Predictive maintenance method and device for medical equipment
By predicting and analyzing the communication monitoring data of medical devices and generating fault warnings, the frequent occurrence of medical device communication failures is solved, the equipment reliability and operation efficiency are improved, and downtime and maintenance costs are reduced.
Patent Information
- Application Number
- CN202411474869.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-22
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing technology has defects in fault prediction and maintenance management in medical device communication, resulting in frequent equipment failures, high maintenance costs and long equipment downtime, affecting the quality and efficiency of medical services.
A predictive maintenance method for medical devices is adopted, by collecting communication monitoring data of medical devices, fault prediction, fault type matching, fault linkage impact analysis and fault correlation divergence, generate fault warnings and shorten maintenance cycles, and realize medical devices Intercommunication correlation analysis.
It improves the reliability of medical devices, reduces equipment downtime, reduces maintenance costs, and improves the quality and efficiency of medical services.
Smart Images

Figure CN118983069A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of equipment maintenance technology, and in particular to a method and device for predictive maintenance of medical equipment. Background Art
[0002] With the widespread application of medical equipment and the continuous advancement of technology, hospitals have an increasing demand for the management and maintenance of medical devices. However, existing technologies have significant defects in fault prediction and maintenance management in communication, mainly manifested in insufficient communication correlation analysis between devices and imperfect fault warning mechanisms. These problems lead to frequent equipment failures, high maintenance costs and long equipment downtime, which affects the quality and efficiency of medical services. Therefore, there is an urgent need for an advanced maintenance method based on big data and intelligent analysis to improve the reliability and operation efficiency of medical devices.
[0003] In summary, the prior art has technical problems such as insufficient analysis of communication correlation between medical devices, which leads to frequent failures in medical device communications and long equipment downtime, further affecting the quality and efficiency of medical services. Summary of the invention
[0004] The purpose of this application is to provide a method and apparatus for predictive maintenance of medical devices, so as to solve the technical problem in the prior art that insufficient analysis of communication correlation between medical devices leads to frequent failures in medical device communication and long equipment downtime, further affecting the quality and efficiency of medical services.
[0005] In view of the above problems, the present application provides a method and apparatus for predictive maintenance of medical equipment.
[0006] In a first aspect, the present application provides a medical equipment predictive maintenance method, which is implemented by a medical equipment predictive maintenance device, including: collecting a set of medical equipment in the hospital and obtaining communication monitoring data of the medical equipment set; performing fault prediction based on the communication monitoring data to obtain equipment fault prediction data; obtaining a target equipment fault type based on the matching of the equipment fault prediction data; performing fault linkage impact analysis and fault time impact analysis on the target equipment fault type based on a multi-equipment association network to obtain linkage impact indicators and time impact indicators; extracting fault sources from the medical equipment fault set in the linkage impact indicators and time impact indicators, and performing fault correlation divergence in the medical equipment fault set based on the fault sources to obtain a fault correlation coefficient; performing fault warning based on the fault correlation coefficient, shortening the maintenance cycle of the warning equipment, and performing maintenance of the warning equipment.
[0007] In a second aspect, the present application further provides a medical device predictive maintenance device for executing a medical device predictive maintenance method as described in the first aspect, including: a communication monitoring data acquisition module, the communication monitoring data acquisition module is used to collect a set of medical devices in the hospital and obtain the communication monitoring data of the medical device set; an equipment fault prediction data acquisition module, the equipment fault prediction data acquisition module is used to perform fault prediction based on the communication monitoring data and obtain equipment fault prediction data; a target equipment fault type acquisition module, the target equipment fault type acquisition module is used to obtain the target equipment fault type based on the equipment fault prediction data; an influencing index acquisition module, the The impact index acquisition module is used to perform fault linkage impact analysis and fault time impact analysis on the target device fault type according to the multi-device association network, and obtain linkage impact indicators and time impact indicators; the fault correlation coefficient acquisition module is used to extract the fault source according to the medical device fault set in the linkage impact indicator and time impact indicator, and perform fault correlation divergence in the medical device fault set according to the fault source to obtain the fault correlation coefficient; the maintenance module is used to perform fault warning according to the fault correlation coefficient, shorten the maintenance cycle of the warning device, and perform maintenance of the warning device.
