An Online Adaptive Precise Diagnosis and Warning Method and Device for Medical Oxygen Generators

Abstract

The present invention provides an online adaptive precise diagnosis and warning method and device for a medical oxygen generator, belonging to the technical field of monitoring devices, specifically including: among them, the data acquisition module is responsible for collecting and processing the operation data of the medical oxygen generator, the atlas library construction module is responsible for using the historical fault data of the medical oxygen generator to establish a typical fault mode atlas library according to the operation parameter characteristics under different fault modes, the diagnosis module construction module is responsible for constructing an intelligent diagnosis model, automatically extracting the characteristic information in the operation data, and comparing it with the typical fault mode atlas library to determine the fault mode, and the atlas library update module is responsible for determining the update processing strategy according to the matching situation between the characteristic information of the medical oxygen generator of the type and the typical fault mode atlas library, and using the update processing strategy to update the typical fault mode atlas library of the medical oxygen generator of the type, improving the accuracy of fault identification and processing.

Description

Technical Field

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

[0002] During the long-term operation of a medical oxygen generator, various faults may occur due to various factors. Most traditional fault diagnosis methods are based on offline analysis and regular detection, and cannot discover equipment faults in real time and accurately.

[0003] To solve the above technical problems, in the invention patent application CN202311379673.8 "A Monitoring System for a Medical Oxygen Generator", numerical parameters are obtained by substituting the parameter intervals required by the segmented monitoring module for data correction, and then the numerical parameters are used as the cross-line warning parameters for comparison with the predicted parameters, so as to determine whether the oxygen supply demand of the oxygen supply pipe network is met or exceeded, avoiding the influence of the accumulation of oxygen production shortage errors on the accuracy of monitoring data. However, the above technical solution has the following technical problems:

[0004] During the monitoring and early warning process of the oxygen generator, the fault modes of the medical oxygen generator are complex and diverse, and different devices may have differences. Using a fixed fault mode atlas library may not be able to accurately identify faults. Therefore, how to realize the adaptive update processing of the fault mode atlas library and accurately identify the faults of the medical oxygen generator has become an urgent technical problem to be solved.

[0005] In view of the above technical problems, specifically, the present application provides an online adaptive precise diagnosis and early warning method and device for a medical oxygen generator. Summary of the Invention

[0006] To achieve the object of the present invention, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present application provides an online adaptive precise diagnosis and early warning device for a medical oxygen generator, specifically including:

[0008] A data acquisition module, an atlas library establishment module, a diagnosis model construction module, and an atlas library update module;

[0009] The data acquisition module is responsible for collecting and processing the operation data of the medical oxygen generator;

[0010] The atlas library construction module is responsible for establishing a typical fault mode atlas library using the historical fault data of the medical oxygen generator according to the operation parameter characteristics under different fault modes;

[0011] The diagnostic module construction module is responsible for constructing an intelligent diagnostic model, automatically extracting feature information from the operation data, and comparing it with the typical fault mode atlas library to determine the fault mode.

[0012] The atlas library update module is responsible for determining the update processing strategy according to the matching situation between the feature information of the medical oxygen generator of the type and the typical fault mode atlas library, and using the update processing strategy to update the typical fault mode atlas library of the medical oxygen generator of the type.

[0013] A further technical solution is that the operating parameter features include one or more of temperature, humidity, pressure, flow rate, purity, rotational speed, vibration, displacement, noise, and key phase.

[0014] A further technical solution is that the update processing strategy is determined according to the matching deviation situation between the feature information of the medical oxygen generator of the type and the typical fault mode atlas library. When the number of historical faults where the matching deviation situation does not meet the requirements is greater than the preset fault number threshold, it is determined that the medical oxygen generator of the type needs to be updated.

[0015] The beneficial effects of the present invention are as follows:

[0016] Real-time and accurate diagnosis: The present invention can collect the operation data of the medical oxygen generator in real time, and combined with the intelligent diagnostic model, realize real-time and accurate diagnosis of equipment faults, and timely discover potential faults.

[0017] Adaptive diagnosis: By updating the diagnostic standard library in real time, it can adapt to the differences between different units and the changes in the operating environment, realize adaptive diagnosis, and improve the accuracy and reliability of diagnosis.

[0018] 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 generator, and reduce the maintenance cost.

