A medical equipment automation management system and method based on cloud platform

Abstract

The present invention discloses a cloud-based medical equipment automation management system and method, which relates to the technical field of medical equipment automation management, including: obtaining usage data and operating parameter data of a target device; determining the loss of the target device based on the usage data of the target device; determining a first failure rate of the target device based on the loss of the target device and the loss of a device with the same specification; determining a second failure rate of the target device based on the operating parameter data of the device and the operating parameter data of a device with the same specification; judging whether a fault diagnosis is required for the target device, and if so, performing a fault diagnosis on the target device, and returning all usage data of the target device to zero after the fault diagnosis is completed; the present invention performs a fault analysis based on the cause and result of the device fault, automatically sends fault information when or before the device fault occurs, and performs a fault diagnosis on the device in a timely manner.

Description

Technical Field

[0001] The present invention relates to the technical field of automated management of medical equipment, and in particular to an automated management system and method for medical equipment based on a cloud platform. Background Art

[0002] Medical equipment refers to equipment, appliances, instruments, devices, and instruments used to prevent, diagnose, treat, and alleviate human diseases, injuries, or disabilities. Medical equipment plays an important role in the medical field and is an indispensable tool for medical work. The working conditions of medical equipment under different loads, such as changes in user weight, may cause different degrees of wear on the equipment, which in turn affects the failure of the medical equipment; the existing technology usually uses regular fault diagnosis to repair medical equipment, which may lead to untimely diagnosis and over-diagnosis; how to take action before medical equipment fails, thereby avoiding catastrophic and costly medical equipment downtime, has become an urgent problem to be solved. Summary of the invention

[0003] The purpose of the present invention is to provide a medical equipment automation management system and method based on a cloud platform to solve the problems raised in the above background technology.

[0004] In one aspect of the present invention, a cloud platform-based medical equipment automation management method is provided, comprising:

[0005] S11, obtaining usage data of the target device and operating parameter data of the target device; the operating parameter data is data showing device wear and failure phenomena;

[0006] S12, determining the wear degree of the target device based on the usage data of the target device; obtaining an electronic tag of the target device, obtaining historical usage data of a device of the same specification according to the electronic tag of the target device, and determining a first failure rate of the target device based on the wear degree of the target device and the wear degree of a device of the same specification;

[0007] S13, determining a second failure rate of the target device based on the operating parameter data of the device and the operating parameter data of devices with the same specification;

[0008] S14, based on the first failure rate and the second failure rate of the target device, determine whether the target device needs to be diagnosed. If so, perform fault diagnosis on the target device, and after the fault diagnosis is completed, all usage data of the target device will be reset to zero; otherwise, continue to determine whether the target device needs to be diagnosed.

[0009] Specifically, the usage data of the target equipment includes the start and stop time, normal working time, static load, dynamic load and stress distribution data of the equipment; the loss degree of the target equipment is calculated by the following formula:

[0010] , where deg is the loss degree of the target device, T is the operating time of the target device, M is the static load of the target device, G is the dynamic load of the target device, and PSO is the stress distribution data; , The time for the target device to work normally. is the start and stop time of the target device, is the start-stop coefficient of the target equipment; , m is the weight of the user using the target device, To preset the weight threshold, set it according to the load capacity of the target device. is the static load factor of the target device, ; , is the user's heart rate, is the user's resting heart rate, is the dynamic load factor of the target device, .

[0011] The usage data contains the reasons for equipment loss, and the operating parameter data shows the phenomenon of equipment loss and failure. When the loss caused by the usage data is high, even if the operating parameter data shows that the equipment is normal, the probability of equipment failure will be higher than that in the case of low loss; and the operating parameter data can directly reflect whether the equipment has a fault. Combining the two makes it more reasonable to determine whether the equipment needs to be diagnosed, and reduces the possibility of untimely diagnosis.

[0012] When the equipment starts up and shuts down, it will cause large instantaneous losses. Since the startup and shutdown of equipment occur in pairs, they are analyzed together. is a preset value, which can be determined through experiments. The time that the equipment can operate normally under high-frequency start-stop state and normal working state is obtained, and the ratio of the normal working time of the equipment under normal working state to the normal working time of the equipment under high-frequency start-stop state is taken as .

