Online self-adaptive accurate diagnosis and early warning method and device for medical oxygen generator

Abstract

The invention provides an online self-adaptive accurate diagnosis early warning method and device for a medical oxygenerator, and belongs to the technical field of monitoring devices.The online self-adaptive accurate diagnosis early warning method and device for the medical oxygenerator specifically comprises the steps that a data collection module is responsible for collecting and processing operation data of the medical oxygenerator, and a map database construction module is responsible for establishing a map database according to historical fault data of the medical oxygenerator; a typical fault mode atlas database is established according to operation parameter characteristics under different fault modes, and a diagnosis module construction module is responsible for constructing an intelligent diagnosis model, automatically extracting characteristic information in operation data, comparing the characteristic information with the typical fault mode atlas database, determining a fault mode and providing a diagnosis result. And the atlas database updating module is responsible for determining an updating processing strategy according to the matching condition of the feature information of the medical oxygenerator of the type and the typical fault mode atlas database, and updating the typical fault mode atlas database of the medical oxygenerator of the type by using the updating processing strategy, so that the accuracy of fault identification processing is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of monitoring devices, and in particular relates to an online adaptive accurate diagnosis and early warning method and device for a medical oxygen concentrator. Background Art

[0002] Medical oxygen concentrators may experience various faults during long-term operation due to various factors. Traditional fault diagnosis methods are mostly based on offline analysis and regular testing, which cannot detect equipment faults in real time and accurately.

[0003] In order to solve the above technical problems, in the invention patent application CN202311379673.8 "A Medical Oxygen Generator Monitoring System", the parameter interval required by the segmented monitoring module is substituted for data correction to obtain numerical parameters, and then the numerical parameters are used as the crossing line warning parameters for comparison with the predicted parameters to determine whether the supply demand of the oxygen pipe network is met or exceeded, so as to avoid the accumulation of oxygen shortage errors affecting the accuracy of monitoring data. However, the above technical solution has the following technical problems: In the process of monitoring and early warning of oxygen concentrators, the failure modes of medical oxygen concentrators are complex and diverse, and there may be differences between different devices. The use of a fixed failure mode spectrum library may not be able to accurately identify the fault. Therefore, how to achieve adaptive update processing of the failure mode spectrum library and accurately identify the failure of the medical oxygen concentrator has become a technical problem that needs to be solved urgently.

[0004] In response to the above technical problems, the present application specifically provides an online adaptive precise diagnosis and early warning method and device for a medical oxygen concentrator. Summary of the invention

[0005] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: In a first aspect, the present application provides an online adaptive accurate diagnosis and early warning device for a medical oxygen concentrator, specifically comprising: Data acquisition module, spectrum library building module, diagnostic model building module, spectrum library updating module; The data acquisition module is responsible for collecting and processing the operating data of the medical oxygen concentrator; The atlas library building module is responsible for using the historical fault data of the medical oxygen concentrator to establish a typical fault mode atlas library according to the operating parameter characteristics under different fault modes; The diagnostic module building module is responsible for building an intelligent diagnostic model, automatically extracting feature information from the operating data, and comparing it with a typical fault mode atlas library to determine the fault mode; The atlas library update module is responsible for determining an update processing strategy according to the matching situation between the characteristic information of the type of medical oxygen concentrator and the typical failure mode atlas library, and using the update processing strategy to update the typical failure mode atlas library of the type of medical oxygen concentrator.

[0006] A further technical solution is that the operating parameter characteristics include one or more of temperature, humidity, pressure, flow, purity, rotation speed, vibration, displacement, noise, and key phase.

[0007] A further technical solution is that the update processing strategy is determined based on the matching deviation between the characteristic information of the medical oxygen concentrator of the type and the typical failure mode map library, wherein when the matching deviation does not meet the requirements and the number of historical failures is greater than a preset failure number threshold, it is determined that the medical oxygen concentrator of the type needs to be updated.

[0008] The beneficial effects of the present invention are: Real-time and accurate diagnosis: The present invention can collect the operating data of the medical oxygen concentrator in real time, and combined with the intelligent diagnosis model, it can realize real-time and accurate diagnosis of equipment failures and timely discover potential failures.

[0009] Adaptive diagnosis: By updating the diagnostic standard library in real time, it can adapt to the differences between different units and changes in the operating environment, realize adaptive diagnosis, and improve the accuracy and reliability of diagnosis.

[0010] Improve maintenance efficiency: Accurate diagnostic results help to quickly locate the cause of the fault, take effective maintenance measures, improve the maintenance efficiency of the medical oxygen concentrator, and reduce maintenance costs.