[0019] On the other hand, the present application provides a method for online adaptive accurate diagnosis and warning of a medical oxygen generator, which specifically includes:

[0020] S1 When the medical oxygen generator of the type is used as the matching oxygen generator and it is determined that the typical fault mode atlas library does not need to be updated according to the preset update strategy based on the analysis results of the historical usage data and fault data of the matching oxygen generator, proceed to the next step;

[0021] S2 When it is determined that there is a matching deviation fault type in the fault type based on the matching situation between the feature information in the operation data and the typical fault mode atlas library, proceed to the next step;

[0022] S3 determines the similarity of the operation data within the preset time period of the historical failure times corresponding to the matching deviation failure type, and determines the matching operation scenario and the matching operation coefficient of the matching deviation failure type by using the similarity;

[0023] S4 obtains the operation data of different matching oxygen generators in different matching operation scenarios and the matching operation coefficients of the matching operation scenarios, and determines the update processing strategy by combining the historical failure times corresponding to the matching deviation failure types of different matching oxygen generators, and uses the update processing strategy to perform the update processing of the typical fault mode atlas library.

[0024] A further technical solution lies in that the historical usage data of the matching oxygen generator includes the historical usage times of the matching oxygen generator, the usage durations and oxygen production amounts of different historical usage times.

[0025] A further technical solution lies in that the analysis results of the fault data include the fault times of different matching oxygen generators in different historical usage times.

[0026] A further technical solution lies in that determining not to perform the update processing of the typical fault mode atlas library according to the preset update strategy specifically includes:

[0027] Determine different historical usage times and the usage durations of different historical usage times with the historical usage data of the matching oxygen generator, and determine the total usage duration of different matching oxygen generators by using the usage durations of different historical usage times, and determine the frequently used oxygen generators in the matching oxygen generators based on the total usage duration;

[0028] According to the analysis results of the fault data of the frequently used oxygen generators, determine the fault times of different frequently used oxygen generators, and determine the problematic oxygen generators in the frequently used oxygen generators by using the fault times;

[0029] Determine whether to perform the update processing of the typical fault mode atlas library according to the preset update strategy by the quantity proportion of the problematic oxygen generators in the frequently used oxygen generators.

[0030] A further technical solution lies in that the frequently used oxygen generators in the matching oxygen generators are the matching oxygen generators with a total usage duration greater than the preset usage duration.

[0031] A further technical solution lies in that the problematic oxygen generators are the frequently used oxygen generators whose fault times do not meet the requirements.

[0032] A further technical solution lies in that when the quantity proportion of the problematic oxygen generators in the frequently used oxygen generators is greater than the preset quantity proportion threshold, it is determined not to perform the update processing of the typical fault mode atlas library according to the preset update strategy.

[0033] Other features and advantages will be described in the following specification. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification and the accompanying drawings.

[0034] To make the above objectives, features, and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given, in conjunction with the accompanying drawings, and are described in detail as follows. Description of the Drawings

[0035] By referring to the accompanying drawings and describing its exemplary embodiments in detail, the above and other features and advantages of the present invention will become more obvious;

[0036] Figure 1 is a framework diagram of an online adaptive precise diagnosis and warning device for a medical oxygen generator;

[0037] Figure 2 is a flowchart of a method for online adaptive precise diagnosis and warning of a medical oxygen generator;

[0038] Figure 3 is a flowchart for determining that the update process of the typical fault mode atlas library does not need to be performed according to the preset update strategy;

[0039] Figure 4 is a flowchart of a method for determining the matching deviation fault type;

[0040] Figure 5 is a flowchart of a method for determining the matching operation scenario of the matching deviation fault type. Detailed Embodiments

[0041] 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 accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of this specification, rather than all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this specification.

[0042] The objective of the present invention is to provide an online adaptive precise diagnosis technology for a medical oxygen generator. By collecting device operation data in real time and combining with an intelligent diagnosis model, online adaptive precise diagnosis of faults in the medical oxygen generator is realized, and the maintenance efficiency and reliability of the device are improved.

[0043] Real-time data acquisition: Use high-precision sensors to collect the operating data of medical oxygen generators in real time, including one or more of the key parameters such as temperature, humidity, pressure, flow rate, purity, rotational speed, vibration, displacement, noise, and key phase. Transmit the collected data to the diagnostic system through wired or wireless communication methods to ensure the real-time and accuracy of the data.

[0044] Establishment of typical fault mode atlas library: Collect historical fault data of medical oxygen generators, analyze the characteristics of operating parameters under different fault modes, and establish a typical fault mode atlas library. This atlas library contains the characteristic information of various common faults and provides a reference basis for fault diagnosis.

[0045] Establishment of equipment operating state model: According to the real-time collected data and the typical fault mode atlas library, establish the operating, fault, and standby state models of medical oxygen generators. Use machine learning algorithms such as decision trees and random forests to train and optimize the models so that they can accurately identify different operating states.

