Hyperbaric chamber management method and system based on multi-dimensional data

Abstract

The application discloses a hyperbaric oxygen chamber management method and system based on multidimensional data, relates to the technical field of data processing, and comprises the following steps: acquiring real-time pressure data, oxygen concentration and oxygen supply management records of a target hyperbaric oxygen chamber, and management records of preset fault types, performing cascade learning, obtaining a plurality of integrated oxygen supply calibration models and a plurality of integrated fault prediction models, and comparing and analyzing to determine a target integrated oxygen supply calibration model and a target integrated fault prediction model; analyzing the oxygen concentration in the target hyperbaric oxygen chamber and the real-time pressure data, outputting oxygen supply calibration information and fault prediction information of the target hyperbaric oxygen chamber, and performing multidimensional management on the target hyperbaric oxygen chamber. The application solves the technical problems of low accuracy and low use safety of the hyperbaric oxygen chamber in the prior art, and achieves the technical effect of improving the accuracy and use safety of hyperbaric oxygen chamber management based on multidimensional data.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a hyperbaric oxygen chamber management method and system based on multi-dimensional data. BACKGROUND

[0002] The hyperbaric oxygen chamber is a special medical equipment for hyperbaric oxygen therapy, which is divided into air pressurized chamber and pure oxygen pressurized chamber according to the pressurized medium. By placing the human body in a chamber and inhaling oxygen under high pressure, the purpose of treating diseases is achieved, and the application range is very wide. Compared with ordinary oxygen inhalation, hyperbaric oxygen has greater strength and better effect, and also has antibacterial effect.

[0003] However, the use and operation management of the hyperbaric oxygen chamber still has the problem that the management operation is not intelligent enough. SUMMARY

[0004] The present application provides a hyperbaric oxygen chamber management method and system based on multi-dimensional data, which is used to solve the technical problem of low accuracy and safety in the management of the hyperbaric oxygen chamber in the prior art.

[0005] The first aspect of the present application provides a hyperbaric oxygen chamber management method based on multi-dimensional data, the method comprising: acquiring real-time pressure data of a target hyperbaric oxygen chamber through the pressure detection device, wherein the real-time pressure data has a temperature attribute; determining the oxygen concentration in the target hyperbaric oxygen chamber based on the determination of the oxygen content in the target hyperbaric oxygen chamber by gas chromatography; obtaining the oxygen supply management record of the target hyperbaric oxygen chamber based on the mapping relationship between the real-time pressure data and its temperature attribute and the oxygen concentration in the target hyperbaric oxygen chamber; obtaining the management log of the target hyperbaric oxygen chamber, wherein the management log of the target hyperbaric oxygen chamber includes M periodic management records, wherein M is an integer greater than 1, and the M periodic management records include the oxygen supply management record of the target hyperbaric oxygen chamber and the management record of the preset fault type; analyzing the M periodic management records to obtain a periodic management data set, and performing cascade learning on the periodic management data set to obtain a set of oxygen supply management calibration models and a set of target fault prediction models, wherein the set of oxygen supply management calibration models includes V calibration models, and the set of target fault prediction models includes N prediction models, wherein V is an integer greater than 1, and N is an integer greater than 1; performing integrated fusion analysis on the V calibration models and the N prediction models respectively to obtain a plurality of integrated oxygen supply calibration models and a plurality of integrated fault prediction models, and determining a target integrated oxygen supply calibration model and a target integrated fault prediction model by comparative analysis; analyzing the oxygen concentration in the target hyperbaric oxygen chamber and the real-time pressure data through the target integrated oxygen supply calibration model and the target integrated fault prediction model, outputting the oxygen supply calibration information and the fault prediction information of the target hyperbaric oxygen chamber, and performing multi-dimensional management on the target hyperbaric oxygen chamber.

[0006] In a second aspect, the application provides a hyperbaric oxygen chamber management system based on multi-dimensional data, comprising: a real-time pressure data acquisition module, configured to acquire real-time pressure data of a target hyperbaric oxygen chamber through the pressure detection device, wherein the real-time pressure data has a temperature attribute; an oxygen concentration determination module, configured to determine the oxygen concentration in the target hyperbaric oxygen chamber based on gas chromatography; an oxygen supply management record acquisition module, configured to acquire the oxygen supply management record of the target hyperbaric oxygen chamber based on the mapping relationship between the real-time pressure data and its temperature attribute and the oxygen concentration in the target hyperbaric oxygen chamber; a regular management record acquisition module, configured to acquire the management log of the target hyperbaric oxygen chamber, wherein the management log of the target hyperbaric oxygen chamber comprises M regular management records, wherein M is an integer greater than 1, and the M regular management records comprise the oxygen supply management record of the target hyperbaric oxygen chamber and the management record of a preset fault type; a model set acquisition module, configured to analyze the M regular management records to obtain a regular management data set, and perform cascaded learning on the regular management data set to obtain an oxygen supply management calibration model set and a target fault prediction model set, wherein the oxygen supply management calibration model set comprises V calibration models, and the target fault prediction model set comprises N prediction models, wherein V is an integer greater than 1, and N is an integer greater than 1; a target integrated prediction model acquisition module, configured to respectively perform integrated fusion analysis on the V calibration models and the N prediction models to obtain a plurality of integrated oxygen supply calibration models and a plurality of integrated fault prediction models, and determine a target integrated oxygen supply calibration model and a target integrated fault prediction model through comparative analysis; and a multi-dimensional management module, configured to analyze the oxygen concentration in the target hyperbaric oxygen chamber and the real-time pressure data through the target integrated oxygen supply calibration model and the target integrated fault prediction model, output oxygen supply calibration information and fault prediction information of the target hyperbaric oxygen chamber, and perform multi-dimensional management on the target hyperbaric oxygen chamber.