[0013] If the user is overweight or exercises vigorously, it will cause additional wear and tear on the device. The intensity of the user's exercise can be determined by the user's heart rate.

[0014] Specifically, the stress distribution data PSO is determined by the following steps:

[0015] S31, establishing a plane rectangular coordinate system on a plane of a use area of ​​a target device used by a user, determining a plane position of a user's center of mass in the use area, wherein the plane position of the user's center of mass is an intersection of a human body midline and the plane of the use area, and obtaining the plane coordinates of the user's center of mass;

[0016] S32, obtaining the centroid plane coordinates of historical users from the historical usage data of the device with the same specification, taking the centroid plane coordinates of the historical users as input features, performing cluster analysis on the input features, and obtaining cluster clusters;

[0017] S33, taking the class center of the i-th cluster as the feature label , i is a positive integer. When the historical usage data of the same specification device is insufficient, the loss caused to the same specification device when the user is in the usage area corresponding to the different class centers is determined by simulating the usage pattern. The i-th feature label is determined based on the loss caused to the same specification device. The stress distribution coefficient ; When there is sufficient historical usage data for the same specification equipment, the i-th feature label is determined based on the historical usage data The stress distribution coefficient ;

[0018] S34, calculating the distance between the user's centroid and the class center of the cluster, the cluster corresponding to the class center with the smallest distance to the user's centroid is the cluster to which the user's centroid belongs, and determining the stress distribution data according to the feature label of the cluster to which the user's centroid belongs.

[0019] The different usage areas where users use the device cause the device to be subjected to different stresses and losses. In the usage area, the horizontal position is sufficient to reflect the user's position, and the horizontal position of the user's center of mass can reflect the user's horizontal position. The center of mass of a person is on the midline of the human body.

[0020] Specifically, the simulated usage mode further includes the following steps:

[0021] S41, defining a location of a user in a usage area, wherein the location of the user in the usage area is a location of the usage area corresponding to a feature tag;

[0022] S42, creating a computer simulation model of the same specifications of equipment and users;

[0023] S43, simulating different positions of the user in the use area, applying the same static load, and determining the time that the same specification equipment can operate normally when the user is in different positions in the use area; repeating the simulation for all positions, obtaining the time that the same specification equipment can operate normally at the i-th position ; The feature label with the most data points in the cluster corresponding to all feature labels The stress distribution coefficient is set to 1, then the i-th feature label The stress distribution coefficient , Feature label The time that equipment of the same specification can operate normally in the corresponding use area.

[0024] Specifically, the i-th feature label is determined based on historical usage data The stress distribution coefficient , including the following steps:

[0025] In the historical usage data of the same specification equipment, find the historical usage data of the faulty equipment and determine the time when the historical user was in the usage area corresponding to the i-th feature tag of the faulty equipment , take any two sets of historical usage data of different faulty devices, subtract the time of the same usage area location to get the time difference , establish the equation , take x different time difference data and use the equation to form a linear equation system of x variables: , solving the equations yields ; Repeat the calculation of historical usage data of different faulty equipment The average value of .

[0026] x is the number of clusters obtained in step S32. After a device fails, it will usually not be used anymore, and the loss will not increase. Different time distributions at x locations bring the same result: when a device fails, the loss caused by different time distributions is the same. By converting the loss at different locations, the loss rate of the device at different locations can be obtained. x unknowns require x function relationships to be solved; in order to eliminate contingency, multiple solutions are averaged.

[0027] In step S12, determining the first failure rate of the target device further includes the following steps:

[0028] S51, based on the historical usage data of the equipment of the same specification, calculate the historical loss degree in the fault state and the non-fault state; for the historical usage data of the equipment of the same specification that has failed, the loss degree data calculated after the failure occurs is the historical loss degree in the fault state, and the loss degree data calculated before the failure occurs is the historical loss degree in the non-fault state;

[0029] S52, based on the current loss degree of the target device deg, let A represent the random event that the target device will fail, and D represent the loss degree random variable, then the first failure rate of the target device is: , is the first failure rate of the target device. Based on the historical usage data of the same specification equipment, the probability that the loss of the target device is greater than deg is obtained. , It is the ratio of the number of historical usage data of the same specification equipment with loss degree greater than deg to the total number of historical usage data of the same specification equipment; It is the ratio of the number of historical usage data of the same specification equipment with a loss degree greater than deg and failure to the total number of historical usage data of the same specification equipment. If the equipment does not fail and continues to be used, the loss degree will be greater than or equal to deg. Under this condition, the historical data is used to determine the failure probability of the equipment.