[0011] On the other hand, the present application provides an online adaptive accurate diagnosis and early warning method for a medical oxygen concentrator, specifically comprising: S1 takes the medical oxygen concentrator of the type as a matching oxygen concentrator, and when it is determined that it is not necessary to update the typical failure mode map library according to the preset update strategy based on the analysis results of the historical usage data and failure data of the matching oxygen concentrator, proceeds to the next step; S2: when it is determined that there is a matching deviation fault type in the fault type based on the matching situation between the characteristic information in the operation data and the typical fault mode atlas library, proceed to the next step; S3 determines the similarity of the operation data within a preset time period of the historical fault number corresponding to the matching deviation fault type, and determines the matching operation scenario and matching operation coefficient of the matching deviation fault type by using the similarity; S4 obtains the operation data of different matching oxygen concentrators in different matching operation scenarios and the matching operation coefficients of the matching operation scenarios, and determines the update processing strategy in combination with the historical fault times corresponding to the matching deviation fault types of different matching oxygen concentrators, and uses the update processing strategy to update the typical fault mode atlas library.

[0012] A further technical solution is that the historical usage data of the matched oxygen concentrator includes the historical usage times of the matched oxygen concentrator, the usage durations of different historical usage times, and the oxygen production amounts.

[0013] A further technical solution is that the analysis result of the fault data includes the number of failures of different matched oxygen concentrators in different historical usage times.

[0014] A further technical solution is to determine that it is not necessary to update the typical failure mode atlas library according to a preset update strategy, specifically including: Determine different historical usage times and usage durations of different historical usage times based on the historical usage data of the matched oxygen concentrator, determine total usage durations of different matched oxygen concentrators based on the usage durations of different historical usage times, and determine a frequently used oxygen concentrator among the matched oxygen concentrators based on the total usage durations; Determining the number of failures of different frequently used oxygen concentrators according to the analysis results of the failure data of the frequently used oxygen concentrators, and determining the problematic oxygen concentrator among the frequently used oxygen concentrators by using the number of failures; Whether it is necessary to update the typical failure mode atlas library according to a preset update strategy is determined based on the proportion of the problematic oxygen concentrators in the frequently used oxygen concentrators.

[0015] A further technical solution is that a frequently used oxygen concentrator in the matched oxygen concentrator is a matched oxygen concentrator whose total usage time is greater than a preset usage time.

[0016] A further technical solution is that the problematic oxygen concentrator is a frequently used oxygen concentrator whose number of failures does not meet the requirements.

[0017] A further technical solution is that when the proportion of the problematic oxygen concentrators in the frequently used oxygen concentrators is greater than a preset proportion threshold, it is determined that there is no need to update the typical failure mode atlas library according to a preset update strategy.

[0018] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings; Figure 1 It is a framework diagram of an online adaptive accurate diagnosis and early warning device for a medical oxygen concentrator; Figure 2 It is a flow chart of an online adaptive accurate diagnosis and early warning method for a medical oxygen concentrator; Figure 3 It is a flow chart for determining that it is not necessary to update the typical failure mode atlas library according to a preset update strategy; Figure 4 is a flow chart of a method for determining a matching deviation fault type; Figure 5 is a flow chart of a method for determining a matching operation scenario of a matching deviation fault type. DETAILED DESCRIPTION

[0021] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0022] The purpose of the present invention is to provide an online adaptive and precise diagnosis technology for a medical oxygen concentrator, which realizes online adaptive and precise diagnosis of medical oxygen concentrator faults by real-time collection of equipment operation data and combines it with an intelligent diagnosis model, thereby improving the maintenance efficiency and reliability of the equipment.

[0023] Real-time data acquisition: Use high-precision sensors to collect the operating data of the medical oxygen concentrator in real time, including one or more of the key parameters such as temperature, humidity, pressure, flow, purity, speed, vibration, displacement, noise, key phase, etc. The collected data is transmitted to the diagnostic system through wired or wireless communication to ensure the real-time and accuracy of the data.

[0024] Establishment of a typical fault mode atlas library: Collect historical fault data of medical oxygen concentrators, analyze the operating parameter characteristics under different fault modes, and establish a typical fault mode atlas library. The atlas library contains characteristic information of various common faults, providing a reference for fault diagnosis.

[0025] Equipment operation status model establishment: Based on real-time collected data and typical fault mode atlas library, the operation, fault and standby status models of medical oxygen concentrators are established. Machine learning algorithms such as decision trees and random forests are used to train and optimize the model so that it can accurately identify different operation states.