[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: By collecting a set of medical devices in the hospital and obtaining communication monitoring data of the medical device set; performing fault prediction based on the communication monitoring data to obtain device fault prediction data; obtaining the target device fault type based on the matching of the device fault prediction data; performing fault linkage impact analysis and fault time impact analysis on the target device fault type based on a multi-device association network to obtain linkage impact indicators and time impact indicators; extracting fault sources from the medical device fault set in the linkage impact indicators and time impact indicators, performing fault correlation divergence in the medical device fault set based on the fault sources, and obtaining a fault correlation coefficient; performing fault warning based on the fault correlation coefficient, shortening the maintenance cycle of the warning device, performing maintenance of the warning device, achieving the technical goal of communication correlation analysis between medical devices, and achieving the technical effect of improving the reliability of medical devices and reducing equipment downtime.
[0009] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0010] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.
[0011] Figure 1 A flowchart of a method for predictive maintenance of medical equipment is provided for this application; Figure 2 This is a schematic diagram of the structure of a predictive maintenance device for medical equipment in this application.
[0012] Description of reference numerals: Communication monitoring data acquisition module 11, equipment fault prediction data acquisition module 12, target equipment fault type acquisition module 13, influence index acquisition module 14, fault correlation coefficient acquisition module 15, maintenance module 16. DETAILED DESCRIPTION
[0013] This application provides a method and device for predictive maintenance of medical devices, which solves the technical problem in the prior art that insufficient analysis of inter-medical device communication associations leads to frequent medical device communication failures and long equipment downtime, further affecting the quality and efficiency of medical services. The technical goal of inter-medical device communication association analysis is achieved, and the technical effect of improving the reliability of medical devices and reducing equipment downtime is achieved.
[0014] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.
[0015] For example, please refer to the attached Figure 1 The present application provides a medical device predictive maintenance method, which is applied to a medical device predictive maintenance device, and specifically includes the following steps: Step 1: Collect the medical device collection in the hospital and obtain the communication monitoring data of the medical device collection.
[0016] Specifically, collecting the collection of medical devices in the hospital means that systematic data collection is required for all medical devices in the hospital. For example, various types of medical devices, including CT machines, MRI machines, ultrasound equipment, infusion pumps, ECG monitors, etc. Connecting medical devices to a unified network platform can continuously and in real time record and transmit their operating status and performance data, ensuring that the operating information of each medical device can be fully and accurately collected, providing a basis for subsequent data analysis and fault prediction.
[0017] Next, the communication status data obtained by monitoring the medical devices during operation is extracted from the medical device set as communication monitoring data. For example, the communication monitoring data includes indicators such as data transmission rate, signal strength, network delay, and packet loss rate between medical devices. By obtaining communication monitoring data, the performance and stability of medical devices in the networked state can be understood, and whether there are problems with poor communication or disconnection between devices can also be found.
[0018] Step 2: Perform fault prediction based on the communication monitoring data to obtain equipment fault prediction data.
[0019] Specifically, based on the communication monitoring data, the established fault prediction model is used for analysis to identify potential failure risks and provide predictive information on the future operating status of the medical device.
[0020] Step 3: Obtain the target device failure type based on the device failure prediction data.
[0021] Specifically, real-time equipment failure prediction data is obtained from the fault prediction model. For example, it includes information such as the failure probability of each device, possible failure time, and failure severity. The acquired fault prediction data is matched with the historical failure types of the device. Through the previously established fault type matching relationship, the device in the prediction data can be associated with the corresponding fault type. According to the matching relationship and the fault value in the prediction data, the fault type is further refined. The fault value includes the probability and severity of the failure, and the specific fault type can be further determined. For example, communication interruption may be divided into minor interruption and severe interruption. By analyzing the fault value, the specific situation can be determined and the fault type of the target device can be determined.