[0046] Construction of deep convolutional network intelligent diagnosis model: Construct a deep convolutional network intelligent diagnosis model, which can automatically extract the characteristic information from the operating data and compare it with the typical fault mode atlas library to determine the fault mode. According to the differences of different units, update the diagnostic standard library in real time to achieve dynamic detection and accurate diagnosis of gradual and sudden faults.

[0047] Use high-precision sensors to collect the oxygen flow rate of medical oxygen generators in real time. The algorithm will automatically calculate the cumulative oxygen consumption and average oxygen consumption in the past day or month. Establish an equipment operating state model based on the real-time collected data. When the oxygen consumption suddenly increases, the algorithm will detect the abnormality and send out a flow warning signal to prevent pressure shortage and energy waste caused by problems such as pipeline leakage.

[0048] The model adopts the convolutional layer formula of the deep convolutional network:

[0049]

[0050] Where W is the convolutional kernel weight, b is the bias term, and f is the ReLU activation function. The accuracy rate of fault diagnosis reaches 98.7%, and the recall rate is 96.5%. Experimental data shows that the system can identify a sudden increase in oxygen flow rate (such as a leakage fault) within 2 seconds, and the false alarm rate is less than 1.2%, significantly improving the maintenance response efficiency.

[0051] Use historical fault data to establish a typical fault mode atlas library, and establish an equipment operating state model based on the real-time collected data. Input the real-time collected data into the deep convolutional network intelligent diagnosis model and compare it with the typical fault mode atlas library to determine the fault mode.

[0052] Example 1 is as followsFigure 1 As shown in the figure, the present application provides an online adaptive precise diagnosis and warning device for a medical oxygen generator, specifically including:

[0053] A data acquisition module, a spectrum library establishment module, a diagnosis model construction module, and a spectrum library update module;

[0054] The data acquisition module is responsible for collecting and processing the operation data of the medical oxygen generator;

[0055] The spectrum library construction module is responsible for using the historical fault data of the medical oxygen generator to establish a typical fault mode spectrum library according to the operation parameter characteristics under different fault modes;

[0056] The diagnosis module construction module is responsible for constructing an intelligent diagnosis model, automatically extracting the characteristic information in the operation data, and comparing it with the typical fault mode spectrum library to determine the fault mode;

[0057] The spectrum library update module is responsible for determining the update processing strategy according to the matching situation between the characteristic information of the medical oxygen generator of the type and the typical fault mode spectrum library, and using the update processing strategy to update the typical fault mode spectrum library of the medical oxygen generator of the type.

[0058] Furthermore, the operation parameter characteristics include one or more of temperature, humidity, pressure, flow rate, purity, rotation speed, vibration, displacement, noise, and key phase.

[0059] Specifically, the update processing strategy is determined according to the matching deviation situation between the characteristic information of the medical oxygen generator of the type and the typical fault mode spectrum library. When the number of historical faults where the matching deviation situation does not meet the requirements is greater than the preset fault number threshold, it is determined that the medical oxygen generator of the type needs to be updated.

[0060] Example 2 On the other hand, as Figure 2 shown in the figure, the present application provides an online adaptive precise diagnosis and warning method for a medical oxygen generator, specifically including:

[0061] S1 When the medical oxygen generator of the type is used as the matching oxygen generator and it is determined that the typical fault mode spectrum library does not need to be updated according to the preset update strategy based on the analysis results of the historical usage data and fault data of the matching oxygen generator, proceed to the next step;

[0062] Furthermore, the historical usage data of the matching oxygen generator includes the historical usage times of the matching oxygen generator, the usage duration and oxygen production amount for different historical usage times.

[0063] Specifically, the analysis result of the fault data includes the number of faults of different matching oxygen generators in different historical usage times.

[0064] It should be noted that, as Figure 3 shown, it is determined that there is no need to update the typical fault mode atlas library according to the preset update strategy, specifically including:

[0065] Determine different historical usage times and the usage durations of different historical usage times based on the historical usage data of the matching oxygen generator, and use the usage durations of different historical usage times to determine the total usage duration of different matching oxygen generators. Based on the total usage duration, determine the frequently used oxygen generators in the matching oxygen generators;

[0066] According to the analysis results of the fault data of the frequently used oxygen generators, determine the fault times of different frequently used oxygen generators, and use the fault times to determine the problematic oxygen generators among the frequently used oxygen generators;

[0067] Determine whether to update the typical fault mode atlas library according to the preset update strategy by the proportion of the number of the problematic oxygen generators in the frequently used oxygen generators.

[0068] Furthermore, the frequently used oxygen generators in the matching oxygen generators are the matching oxygen generators with a total usage duration greater than the preset usage duration.

[0069] It can be understood that the problematic oxygen generators are the frequently used oxygen generators whose fault times do not meet the requirements.