[0026] Construction of deep convolutional network intelligent diagnosis model: A deep convolutional network intelligent diagnosis model is constructed, which can automatically extract feature information from operating data and compare it with the typical fault mode map library to determine the fault mode. According to the differences between different units, the diagnostic standard library is updated in real time to achieve dynamic detection and accurate diagnosis of gradual and sudden faults.

[0027] High-precision sensors are used to collect the oxygen flow of the medical oxygen concentrator in real time. The algorithm will automatically calculate the cumulative oxygen consumption and average oxygen consumption in the past day or month, and establish an equipment operation status model based on the real-time collected data. When the oxygen consumption suddenly increases, the algorithm will detect the abnormality and issue a flow warning signal to prevent insufficient pressure and energy waste caused by problems such as pipeline leakage.

[0028] The model uses the convolutional layer formula of the deep convolutional network:

[0029] Where W is the convolution kernel weight, b is the bias term, and f is the ReLU activation function. The fault diagnosis accuracy rate is 98.7%, and the recall rate is 96.5%. Experimental data shows that the system can identify a sudden increase in oxygen flow (such as a leakage fault) within 2 seconds, with a false alarm rate of less than 1.2%, significantly improving maintenance response efficiency.

[0030] Use historical fault data to build a typical fault mode atlas library, and build an equipment operation status model based on real-time collected data. Input the real-time collected data into the deep convolutional network intelligent diagnosis model, compare it with the typical fault mode atlas library, and determine the fault mode.

[0031] Example 1 Figure 1 As shown, the present application provides an online adaptive accurate diagnosis and early warning device for a medical oxygen concentrator, specifically comprising: Data acquisition module, spectrum library building module, diagnostic model building module, spectrum library updating module; The data acquisition module is responsible for collecting and processing the operating data of the medical oxygen concentrator; The atlas library building module is responsible for using the historical fault data of the medical oxygen concentrator to establish a typical fault mode atlas library according to the operating parameter characteristics under different fault modes; The diagnostic module building module is responsible for building an intelligent diagnostic model, automatically extracting feature information from the operating data, and comparing it with a typical fault mode atlas library to determine the fault mode; The atlas library update module is responsible for determining an update processing strategy according to the matching situation between the characteristic information of the type of medical oxygen concentrator and the typical failure mode atlas library, and using the update processing strategy to update the typical failure mode atlas library of the type of medical oxygen concentrator.

[0032] Furthermore, the operating parameter characteristics include one or more of temperature, humidity, pressure, flow, purity, rotation speed, vibration, displacement, noise, and key phase.

[0033] Specifically, the update processing strategy is determined based on the matching deviation between the characteristic information of the medical oxygen concentrator of the type and the typical failure mode map library, wherein when the matching deviation does not meet the requirement and the number of historical failures is greater than a preset failure number threshold, it is determined that the medical oxygen concentrator of the type needs to be updated.

[0034] Embodiment 2 On the other hand, as Figure 2 As shown, the present application provides an online adaptive accurate diagnosis and early warning method for a medical oxygen concentrator, specifically comprising: S1 takes the medical oxygen concentrator of the type as a matching oxygen concentrator, and when it is determined that it is not necessary to update the typical failure mode map library according to the preset update strategy based on the analysis results of the historical usage data and failure data of the matching oxygen concentrator, proceeds to the next step; Furthermore, the historical usage data of the matched oxygen concentrator includes the historical usage times of the matched oxygen concentrator, the usage durations of different historical usage times, and the oxygen production amounts.

[0035] Specifically, the analysis result of the fault data includes the number of faults of different matched oxygen concentrators in different historical usage times.

[0036] It should be noted that if Figure 3 As shown, it is determined that there is no need to update the typical failure mode atlas library according to the preset update strategy, specifically including: Determine different historical usage times and usage durations of different historical usage times based on the historical usage data of the matched oxygen concentrator, determine total usage durations of different matched oxygen concentrators based on the usage durations of different historical usage times, and determine a frequently used oxygen concentrator among the matched oxygen concentrators based on the total usage durations; Determining the number of failures of different frequently used oxygen concentrators according to the analysis results of the failure data of the frequently used oxygen concentrators, and determining the problematic oxygen concentrator among the frequently used oxygen concentrators by using the number of failures; Whether it is necessary to update the typical failure mode atlas library according to a preset update strategy is determined based on the proportion of the problematic oxygen concentrators in the frequently used oxygen concentrators.

[0037] Furthermore, the frequently used oxygen concentrator among the matched oxygen concentrators is a matched oxygen concentrator whose total usage time is greater than a preset usage time.