[0007] The one or more technical solutions provided in the application have at least the following technical effects or advantages:

[0008] The high-pressure oxygen cabin management method based on multi-dimensional data provided in the application relates to the technical field of data processing, and comprises the following steps: acquiring real-time pressure data, oxygen concentration and oxygen supply management records of a target high-pressure oxygen cabin, and management records of preset fault types, performing cascade learning, obtaining a plurality of integrated oxygen supply calibration models and a plurality of integrated fault prediction models, comparing and analyzing to determine a target integrated oxygen supply calibration model and a target integrated fault prediction model, analyzing the oxygen concentration in the target high-pressure oxygen cabin and the real-time pressure data, and outputting oxygen supply calibration information and fault prediction information of the target high-pressure oxygen cabin, so as to perform multi-dimensional management on the target high-pressure oxygen cabin, and solve the technical problem of low accuracy and use safety in the prior art when the high-pressure oxygen cabin is managed, and achieve the technical effect of improving the accuracy and use safety of the management of the high-pressure oxygen cabin based on multi-dimensional data. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0010] Figure 1 The flowchart of the high-pressure oxygen cabin management method based on multi-dimensional data provided in the embodiment of the present application is shown in the figure.

[0011] Figure 2 The flowchart of acquiring the periodic management data set in the high-pressure oxygen cabin management method based on multi-dimensional data provided in the embodiment of the present application is shown in the figure.

[0012] Figure 3 The flowchart of determining the target integrated oxygen supply calibration model and the target integrated fault prediction model in the high-pressure oxygen cabin management method based on multi-dimensional data provided in the embodiment of the present application is shown in the figure.

[0013] Figure 4 The structure diagram of the high-pressure oxygen cabin management system based on multi-dimensional data provided in the embodiment of the present application is shown in the figure.

[0014] Explanation of reference numerals: real-time pressure data acquisition module 11, oxygen concentration determination module 12, oxygen supply management record acquisition module 13, periodic management record acquisition module 14, model set acquisition module 15, target integrated prediction model acquisition module 16, multi-dimensional management module 17. DETAILED DESCRIPTION

[0015] The high-pressure oxygen cabin management method based on multi-dimensional data provided in the present application is used to solve the technical problem of low accuracy and use safety in the prior art when the high-pressure oxygen cabin is managed.

[0016] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to the clearly listed steps or units, but can include other steps or modules that are not clearly listed or inherent to the process, method, product or device.

[0018] Embodiment one

[0019] As shown in Figure 1 The present application provides a hyperbaric oxygen chamber management method based on multi-dimensional data, which comprises:

[0020] S100: acquiring real-time pressure data of a target hyperbaric oxygen chamber through the pressure detection device, wherein the real-time pressure data has a temperature attribute;

[0021] Specifically, the pressure detection device installed in the target hyperbaric oxygen chamber monitors the pressure in the target hyperbaric oxygen chamber in real time, and synchronously transmits the monitoring data to the intelligent management system. The real-time pressure data of the target hyperbaric oxygen chamber can be extracted by logging into the intelligent management system. The pressure detection device is a device for monitoring the pressure in the target hyperbaric oxygen chamber, which can be a pressure gauge, a pressure monitor, a pressure sensor, etc. In a closed environment (constant volume), the higher the temperature, the higher the air pressure. Therefore, the real-time pressure data has a temperature attribute. The real-time pressure data can be used as reference data for subsequent oxygen supply management.

[0022] S200: determining the oxygen concentration in the target hyperbaric oxygen chamber based on the gas chromatography method;

[0023] Specifically, a gas chromatograph and a corresponding detector are installed in the target hyperbaric oxygen chamber, and the oxygen content in the target hyperbaric oxygen chamber is determined based on gas chromatography. Gas chromatography is a chromatographic separation and analysis method using gas as the mobile phase. The vaporized sample is carried into the chromatographic column of the gas chromatograph by the mobile phase. The fixed phase in the column and the molecules in the sample have different interaction forces, and each component flows out of the chromatographic column at different times. The components are separated from each other. An appropriate identification and recording system is used to produce a chromatogram showing the time and concentration of each component flowing out of the chromatographic column. According to the peak time and order shown in the graph, the compound can be qualitatively analyzed to determine the oxygen component. Then, based on the height and area of the peak, quantitative analysis is performed to determine the oxygen content. Then, the oxygen concentration in the target hyperbaric oxygen chamber is calculated from the oxygen content, which can be used as reference data for subsequent oxygen supply management.

[0024] S300: Obtain oxygen supply management records of the target hyperbaric oxygen chamber based on the mapping relationship between the real-time pressure data and its temperature attribute and the oxygen concentration in the target hyperbaric oxygen chamber;

[0025] Specifically, based on the mapping relationship between the real-time pressure data and its temperature attribute and the oxygen concentration in the target hyperbaric oxygen chamber, that is, the correlation of each parameter in the target hyperbaric oxygen chamber, multiple oxygen supply pressure data, oxygen supply speed data, oxygen supply concentration data, etc. of the target hyperbaric oxygen chamber are extracted from the oxygen supply management records of the target hyperbaric oxygen chamber, which are used as basic data for subsequent construction of oxygen supply management prediction model.

[0026] S400: Obtain the management log of the target hyperbaric oxygen chamber, wherein the management log of the target hyperbaric oxygen chamber includes M periodic management records, wherein M is an integer greater than 1, and the M periodic management records include oxygen supply management records of the target hyperbaric oxygen chamber and management records of preset fault types;

[0027] Specifically, the management log of the target hyperbaric oxygen chamber is retrieved from the intelligent management system. The management log includes records of multiple periodic management of the target hyperbaric oxygen chamber in the past. It is assumed that M periodic management is performed, and at least one periodic management record is obtained. The M periodic management records include oxygen supply management records of the target hyperbaric oxygen chamber and management records of preset fault types. The oxygen supply management records refer to the adjustment records of the oxygen supply pressure, oxygen supply speed, and oxygen supply concentration of the target hyperbaric oxygen chamber. The management records of the preset fault types refer to the processing records of the past faults of the target hyperbaric oxygen chamber, including fault types, fault causes, and fault handling schemes. They can be used as basic data for subsequent construction of oxygen supply management calibration model and target fault prediction model.