[0022] Step 4: Perform fault linkage impact analysis and fault time impact analysis on the target device fault type according to the multi-device association network to obtain linkage impact indicators and time impact indicators.
[0023] Specifically, the impact of a specific fault type on other devices is analyzed through the communication and operation association between devices in the multi-device association network. Specifically, data analysis and modeling can be used to identify devices whose operating status will be significantly affected when a certain target device fault type occurs. For example, if a certain device has a communication interruption, it may cause abnormal operation or data transmission delay in other devices that rely on the data of the device. Through this linkage impact analysis, the impact of the target fault on other devices in the device can be quantified to form a linkage impact index. Next, the impact of a specific fault type on the time dimension is evaluated, mainly analyzing the time delay and response time when and after the fault occurs. Specifically, the fault time impact analysis can reveal the impact of device faults on the overall response speed and communication delay of the device. For example, when a certain device fails, it may cause a delay in data transmission or an increase in the response time of other devices. By quantifying the time impact, a time impact index can be formed to reflect the depth and breadth of the impact of the fault on the time dimension. Through two-step analysis, linkage impact index and time impact index are obtained.
[0024] Step 5: Extract the fault source according to the medical device fault set in the linkage influence index and the time influence index, and perform fault correlation divergence in the medical device fault set according to the fault source to obtain the fault correlation coefficient.
[0025] Specifically, the fault source is extracted based on the set of medical device faults in the linkage influence index and the time influence index. From the set of medical device faults, the linkage influence index and the time influence index are used to identify the key devices or components that may cause the fault. The linkage influence index reflects the degree of mutual influence between devices, while the time influence index reflects the response time and delay of the device when a fault occurs. By comprehensively analyzing the two indicators, the device that has the greatest impact on the overall device when a fault occurs can be identified as the potential source of the fault.
[0026] Next, the fault correlation is diverged in the medical device fault set according to the fault source to obtain the fault correlation coefficient. The identified fault sources are analyzed in the fault set to calculate the correlation coefficient between each fault source and other device faults. The fault correlation coefficient is a numerical value that reflects the degree of correlation between the fault source and other device faults. For example, if the failure of a certain device frequently causes abnormal operation of other devices, then the fault correlation coefficient between the devices will be high, which can quantify the fault correlation between the devices and help predict and manage device failures more accurately.
[0027] Step 6: Perform fault warning according to the fault correlation coefficient, shorten the maintenance cycle of the warning device, and perform maintenance of the warning device.
[0028] Specifically, fault warning is performed based on the fault correlation coefficient, and the maintenance cycle of the warning device is shortened. Based on the calculated fault correlation coefficient, the device is given a fault warning. A high correlation coefficient indicates that the fault correlation between the devices is strong and requires special attention. When the fault correlation coefficient of the device reaches the predetermined warning threshold, the device will issue a fault warning. The warning not only reminds maintenance personnel to pay attention to possible failure risks, but also requires shortening the maintenance cycle of the warning device. By shortening the maintenance cycle, these high-risk devices can be inspected and maintained more frequently to prevent failures, reduce downtime and maintenance costs. Finally, perform maintenance of the warning device. Once the device is marked as a warning state, the maintenance personnel need to perform detailed inspections and maintenance on it according to the shortened maintenance cycle, including checking the key components of the device, updating the software, calibrating the instrument, etc., to ensure that the device operates in the best condition. Through timely maintenance and care, potential failures can be prevented, the service life of the device can be extended, and the overall reliability of the device can be improved.
[0029] The medical device predictive maintenance method is applied to a medical device predictive maintenance device to achieve the technical goal of communication association analysis between medical devices, thereby achieving the technical effect of improving the reliability of medical devices and reducing equipment downtime.
[0030] Furthermore, the present application also includes: Acquire historical communication monitoring data of the medical device set, and extract historical communication fault data from the historical communication monitoring data; perform fault learning based on the historical communication fault data to establish a device fault prediction model; input the communication monitoring data into the device fault prediction model to obtain the device fault prediction data.