[0038] It can be understood that the problematic oxygen concentrator is a frequently used oxygen concentrator whose failure frequency does not meet the requirements.

[0039] Specifically, when the proportion of the problematic oxygen concentrators in the frequently used oxygen concentrators is greater than a preset proportion threshold, it is determined that there is no need to update the typical failure mode atlas library according to the preset update strategy.

[0040] Optionally, determining that it is not necessary to update the typical failure mode atlas library according to a preset update strategy specifically includes: Determine different historical usage times and usage durations of different historical usage times based on the historical usage data of the matched oxygen concentrator, determine total usage durations of different matched oxygen concentrators based on the usage durations of different historical usage times, and determine a frequently used oxygen concentrator among the matched oxygen concentrators based on the total usage durations; Determining the number of failures of different frequently used oxygen concentrators according to the analysis results of the failure data of the frequently used oxygen concentrators, and determining the problematic oxygen concentrator among the frequently used oxygen concentrators by using the number of failures; According to the number of problematic oxygen concentrators and the number of frequently used oxygen concentrators, it is determined whether it is necessary to update the typical failure mode atlas library according to a preset update strategy.

[0041] Further, when the number of the problematic oxygen concentrators is greater than a preset number of problematic oxygen concentrators and the number of frequently used oxygen concentrators is greater than a preset number of frequently used oxygen concentrators, it is determined that the typical failure mode atlas library needs to be updated according to a preset update strategy.

[0042] Optionally, determining that it is not necessary to update the typical failure mode atlas library according to a preset update strategy specifically includes: Determine different historical usage times and usage durations of different historical usage times by using the historical usage data of the matched oxygen concentrator, and determine total usage durations of different matched oxygen concentrators by using the usage durations of different historical usage times, and when it is determined based on the total usage duration that there is no frequently used oxygen concentrator among the matched oxygen concentrators, it is determined that there is no need to perform update processing of the typical failure mode atlas library according to a preset update strategy; When it is determined based on the total usage time that there is a frequently used oxygen concentrator among the matched oxygen concentrators: Determine usage weight coefficients of different frequently used oxygen concentrators according to the total usage time of different frequently used oxygen concentrators, and when the sum of the usage weight coefficients of different frequently used oxygen concentrators is greater than a preset weight coefficient threshold, determine that it is necessary to update the typical failure mode atlas library according to a preset update strategy; When the sum of the usage weight coefficients of different frequently used oxygen concentrators is not greater than the preset weight coefficient threshold: When the sum of the usage weight coefficients of different frequently used oxygen concentrators is within a preset usage weight coefficient interval, it is determined that there is no need to update the typical failure mode atlas library according to the preset update strategy; When the sum of the usage weight coefficients of different frequently used oxygen concentrators is not within the preset usage weight coefficient range: According to the analysis result of the fault data of the frequently used oxygen concentrator, the number of faults of different frequently used oxygen concentrators is determined, and when the sum of the number of faults of different frequently used oxygen concentrators does not meet the requirement, it is determined that the typical fault mode atlas library needs to be updated according to the preset update strategy; When the sum of the failure times of different frequently used oxygen concentrators meets the requirements: Determining problematic oxygen concentrators among the frequently used oxygen concentrators by using the number of failures, and when the number of problematic oxygen concentrators does not meet the requirement, determining that an update process of a typical failure mode atlas library needs to be performed according to a preset update strategy; When the number of oxygen concentrators in question meets the requirements: The comprehensive update requirement coefficient is determined by the number of failures of different frequently used oxygen concentrators and the usage weight coefficient, and the comprehensive update requirement coefficient is used to determine whether it is necessary to update the typical failure mode atlas library according to a preset update strategy.

[0043] It should be noted that when the comprehensive update requirement coefficient is greater than the preset update requirement coefficient threshold, it is determined that the typical failure mode atlas library needs to be updated according to the preset update strategy.

[0044] S2: when it is determined that there is a matching deviation fault type in the fault type based on the matching situation between the characteristic information in the operation data and the typical fault mode atlas library, proceed to the next step; Specifically, the matching condition includes the deviation between the characteristic information and the operating parameter characteristics of the fault type in the typical fault mode spectrum library.

[0045] Specifically, Figure 4 As shown, the method for determining the matching deviation fault type is: The number of historical faults corresponding to the fault type is used as the matching fault number, and the deviation between the characteristic information and the operating parameter characteristics of different matching fault times is determined based on the matching of the characteristic information in the operating data corresponding to the fault type and the operating parameter characteristics of the fault type in the typical fault mode atlas library; Determine the number of deviations of the operating parameter characteristics in different matching failure times that do not meet the requirements according to the deviation situation, and determine the matching deviation coefficients of different matching failure times according to the proportion of the number of deviations that do not meet the requirements in the number of the operating parameter characteristics; Based on average values ​​of matching deviation coefficients of different matching failure times, it is determined whether the fault type is a matching deviation fault type.