[0030] In step S13, determining the second failure rate of the target device based on the operating parameter data of the target device further includes the following steps:

[0031] Obtain the operating parameter data of the target device and the historical operating parameter data of the device of the same specification, perform feature splicing on the operating parameter data to obtain the feature vector of the target device and the feature vector of the device of the same specification, perform unsupervised classification on the feature vector, determine the target classification cluster to which the feature vector of the target device belongs, and determine the second failure rate of the target device based on the failure condition of the feature vector of the device of the same specification in the target classification cluster , , is the number of faulty device feature vectors in the target classification cluster, is the total number of feature vectors in the target classification cluster.

[0032] In step S14, determining whether the target device needs to be diagnosed includes the following steps:

[0033] Determine the comprehensive failure rate of the target device based on the first failure rate and the second failure rate of the target device , , if the comprehensive failure rate of the target device If the target device has a fault rate greater than or equal to the preset fault threshold, it is determined that the target device needs to be diagnosed for a fault. If the value is less than the preset fault threshold, it is determined that the target device does not need to be diagnosed for a fault.

[0034] In another aspect of the present invention, a cloud-based automated medical equipment management system is provided, comprising: a data acquisition module, a cloud platform and a fault diagnosis module; the output end of the data acquisition module is connected to the input end of the cloud platform, for acquiring equipment usage data and operating parameter data; the output end of the cloud platform is connected to the input end of the fault diagnosis module, the degree of equipment loss is determined based on the equipment usage data, the first failure rate and the second failure rate of the equipment are determined based on the degree of equipment loss and the operating parameter data, and whether the equipment needs to be fault diagnosed is determined according to the first failure rate and the second failure rate; if so, the cloud platform sends an instruction to the fault diagnosis module to perform fault diagnosis on the target equipment; otherwise, it continues to determine whether the target equipment needs to be fault diagnosed; after receiving the instruction from the cloud platform, the fault diagnosis module sends a warning message to remind management personnel that the equipment needs to be fault diagnosed.

[0035] The data acquisition module also includes a usage data acquisition unit and a parameter data acquisition unit; in order to provide users with a better user experience, the usage data acquisition unit is used to obtain the user's weight, heart rate, and location information in the device after obtaining the user's authorization; the parameter data acquisition unit is used to obtain the device's operating parameter data. The cloud platform also includes a data service layer, an application layer, a resource layer, and a network service layer; the data service layer is used to store the data acquired by the data acquisition module; the application layer is used to perform automatic fault diagnosis on the device; the resource layer is used to calculate resources and storage resources for the cloud platform; and the network service layer is used to transmit data on the device.

[0036] Compared with the prior art, the beneficial effects achieved by the present invention are: obtaining the usage data and operating parameter data of the equipment, the usage data being the cause of the fault, the operating parameter data being the result of the equipment fault, and judging the first failure rate and the second failure rate of the equipment; performing fault analysis based on the cause and result of the equipment fault, automatically issuing fault information before or when the equipment fails, without the need for manual judgment, and timely diagnosing the equipment fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0038] Figure 1 It is a structural diagram of a cloud platform-based medical equipment automation management system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] In an embodiment of the present invention, the target device is a spa machine, see Figure 1 , provides a medical equipment automation management system based on a cloud platform, including:

[0041] A data acquisition module, a cloud platform and a fault diagnosis module; the output end of the data acquisition module is connected to the input end of the cloud platform, and is used to obtain usage data and operating parameter data of the spa machine; the output end of the cloud platform is connected to the input end of the fault diagnosis module, the wear degree of the spa machine is determined based on the usage data of the spa machine, the first failure rate and the second failure rate of the spa machine are determined based on the wear degree and operating parameter data of the spa machine, and whether the spa machine needs to be diagnosed according to the first failure rate and the second failure rate; if so, the cloud platform sends an instruction to the fault diagnosis module to perform fault diagnosis on the target spa machine; otherwise, it continues to determine whether the target spa machine needs to be diagnosed; after receiving the instruction from the cloud platform, the fault diagnosis module sends a warning message to remind the management personnel that the spa machine needs to be diagnosed.