[0031] Specifically, all communication monitoring data in the past period of time is extracted from the storage system, and data is collected from the past communication monitoring records of all medical devices in the hospital, including, for example, the communication connection status, data transmission rate, delay, packet loss rate and other indicators of medical devices.
[0032] Next, data related to communication failures are screened out from the historical communication monitoring data to extract historical communication failure data. For example, historical communication failure data includes data on phenomena such as communication interruption, abnormal delay, and data loss. By analyzing historical communication failure data, the types and frequencies of problems that may occur during the use of medical devices can be identified.
[0033] Then, the machine learning algorithm is used to analyze and learn the extracted historical communication failure data to establish a device failure prediction model, which can identify the patterns and characteristics of medical device failures. By establishing a device failure prediction model, possible failures can be predicted in advance during future use, so that preventive measures can be taken to reduce equipment downtime and maintenance costs.
[0034] Finally, in actual use, the real-time communication monitoring data is input into the trained device failure prediction model. The device failure prediction model analyzes the input communication monitoring data and predicts the type and probability of failure that may occur in the medical device in a certain period of time in the future, providing real-time reference and guidance for medical device maintenance to ensure the normal operation of the medical device.
[0035] By acquiring the historical communication monitoring data of a collection of medical devices, extracting the historical communication failure data from it, and establishing a device failure prediction model, it is possible to effectively predict the possible future failures of the equipment. By inputting the real-time monitoring data into the prediction model, accurate failure prediction results can be obtained, thereby providing a scientific basis for the maintenance and management of the equipment and improving the operating efficiency and reliability of the equipment.
[0036] Furthermore, the present application also includes: The matching relationship between the faulty device and the device failure type is extracted based on big data, wherein at least one device failure type matches the faulty device; the faulty device is extracted based on the device failure prediction data, and the device failure type is obtained by matching the faulty device through the matching relationship; the device failure value is extracted based on the device failure prediction data, and the target device failure type is obtained by extracting from the device failure type.
[0037] Specifically, using big data technology, we can extract the relationship between each faulty device and the possible fault type from a large amount of device operation and fault data. By establishing a matching relationship, we can associate a specific fault type with a specific device. For example, some devices are more likely to have circuit board failures in high temperature environments, or communication failures when running under high load. Through the matching relationship, we can establish a detailed list of fault types for each faulty device to ensure that they can be quickly identified and classified when a fault occurs.
[0038] Next, in the actual application process, the real-time device failure prediction data is used to extract the currently predicted faulty devices. Through the matching relationship, the faulty device can be matched with its possible device failure type to determine the most likely failure type of each device. For example, if the prediction data indicates that a certain device has a high risk of communication interruption, the matching relationship can further confirm the possible specific failure type of the device, such as network module failure or data transmission abnormality.
[0039] Then, the fault prediction data not only provides the possibility of equipment failure, but also contains specific fault values, such as the probability or severity of the fault. By analyzing the fault value and combining it with the equipment's fault type, the most critical fault type, that is, the target equipment fault type, can be extracted. For example, the fault value can be used to determine the specific performance of a certain equipment in the risk of communication interruption, determine whether it is due to frequent packet loss or long delays, and further clarify the fault type.
[0040] By extracting the matching relationship between faulty equipment and fault types through big data, and determining the specific fault type through the matching relationship, and then extracting the target fault type in combination with the fault value, not only the accuracy of fault prediction is improved, but also maintenance work is more precise and efficient, ensuring that equipment can be intervened and repaired in time before a fault occurs, thereby improving the operational reliability and service life of medical devices.
[0041] Furthermore, the present application also includes: According to the communication operation data of the medical device set, multiple devices are associated with each other in communication operation to obtain multiple devices communication associated lines; according to the overlapping devices, the multiple devices communication associated lines are superimposed and diverged to obtain the multiple devices associated network.
[0042] Specifically, by analyzing the communication operation data of all medical devices and identifying the communication associations between each medical device and other medical devices, it is possible to determine which medical devices have associations during the communication process. For example, some medical devices may share data through the network, or frequently exchange data in specific operating scenarios, showing the connection relationship between each medical device and other medical devices.