[0028] S500: analyze the M times of periodic management record to obtain a periodic management dataset, and perform cascade learning on the periodic management dataset to obtain an oxygen supply management calibration model set and a target fault prediction model set, wherein the oxygen supply management calibration model set includes V calibration models, and the target fault prediction model set includes N prediction models, V is an integer greater than 1, and N is an integer greater than 1;

[0029] Specifically, the M times of periodic management records are sorted, effective data in the oxygen supply management records and the management records of the preset fault type are extracted, and the periodic management dataset is arranged. The periodic management dataset is subjected to cascade learning. Cascade in computer science refers to the mapping relationship between multiple objects, and the cascade relationship between data is established to improve management efficiency. The present application finds the mapping relationship between multiple oxygen supply pressures, oxygen supply speeds and oxygen supply concentrations in the periodic management dataset, establishes multiple oxygen supply management cascade relationships, and establishes multiple oxygen supply management calibration models to form an oxygen supply management calibration model set. Similarly, the management records of multiple fault types in the periodic management dataset are found, including fault types, fault causes, fault handling schemes, and the like. Multiple fault management cascade relationships are established, and multiple target fault prediction models are established to form a target fault prediction model set. The oxygen supply management calibration model set includes V calibration models, the target fault prediction model set includes N prediction models, and at least one calibration model and one prediction model are included. The calibration model and the prediction model can be used as a basic model for subsequent integrated fusion analysis.

[0030] Further, as shown in Figure 2 the step S500 of the embodiment of the present application further includes:

[0031] S510: obtaining a preset classification coding standard;

[0032] S520: dividing the target hyperbaric oxygen chamber into types based on the preset classification coding standard to obtain a type division result;

[0033] S530: randomly extracting an oxygen chamber type in the type division result and setting it as a target oxygen chamber type;

[0034] S540: matching oxygen supply information and fault information of the target oxygen chamber type to obtain oxygen supply information and fault information of the target oxygen chamber, and assembling an oxygen chamber oxygen supply dataset and an oxygen chamber fault dataset;

[0035] S550: taking the oxygen chamber oxygen supply dataset and the oxygen chamber fault dataset as a first preset oxygen supply type and a first preset fault type;

[0036] S560: traversing the M times of periodic management records based on the first preset oxygen supply type and the first preset fault type to match first oxygen supply records and first fault records;

[0037] S570: Obtain the first oxygen supply record, the first cabin oxygen concentration information in the first failure record, the first cabin pressure information, and combine the first preset oxygen supply type and the first preset failure type to obtain the first oxygen supply training data set and the first failure training data set;

[0038] S580: According to the first oxygen supply training data set and the first failure training data set, the periodic management data set is established.

[0039] Specifically, a preset classification coding standard is obtained, which is a preset coding rule for constructing a data set, and is coded by professionals according to experience, and a classification coding standard is generated. Then, according to the preset classification coding standard, the target hyperbaric oxygen chamber is divided by type, and a type division result is obtained, that is, the type of all target hyperbaric oxygen chambers. An oxygen chamber type in the type division result is randomly extracted and set as a target oxygen chamber type. The oxygen supply information and failure information of the target oxygen chamber type are matched from the M periodic management records, and the matched oxygen supply information and failure information of the target oxygen chamber are established into an oxygen chamber oxygen supply data set and an oxygen chamber failure data set. The oxygen chamber oxygen supply data set and the oxygen chamber failure data set are used as the first preset oxygen supply type and the first preset failure type. Based on the first preset oxygen supply type and the first preset failure type, the M periodic management records are traversed, and the corresponding first oxygen supply record and first failure record are matched. Then, the first cabin oxygen concentration information in the first oxygen supply record and the first failure record is obtained, and the first preset oxygen supply type and the first preset failure type are combined to obtain the first oxygen supply training data set and the first failure training data set, which are used as training data for training the oxygen supply management calibration model and the target failure prediction model.

[0040] S600: Respectively, the V calibration models and the N prediction models are integrated and analyzed to obtain a plurality of integrated oxygen supply calibration models and a plurality of integrated failure prediction models, and a target integrated oxygen supply calibration model and a target integrated failure prediction model are determined by comparative analysis;

[0041] Further, as shown in Figure 3 , the step S600 of the embodiment of the application further comprises:

[0042] S610: Based on the principle of integrated learning method, the V calibration models and the N prediction models are modeled to obtain a plurality of integrated calibration models and a plurality of integrated prediction models;

[0043] S620: Assemble a prediction calibration dataset and a prediction test dataset according to the periodic management dataset, wherein the prediction calibration dataset contains multiple sets of oxygen concentration information in the target hyperbaric oxygen chamber, and the prediction test dataset includes multiple sets of pressure information in the target hyperbaric oxygen chamber.

[0044] S630: The multiple sets of oxygen concentration information in the target hyperbaric oxygen chamber have multiple calibration type identifiers, and the multiple sets of pressure information in the target hyperbaric oxygen chamber have multiple fault type identifiers.

[0045] S640: Predict the multiple sets of oxygen concentration information in the target hyperbaric oxygen chamber and the multiple sets of pressure information in the target hyperbaric oxygen chamber by the multiple integrated calibration models and the multiple integrated prediction models in turn to obtain multiple calibration results and multiple prediction results.

[0046] S650: Compare the multiple calibration results and the multiple prediction results with the multiple calibration type identifiers and the multiple fault type identifiers in turn to obtain calibration comparison results and fault comparison results.

[0047] S660: Analyze the calibration comparison results and the fault comparison results and determine the best calibration result and the best prediction result, respectively.

[0048] S670: Reverse match the integrated prediction model of the best calibration result and the best prediction result as the target integrated oxygen supply calibration model and the target integrated fault prediction model.