[0042] Specifically, the data acquisition module also includes a usage data acquisition unit and a parameter data acquisition unit; for the purpose of providing users with a better user experience, after obtaining user authorization, the usage data acquisition unit is used to acquire the user's weight, heart rate, and location information in the spa machine; the parameter data acquisition unit is used to acquire the operating parameter data of the spa machine. The cloud platform also includes a data service layer, an application layer, a resource layer, and a network service layer; the data service layer is used to store the data acquired by the data acquisition module; the application layer is used to perform automatic fault diagnosis on the spa machine; the resource layer is used to calculate resources and storage resources for the cloud platform; and the network service layer is used to transmit data of the spa machine.

[0043] In an embodiment of the present invention, a cloud platform-based medical equipment automation management method is provided, comprising:

[0044] S11, obtain the usage data of the target spa machine and the operating parameter data of the target spa machine; the operating parameter data is data showing equipment loss and fault phenomena; the usage data of the target spa machine includes the start and stop time, normal working time, static load, dynamic load and stress distribution data of the spa machine; the operating parameter data includes water temperature, spa machine vibration, water pressure, voltage and current data. The static load is the user's weight, which is obtained through equipment such as a weight scale; the dynamic load is obtained through equipment such as a heart rate meter, and the stress distribution data is determined by the user's center of mass position through a camera; the operating parameters are collected through sensors.

[0045] S12, based on the usage data of the target spa machine, determine the wear degree of the target spa machine; obtain the electronic tag of the target spa machine, obtain the historical usage data of spa machines of the same specification according to the electronic tag of the target spa machine, and determine the first failure rate of the target spa machine based on the wear degree of the target spa machine and the wear degree of spa machines of the same specification;

[0046] The loss of the target hydrotherapy machine is calculated by the following formula:

[0047] , where deg is the loss degree of the target spa machine, T is the operating time of the target spa machine, M is the static load of the target spa machine, G is the dynamic load of the target spa machine, and PSO is the stress distribution data; , The time for the target spa machine to work normally, is the start and stop time of the target spa machine, is the target hydrotherapy machine start-stop coefficient; , m is the weight of the user using the target spa machine, To preset the weight threshold, set it according to the load capacity of the target spa machine. is the static load factor of the target spa machine, ; , is the user's heart rate, is the user's resting heart rate, is the dynamic load factor of the target spa machine, .

[0048] For example, for a spa machine, the startup time is 60 seconds, the shutdown time is 60 seconds, and the normal working time is 3600 seconds. It consists of two parts: 120s start and stop time, when the user does not use the spa machine, M, G and PSO are all 1; and the normal working time is 3600s, when M, G and PSO need to be judged. The loss increases with time and changes with the changes of G and PSO. The sampling period can be set , decompose 3600s into multiple sampling periods, G and PSO remain unchanged in each sampling period, and add the data of multiple sampling periods to obtain the data of normal working time.

[0049] The stress distribution data PSO is determined by the following steps:

[0050] S31, establishing a plane rectangular coordinate system on the hydrotherapy pool plane of the target hydrotherapy machine, determining the plane position of the user's center of mass in the hydrotherapy pool, wherein the plane position of the user's center of mass is the intersection of the human body midline and the hydrotherapy pool plane, and obtaining the plane coordinates of the user's center of mass;

[0051] S32, obtaining the centroid plane coordinates of historical users from the historical usage data of the spa machine of the same specification, taking the centroid plane coordinates of the historical users as input features, performing cluster analysis on the input features, and obtaining cluster clusters;

[0052] S33, taking the class center of the i-th cluster as the feature label , i is a positive integer. When the historical usage data of the spa machine of the same specification is insufficient, the loss caused to the spa machine of the same specification when the user is in the spa pool position corresponding to the different class centers is determined by simulating the usage pattern. The i-th feature label is determined based on the loss caused to the spa machine of the same specification The stress distribution coefficient ; When there is sufficient historical usage data for the same specification of spa machine, the i-th feature label is determined based on the historical usage data The stress distribution coefficient ;

[0053] S34, calculating the distance between the user's centroid and the class center of the cluster, the cluster corresponding to the class center with the smallest distance to the user's centroid is the cluster to which the user's centroid belongs, and determining the stress distribution data according to the feature label of the cluster to which the user's centroid belongs.

