humidity of the atomization environment monitoring data and the data actually detected is within a certain range in the actual execution process, the salt mist concentration can be generated by the atomization environment monitoring data and the target salt mist concentration.
[0030] In the embodiment, the control data of the atomizer at the current moment, the liquid medicine parameter and the atomization environment monitoring data are acquired, and the target environment state data is determined according to the control data, the liquid medicine parameter and the running parameter prediction model, so that the prediction of the salt mist data can be realized based on the control data in the running process, and the salt mist concentration is determined according to the predicted result and the target environment state data determined by the atomization environment monitoring data actually collected, so that the indirect measurement of the salt mist concentration can be realized, and the low-cost measurement of the running data of the atomizer can be realized.
[0031] Further, based on the first embodiment, a second embodiment of the medical atomizer salt mist concentration detection method is provided, in the embodiment, referring to Figure 3 , before the step of determining the running state data according to the control data, the liquid medicine parameter and the prediction model, the method further comprises: Step S201, record the historical control data, the historical liquid medicine parameter and the historical atomization environment monitoring data of the atomizer acquired at the same acquisition time before the current moment; In the embodiment, the salt mist concentration in the historical atomization environment monitoring data is detected by the external detection salt mist concentration detection device. It should be noted that the type of the detection device is not limited, preferably, the salt mist concentration in the historical atomization environment monitoring data can be detected by backscattering. The accuracy of the detected salt mist concentration can be improved by the external detection device. The running parameter prediction model is obtained by training based on the data collected in the measurement process before the current moment. The historical control data, the historical liquid medicine parameter and the historical atomization environment monitoring data are all data for training the model. The historical control data, the historical liquid medicine parameter and the historical atomization environment monitoring data are all data for training the model, and are detected at the same time, so that the data is corresponding to each other.
[0032] Step S202, training the deep neural network model according to the historical control data, historical drug liquid parameters and historical atomization environment monitoring data, and obtaining the running parameter prediction model.
[0033] Specifically, the historical control data and historical drug liquid parameters are taken as model inputs, and the historical atomization environment monitoring data is taken as model output, and the deep neural network model is trained.
[0034] In the embodiment, the historical control data, historical drug liquid parameters and historical atomization environment monitoring data of the atomizer obtained at the same collection time before the current time are recorded, the deep neural network model is trained according to the historical control data, historical drug liquid parameters and historical atomization environment monitoring data, and the running parameter prediction model is obtained, so that the accuracy of the running parameter prediction model obtained by training can be improved.
[0035] Further, the step of training the deep neural network model according to the historical control data, historical drug liquid parameters and historical atomization environment monitoring data to obtain the running parameter prediction model comprises: normalizing the historical control data, historical drug liquid parameters and historical atomization environment monitoring data, and grouping the historical control data, historical drug liquid parameters and historical atomization environment monitoring data into a training set and a test set according to a preset proportion; By normalization processing, the range of the collected atomization power and working frequency is mapped to the same range, which can be specifically an interval of 0 to 1. 70% of the historical control data, historical drug liquid parameters and historical atomization environment monitoring data are taken as the training set, and 30% of the historical control data, historical drug liquid parameters and historical atomization environment monitoring data are taken as the test set.
[0036] Training the deep neural network model according to the training set to obtain an intermediate model to be tested; Initializing the deep neural network model, setting training parameters such as learning rate, etc. The historical control data and historical drug liquid parameters are input into the deep neural network model, the output and loss value are calculated, and the weights of the model are adjusted according to the loss value by direction propagation.
[0037] According to the test set, the intermediate model is tested to obtain a test result; The weights of the model are not adjusted in the test of the test set, the accuracy of the output of the intermediate model is calculated, when the test result of the output is only different from the historical atomization environment monitoring data of the test set by less than or greater than a preset judgment threshold, the output result is determined to be correct; when the test result of the output is only different from the historical atomization environment monitoring data of the test set by greater than the preset judgment threshold, the output result is determined to be incorrect. In other embodiments, the mean square error or the absolute error of the output result and the historical atomization environment monitoring data can also be calculated.
[0038] When the test result is that the preset training target is reached, the intermediate model is taken as the running parameter prediction model.
[0039] Specifically, when the accuracy is higher than a preset accuracy threshold, the intermediate model is taken as the running parameter prediction model.
[0040] In the embodiment, after the step of testing the intermediate model according to the test set to obtain a test result, the method further includes: When the test result is that the preset training target is not reached, the parameters of the deep neural network model are updated, and the step of training the deep neural network model according to the training set to obtain the intermediate model to be tested is performed again.
[0041] By adjusting the index data of training, the deep neural network model can reach the target index, so as to improve the accuracy of the running parameter prediction model.