[0070] Specifically, when the proportion of the number of the problematic oxygen generators in the frequently used oxygen generators is greater than the preset proportion threshold, it is determined that there is no need to update the typical fault mode atlas library according to the preset update strategy.

[0071] Optionally, determining that there is no need to update the typical fault mode atlas library according to the preset update strategy specifically includes:

[0072] Determine different historical usage times and the usage durations of different historical usage times based on the historical usage data of the matching oxygen generator, and use the usage durations of different historical usage times to determine the total usage duration of different matching oxygen generators. Based on the total usage duration, determine the frequently used oxygen generators in the matching oxygen generators;

[0073] According to the analysis results of the fault data of the frequently used oxygen generators, determine the fault times of different frequently used oxygen generators, and use the fault times to determine the problematic oxygen generators among the frequently used oxygen generators;

[0074] Determine whether to update the typical fault mode atlas library according to the preset update strategy through the number of the problematic oxygen generators and the number of the frequently used oxygen generators.

[0075] Further, when the number of the problem oxygen generators is greater than the preset number of problem oxygen generators and the number of frequently used oxygen generators is greater than the preset number of frequently used oxygen generators, it is determined that the update process of the typical fault mode atlas library needs to be carried out according to the preset update strategy.

[0076] Optionally, determining that the update process of the typical fault mode atlas library does not need to be carried out according to the preset update strategy specifically includes:

[0077] Determining different historical usage times and the usage durations of different historical usage times based on the historical usage data of the matching oxygen generators, and determining the total usage duration of the matching oxygen generators by using the usage durations of different historical usage times. When it is determined that there are no frequently used oxygen generators among the matching oxygen generators based on the total usage duration, it is determined that the update process of the typical fault mode atlas library does not need to be carried out according to the preset update strategy;

[0078] When it is determined that there are frequently used oxygen generators among the matching oxygen generators based on the total usage duration:

[0079] Determining the usage weight coefficients of different frequently used oxygen generators based on the total usage durations of different frequently used oxygen generators. When the sum of the usage weight coefficients of different frequently used oxygen generators is greater than the preset weight coefficient threshold, it is determined that the update process of the typical fault mode atlas library needs to be carried out according to the preset update strategy;

[0080] When the sum of the usage weight coefficients of different frequently used oxygen generators is not greater than the preset weight coefficient threshold:

[0081] When the sum of the usage weight coefficients of different frequently used oxygen generators is within the preset usage weight coefficient range, it is determined that the update process of the typical fault mode atlas library does not need to be carried out according to the preset update strategy;

[0082] When the sum of the usage weight coefficients of different frequently used oxygen generators is not within the preset usage weight coefficient range:

[0083] Determining the fault times of different frequently used oxygen generators according to the analysis results of the fault data of the frequently used oxygen generators. When the sum of the fault times of different frequently used oxygen generators does not meet the requirements, it is determined that the update process of the typical fault mode atlas library needs to be carried out according to the preset update strategy;

[0084] When the sum of the fault times of different frequently used oxygen generators meets the requirements:

[0085] Determine the problematic oxygen generators among the frequently used oxygen generators by using the number of failures. When the number of problematic oxygen generators does not meet the requirements, it is determined that the typical fault mode atlas library needs to be updated according to the preset update strategy;

[0086] When the number of problematic oxygen generators meets the requirements:

[0087] Determine the comprehensive update demand coefficient based on the number of failures and the usage weight coefficients of different frequently used oxygen generators, and use the comprehensive update demand coefficient to determine whether the typical fault mode atlas library needs to be updated according to the preset update strategy.

[0088] It should be noted that when the comprehensive update demand coefficient is greater than the preset update demand coefficient threshold, it is determined that the typical fault mode atlas library needs to be updated according to the preset update strategy.

[0089] S2 When it is determined that there is a matching deviation fault type among the fault types based on the matching situation between the characteristic information in the operation data and the typical fault mode atlas library, enter the next step;

[0090] Specifically, the matching situation includes the deviation situation between the characteristic information and the operation parameter characteristics of the fault types in the typical fault mode atlas library.

[0091] Specifically, as Figure 4 shown, the method for determining the matching deviation fault type is:

[0092] Take the historical number of failures corresponding to the fault type as the matching number of failures, and determine the deviation situation between the characteristic information of different matching numbers of failures and the operation parameter characteristics of the fault types in the typical fault mode atlas library based on the matching situation between the characteristic information in the operation data corresponding to the fault type and the operation parameter characteristics of the fault types in the typical fault mode atlas library;

[0093] Determine the number of operation parameter characteristics whose deviation amounts do not meet the requirements among different matching numbers of failures according to the deviation situation, and use the proportion of the number of deviation amounts that do not meet the requirements in the number of operation parameter characteristics to determine the matching deviation coefficient of different matching numbers of failures;

[0094] Based on the average value of the matching deviation coefficients of different matching numbers of failures, determine whether the fault type is a matching deviation fault type.