[0054] The simulated usage mode also includes the following steps:

[0055] S41, defining a position of a user in a hydrotherapy pool, wherein the position of the user in the hydrotherapy pool is a position of the hydrotherapy pool corresponding to a feature tag;

[0056] S42, creating a computer simulation model of a spa machine and a user of the same specification;

[0057] S43, simulating different positions of the user in the spa pool, applying the same static load, and determining the time that the spa machine of the same specification can operate normally when the user is in different positions in the spa pool; repeating the simulation for all positions, and obtaining the time that the spa machine of the same specification can operate normally at the i-th position ; The feature label with the most data points in the cluster corresponding to all feature labels The stress distribution coefficient is set to 1, then the i-th feature label The stress distribution coefficient , Feature label The time that a spa machine of the same specification at the corresponding spa pool location can operate normally.

[0058] Determine the i-th feature label based on historical usage data The stress distribution coefficient , including the following steps:

[0059] In the historical usage data of the spa machine of the same specification, find the historical usage data of the faulty spa machine and determine the time when the historical user was in the spa pool corresponding to the i-th feature label of the faulty spa machine , randomly select two different sets of historical usage data of faulty spa machines, and subtract the time at the same spa pool location to get the time difference , establish the equation , take x different time difference data and use the equation to form a linear equation system of x variables: , solving the equations yields ; Repeat the calculation of historical usage data of different faulty spa machines The average value of .

[0060] Taking the number of clusters as 2 as an example, x is 2, and the historical usage data of 3 different groups of faulty spa machines are obtained. The time at the spa pool location is , , , we can get three sets of time difference data, and take two sets of time difference data to construct the equation system: , can solve and .

[0061] Determining the first failure rate of the target hydrotherapy machine further includes the following steps:

[0062] S51, based on the historical usage data of the spa machine of the same specification, calculate the historical loss degree under the fault state and the non-fault state; for the historical usage data of the spa machine of the same specification that has failed, the loss degree data calculated after the failure occurs is the historical loss degree under the failure state, and the loss degree data calculated before the failure occurs is the historical loss degree under the non-fault state;

[0063] S52, based on the current loss degree deg of the target spa machine, let A represent the random event that the target spa machine will fail, and D represent the loss degree random variable, then the first failure rate of the target spa machine is: , is the first failure rate of the target spa machine. Based on the historical usage data of spa machines of the same specification, the probability that the loss of the target spa machine is greater than deg is obtained. , It is the ratio of the number of historical usage data of spa machines of the same specification with a loss degree greater than deg to the total number of historical usage data of spa machines of the same specification; It is the ratio of the number of historical usage data of spa machines of the same specification with a loss degree greater than deg and failure to the total number of historical usage data of spa machines of the same specification.

[0064] S13, determining a second failure rate of the target spa machine based on the operating parameter data of the spa machine and the operating parameter data of spa machines of the same specification:

[0065] Obtain the operating parameter data of the target spa machine and the historical operating parameter data of the spa machine of the same specification, perform feature splicing on the operating parameter data to obtain the feature vector of the target spa machine and the feature vector of the spa machine of the same specification, perform unsupervised classification on the feature vector, determine the target classification cluster to which the feature vector of the target spa machine belongs, and determine the second failure rate of the target spa machine based on the failure condition of the feature vector of the spa machine of the same specification in the target classification cluster , , is the number of faulty spa feature vectors in the target classification cluster, is the total number of feature vectors in the target classification cluster.