[0049] Specifically, based on the principle of integrated learning method, the V calibration models and the N prediction models are model built to obtain multiple integrated calibration models and multiple integrated prediction models. The integrated learning is a machine learning paradigm, which is to train multiple weak supervised models as weak learners first, and then combine multiple weak learners to obtain a better strong supervised model. The strong supervised model has better performance and more comprehensive and accurate prediction results. The multiple integrated calibration models and the multiple integrated prediction models of the present application are weak supervised models. Further, the prediction calibration dataset and the prediction test dataset are extracted from the periodic management dataset, wherein the prediction calibration dataset contains multiple sets of oxygen concentration information in the target hyperbaric oxygen chamber, and the prediction test dataset includes multiple sets of pressure information in the target hyperbaric oxygen chamber, and the multiple sets of oxygen concentration information in the target hyperbaric oxygen chamber have corresponding multiple calibration type identifiers, and the multiple sets of pressure information in the target hyperbaric oxygen chamber have corresponding multiple fault type identifiers, which can be used as a benchmark for subsequent model output result accuracy calculation.

[0050] Further, the oxygen concentration information in the multiple groups of target hyperbaric oxygen chambers and the pressure information in the multiple groups of target hyperbaric oxygen chambers are sequentially input into the multiple integrated calibration models and the multiple integrated prediction models for processing, and then multiple calibration results and multiple prediction results are output by the multiple integrated calibration models and the multiple integrated prediction models. The multiple calibration results and the multiple prediction results are sequentially compared with the multiple calibration type identifiers and the multiple fault type identifiers, and the error values of the multiple calibration results and the multiple prediction results with respect to actual calibration and prediction data are determined as calibration comparison results and fault comparison results. The calibration result and the prediction result with the minimum error value are selected from the calibration comparison results and the fault comparison results as optimal calibration results and optimal prediction results. The optimal calibration results and the optimal prediction results are used to reversely match the corresponding integrated prediction models as the target integrated oxygen supply calibration model and the target integrated fault prediction model of the target hyperbaric oxygen chamber, which can be used for oxygen supply calibration and fault prediction, respectively.

[0051] S700: The oxygen concentration in the target hyperbaric oxygen chamber and the real-time pressure data are analyzed by the target integrated oxygen supply calibration model and the target integrated fault prediction model, and oxygen supply calibration information and fault prediction information of the target hyperbaric oxygen chamber are output for multi-dimensional management of the target hyperbaric oxygen chamber.

[0052] Specifically, the oxygen concentration and real-time pressure data of the target hyperbaric oxygen chamber are input into the target integrated oxygen supply calibration model and the target integrated fault prediction model, respectively. Whether the oxygen supply pressure and the oxygen supply concentration of the current target hyperbaric oxygen chamber meet the standard is determined by the target integrated oxygen supply calibration model, and the values of the oxygen supply pressure and the oxygen supply concentration that need to be adjusted are calculated, and the oxygen supply calibration information of the target hyperbaric oxygen chamber is output. The target integrated fault prediction model is used to predict the possible faults of the target hyperbaric oxygen chamber under the current oxygen supply pressure and oxygen supply concentration, and the fault prediction information of the target hyperbaric oxygen chamber is output. Subsequently, the oxygen supply pressure, oxygen supply speed, and oxygen supply concentration of the target hyperbaric oxygen chamber can be adjusted according to the oxygen supply calibration information, which can improve the accuracy of oxygen supply management of the target hyperbaric oxygen chamber. A fault warning scheme can be generated according to the fault prediction information, and fault handling can be performed according to the scheme, which can improve the safety of the target hyperbaric oxygen chamber during use.

[0053] Further, the embodiment of the present application further includes a step S800, and the step S800 further includes:

[0054] S810: The target hyperbaric oxygen chamber is subjected to stage pressure testing by the pressure detection device to determine a first stage, a second stage, and a third stage.

[0055] S820: judging whether the target hyperbaric oxygen chamber is in the first stage, if yes, performing a pressurization operation;

[0056] S830: judging whether the target hyperbaric oxygen chamber is in the second stage, if yes, performing a pressure stabilization operation;

[0057] S840: judging whether the target hyperbaric oxygen chamber is in the third stage, if yes, performing a depressurization operation.

[0058] Specifically, the pressure detection device performs a stage pressure test on the target hyperbaric oxygen chamber, that is, the pressure detection device acquires the pressure value of the target hyperbaric oxygen chamber at present, judges whether the pressure value of the target hyperbaric oxygen chamber at present meets the use requirement, and then judges whether the target hyperbaric oxygen chamber at present needs to be pressurized, stabilized or depressurized according to the size of the pressure value, that is, determines whether the target hyperbaric oxygen chamber at present is in a pressurization stage, a pressure stabilization stage or a depressurization stage, and takes the pressurization stage, the pressure stabilization stage and the depressurization stage as the first stage, the second stage and the third stage. Judging which stage the target hyperbaric oxygen chamber is in, if it is in the pressurization stage, performing a pressurization operation, if it is in the pressure stabilization stage, performing a pressure stabilization operation, and if it is in the depressurization stage, performing a depressurization operation. The pressure adjustment operation can be performed according to the pressure state of the target hyperbaric oxygen chamber, and the accuracy of the pressure adjustment is improved.

[0059] Further, the step S820 of the embodiment of the present application further comprises:

[0060] S821: acquiring initial chamber pressure data of the target hyperbaric oxygen chamber when the target hyperbaric oxygen chamber is in the first stage;

[0061] S822: presetting a target chamber pressure;

[0062] S823: pressurizing the target hyperbaric oxygen chamber based on the initial chamber pressure data, and determining pressurization data, wherein the pressurization data includes the degree of pressurization in the chamber, the speed of pressurization in the chamber and the temperature of pressurization in the chamber;

[0063] S824: adjusting the degree of pressurization in the chamber, the speed of pressurization in the chamber and the temperature of pressurization in the chamber in real time according to the feedback information of the target patient, and updating the pressurization data;

[0064] S825: completing the pressurization operation when the chamber pressure in the target hyperbaric oxygen chamber reaches the preset target chamber pressure according to the updated pressurization data.