[0043] Next, the previous association analysis is further refined and expanded to identify overlapping devices that have communication associations with multiple medical devices at the same time. By analyzing the communication patterns of these overlapping devices, key nodes in the communication network can be found. By superimposing the communication association lines of overlapping devices and associating all the multi-device communication association lines involved, a multi-device association network can be drawn.
[0044] The multi-device association network not only displays the complex communication relationship between medical devices, but also helps identify key nodes and potential failure points, providing an important basis for the maintenance and optimization of medical devices. It can comprehensively improve the communication efficiency and operational reliability of medical equipment and ensure that medical devices remain stable and efficient during use.
[0045] Furthermore, the present application also includes: The sample linkage influence indicators and sample time influence indicators of the medical device set are collected through the multi-device association network; the linkage relationship and waiting time relationship of the medical device set are extracted according to the sample linkage influence indicators and sample time influence indicators to obtain a preliminary set of faulty devices; the preliminary set of faulty devices is screened according to the target device failure type to obtain the medical device failure set, which is added to the linkage influence indicators and time influence indicators.
[0046] Specifically, extracting the sample linkage impact index associated with the fault and the sample time impact index of the consumed time affected by the fault from the multi-device association network can reflect the mutual impact of faults between devices and the corresponding time delay. For example, the sample linkage impact index can include the degree of influence of the fault of a certain device on the possible fault of other devices, such as the change in communication traffic. The sample time impact index records the communication time delay and communication response time delay caused by the communication fault between devices.
[0047] Next, based on the sample linkage influence index and sample time influence index, the linkage relationship and time relationship between instruments are specifically analyzed. The linkage relationship refers to the degree of influence of failures between instruments leading to successive failures. For example, the failure of a certain instrument will cause the performance of other instruments to decline or the communication to be interrupted. The waiting time relationship reflects the time delay and other failures of the instrument during the communication process, which causes the response delay of other instruments and delays the efficiency of treatment through medical instruments. Instruments with linkage relationships and waiting time relationships are aggregated from the multi-instrument association network to form a preliminary set of faulty instruments.
[0048] Then, through the preliminary selection of faulty device sets, further screening is performed to ensure that only devices that match the target fault type are retained. By comparing and screening the devices in the preliminary selection of faulty device sets with the target fault type, devices that do not match the fault type are eliminated, thereby obtaining a more accurate set of medical device faults.
[0049] By accurately identifying and predicting equipment failures, fault models can also be dynamically updated and optimized to improve the stability of equipment operation and the effectiveness of maintenance.
[0050] Furthermore, the present application also includes: The initially selected faulty equipment is prioritized for maintenance according to the sample linkage influence in the sample linkage influence index, and the once prioritized equipment is prioritized for maintenance twice according to the sample time influence in the sample time influence index to obtain the secondarily prioritized equipment, which is added to the initially selected faulty equipment set.
[0051] Specifically, the primary selected faulty equipment is prioritized for maintenance according to the sample linkage influence in the sample linkage influence index. Based on the equipment in the primary selected faulty equipment set, the sample linkage influence index is used for priority sorting. The sample linkage influence index reflects the degree of influence of each equipment on other equipment, and can identify equipment that will have a greater negative impact on the overall device when a failure occurs. Therefore, key equipment should be given priority during maintenance, because equipment failure may trigger a chain reaction and affect the normal operation of other equipment.
[0052] Next, the first-prioritized instruments are prioritized for secondary maintenance according to the sample time influence in the sample time influence index. On the basis of the completed first-time maintenance priority ranking, the sample time influence index is further used for secondary sorting. The sample time influence index reflects the time delay and response time of the instrument during the communication or operation process, and can identify equipment that behaves abnormally in time, that is, those that may affect the overall performance of the device due to time delays or untimely responses, and then prioritize them to ensure efficient operation of the device in the time dimension. Adding the second-prioritized instruments to the primary faulty instrument set can further improve the primary faulty instrument set to ensure that all equipment that requires priority maintenance is included.