[0046] Further, when an average value of the matching deviation coefficients of the fault type at different matching failure times is greater than a preset deviation coefficient threshold, the fault type is determined to be a matching deviation fault type.

[0047] It can be understood that when there is no matching deviation fault type, the updating process of the typical fault mode map library of the matching oxygen concentrator is performed in a preset time period.

[0048] It should also be noted that the method for determining the matching deviation fault type is: The number of historical faults corresponding to the fault type is used as the matching fault number, and the deviation between the characteristic information and the operating parameter characteristics of different matching fault times is determined based on the matching of the characteristic information in the operating data corresponding to the fault type and the operating parameter characteristics of the fault type in the typical fault mode atlas library; Determine the number of deviations of the operating parameter characteristics in different matching failure times that do not meet the requirements according to the deviation situation, and determine the matching deviation coefficients of different matching failure times according to the proportion of the number of deviations that do not meet the requirements in the number of the operating parameter characteristics; The number of matching failures in which the matching deviation coefficient does not meet the requirements is taken as the number of identification deviation failures, and the number of matching oxygen concentrators with the number of identification deviation failures is used to determine whether the fault type is a matching deviation fault type.

[0049] Specifically, when the number of matching oxygen concentrators having the identification deviation fault times is greater than the preset number of matching oxygen concentrators, it is determined that the fault type is a matching deviation fault type.

[0050] In another possible embodiment, the method for determining the matching deviation fault type is: The number of historical faults corresponding to the fault type is used as the matching fault number, and the deviation between the characteristic information of different matching fault times and the operating parameter characteristics is determined based on the matching situation of the characteristic information in the operating data corresponding to the fault type and the operating parameter characteristics of the fault type in the typical fault mode spectrum library. When the deviation between the characteristic information of different matching fault times and the operating parameter characteristics of the fault type meets the requirements, it is determined that the fault type does not belong to the matching deviation fault type; When the deviation between the characteristic information of the fault type and the operating parameter characteristics does not meet the required matching fault times: Determine the number of deviations of the operating parameter characteristics in different matching fault times that do not meet the requirements according to the deviation situation, and determine the matching deviation coefficients of different matching fault times by using the proportion of the number of deviations that do not meet the requirements in the number of the operating parameter characteristics, and when the average value of the matching deviation coefficients of different matching fault times is greater than a preset deviation coefficient threshold, determine that the fault type is a matching deviation fault type; When the average value of the matching deviation coefficients of different matching failure times is not greater than the preset deviation coefficient threshold: The number of matching failures in which the matching deviation coefficient does not meet the requirement is used as the number of identification deviation failures. When the number of identification deviation failures does not meet the requirement or the number of matching oxygen concentrators with the number of identification deviation failures does not meet the requirement, the fault type is determined to be a matching deviation fault type. When the number of identification deviation faults and the number of matched oxygen concentrators with identification deviation faults meet the requirements: Determine the identification deviation coefficients of different matching oxygen concentrators at different matching fault times according to the matching deviation coefficients of different matching oxygen concentrators at the fault type; when the identification deviation coefficients of different matching oxygen concentrators at the fault type meet the requirements, determine that the fault type does not belong to the matching deviation fault type; When there is a matching oxygen concentrator whose identification deviation coefficient does not meet the requirements in the fault type: When the number of matched oxygen concentrators whose identification deviation coefficients do not meet the requirements is greater than a preset number threshold, it is determined that the fault type is a matching deviation fault type; When the number of matching oxygen concentrators that do not meet the identification deviation coefficient requirement is not greater than the preset number threshold: The identification deviation amount of the fault type is determined according to the identification deviation coefficient of the fault type for different matching oxygen concentrators, and the identification deviation amount is used to determine whether the fault type is a matching deviation fault type.

[0051] Further, when the identification deviation of the fault type is greater than a preset deviation threshold, the fault type is determined to be a matching deviation fault type.

[0052] S3 determines the similarity of the operation data within a preset time period of the historical fault number corresponding to the matching deviation fault type, and determines the matching operation scenario and matching operation coefficient of the matching deviation fault type by using the similarity; Specifically, the similarity of the operating data within the preset time period is determined according to the deviation of the operating data at different moments within the preset time period.