[0065] Specifically, when the target hyperbaric oxygen chamber is in the first stage, that is, the pressurization stage, initial chamber pressure data of the target hyperbaric oxygen chamber, that is, the current chamber pressure value of the target hyperbaric oxygen chamber, is obtained, and a target chamber pressure, that is, a required chamber pressure value, is preset. The target hyperbaric oxygen chamber is pressurized based on the initial chamber pressure data, the chamber pressurization degree, the chamber pressurization speed, and the chamber pressurization temperature are determined according to the relationship between the chamber pressure and the temperature and the pressurization speed, the chamber pressurization degree, the chamber pressurization speed, and the chamber pressurization temperature are adjusted in real time according to the feedback information of the target patient, that is, the pressurization data is adjusted and updated, and the pressurization operation of the target hyperbaric oxygen chamber is completed using the updated pressurization data, so as to flexibly control the pressurization data according to the individual physical condition difference of the patient and improve the patient comfort.

[0066] Further, the step S830 of the embodiment of the present application further includes:

[0067] S831: When the target hyperbaric oxygen chamber is in the second stage, obtaining the target patient's chamber treatment pressure data;

[0068] S832: Determining the initial value of the chamber oxygen concentration by real-time detection of the oxygen concentration in the target hyperbaric oxygen chamber;

[0069] S833: Constructing an oxygen concentration change curve based on the initial value of the chamber oxygen concentration and the real-time oxygen concentration in the target hyperbaric oxygen chamber;

[0070] S834: Extracting the oxygen concentration change rate according to the oxygen concentration change curve;

[0071] S835: Performing a pressure stabilization operation on the target hyperbaric oxygen chamber based on the correlation between the oxygen concentration change rate and the target patient's chamber treatment pressure data.

[0072] Specifically, when the target hyperbaric oxygen chamber is in the second stage, that is, the pressure stabilization stage, the target patient's chamber treatment pressure data, that is, the required treatment pressure data of the target patient, is obtained from the treatment scheme, the oxygen concentration in the target hyperbaric oxygen chamber is detected in real time, and the initial value and the real-time change value of the chamber oxygen concentration are recorded, then the initial value of the chamber oxygen concentration is taken as the starting point, the real-time oxygen concentration in the target hyperbaric oxygen chamber is combined to draw an oxygen concentration change curve, the oxygen concentration change rate is calculated according to the oxygen concentration change curve, and finally the oxygen concentration change rate is associated with the target patient's chamber treatment pressure data, the oxygen concentration change rate is adjusted according to the requirements of the target patient's chamber treatment pressure data, and the chamber pressure of the target hyperbaric oxygen chamber is stabilized within the required range of the target patient's chamber treatment pressure.

[0073] Further, the step S840 of the embodiment of the present application further includes:

[0074] S841: determining a plurality of time nodes based on the third stage;

[0075] S842: obtaining target patient out-cabin pressure data when the target hyperbaric oxygen cabin is in the third stage, wherein the target patient out-cabin pressure data and the plurality of time nodes are in a corresponding relationship;

[0076] S843: obtaining cabin real-time temperature data by temperature sensing of the target hyperbaric oxygen cabin through the temperature sensor;

[0077] S844: mapping the cabin real-time temperature data in the plurality of time nodes to obtain temperature node data corresponding to the plurality of time nodes;

[0078] S845: adapting the target patient out-cabin pressure data and the temperature node data at different time nodes based on the oxygen concentration in the target hyperbaric oxygen cabin to complete the decompression operation in the third stage.

[0079] Specifically, based on the decompression range and required time of the third stage, a plurality of time nodes are set in the entire decompression stage, and stable decompression is realized by controlling the pressure, temperature and other parameters of each time node. When the target hyperbaric oxygen cabin is in the third stage, that is, the decompression stage, target patient out-cabin pressure data is obtained, that is, the cabin pressure requirement of the target hyperbaric oxygen cabin when the target patient exits the cabin, wherein the target patient out-cabin pressure data and the plurality of time nodes are in a corresponding relationship, that is, the target patient out-cabin pressure data is taken as a target, and the pressure data of each time node changes uniformly until the target patient out-cabin pressure data is reached. The cabin real-time temperature data is obtained by real-time temperature sensing of the target hyperbaric oxygen cabin through the temperature sensor, the cabin real-time temperature data is mapped in the plurality of time nodes, the temperature value of each time node is set, and the temperature node data corresponding to the plurality of time nodes is obtained. Based on the oxygen concentration in the target hyperbaric oxygen cabin, the target patient out-cabin pressure data and the temperature node data at different time nodes are controlled respectively to ensure uniform completion of the decompression operation in the third stage, reduce the discomfort of the patient during decompression, and improve the safety of the decompression process.

[0080] In summary, the embodiment of the present application has at least the following technical effects:

[0081] This application acquires real-time pressure data, oxygen concentration, oxygen supply management records, and management records of preset fault types from the target hyperbaric oxygen chamber. Through cascade learning, it obtains multiple integrated oxygen supply calibration models and multiple integrated fault prediction models. These are then compared and analyzed to determine the target integrated oxygen supply calibration model and the target integrated fault prediction model. The application analyzes the oxygen concentration and real-time pressure data within the target hyperbaric oxygen chamber, outputting oxygen supply calibration information and fault prediction information for the target hyperbaric oxygen chamber, thus enabling multi-dimensional management of the target hyperbaric oxygen chamber.

[0082] This technology achieves the goal of improving the accuracy of hyperbaric oxygen chamber management and the safety of its use based on multidimensional data.

[0083] Example 2

[0084] Based on the same inventive concept as the hyperbaric oxygen chamber management method based on multi-dimensional data in the foregoing embodiments, such as Figure 4 As shown, this application provides a hyperbaric oxygen chamber management system based on multi-dimensional data. The system and method embodiments in this application are based on the same inventive concept. The system includes:

[0085] Real-time pressure data acquisition module 11, the real-time pressure data acquisition module 11 is used to acquire real-time pressure data of the target hyperbaric oxygen chamber through the pressure detection device, wherein the real-time pressure data has a temperature attribute;

[0086] Oxygen concentration determination module 12 is used to determine the oxygen content in the target hyperbaric oxygen chamber based on gas chromatography, and to determine the oxygen concentration in the target hyperbaric oxygen chamber.