[0053] By preliminarily selecting a set of faulty devices, a comprehensive and scientific maintenance plan is formed to effectively improve the maintenance efficiency of medical devices and the overall reliability of the equipment.
[0054] Furthermore, the present application also includes: A fault judgment result is obtained by comparing the fault correlation coefficient with the fault threshold; if the fault judgment result is that the fault correlation coefficient does not meet the fault threshold, continuous monitoring is performed; if the fault judgment result is that the fault correlation coefficient meets the fault threshold, a fault warning is performed.
[0055] Specifically, the fault correlation coefficient of the device is compared with the pre-set fault threshold to determine whether the device is at risk of failure. The fault correlation coefficient is obtained by analyzing the device operation data and reflects the similarity between the current state of the device and the known failure mode. The failure threshold is a pre-set standard used to determine whether the device is in normal operation. When the fault correlation coefficient exceeds or falls below the fault threshold, it indicates that the device may fail.
[0056] Next, if the fault judgment result is that the fault correlation coefficient does not meet the fault threshold, continuous monitoring is performed. The current device status does not meet the standard for triggering a fault warning, but its operating status still needs to be monitored. Continuous monitoring can be achieved through real-time data collection and analysis to ensure that the device can be tracked at any time during operation. Once the fault correlation coefficient of the device changes, the device can update the judgment result in time.
[0057] Next, if the fault judgment result is that the fault correlation coefficient meets the fault threshold, a fault warning is issued, which means that the status of the device has reached the standard for triggering the warning, and the device needs to immediately issue a fault warning notification. Fault warnings can be carried out in a variety of ways, such as notifying maintenance personnel through alarm devices, text messages, emails, etc. The warning information should include the specific fault type of the device, possible causes, and recommended maintenance measures so that maintenance personnel can respond and handle it quickly.
[0058] By comparing the fault correlation coefficient with the fault threshold, the fault judgment result of the device is determined. If the fault correlation coefficient does not meet the fault threshold, continuous monitoring will continue to ensure real-time tracking of the device's operating status; if the fault correlation coefficient meets the fault threshold, the device will issue a fault warning notification to prompt maintenance personnel to intervene and handle it in time, which can achieve accurate judgment and timely response to device failures, improve the reliability of device operation and the effectiveness of maintenance.
[0059] In summary, the predictive maintenance method for medical devices provided in this application has the following technical effects: By collecting a set of medical devices in the hospital and obtaining communication monitoring data of the medical device set; performing fault prediction based on the communication monitoring data to obtain device fault prediction data; obtaining the target device fault type based on the matching of the device fault prediction data; performing fault linkage impact analysis and fault time impact analysis on the target device fault type based on a multi-device association network to obtain linkage impact indicators and time impact indicators; extracting fault sources from the medical device fault set in the linkage impact indicators and time impact indicators, performing fault correlation divergence in the medical device fault set based on the fault sources, and obtaining a fault correlation coefficient; performing fault warning based on the fault correlation coefficient, shortening the maintenance cycle of the warning device, performing maintenance of the warning device, achieving the technical goal of communication correlation analysis between medical devices, and achieving the technical effect of improving the reliability of medical devices and reducing equipment downtime.
[0060] Embodiment 2: Based on the same inventive concept as the medical device predictive maintenance method in the above embodiment, the present application also provides a medical device predictive maintenance device, see the attached Figure 2 ,include: A communication monitoring data acquisition module 11 is used to collect a set of medical devices in the hospital and obtain the communication monitoring data of the medical device set; an equipment failure prediction data acquisition module 12 is used to perform failure prediction based on the communication monitoring data and obtain equipment failure prediction data; a target equipment failure type acquisition module 13 is used to obtain the target equipment failure type according to the equipment failure prediction data; an influence index acquisition module 14 is used to match the target equipment failure type according to the multi-equipment association network. A fault linkage impact analysis and a fault time impact analysis are performed on the type of medical fault to obtain linkage impact indicators and time impact indicators; a fault correlation coefficient acquisition module 15 is used to extract the fault source according to the medical device fault set in the linkage impact indicators and time impact indicators, and to perform fault correlation divergence in the medical device fault set according to the fault source to obtain the fault correlation coefficient; a maintenance module 16 is used to perform fault warning according to the fault correlation coefficient, shorten the maintenance cycle of the warning equipment, and perform maintenance of the warning equipment.