[0053] Specifically, Figure 5 As shown, the method for determining the matching operation scenario of the matching deviation fault type is: The number of faults corresponding to the matching deviation fault type is used as the number of matching deviation faults, and based on the similarity of the operating data of different matching deviation fault numbers within the corresponding preset time period, the similarity coefficients of the operating data corresponding to different matching deviation fault numbers are determined; Based on the similarity coefficient of the operating data, the matching deviation fault number is divided into different similar operating data intervals; The matching operation scenario of the matching deviation fault type is determined according to the number of matching deviation fault times in different similar operation data intervals.

[0054] It should be noted that the matching operation scenario of the matching deviation fault type is determined by the number of matching deviation fault times in different similar operation data intervals, specifically including: The similar operation data interval with the largest number of matching deviation failures is used as the matching operation data interval; A matching operation scenario of the matching deviation fault type is determined according to the intervals in which different operation data corresponding to the matching operation data interval are located.

[0055] Furthermore, the matching operation coefficient is determined according to the proportion of the number of matching deviation failures corresponding to the matching operation scenario.

[0056] S4 obtains the operation data of different matching oxygen concentrators in different matching operation scenarios and the matching operation coefficients of the matching operation scenarios, and determines the update processing strategy in combination with the historical fault times corresponding to the matching deviation fault types of different matching oxygen concentrators, and uses the update processing strategy to update the typical fault mode atlas library.

[0057] It can be understood that the method for determining the update processing strategy is: Determine the number of historical failures of different matching oxygen concentrators in the matching deviation fault type according to the number of historical failures corresponding to the matching deviation fault type of different matching oxygen concentrators; Determine the historical operation times of different matching oxygen concentrators in the matching deviation fault type based on the operation data of the matching operation scenarios of different matching oxygen concentrators, and determine the operation risk coefficients of different matching oxygen concentrators in combination with the matching operation scenarios and the matching operation coefficients of the matching deviation fault type; The fault identification risk coefficient of the matching deviation fault type is determined according to the number of historical faults of different matching oxygen concentrators in the matching deviation fault type and the operation risk coefficient, and the update processing strategy is determined according to the sum of the fault identification risk coefficients of different matching deviation fault types.

[0058] Furthermore, the method for determining the fault identification risk coefficient of the matching deviation fault type is: According to the historical fault times and operation risk coefficients of the matching deviation fault types of different matching oxygen concentrators, a matching oxygen concentrator with a historical fault time within a preset fault time range and an operation risk coefficient greater than a preset coefficient threshold is determined, and the matching oxygen concentrator is used as a screening matching oxygen concentrator; A fault identification risk coefficient of the matching deviation fault type is determined according to a proportion of the screened matching oxygen concentrators in the number of the matching oxygen concentrators.

[0059] It should be noted that the update processing strategy is determined according to the sum of the fault identification risk coefficients of different matching deviation fault types, specifically including: When the sum of the fault identification risk coefficients of different matching deviation fault types is greater than the preset risk coefficient threshold, the typical fault mode atlas library is updated according to the preset update strategy; When the sum of the fault identification risk coefficients of different matching deviation fault types is not greater than the preset risk coefficient threshold, the update processing strategy is determined using the risk coefficient interval corresponding to the sum of the fault identification risk coefficients of different matching deviation fault types.

[0060] Furthermore, the update processing strategy is divided according to update objects, wherein the update objects include updating all fault types and updating only matching deviation fault types.

[0061] It can be understood that when the sum of the fault identification risk coefficients of different matching deviation fault types is less than the preset value of the risk coefficient, the matching deviation fault type is only updated according to the preset time period; when the sum of the fault identification risk coefficients of different matching deviation fault types is not less than the preset value of the risk coefficient, all fault types are updated according to the preset time period.

[0062] In another possible embodiment, the method for determining the update processing strategy is: S41 determines the number of historical failures of different matching oxygen concentrators at the matching deviation fault type according to the number of historical failures corresponding to the matching deviation fault type of different matching oxygen concentrators, determines the number of historical operation of different matching oxygen concentrators at the matching deviation fault type according to the operation data of the matching operation scenario of the matching deviation fault type, and determines the identification deviation risk value of different matching oxygen concentrators at the matching deviation fault type in combination with the matching operation scenario and the matching operation coefficient of the matching deviation fault type and the number of historical failures of the matching oxygen concentrator at the matching deviation fault type; S42 determines the fault identification reliability coefficients of different matching deviation fault types according to the identification deviation risk values ​​of the matching deviation fault types for different matching oxygen concentrators; S43 determines a fault identification reliability value using the fault identification reliability coefficients of different matching deviation fault types, and determines the update processing strategy according to the fault identification reliability value.