[0087] Oxygen supply management record acquisition module 13 is used to acquire the oxygen supply management record of the target hyperbaric oxygen chamber based on the mapping relationship between the real-time pressure data and its temperature attributes and the oxygen concentration in the target hyperbaric oxygen chamber.

[0088] The periodic management record acquisition module 14 is used to acquire the management log of the target hyperbaric oxygen chamber. The management log of the target hyperbaric oxygen chamber includes M periodic management records, where M is an integer greater than 1, and the M periodic management records include the oxygen supply management record of the target hyperbaric oxygen chamber and the management record of preset fault types.

[0089] The model set acquisition module 15 is configured to analyze the M periodic management record acquisition periodic management data sets and perform cascade learning on the periodic management data sets to obtain an oxygen supply management calibration model set and a target fault prediction model set, wherein the oxygen supply management calibration model set includes V calibration models, and the target fault prediction model set includes N prediction models, V is an integer greater than 1, and N is an integer greater than 1.

[0090] The target integrated prediction model acquisition module 16 is configured to perform integrated fusion analysis on the V calibration models and the N prediction models respectively to obtain a plurality of integrated oxygen supply calibration models and a plurality of integrated fault prediction models, and determine a target integrated oxygen supply calibration model and a target integrated fault prediction model through comparative analysis.

[0091] The multi-dimensional management module 17 is configured to analyze the oxygen concentration in the target hyperbaric oxygen chamber and the real-time pressure data through the target integrated oxygen supply calibration model and the target integrated fault prediction model, output oxygen supply calibration information and fault prediction information of the target hyperbaric oxygen chamber, and perform multi-dimensional management on the target hyperbaric oxygen chamber.

[0092] Further, the system further comprises:

[0093] The phase pressure test module is configured to perform phase pressure test on the target hyperbaric oxygen chamber through the pressure detection device to determine a first phase, a second phase and a third phase.

[0094] The first phase judgment module is configured to judge whether the target hyperbaric oxygen chamber is in the first phase, and if so, perform pressurization operation.

[0095] The second phase judgment module is configured to judge whether the target hyperbaric oxygen chamber is in the second phase, and if so, perform pressure stabilization operation.

[0096] The third phase judgment module is configured to judge whether the target hyperbaric oxygen chamber is in the third phase, and if so, perform depressurization operation.

[0097] Further, the system further comprises:

[0098] The initial chamber pressure data acquisition module is configured to acquire initial chamber pressure data of the target hyperbaric oxygen chamber when the target hyperbaric oxygen chamber is in the first phase.

[0099] The target chamber pressure preset module is configured to preset a target chamber pressure.

[0100] a pressurization data determination module, configured to determine pressurization data of the target hyperbaric oxygen chamber based on the initial cabin pressure data, wherein the pressurization data comprises a cabin pressurization degree, a cabin pressurization speed, and a cabin pressurization temperature;

[0101] a pressurization data adjustment module, configured to adjust the cabin pressurization degree, the cabin pressurization speed, and the cabin pressurization temperature in real time according to target patient feedback information, and to update the pressurization data;

[0102] a pressurization operation module, configured to complete a pressurization operation when the cabin pressure in the target hyperbaric oxygen chamber reaches the preset target cabin pressure according to the updated pressurization data;

[0103] Further, the system further comprises:

[0104] a treatment pressure data obtaining module, configured to obtain target patient cabin treatment pressure data when the target hyperbaric oxygen chamber is in the second stage;

[0105] an oxygen concentration initial value determination module, configured to determine a cabin oxygen concentration initial value by detecting the oxygen concentration in the target hyperbaric oxygen chamber in real time;

[0106] an oxygen concentration change curve construction module, configured to construct an oxygen concentration change curve based on the cabin oxygen concentration initial value and the real-time oxygen concentration in the target hyperbaric oxygen chamber;

[0107] an oxygen concentration change rate extraction module, configured to extract an oxygen concentration change rate according to the oxygen concentration change curve;

[0108] a pressure stabilization operation module, configured to perform a pressure stabilization operation on the target hyperbaric oxygen chamber based on the correlation between the oxygen concentration change rate and the target patient cabin treatment pressure data;

[0109] Further, the system further comprises:

[0110] a plurality of time node determination modules, configured to determine a plurality of time nodes based on the third stage;

[0111] an egress pressure data obtaining module, configured to obtain target patient egress pressure data when the target hyperbaric oxygen chamber is in the third stage, wherein the target patient egress pressure data and the plurality of time nodes are in a corresponding relationship;

[0112] An in-cabin real-time temperature data acquisition module is configured to monitor and sense the temperature of the target hyperbaric oxygen cabin through the temperature sensor, and obtain in-cabin real-time temperature data.

[0113] A temperature node data acquisition module is configured to map the in-cabin real-time temperature data at the plurality of time nodes, and obtain temperature node data corresponding to the plurality of time nodes.

[0114] A decompression operation module is configured to adapt the target patient out-cabin pressure data at different time nodes and the temperature node data based on the oxygen concentration in the target hyperbaric oxygen cabin, and complete the third-stage decompression operation.

[0115] Further, the system further comprises:

[0116] A classification coding standard preset module is configured to obtain a preset classification coding standard.

[0117] A model division result acquisition module is configured to divide the target hyperbaric oxygen cabin into different models based on the preset classification coding standard, and obtain a model division result.

[0118] A target oxygen cabin type setting module is configured to randomly extract an oxygen cabin type in the model division result, and set it as a target oxygen cabin type.

[0119] An oxygen cabin oxygen supply data set construction module is configured to match oxygen supply information and fault information of the target oxygen cabin type, obtain oxygen supply information and fault information of the target oxygen cabin, and construct an oxygen cabin oxygen supply data set and an oxygen cabin fault data set.