[0095] Furthermore, when the average value of the matching deviation coefficients of the fault type for different matching numbers of failures is greater than the preset deviation coefficient threshold, it is determined that the fault type is a matching deviation fault type.

[0096] It is understandable that when there is no matching deviation fault type, the update process of the typical fault mode atlas library of the matching oxygen generator is carried out using a preset time period.

[0097] In addition, it should be noted that the method for determining the matching deviation fault type is as follows:

[0098] Taking the historical fault times corresponding to the fault type as the matching fault times, based on the matching situation between the characteristic information in the operation data corresponding to the fault type and the operation parameter characteristics of the fault type in the typical fault mode atlas library, determine the deviation situation between the characteristic information and the operation parameter characteristics of different matching fault times;

[0099] According to the deviation situation, determine the number of operation parameter characteristics whose deviation amount does not meet the requirements among different matching fault times, and use the proportion of the number of deviation amounts that do not meet the requirements in the number of operation parameter characteristics to determine the matching deviation coefficient of different matching fault times;

[0100] Taking the matching fault times with the matching deviation coefficient not meeting the requirements as the identified deviation fault times, and using the number of matching oxygen generators with identified deviation fault times, determine whether the fault type is a matching deviation fault type.

[0101] Specifically, when the number of matching oxygen generators with identified deviation fault times is greater than the preset number of matching oxygen generators, it is determined that the fault type is a matching deviation fault type.

[0102] In another possible embodiment, the method for determining the matching deviation fault type is as follows:

[0103] Taking the historical fault times corresponding to the fault type as the matching fault times, based on the matching situation between the characteristic information in the operation data corresponding to the fault type and the operation parameter characteristics of the fault type in the typical fault mode atlas library, determine the deviation situation between the characteristic information and the operation parameter characteristics of different matching fault times. When the deviation situations between the characteristic information and the operation parameter characteristics of the fault type in different matching fault times all meet the requirements, it is determined that the fault type does not belong to the matching deviation fault type;

[0104] When there are matching fault times for the fault type where the deviation situation between the characteristic information and the operation parameter characteristics does not meet the requirements:

[0105] Determine the number of running parameter characteristics whose deviation amounts in different matching failure times do not meet the requirements according to the deviation situation, and use the proportion of the number of deviation amounts that do not meet the requirements in the number of running parameter characteristics to determine the matching deviation coefficients of different matching failure times. When the average value of the matching deviation coefficients of different matching failure times is greater than the preset deviation coefficient threshold, determine that the fault type is the matching deviation fault type;

[0106] When the average value of the matching deviation coefficients of different matching failure times is not greater than the preset deviation coefficient threshold:

[0107] Take the matching failure times with matching deviation coefficients that do not meet the requirements as the identification deviation failure times. When the identification deviation failure times do not meet the requirements or the number of matching oxygen generators with identification deviation failure times does not meet the requirements, determine that the fault type is the matching deviation fault type;

[0108] When both the identification deviation failure times and the number of matching oxygen generators with identification deviation failure times meet the requirements:

[0109] Determine the identification deviation coefficients of different matching oxygen generators for the fault type based on the matching deviation coefficients of different matching oxygen generators in different matching failure times. When the identification deviation coefficients of different matching oxygen generators for the fault type all meet the requirements, determine that the fault type does not belong to the matching deviation fault type;

[0110] When there are matching oxygen generators with identification deviation coefficients that do not meet the requirements for the fault type:

[0111] When the number of matching oxygen generators with identification deviation coefficients that do not meet the requirements is greater than the preset quantity threshold, determine that the fault type is the matching deviation fault type;

[0112] When the number of matching oxygen generators with identification deviation coefficients that do not meet the requirements is not greater than the preset quantity threshold:

[0113] Determine the identification deviation amount of the fault type according to the identification deviation coefficients of different matching oxygen generators for the fault type, and use the identification deviation amount to determine whether the fault type is the matching deviation fault type.

[0114] Furthermore, when the identification deviation amount of the fault type is greater than the preset deviation amount threshold, determine that the fault type is the matching deviation fault type.

[0115] S3 Determine the similarity of the operation data within the preset time period of the historical fault times corresponding to the matching deviation fault type, and use the similarity to determine the matching operation scenario and the matching operation coefficient of the matching deviation fault type;

[0116] Specifically, the similarity of the operation data within the preset time period is determined according to the deviation amount of the operation data at different times within the preset time period.