[0063] Specifically, the update processing strategy is determined according to the fault identification reliability value, and specifically includes: When the fault identification reliability value is greater than a preset fault identification reliability threshold, the update processing strategy is determined by using the preset reliability interval in which the fault identification reliability value is located and the corresponding set processing strategy; When the fault identification reliability value is not greater than a preset fault identification reliability threshold, the typical fault mode atlas library is updated according to a preset update strategy.

[0064] Optionally, the above step S41 includes the following contents: S411 determines the number of historical failures of different matching oxygen concentrators in different matching deviation fault types according to the number of historical failures of different matching oxygen concentrators corresponding to the matching deviation fault types. When there is a matching oxygen concentrator whose number of historical failures in different matching deviation fault types does not meet the requirements, the process proceeds to step S412. When there is no matching oxygen concentrator whose number of historical failures in different matching deviation fault types does not meet the requirements, the process proceeds to step S413. S412: When the number of historical failures of different matching deviation failure types does not meet the requirement and the number of matching oxygen concentrators does not meet the requirement, the typical failure mode map library is updated according to the preset update strategy; when the number of historical failures of different matching deviation failure types does not meet the requirement and the number of matching oxygen concentrators does meet the requirement, the process proceeds to step S413; S413 determines the historical operation times of different matching oxygen concentrators in the matching deviation fault type according to the operation data of the matching operation scenarios of the matching deviation fault type of different matching oxygen concentrators, and determines the identification deviation risk values ​​of different matching oxygen concentrators in the matching deviation fault type according to the matching operation scenarios and the matching operation coefficients of the matching deviation fault type and the historical failure times of the matching oxygen concentrators in the matching deviation fault type. When there are matching oxygen concentrators whose sum of identification deviation risk values ​​in different matching deviation fault types does not meet the requirements, the process proceeds to step S414. When there are no matching oxygen concentrators whose sum of identification deviation risk values ​​in different matching deviation fault types does not meet the requirements, the process proceeds to step S42. S414 When the sum of the identification deviation risk values ​​of different matching deviation fault types and the number of matching oxygen concentrators that do not meet the requirements are greater than the preset number of matching oxygen concentrators, the typical failure mode spectrum library is updated according to the preset update strategy; when the sum of the identification deviation risk values ​​of different matching deviation fault types and the number of matching oxygen concentrators that do not meet the requirements are not greater than the preset number of matching oxygen concentrators, proceed to step S42.

[0065] Optionally, the above step S42 includes the following contents: S421 determines the fault identification reliability coefficients of different matching deviation fault types according to the identification deviation risk values ​​of the matching deviation fault types of different matching oxygen concentrators. When there is a matching deviation fault type whose fault identification reliability coefficient does not meet the requirements, the typical fault mode atlas library is updated according to the preset update strategy. When there is no matching deviation fault type whose fault identification reliability coefficient does not meet the requirements, the process proceeds to step S422. S422: When the fault identification reliability coefficients of different matching deviation fault types are all greater than the preset reliability coefficient threshold, the typical fault mode map library of the matching oxygen concentrator is updated using a preset time period; when there is a matching deviation fault type whose fault identification reliability coefficient is not greater than the preset reliability coefficient threshold, the process proceeds to step S423; S423 When the number of matching deviation fault types whose fault identification reliability coefficient is not greater than the preset reliability coefficient threshold does not meet the requirements, the typical fault mode spectrum library is updated according to the preset update strategy; when the number of matching deviation fault types whose fault identification reliability coefficient is not greater than the preset reliability coefficient threshold meets the requirements, proceed to step S43.

[0066] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0067] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded 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, multitasking and parallel processing are also possible or may be advantageous.

[0068] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. An online adaptive accurate diagnosis and early warning device for a medical oxygen concentrator, characterized in that: Specifically include: Data acquisition module, spectrum library building module, diagnostic model building module, spectrum library updating module; The data acquisition module is responsible for collecting and processing the operating data of the medical oxygen concentrator; The atlas library building module is responsible for using the historical fault data of the medical oxygen concentrator to establish a typical fault mode atlas library according to the operating parameter characteristics under different fault modes; The diagnostic module building module is responsible for building an intelligent diagnostic model, automatically extracting feature information from the operating data, and comparing it with a typical fault mode atlas library to determine the fault mode; The atlas library update module is responsible for determining an update processing strategy according to the matching situation between the characteristic information of the type of medical oxygen concentrator and the typical failure mode atlas library, and using the update processing strategy to update the typical failure mode atlas library of the type of medical oxygen concentrator.