[0120] A regular management record matching module is configured to traverse the M times of regular management records based on the first preset oxygen supply type and the first preset fault type, and match a first oxygen supply record and a first fault record.

[0121] A training data group acquisition module is configured to obtain first in-cabin oxygen concentration information and first in-cabin pressure information in the first oxygen supply record and the first fault record, and combine the first preset oxygen supply type and the first preset fault type to obtain a first oxygen supply training data group and a first fault training data group.

[0122] A regular management data set construction module is configured to construct a regular management data set according to the first oxygen supply training data group and the first fault training data group.

[0123] Further, the system further comprises:

[0124] A model building module, configured to build models for the V calibration models and the N prediction models based on the principle of ensemble learning method, to obtain a plurality of ensemble calibration models and a plurality of ensemble prediction models;

[0125] A dataset building module, configured to build a prediction calibration dataset and a prediction test dataset according to the periodic management dataset, wherein the prediction calibration dataset contains a plurality of sets of target hyperbaric oxygen chamber oxygen concentration information, and the prediction test dataset includes a plurality of sets of target hyperbaric oxygen chamber pressure information;

[0126] A prediction result obtaining module, configured to sequentially predict the plurality of sets of target hyperbaric oxygen chamber oxygen concentration information and the plurality of sets of target hyperbaric oxygen chamber pressure information through the plurality of ensemble calibration models and the plurality of ensemble prediction models, to obtain a plurality of calibration results and a plurality of prediction results;

[0127] A comparison result obtaining module, configured to compare the plurality of calibration results and the plurality of prediction results with the plurality of calibration type identifiers and the plurality of fault type identifiers in sequence, to obtain calibration comparison results and fault comparison results;

[0128] An optimal prediction result obtaining module, configured to analyze the calibration comparison results and the fault comparison results and determine optimal calibration results and optimal prediction results, respectively;

[0129] A target ensemble prediction model obtaining module, configured to reversely match the optimal calibration results and the optimal prediction results to obtain ensemble prediction models of the optimal calibration results and the optimal prediction results as the target ensemble oxygen supply calibration model and the target ensemble fault prediction model.

[0130] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The above-mentioned embodiments are described in the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0131] The above description is only the preferred embodiment of the present application, and is not intended to limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0132] The specification and drawings are only exemplary and illustrative of the present application and are considered to cover any and all modifications, variations, combinations or equivalents that are within the scope of the present application. Obviously, various modifications and changes can be made to the present application by those skilled in the art without departing from the scope of the present application. Thus, it is intended that the present application cover the modifications and changes as they come within the scope of the application, and that the scope of the application be limited only by the claims.

Claims

1. A hyperbaric chamber management method based on multi-dimensional data, characterized in that, The method is applied to an intelligent management system in communication connection with a pressure detection device and a temperature sensor, and comprises the following steps: Obtaining real-time pressure data of a target hyperbaric oxygen chamber through the pressure detection device, wherein the real-time pressure data has a temperature attribute; Determining the oxygen concentration in the target hyperbaric oxygen chamber based on the determination of the oxygen content in the target hyperbaric oxygen chamber by gas chromatography; Obtaining the oxygen supply management record of the target hyperbaric oxygen chamber based on the mapping relationship between the real-time pressure data and its temperature attribute and the oxygen concentration in the target hyperbaric oxygen chamber; Obtaining the management log of the target hyperbaric oxygen chamber, wherein the management log of the target hyperbaric oxygen chamber comprises M periodic management records, wherein M is an integer greater than 1, and the M periodic management records comprise the oxygen supply management record of the target hyperbaric oxygen chamber and the management record of a preset fault type; Analyzing the M periodic management records to obtain a periodic management data set, and performing cascade learning on the periodic management data set to obtain an oxygen supply management calibration model set and a target fault prediction model set, wherein the oxygen supply management calibration model set comprises V calibration models, and the target fault prediction model set comprises N prediction models, wherein V is an integer greater than 1, and N is an integer greater than 1; Performing integrated fusion analysis on the V calibration models and the N prediction models respectively to obtain a plurality of integrated oxygen supply calibration models and a plurality of integrated fault prediction models, and determining a target integrated oxygen supply calibration model and a target integrated fault prediction model through comparative analysis; Analyzing the oxygen concentration in the target hyperbaric oxygen chamber and the real-time pressure data through the target integrated oxygen supply calibration model and the target integrated fault prediction model, and outputting oxygen supply calibration information and fault prediction information of the target hyperbaric oxygen chamber to perform multi-dimensional management on the target hyperbaric oxygen chamber; Obtaining the periodic management data set, and the method further comprises: Obtaining a preset classification coding standard; Dividing the target hyperbaric oxygen chamber into different types based on the preset classification coding standard to obtain a type division result; Randomly extracting an oxygen chamber type from the type division result and setting it as a target oxygen chamber type; Matching the oxygen supply information and the fault information of the target oxygen chamber type to obtain the oxygen supply information and the fault information of the target oxygen chamber, and assembling an oxygen chamber oxygen supply data set and an oxygen chamber fault data set; Taking the oxygen chamber oxygen supply data set and the oxygen chamber fault data set as a first preset oxygen supply type and a first preset fault type; Iterating the M periodic management records based on the first preset oxygen supply type and the first preset fault type to match a first oxygen supply record and a first fault record; Obtaining first in-chamber oxygen concentration information and first in-chamber pressure information from the first oxygen supply record and the first fault record, and combining the first preset oxygen supply type and the first preset fault type to obtain a first oxygen supply training data set and a first fault training data set; Assembling the periodic management data set according to the first oxygen supply training data set and the first fault training data set; Comparatively analyzing the target integrated oxygen supply calibration model and the target integrated fault prediction model, and the method further comprises: The V calibration models and the N prediction models are built based on the principle of the ensemble learning method to obtain a plurality of ensemble calibration models and a plurality of ensemble prediction models; The prediction calibration dataset and the prediction test dataset are established according to the periodic management dataset, wherein the prediction calibration dataset contains a plurality of sets of oxygen concentration information in the target hyperbaric oxygen chamber, and the prediction test dataset includes a plurality of sets of pressure information in the target hyperbaric oxygen chamber; The plurality of sets of oxygen concentration information in the target hyperbaric oxygen chamber have a plurality of calibration type identifiers, and the plurality of sets of pressure information in the target hyperbaric oxygen chamber have a plurality of fault type identifiers; The plurality of sets of oxygen concentration information in the target hyperbaric oxygen chamber and the plurality of sets of pressure information in the target hyperbaric oxygen chamber are sequentially predicted through the plurality of ensemble calibration models and the plurality of ensemble prediction models to obtain a plurality of calibration results and a plurality of prediction results; The plurality of calibration results and the plurality of prediction results are compared with the plurality of calibration type identifiers and the plurality of fault type identifiers to obtain calibration comparison results and fault comparison results; The calibration comparison results and the fault comparison results are analyzed to determine the best calibration result and the best prediction result, respectively; The ensemble prediction model of the best calibration result and the best prediction result is reversely matched to serve as the target ensemble oxygen supply calibration model and the target ensemble fault prediction model.