[0117] Specifically, as Figure 5 shown, the method for determining the matching operation scenario of the matching deviation fault type is:

[0118] Taking the number of faults corresponding to the matching deviation fault type as the matching deviation fault number, based on the similarity of the operation data within the corresponding preset time period for different matching deviation fault numbers, determining the similarity coefficient of the operation data corresponding to different matching deviation fault numbers;

[0119] Based on the similarity coefficient of the operation data, dividing the matching deviation fault numbers into different similar operation data intervals;

[0120] Determining the matching operation scenario of the matching deviation fault type through the number of matching deviation fault numbers within different similar operation data intervals.

[0121] It should be noted that determining the matching operation scenario of the matching deviation fault type through the number of matching deviation fault numbers within different similar operation data intervals specifically includes:

[0122] Taking the similar operation data interval with the largest number of matching deviation fault numbers as the matching operation data interval;

[0123] According to the intervals where the different operation data corresponding to the matching operation data interval are located, determining the matching operation scenario of the matching deviation fault type.

[0124] Furthermore, the matching operation coefficient is determined according to the proportion of the matching deviation fault numbers corresponding to the matching operation scenario.

[0125] S4 Obtaining the operation data of different matching oxygen generators in different matching operation scenarios and the matching operation coefficients of the matching operation scenarios, and combining the historical fault numbers corresponding to the matching deviation fault types of different matching oxygen generators to determine an update processing strategy, and using the update processing strategy to update the typical fault mode atlas library.

[0126] It can be understood that the method for determining the update processing strategy is:

[0127] Determining the historical fault numbers of different matching oxygen generators in the matching deviation fault type based on the historical fault numbers corresponding to the matching deviation fault type of different matching oxygen generators;

[0128] Determine the historical operation times of different matching oxygen generators in the matching operation scenario of the matching deviation fault type with the operation data of different matching oxygen generators, and determine the operation risk coefficients of different matching oxygen generators in combination with the matching operation coefficient of the matching operation scenario and the matching deviation fault type;

[0129] Determine the fault identification risk coefficient of the matching deviation fault type according to the historical fault times and operation risk coefficients of different matching oxygen generators in the matching deviation fault type, and determine the update processing strategy according to the sum of the fault identification risk coefficients of different matching deviation fault types.

[0130] Further, the method for determining the fault identification risk coefficient of the matching deviation fault type is as follows:

[0131] Determine the matching oxygen generators whose historical fault times are within the preset fault times range and the operation risk coefficients are greater than the preset coefficient threshold with the historical fault times and operation risk coefficients of different matching oxygen generators in the matching deviation fault type, and use them as the screened matching oxygen generators;

[0132] Determine the fault identification risk coefficient of the matching deviation fault type according to the proportion of the screened matching oxygen generators in the number of the matching oxygen generators.

[0133] It should be noted that determining the update processing strategy according to the sum of the fault identification risk coefficients of different matching deviation fault types specifically includes:

[0134] When the sum of the fault identification risk coefficients of different matching deviation fault types is greater than the preset risk coefficient threshold, update the typical fault mode atlas library according to the preset update strategy;

[0135] When the sum of the fault identification risk coefficients of different matching deviation fault types is not greater than the preset risk coefficient threshold, use the risk coefficient interval corresponding to the sum of the fault identification risk coefficients of different matching deviation fault types to determine the update processing strategy.

[0136] Further, the update processing strategy is divided according to the update object, where the update object includes updating all fault types and only updating the matching deviation fault type.

[0137] 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 risk coefficient value, only update the matching deviation fault type 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 risk coefficient value, update all fault types according to the preset time period.

[0138] In another possible embodiment, the method for determining the update processing strategy is as follows:

[0139] S41 Determine the historical failure times of different matching oxygen generators in the matching deviation failure type according to the historical failure times corresponding to the matching oxygen generators in different matching systems, and determine the historical operation times of different matching oxygen generators in the matching operation scenario of the matching deviation failure type according to the operation data of different matching oxygen generators in the matching operation scenario of the matching deviation failure type. Then, combine the matching operation scenario, the matching operation coefficient of the matching deviation failure type, and the historical failure times of the matching oxygen generator in the matching deviation failure type to determine the identification deviation risk value of different matching oxygen generators in the matching deviation failure type;

[0140] S42 Determine the failure identification reliability coefficient of different matching deviation failure types according to the identification deviation risk value of different matching oxygen generators in the matching deviation failure type;

[0141] S43 Use the failure identification reliability coefficient of different matching deviation failure types to determine the failure identification reliability value, and determine the update processing strategy according to the failure identification reliability value.