2. The online adaptive accurate diagnosis and early warning device for medical oxygen concentrator according to claim 1, characterized in that: The operating parameter characteristics include one or more of temperature, humidity, pressure, flow, purity, rotation speed, vibration, displacement, noise, and key phase.

3. The online adaptive accurate diagnosis and early warning device for medical oxygen concentrator according to claim 1, characterized in that: The update processing strategy is determined based on the matching deviation between the characteristic information of the medical oxygen concentrator of the type and the typical failure mode map library, wherein when the matching deviation does not meet the requirements and the number of historical failures is greater than a preset failure number threshold, it is determined that the medical oxygen concentrator of the type needs to be updated.

4. An online adaptive accurate diagnosis and early warning method for a medical oxygen concentrator, characterized in that: Specifically include: The medical oxygen concentrator of the type is used as a matching oxygen concentrator, and when it is determined that it is not necessary to update the typical failure mode atlas library according to the preset update strategy based on the analysis results of the historical usage data and failure data of the matching oxygen concentrator, the next step is entered; When it is determined that there is a matching deviation fault type in the fault type based on the matching situation between the characteristic information in the operation data and the typical fault mode atlas library, proceed to the next step; Determine similarities of operation data within a preset time period of the number of historical faults corresponding to the matching deviation fault type, and determine a matching operation scenario and a matching operation coefficient of the matching deviation fault type using the similarities; The operation data of different matching oxygen concentrators in different matching operation scenarios and the matching operation coefficients of the matching operation scenarios are obtained, and the update processing strategy is determined in combination with the historical fault times corresponding to the matching deviation fault types of different matching oxygen concentrators, and the update processing strategy is used to update the typical failure mode atlas library.

5. The online adaptive accurate diagnosis and early warning method for medical oxygen concentrator according to claim 4, characterized in that: The historical usage data of the matched oxygen concentrator includes the historical usage times of the matched oxygen concentrator, the usage durations of different historical usage times, and the oxygen production amounts.

6. The online adaptive accurate diagnosis and early warning method for medical oxygen concentrator according to claim 4, characterized in that: The analysis result of the fault data includes the number of faults of different matched oxygen concentrators in different historical usage times.

7. The online adaptive accurate diagnosis and early warning method for medical oxygen concentrator according to claim 4, characterized in that: Determine that it is not necessary to update the typical failure mode atlas library according to the preset update strategy, including: Determine different historical usage times and usage durations of different historical usage times based on the historical usage data of the matched oxygen concentrator, determine total usage durations of different matched oxygen concentrators based on the usage durations of different historical usage times, and determine a frequently used oxygen concentrator among the matched oxygen concentrators based on the total usage durations; Determining the number of failures of different frequently used oxygen concentrators according to the analysis results of the failure data of the frequently used oxygen concentrators, and determining the problematic oxygen concentrator among the frequently used oxygen concentrators by using the number of failures; Whether it is necessary to update the typical failure mode atlas library according to a preset update strategy is determined based on the proportion of the problematic oxygen concentrators in the frequently used oxygen concentrators.

8. The online adaptive accurate diagnosis and early warning method for medical oxygen concentrator according to claim 7, characterized in that: When the proportion of the problematic oxygen concentrators in the frequently used oxygen concentrators is greater than a preset proportion threshold, it is determined that there is no need to update the typical failure mode atlas library according to a preset update strategy.

9. The online adaptive accurate diagnosis and early warning method for medical oxygen concentrator according to claim 4, characterized in that: The method for determining the fault identification risk coefficient of the matching deviation fault type is: According to the historical fault times and operation risk coefficients of the matching deviation fault types of different matching oxygen concentrators, a matching oxygen concentrator with a historical fault time within a preset fault time range and an operation risk coefficient greater than a preset coefficient threshold is determined, and the matching oxygen concentrator is used as a screening matching oxygen concentrator; A fault identification risk coefficient of the matching deviation fault type is determined according to a proportion of the screened matching oxygen concentrators in the number of the matching oxygen concentrators.

10. The online adaptive accurate diagnosis and early warning method for medical oxygen concentrator according to claim 9, characterized in that: The update processing strategy is determined according to the sum of the fault identification risk coefficients of different matching deviation fault types, specifically including: When the sum of the fault identification risk coefficients of different matching deviation fault types is greater than the preset risk coefficient threshold, the typical fault mode atlas library is updated according to the preset update strategy; When the sum of the fault identification risk coefficients of different matching deviation fault types is not greater than the preset risk coefficient threshold, the update processing strategy is determined using the risk coefficient interval corresponding to the sum of the fault identification risk coefficients of different matching deviation fault types.

Images