[0066] S14, based on the first failure rate and the second failure rate of the target spa machine, determine whether the target spa machine needs to be diagnosed for a fault. If so, perform a fault diagnosis on the target spa machine, and after the fault diagnosis is completed, all usage data of the target spa machine are reset to zero; otherwise, continue to determine whether the target spa machine needs to be diagnosed for a fault.

[0067] Determine the comprehensive failure rate of the target spa machine based on the first failure rate and the second failure rate of the target spa machine , , if the comprehensive failure rate of the target spa machine is greater than or equal to the preset fault threshold, the target spa machine is judged to need fault diagnosis; if the comprehensive fault rate of the target spa machine If it is less than the preset fault threshold, it is determined that the target spa machine does not need to be diagnosed for faults.

[0068] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0069] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A cloud platform-based automated management method for medical equipment, characterized in that: The following steps are involved: S11, obtaining usage data of the target device and operating parameter data of the target device; the operating parameter data is data showing device wear and failure phenomena; S12, determining the wear degree of the target device based on the usage data of the target device; obtaining an electronic tag of the target device, obtaining historical usage data of a device of the same specification according to the electronic tag of the target device, and determining a first failure rate of the target device based on the wear degree of the target device and the wear degree of a device of the same specification; The step of determining the first failure rate of the target device further comprises the following steps S51 and S52: S51, based on the historical usage data of the equipment of the same specification, calculate the historical loss degree in the fault state and the non-fault state; for the historical usage data of the equipment of the same specification that has failed, the loss degree data calculated after the failure occurs is the historical loss degree in the fault state, and the loss degree data calculated before the failure occurs is the historical loss degree in the non-fault state; S52, based on the current loss degree of the target device deg, let A represent the random event that the target device will fail, and D represent the loss degree random variable, then the first failure rate of the target device is: , is the first failure rate of the target device. Based on the historical usage data of the same specification equipment, the probability that the loss of the target device is greater than deg is obtained. , It is the ratio of the number of historical usage data of the same specification equipment with loss degree greater than deg to the total number of historical usage data of the same specification equipment; It is the ratio of the number of historical usage data of the same specification equipment with a loss degree greater than deg and a fault to the total number of historical usage data of the same specification equipment; S13, determining a second failure rate of the target device based on the operating parameter data of the device and the operating parameter data of devices with the same specification: Obtain the operating parameter data of the target device and the historical operating parameter data of the device of the same specification, perform feature splicing on the operating parameter data to obtain the feature vector of the target device and the feature vector of the device of the same specification, perform unsupervised classification on the feature vector, determine the target classification cluster to which the feature vector of the target device belongs, and determine the second failure rate of the target device based on the failure condition of the feature vector of the device of the same specification in the target classification cluster , , is the number of faulty device feature vectors in the target classification cluster, is the total number of feature vectors in the target classification cluster; S14, based on the first failure rate and the second failure rate of the target device, determine whether the target device needs to be diagnosed. If so, perform fault diagnosis on the target device, and after the fault diagnosis is completed, all usage data of the target device will be reset to zero; otherwise, continue to determine whether the target device needs to be diagnosed.

2. According to claim 1, a cloud platform-based medical equipment automation management method is characterized in that: The usage data of the target equipment includes the start and stop time, normal working time, static load, dynamic load and stress distribution data of the equipment; the loss degree of the target equipment is calculated by the following formula: , where deg is the loss degree of the target device, T is the operating time of the target device, M is the static load of the target device, G is the dynamic load of the target device, and PSO is the stress distribution data; , The time for the target device to work normally. is the start and stop time of the target device, is the start-stop coefficient of the target equipment; , m is the weight of the user using the target device, To preset the weight threshold, set it according to the load capacity of the target device. is the static load factor of the target device, ; , is the user's heart rate, is the user's resting heart rate, is the dynamic load factor of the target device, .