[0142] Specifically, determining the update processing strategy according to the failure identification reliability value specifically includes:

[0143] When the failure identification reliability value is greater than the preset failure identification reliability threshold, use the preset reliable interval where the failure identification reliability value is located, and the corresponding set processing strategy to determine the update processing strategy;

[0144] When the failure identification reliability value is not greater than the preset failure identification reliability threshold, update the typical failure mode atlas library according to the preset update strategy.

[0145] Optionally, the above step S41 includes the following content:

[0146] S411 Determine the historical failure times of different matching oxygen generators in different matching deviation failure types according to the historical failure times corresponding to the matching oxygen generators in different matching systems. When there are matching oxygen generators whose historical failure times in different matching deviation failure types do not meet the requirements, go to step S412; when there are no matching oxygen generators whose historical failure times in different matching deviation failure types do not meet the requirements, go to step S413;

[0147] When the number of oxygen generators that do not meet the requirements in the historical failure times of different matching deviation fault types does not meet the requirements, the typical fault mode atlas library is updated according to the preset update strategy. When the number of oxygen generators that do not meet the requirements in the historical failure times of different matching deviation fault types meets the requirements, step S413 is entered;

[0148] S413 Use the operation data of different matching oxygen generators in the matching operation scenarios of the matching deviation fault type to determine the historical operation times of different matching oxygen generators in the matching deviation fault type, and combine the matching operation scenario, the matching operation coefficient of the matching deviation fault type, and the historical failure times of the matching oxygen generator in the matching deviation fault type to determine the identification deviation risk value of different matching oxygen generators in the matching deviation fault type. When there are oxygen generators whose sum of identification deviation risk values in different matching deviation fault types does not meet the requirements, step S414 is entered. When there are no oxygen generators whose sum of identification deviation risk values in different matching deviation fault types does not meet the requirements, step S42 is entered;

[0149] S414 When the number of oxygen generators whose sum of identification deviation risk values in different matching deviation fault types does not meet the requirements is greater than the preset number of oxygen generators, the typical fault mode atlas library is updated according to the preset update strategy. When the number of oxygen generators whose sum of identification deviation risk values in different matching deviation fault types does not meet the requirements is not greater than the preset number of oxygen generators, step S42 is entered.

[0150] Optionally, the following content is included in step S42 above:

[0151] S421 Determine the fault identification reliability coefficient of different matching deviation fault types according to the identification deviation risk value of different matching oxygen generators in the matching deviation fault type. When there are matching deviation fault types 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 are no matching deviation fault types whose fault identification reliability coefficient does not meet the requirements, step S422 is entered;

[0152] 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 atlas library of the oxygen generator is updated using the preset time period. When there are matching deviation fault types whose fault identification reliability coefficient is not greater than the preset reliability coefficient threshold, step S423 is entered;

[0153] When the number of matching deviation fault types with a fault recognition reliability coefficient not greater than the preset reliability coefficient threshold does not meet the requirements, the typical fault mode atlas library is updated according to the preset update strategy. When the number of matching deviation fault types with a fault recognition reliability coefficient not greater than the preset reliability coefficient threshold meets the requirements, proceed to step S43.

[0154] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments of the device, equipment, and non-volatile computer storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments.

[0155] The specific embodiments of this specification are described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be executed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0156] The above description is only for one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, there can be various modifications and changes to one or more embodiments of this specification. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included within the scope of the claims of this specification.