2. The method of claim 1, wherein, After obtaining the real-time pressure data, the method further comprises: The target hyperbaric oxygen chamber is subjected to stage pressure testing through the pressure detection device to determine a first stage, a second stage and a third stage; It is judged whether the target hyperbaric oxygen chamber is in the first stage, and if so, a pressurization operation is performed; It is judged whether the target hyperbaric oxygen chamber is in the second stage, and if so, a pressure stabilization operation is performed; It is judged whether the target hyperbaric oxygen chamber is in the third stage, and if so, a depressurization operation is performed.

3. The method of claim 2, wherein, The pressurization operation, the method further comprises: When the target hyperbaric oxygen chamber is in the first stage, initial chamber pressure data of the target hyperbaric oxygen chamber is obtained; A target chamber pressure is preset; The target hyperbaric oxygen chamber is pressurized based on the initial chamber pressure data to determine pressurization data, wherein the pressurization data contains the degree of pressurization in the chamber, the pressurization speed in the chamber and the pressurization temperature in the chamber; The degree of pressurization in the chamber, the pressurization speed in the chamber and the pressurization temperature in the chamber are adjusted in real time according to the target patient feedback information, and the pressurization data is updated; When the chamber pressure in the target hyperbaric oxygen chamber reaches the preset target chamber pressure, the pressurization operation is completed according to the updated pressurization data.

4. The method of claim 2, wherein, The pressure stabilization operation, the method further comprises: When the target hyperbaric oxygen chamber is in the second stage, target patient chamber treatment pressure data is obtained; The initial value of the oxygen concentration in the chamber is determined by real-time detection of the oxygen concentration in the target hyperbaric oxygen chamber; An oxygen concentration change curve is constructed based on the initial value of the oxygen concentration in the chamber and the real-time oxygen concentration in the target hyperbaric oxygen chamber; The oxygen concentration change rate is extracted according to the oxygen concentration change curve; Based on the correlation between the oxygen concentration change rate and the target patient cabin pressure data, the target hyperbaric oxygen chamber is operated at a stable pressure.

5. The method of claim 2, wherein, The decompression operation, the method further comprises: Based on the third stage, a plurality of time nodes are determined; When the target hyperbaric oxygen chamber is in the third stage, target patient out-of-cabin pressure data is obtained, wherein the target patient out-of-cabin pressure data and the plurality of time nodes are in a corresponding relationship; The temperature sensor is used to monitor the temperature of the target hyperbaric oxygen chamber, and real-time temperature data in the cabin is obtained; The real-time temperature data in the cabin is mapped in the plurality of time nodes, and temperature node data corresponding to the plurality of time nodes is obtained; Based on the oxygen concentration in the target hyperbaric oxygen chamber, the target patient out-of-cabin pressure data at different time nodes and the temperature node data are adapted, and the decompression operation of the third stage is completed.

6. A hyperbaric chamber management system based on multi-dimensional data, characterized in that, The system is used to execute the method of any one of claims 1 to 5, and the system comprises: A real-time pressure data acquisition module is used to acquire real-time pressure data of a target hyperbaric oxygen chamber through a pressure detection device, wherein the real-time pressure data has a temperature attribute; An oxygen concentration determination module is used to determine the oxygen content in the target hyperbaric oxygen chamber based on gas chromatography, and determine the oxygen concentration in the target hyperbaric oxygen chamber; An oxygen supply management record acquisition module is used to acquire the oxygen supply management record of the target hyperbaric oxygen chamber based on the mapping relationship between the real-time pressure data and its temperature attribute and the oxygen concentration in the target hyperbaric oxygen chamber; A periodic management record acquisition module is used to acquire the management log of the target hyperbaric oxygen chamber, wherein the management log of the target hyperbaric oxygen chamber comprises M periodic management records, wherein M is an integer greater than 1, and the M periodic management records comprise the oxygen supply management record of the target hyperbaric oxygen chamber and the management record of the preset fault type; A model set acquisition module is used to analyze the M periodic management records to obtain periodic management data sets, and perform cascaded learning on the periodic management data sets to obtain an oxygen supply management calibration model set and a target fault prediction model set, wherein the oxygen supply management calibration model set comprises V calibration models, and the target fault prediction model set comprises N prediction models, wherein V is an integer greater than 1, and N is an integer greater than 1; A target integrated prediction model acquisition module is used to respectively integrate and fuse the V calibration models and the N prediction models to obtain a plurality of integrated oxygen supply calibration models and a plurality of integrated fault prediction models, and determine a target integrated oxygen supply calibration model and a target integrated fault prediction model through comparative analysis. A multi-dimensional management module is configured to analyze the target integrated oxygen supply calibration model, the target integrated fault prediction model, the oxygen concentration in the target hyperbaric oxygen chamber, and the real-time pressure data, and output oxygen supply calibration information and fault prediction information of the target hyperbaric oxygen chamber, thereby performing multi-dimensional management on the target hyperbaric oxygen chamber.

Images