[0042] Further, based on the first embodiment or the second embodiment, a third embodiment of the medical atomizer salt mist concentration detection method is proposed, referring to Figure 4 The target environment state data includes target temperature data, target humidity data and target salt mist concentration, the atomization environment monitoring data includes temperature monitoring data and humidity monitoring data, and the step of determining the salt mist concentration according to the target environment state data and the atomization environment monitoring data includes: Step S31, when the target temperature data is equal to the temperature monitoring data, and the target humidity data is equal to the humidity monitoring data, the target salt mist concentration is taken as the salt mist concentration.
[0043] In the embodiment, whether each output target environment state data is accurate is determined by comparing the output data of the model with the monitoring data, specifically, when the target temperature data and the target humidity data are determined to be accurate, other data in the target environment state data is also determined to be accurate, so that the target salt mist concentration data in the target environment state data is taken as the salt mist concentration data.
[0044] Step S32, when the target temperature data is equal to the temperature monitoring data, or when the target humidity data is equal to the humidity monitoring data, determining the salt mist concentration according to the target temperature data, the target humidity data, the temperature monitoring data, the humidity monitoring data and the target salt mist concentration.
[0045] When there is a difference between the target environment state data and the atomization environment monitoring data, the salt mist concentration is determined by the relationship between the target temperature data, the target humidity data and the target salt mist concentration, and the temperature monitoring data and the humidity monitoring data.
[0046] Further, the step of determining the salt mist concentration according to the target temperature data, the target humidity data, the temperature monitoring data, the humidity monitoring data and the target salt mist concentration comprises: According to the target temperature data, the target humidity data, the temperature monitoring data and the humidity monitoring data. Preferably, when the first ratio of the target temperature data to the temperature monitoring data is equal to the second ratio of the target humidity data to the humidity monitoring data in a preset ratio interval, the average ratio of the first ratio of the target temperature data to the temperature monitoring data and the second ratio of the target humidity data to the humidity monitoring data is calculated, and the first mapping relationship is a mapping coefficient, and the mapping coefficient is the average ratio.
[0047] The salt mist concentration is determined according to the target salt mist concentration and the first mapping relationship.
[0048] Specifically, the salt mist concentration is obtained by multiplying the target salt mist concentration and the mapping coefficient.
[0049] In this embodiment, even if the output target environment state data has a certain error, the accuracy of the obtained salt mist concentration can be improved by combining the atomization environment monitoring data for correction.
[0050] Further, based on any of the above embodiments, a fourth embodiment of a medical atomizer salt mist concentration detection method is proposed, referring to Figure 5 The step of obtaining the control data, the liquid medicine parameter and the atomization environment monitoring data of the atomizer at the current time comprises: Step S11, obtaining the control data and the liquid medicine parameter of the atomizer at the current time; The liquid medicine type can be set by the user, and the corresponding liquid medicine parameter is used by default after the first setting. In particular, the content of the liquid medicine is obtained by real-time detection of a sensor. The control data of the atomizer is stored in the storage unit of the atomizer and can be directly used. Step S12, when the control data is the same as the previous control data before the current time, the atomization environment monitoring data is collected; Specifically, when the control data is the same as the data 1 minute before the current time, the atomization environment monitoring data can be collected Step S13, when the control data is not the same as the previous control data before the current time, the atomization environment monitoring data is collected after a preset time.
[0051] The purpose of collecting after a preset time is to avoid the problem of atomization environment monitoring data fluctuation caused by the fact that the environment inside the atomizer has not changed stably after the control data changes, so as to improve the accuracy of the atomization environment monitoring data.
[0052] In addition, the embodiment of the present application also provides a medical atomizer salt mist concentration detection device, the medical atomizer salt mist concentration detection device comprises: An acquisition module is configured to acquire control data, liquid medicine parameters and atomization environment monitoring data of an atomizer at a current time, wherein the control data comprises atomization power and working frequency, and the liquid medicine parameters comprise liquid medicine type and liquid medicine amount; A prediction module is configured to determine target environment state data according to the control data, the liquid medicine parameters and a running parameter prediction model; A calculation module is configured to determine a salt mist concentration at the current time according to the target environment state data and the atomization environment monitoring data.
[0053] In addition, the embodiment of the present application also provides an ultrasonic atomization device, which comprises a memory, a processor and a medical atomizer salt mist concentration detection program stored in the memory and executable on the processor, and the medical atomizer salt mist concentration detection program is configured to implement the steps of the medical atomizer salt mist concentration detection method according to any one of the above.
[0054] In addition, the embodiment of the present application also provides a storage medium, and the storage medium stores a medical atomizer salt mist concentration detection program, and the medical atomizer salt mist concentration detection program implements the steps of the medical atomizer salt mist concentration detection method according to any one of the above when executed by a processor.
[0055] It should be noted that, in this document, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or system that comprises the identified element.
[0056] The above-mentioned embodiment numbers of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments.
[0057] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be realized by means of software and the necessary general hardware platform, and of course, they can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) as described above, and includes a number of instructions for making a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) execute the methods described in the various embodiments of the present application.