[0061] Furthermore, the equipment failure prediction data acquisition module in the medical equipment predictive maintenance device obtains historical communication monitoring data of the medical equipment set, extracts historical communication failure data from the historical communication monitoring data; performs fault learning based on the historical communication failure data to establish an equipment failure prediction model; and inputs the communication monitoring data into the equipment failure prediction model to obtain the equipment failure prediction data.
[0062] Furthermore, the target device fault type obtaining module 13 in the medical device predictive maintenance device is also used for: The matching relationship between the faulty device and the device failure type is extracted based on big data, wherein at least one device failure type matches the faulty device; the faulty device is extracted based on the device failure prediction data, and the device failure type is obtained by matching the faulty device through the matching relationship; the device failure value is extracted based on the device failure prediction data, and the target device failure type is obtained by extracting from the device failure type.
[0063] Furthermore, the influencing index obtaining module 14 in the medical device predictive maintenance device is also used for: According to the communication operation data of the medical device set, multiple devices are associated with each other in communication operation to obtain multiple devices communication associated lines; according to the overlapping devices, the multiple devices communication associated lines are superimposed and diverged to obtain the multiple devices associated network.
[0064] Furthermore, the influencing index obtaining module 14 in the medical device predictive maintenance device is also used for: The sample linkage influence indicators and sample time influence indicators of the medical device set are collected through the multi-device association network; the linkage relationship and waiting time relationship of the medical device set are extracted according to the sample linkage influence indicators and sample time influence indicators to obtain a preliminary set of faulty devices; the preliminary set of faulty devices is screened according to the target device failure type to obtain the medical device failure set, which is added to the linkage influence indicators and time influence indicators.
[0065] Furthermore, the influencing index obtaining module 14 in the medical device predictive maintenance device is also used for: The initially selected faulty equipment is prioritized for maintenance according to the sample linkage influence in the sample linkage influence index, and the once prioritized equipment is prioritized for maintenance twice according to the sample time influence in the sample time influence index to obtain the secondarily prioritized equipment, which is added to the initially selected faulty equipment set.
[0066] Furthermore, the maintenance module 16 in the medical device predictive maintenance device is also used for: A fault judgment result is obtained by comparing the fault correlation coefficient with the fault threshold; if the fault judgment result is that the fault correlation coefficient does not meet the fault threshold, continuous monitoring is performed; if the fault judgment result is that the fault correlation coefficient meets the fault threshold, a fault warning is performed.
[0067] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The medical device predictive maintenance method and specific examples in the aforementioned embodiment 1 are also applicable to a medical device predictive maintenance device in this embodiment. Through the aforementioned detailed description of a medical device predictive maintenance method, those skilled in the art can clearly understand a medical device predictive maintenance device in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.
[0068] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
[0069] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.
Claims
1. A method for predictive maintenance of medical equipment, characterized in that: include: Collect the medical equipment collection in the hospital and obtain the communication monitoring data of the medical equipment collection; Perform fault prediction based on the communication monitoring data to obtain device fault prediction data; Obtaining a target device failure type according to the device failure prediction data; Performing fault linkage impact analysis and fault time impact analysis on the target device fault type according to the multi-device association network to obtain linkage impact indicators and time impact indicators; Extracting fault sources from the medical device fault set in the linkage influence index and the time influence index, and performing fault correlation divergence in the medical device fault set according to the fault sources to obtain a fault correlation coefficient; Fault warning is performed according to the fault correlation coefficient, and the maintenance cycle of the warning equipment is shortened, and the maintenance of the warning equipment is performed.