Claims

1. An online adaptive precise diagnosis and warning device for a medical oxygen generator, characterized in that Specifically, it includes: A data acquisition module, a spectrum library establishment module, a diagnostic model construction module, and a spectrum library update module; The data acquisition module is responsible for collecting and processing the operation data of the medical oxygen generator; The spectrum library construction module is responsible for establishing a typical fault mode spectrum library by using the historical fault data of the medical oxygen generator and according to the operation parameter characteristics under different fault modes; The diagnostic module construction module is responsible for constructing an intelligent diagnostic model, automatically extracting the characteristic information in the operation data, and comparing it with the typical fault mode spectrum library to determine the fault mode; The spectrum library update module is responsible for determining the update processing strategy according to the matching situation between the characteristic information of the medical oxygen generator of the type and the typical fault mode spectrum library, and using the update processing strategy to update the typical fault mode spectrum library of the medical oxygen generator of the type; The method for determining the update processing strategy is as follows: Taking the medical oxygen generator of the type as the matching oxygen generator, when it is determined according to the analysis results of the historical usage data and fault data of the matching oxygen generator that the typical fault mode spectrum library does not need to be updated according to the preset update strategy, the similarity of the operation data within the preset time period of the historical fault times corresponding to the matching deviation fault type is determined according to the matching situation between the characteristic information in the operation data and the typical fault mode spectrum library; Using the similarity to determine the matching operation scenario and the matching operation coefficient of the matching deviation fault type; Obtaining the operation data of different matching oxygen generators in different matching operation scenarios and the matching operation coefficients of the matching operation scenarios, and combining the historical fault times corresponding to the matching deviation fault types of different matching oxygen generators to determine the update processing strategy, and using the update processing strategy to update the typical fault mode spectrum library; Determining the historical fault times of different matching oxygen generators in the matching deviation fault type according to the historical fault times corresponding to the matching deviation fault type of different matching oxygen generators; Determining the historical operation times of different matching oxygen generators in the matching deviation fault type according to the operation data of different matching oxygen generators in the matching operation scenario of the matching deviation fault type, and combining the matching operation scenario and the matching operation coefficient of the matching deviation fault type to determine the operation risk coefficient of different matching oxygen generators; Determining the fault recognition risk coefficient of the matching deviation fault type according to the historical fault times and the operation risk coefficient of different matching oxygen generators in the matching deviation fault type, and determining the update processing strategy according to the sum of the fault recognition risk coefficients of different matching deviation fault types; When the sum of the fault recognition risk coefficients of different matching deviation fault types is less than the preset risk coefficient value, only the matching deviation fault type is updated according to the preset time period; when the sum of the fault recognition risk coefficients of different matching deviation fault types is not less than the preset risk coefficient value, all fault types are updated according to the preset time period.

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

3. The on-line adaptive precise diagnosis and early warning device for medical oxygen generators according to claim 1, characterized in that, The update processing strategy is determined according to the matching deviation between the characteristic information of the type of medical oxygen generator and the typical fault mode atlas library. When the number of historical faults where the matching deviation does not meet the requirements is greater than the preset fault number threshold, it is determined that the type of medical oxygen generator needs to be updated.

4. The online adaptive precise diagnosis and warning device for medical oxygen generators according to claim 1, characterized in that The historical usage data of the matching oxygen generator includes the historical usage times of the matching oxygen generator, the usage durations for different historical usage times, and the oxygen production amounts.

5. The online adaptive precise diagnosis and warning device for medical oxygen generators according to claim 1, wherein The analysis results of the fault data include the number of faults of different matching oxygen generators at different historical usage times.

6. The online adaptive precise diagnosis and warning device for medical oxygen generators according to claim 1, characterized in that, Determining that there is no need to update the typical fault mode atlas library according to the preset update strategy specifically includes: Determining different historical usage times and the usage durations for different historical usage times based on the historical usage data of the matching oxygen generator, and using the usage durations for different historical usage times to determine the total usage duration of different matching oxygen generators. Based on the total usage duration, determining the frequently used oxygen generators among the matching oxygen generators; According to the analysis results of the fault data of the frequently used oxygen generators, determining the number of faults of different frequently used oxygen generators, and using the number of faults to determine the problematic oxygen generators among the frequently used oxygen generators; Determining whether to update the typical fault mode atlas library according to the preset update strategy by the proportion of the number of problematic oxygen generators among the frequently used oxygen generators.

7. The online adaptive precise diagnosis and warning device for medical oxygen generators according to claim 6, characterized in that, When the proportion of the number of problematic oxygen generators among the frequently used oxygen generators is greater than the preset proportion threshold, it is determined that there is no need to update the typical fault mode atlas library according to the preset update strategy.

8. The on-line adaptive precise diagnosis and warning device for medical oxygen generators according to claim 1, characterized in that, The method for determining the fault recognition risk coefficient of the matching deviation fault type is: Determining the matching oxygen generators with historical fault times within the preset fault number range and operating risk coefficients greater than the preset coefficient threshold based on the historical fault times and operating risk coefficients of different matching oxygen generators in the matching deviation fault type, and using them as the screened matching oxygen generators; Determining the fault recognition risk coefficient of the matching deviation fault type according to the proportion of the screened matching oxygen generators in the number of the matching oxygen generators.

9. The on-line adaptive precise diagnosis and warning device for medical oxygen generators according to claim 1, characterized in that, Determining the update processing strategy according to the sum of the fault recognition risk coefficients of different matching deviation fault types, specifically including: When the sum of the fault recognition risk coefficients of different matching deviation fault types is greater than the preset risk coefficient threshold, updating the typical fault mode atlas library according to the preset update strategy; When the sum of the fault recognition risk coefficients of different matching deviation fault types is not greater than the preset risk coefficient threshold, determining the update processing strategy using the risk coefficient interval corresponding to the sum of the fault recognition risk coefficients of different matching deviation fault types.

Images