[0058] The above is only the preferred embodiment of the present application, and does not limit the patent scope of the present application, and any equivalent structure or equivalent process transformation, or direct or indirect application in other related technical fields, which is made by using the content of the specification and drawings of the present application, is also included in the patent protection scope of the present application.
Claims
1. A method for detecting salt spray concentration of a medical nebulizer, characterized in that: Applied to an ultrasonic atomization device, the medical atomizer salt spray concentration detection method comprises the following steps: Obtaining the current atomizer control data, liquid parameters, and atomization environment monitoring data, wherein the control data includes atomization power and operating frequency, and the liquid parameters include liquid type and liquid volume; Determining target environmental state data based on the control data, the liquid medicine parameters, and the operating parameter prediction model; The salt spray concentration at the current moment is determined according to the target environment state data and the atomization environment monitoring data.
2. The method for detecting salt spray concentration of a medical nebulizer according to claim 1, wherein: Before the step of determining the operating status data according to the control data, the liquid medicine parameters and the prediction model, the method further includes: Record the historical control data, historical liquid parameters and historical atomization environment monitoring data of the nebulizer before the current moment and acquired at the same collection time; The deep neural network model is trained according to the historical control data, historical liquid medicine parameters and historical atomization environment monitoring data to obtain the operating parameter prediction model.
3. The method for detecting salt spray concentration of a medical nebulizer according to claim 2, wherein: The step of training the deep neural network model based on the historical control data, historical liquid medicine parameters, and historical atomization environment monitoring data to obtain the operating parameter prediction model includes: Normalizing the historical control data, historical liquid medicine parameters, and historical atomization environment monitoring data, and grouping the historical control data, historical liquid medicine parameters, and historical atomization environment monitoring data into a training set and a test set according to a preset ratio; Training a deep neural network model according to the training set to obtain an intermediate model to be tested; Testing the intermediate model according to the test set to obtain a test result; When the test result reaches the preset training target, the intermediate model is used as the operating parameter prediction model.
4. The method for detecting salt spray concentration of a medical nebulizer according to claim 3, wherein: After the step of testing the intermediate model according to the test set to obtain the test result, the method further includes: When the test result shows that the preset training target is not achieved, the parameters of the deep neural network model are updated, and the step of training the deep neural network model according to the training set to obtain an intermediate model to be tested is returned.
5. The method for detecting salt spray concentration of a medical nebulizer according to claim 1, wherein: The target environmental state data includes target temperature data, target humidity data, and target salt spray concentration. The atomization environment monitoring data includes temperature monitoring data and humidity monitoring data. The step of determining the salt spray concentration based on the target environmental state data and the atomization environment monitoring data includes: When the target temperature data is equal to the temperature monitoring data, and the target humidity data is equal to the humidity monitoring data, the target salt mist concentration is used as the salt mist concentration. When the target temperature data is not equal to the temperature monitoring data, or when the target humidity data is not equal to the humidity monitoring data, the salt spray concentration is determined according to the target temperature data, the target humidity data, the temperature monitoring data, the humidity monitoring data and the target salt spray concentration.
6. The method for detecting salt spray concentration of a medical nebulizer according to claim 5, wherein: The step of determining the salt mist concentration according to the target temperature data, the target humidity data, the temperature monitoring data, the humidity monitoring data and the target salt mist concentration comprises: According to the target temperature data, the target humidity data, the temperature monitoring data and the humidity monitoring data; The salt mist concentration is determined according to the target salt mist concentration and a first mapping relationship.
7. The method for detecting salt spray concentration of a medical nebulizer according to claim 1, wherein: The step of obtaining the current atomizer control data, liquid parameters, and atomization environment monitoring data includes: Obtain the current control data and liquid parameters of the atomizer; When the control data is the same as the previous control data before the current moment, collecting the atomization environment monitoring data; When the control data is different from the previous control data before the current moment, the atomization environment monitoring data is collected after a preset time.
8. A medical nebulizer salt spray concentration detection device, characterized in that: The medical nebulizer salt spray concentration detection device comprises: An acquisition module is used to obtain the current atomizer control data, liquid parameters, and atomization environment monitoring data. The control data includes: atomization power and operating frequency. The liquid parameters include: liquid type and liquid volume. A prediction module, configured to determine target environmental state data based on the control data, the liquid medicine parameters, and an operating parameter prediction model; The calculation module is used to determine the salt spray concentration at a current moment according to the target environment state data and the atomization environment monitoring data.
9. An ultrasonic atomization device, characterized in that: The ultrasonic atomization device includes: a memory, a processor, and a medical nebulizer salt mist concentration detection program stored in the memory and executable on the processor, wherein the medical nebulizer salt mist concentration detection program is configured to implement the steps of the medical nebulizer salt mist concentration detection method according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium stores a medical nebulizer salt spray concentration detection program, which, when executed by a processor, implements the steps of the medical nebulizer salt spray concentration detection method according to any one of claims 1 to 7.