2. A method for predictive maintenance of medical equipment according to claim 1, characterized in that: The performing fault prediction according to the communication monitoring data to obtain device fault prediction data includes: Acquire historical communication monitoring data of the medical device set, and extract historical communication fault data from the historical communication monitoring data; Perform fault learning based on the historical communication fault data to establish a device fault prediction model; The communication monitoring data is input into the device failure prediction model to obtain the device failure prediction data.
3. A method for predictive maintenance of medical equipment according to claim 1, characterized in that: The obtaining the target device failure type according to the device failure prediction data matching includes: Extracting a matching relationship between a faulty device and a device fault type based on big data, wherein at least one device fault type matches the faulty device; Extracting the faulty device according to the device fault prediction data, and matching the faulty device through the matching relationship to obtain the device fault type; The device failure value is extracted according to the device failure prediction data, and the target device failure type is obtained by extracting from the device failure type.
4. A method for predictive maintenance of medical equipment according to claim 1, characterized in that: Establish a multi-device association network, including: Performing multi-device communication operation association according to the communication operation data of the medical device set to obtain multi-device communication association lines; The communication association lines of the multiple devices are superimposed and diverged according to the overlapping devices to obtain the multiple device association network.
5. A method for predictive maintenance of medical equipment as claimed in claim 1, characterized in that: The performing of the fault linkage impact analysis and the fault time impact analysis on the target device fault type according to the multi-device association network to obtain the linkage impact index and the time impact index includes: Collecting sample linkage influence indicators and sample time influence indicators of a medical device set through the multi-device association network; Extracting the linkage relationship and waiting time relationship of the medical device set according to the sample linkage influence index and the sample time influence index to obtain a preliminary selection of faulty device set; The preliminary selected faulty equipment set is screened according to the target equipment fault type to obtain the medical equipment fault set, which is added to the linkage influence index and time influence index.
6. A method for predictive maintenance of medical equipment as claimed in claim 5, characterized in that: The initially selected faulty equipment is prioritized for maintenance according to the sample linkage influence in the sample linkage influence index, and the once prioritized equipment is prioritized for maintenance twice according to the sample time influence in the sample time influence index to obtain the secondarily prioritized equipment, which is added to the initially selected faulty equipment set.
7. A method for predictive maintenance of medical equipment as claimed in claim 1, characterized in that: The performing fault early warning according to the fault correlation coefficient includes: Comparing the fault correlation coefficient with the fault threshold to obtain a fault judgment result; If the fault judgment result is that the fault correlation coefficient does not meet the fault threshold, continuous monitoring is performed; if the fault judgment result is that the fault correlation coefficient meets the fault threshold, a fault warning is performed.
8. A predictive maintenance device for medical equipment, characterized in that: The steps for implementing a method for predictive maintenance of a medical device as described in any one of claims 1 to 7 include: A communication monitoring data acquisition module, which is used to collect a set of medical devices in the hospital and acquire communication monitoring data of the set of medical devices; An equipment failure prediction data acquisition module, the equipment failure prediction data acquisition module is used to perform failure prediction based on the communication monitoring data to obtain equipment failure prediction data; A target device fault type acquisition module, the target device fault type acquisition module is used to obtain the target device fault type according to the device fault prediction data; An influence index obtaining module, the influence index obtaining module is used to perform a fault linkage influence analysis and a fault time influence analysis on the target device fault type according to a multi-device association network, and obtain a linkage influence index and a time influence index; A fault correlation coefficient obtaining module, the fault correlation coefficient obtaining module is used to extract fault sources according to the medical device fault set in the linkage influence index and the time influence index, and to perform fault correlation divergence in the medical device fault set according to the fault sources to obtain a fault correlation coefficient; A maintenance module is used to perform fault warning according to the fault correlation coefficient, shorten the maintenance cycle of the warning equipment, and perform maintenance of the warning equipment.
Citation Information
Patent Citations
Circuit fault prediction method, device and equipment and computer readable medium
CN111476400A
Abnormality detection model training method and device and fault scene positioning method and device
CN116304909A
Power operation risk early warning method and system based on deep learning
CN117391459A
Device predictive maintenance method and system based on neural network
CN117436846A
Industrial data management method and system based on cloud edge fusion
CN117872989A