3. The method for automated management of medical equipment based on a cloud platform according to claim 2, characterized in that: The stress distribution data PSO is determined by the following steps: S31, establishing a plane rectangular coordinate system on a plane of a use area of ​​a target device used by a user, determining a plane position of a user's center of mass in the use area, wherein the plane position of the user's center of mass is an intersection of a human body midline and the plane of the use area, and obtaining the plane coordinates of the user's center of mass; S32, obtaining the centroid plane coordinates of historical users from the historical usage data of the device with the same specification, taking the centroid plane coordinates of the historical users as input features, performing cluster analysis on the input features, and obtaining cluster clusters; S33, taking the class center of the i-th cluster as the feature label , i is a positive integer. When the historical usage data of the same specification device is insufficient, the loss caused to the same specification device when the user is in the usage area corresponding to the different class centers is determined by simulating the usage pattern. The i-th feature label is determined based on the loss caused to the same specification device. The stress distribution coefficient ; When there is sufficient historical usage data for the same specification equipment, the i-th feature label is determined based on the historical usage data The stress distribution coefficient ; S34, calculating the distance between the user's centroid and the class center of the cluster, the cluster corresponding to the class center with the smallest distance to the user's centroid is the cluster to which the user's centroid belongs, and determining the stress distribution data according to the feature label of the cluster to which the user's centroid belongs.

4. According to claim 3, a cloud platform-based medical equipment automation management method is characterized in that: The simulated usage mode also includes the following steps: S41, defining a location of a user in a usage area, wherein the location of the user in the usage area is a location of the usage area corresponding to a feature tag; S42, creating a computer simulation model of the same specifications of equipment and users; S43, simulating different positions of the user in the use area, applying the same static load, and determining the time that the same specification equipment can operate normally when the user is in different positions in the use area; repeating the simulation for all positions, obtaining the time that the same specification equipment can operate normally at the i-th position ; The feature label with the most data points in the cluster corresponding to all feature labels The stress distribution coefficient is set to 1, then the i-th feature label The stress distribution coefficient , is the feature label The time that equipment of the same specification can operate normally in the corresponding use area; Determine the i-th feature label based on historical usage data The stress distribution coefficient , including the following steps: In the historical usage data of the same specification equipment, find the historical usage data of the faulty equipment and determine the time when the historical user was in the usage area corresponding to the i-th feature tag of the faulty equipment , take any two sets of historical usage data of different faulty devices, subtract the time of the same usage area location to get the time difference , establish the equation , take x different time difference data and use the equation to form a linear equation system of x variables: , solving the equations yields ; Repeat the calculation of historical usage data of different faulty equipment The average value of .

5. The method for automated management of medical equipment based on a cloud platform according to claim 4, characterized in that: In step S14, determining whether the target device needs to be diagnosed includes the following steps: Determine the comprehensive failure rate of the target device based on the first failure rate and the second failure rate of the target device , , if the comprehensive failure rate of the target device If the target device has a fault rate greater than or equal to the preset fault threshold, it is determined that the target device needs to be diagnosed for a fault. If the value is less than the preset fault threshold, it is determined that the target device does not need to be diagnosed for a fault.

6. A cloud-based automated medical equipment management system, using a cloud-based automated medical equipment management method as described in any one of claims 1 to 5, characterized in that: include: A data acquisition module, a cloud platform and a fault diagnosis module; the output end of the data acquisition module is connected to the input end of the cloud platform to obtain the usage data and operating parameter data of the equipment; the output end of the cloud platform is connected to the input end of the fault diagnosis module, the degree of wear of the equipment is determined based on the usage data of the equipment, the first failure rate and the second failure rate of the equipment are determined based on the wear rate and the operating parameter data of the equipment, and whether the equipment needs to be diagnosed according to the first failure rate and the second failure rate is judged; if so, the cloud platform sends an instruction to the fault diagnosis module to perform fault diagnosis on the target equipment; otherwise, it continues to judge whether the target equipment needs to be diagnosed; after receiving the instruction from the cloud platform, the fault diagnosis module sends a warning message to remind the management personnel that the equipment needs to be diagnosed.

7. The cloud platform-based medical equipment automation management system according to claim 6, characterized in that: The cloud platform also includes a data service layer, an application layer, a resource layer and a network service layer; the data service layer is used to store data acquired by the data acquisition module; the application layer is used to perform automatic fault diagnosis on the equipment; the resource layer is used to calculate resources and storage resources for the cloud platform; and the network service layer is used to perform data transmission on the equipment.

Images