Intelligent diagnosis method and system for faults of medical apparatus and instruments

Abstract

The invention provides a medical instrument fault intelligent diagnosis method and system. The method comprises the following steps: collecting electromagnetic signals generated by current flowing through each monitoring point; decomposing each electromagnetic signal into a plurality of electromagnetic components, and constructing a space gradient field of magnetic field change according to the trend characteristics of each electromagnetic component; acquiring saturation current of a common mode choke in the medical instrument when a magnetic core is saturated, and determining degradation constraint of saturation margin of an electromagnetic compatibility protection element in the medical instrument according to the time sequence change rate of magnetic field intensity in the space gradient field and the saturation current; mapping the operation data of the medical device during operation into a dynamic slow characteristic of electromagnetic compatibility long-term aging during operation of the medical device based on degradation constraint; and performing time sequence mutation detection on the dynamic slow characteristic to obtain a fault moment of electromagnetic compatibility failure of the medical device. By adopting the scheme of the invention, the long-term aging trend of the electromagnetic compatibility protection element of the medical instrument can be captured under the condition that the influence of short-term rapid change data is eliminated.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault diagnosis, and more particularly, to a medical instrument fault intelligent diagnosis method and system. BACKGROUND

[0002] As the core equipment of modern medical diagnosis and treatment, the running stability of medical instruments is directly related to the diagnosis and treatment accuracy and patient safety, especially in the scene of high field strength and multi-module collaborative work (such as magnetic resonance imaging equipment and high-frequency surgical equipment). The performance attenuation of electromagnetic compatibility protection elements (such as common-mode choke coils and filters) may cause electromagnetic interference to exceed the standard, triggering equipment misfire, signal distortion and other faults. Therefore, real-time fault diagnosis of medical instruments is of great significance. With the development of intelligent technology, intelligent diagnosis methods based on multi-sensor data have gradually become a research hotspot. By analyzing the physical signals during the operation of the equipment, early warning and positioning of faults can be achieved.

[0003] In the prior art, medical instrument fault diagnosis relies on voltage, current and other electrical parameter monitoring. Although this method can identify sudden faults, it is difficult to effectively distinguish short-term electromagnetic fluctuations from long-term aging trends of electromagnetic compatibility protection elements. Due to the complex working environment of medical instruments, electromagnetic signals often contain short-term rapid interference such as equipment start-stop and load changes. These interferences can easily mask the slow performance degradation characteristics of protection elements caused by magnetic core loss and insulation aging, resulting in insufficient sensitivity of existing methods in capturing long-term aging trends. Therefore, how to capture the long-term aging trend of electromagnetic compatibility protection elements of medical instruments while excluding the influence of short-term rapid change data has become a difficult problem in the industry. SUMMARY

[0004] The present application provides a medical instrument fault intelligent diagnosis method and system, which can capture the long-term aging trend of electromagnetic compatibility protection elements of medical instruments while excluding the influence of short-term rapid change data.

[0005] In a first aspect, the present application provides a medical instrument fault intelligent diagnosis method, comprising: A plurality of monitoring points are arranged on the circuit path of the common-mode choke coil in the medical instrument, and electromagnetic signals generated by the current flowing through each monitoring point are collected; Each electromagnetic signal is decomposed into a plurality of electromagnetic components, an operating state space of the medical instrument is constructed according to the trend characteristics of each electromagnetic component, and a spatial gradient field of the magnetic field change on the current path of the common-mode choke coil is determined according to the correlation between each monitoring point in the operating state space; The saturation current of the common-mode choke coil in the medical instrument when the magnetic core is saturated is obtained, and the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument is determined according to the time sequence change rate of the magnetic field intensity in the spatial gradient field and the saturation current; monitoring running data of the medical instrument in real time, mapping the running data into a dynamic slow feature of long-term aging of electromagnetic compatibility of the medical instrument in running based on the degradation constraint; detecting time sequence mutation of the dynamic slow feature to obtain a failure time of electromagnetic compatibility failure of the medical instrument.

[0006] In some embodiments, decomposing each electromagnetic signal into a plurality of electromagnetic components specifically includes: selecting one electromagnetic signal as a selected signal, and marking all maximum points and minimum points in the selected signal; performing interpolation fitting on all maximum points and all minimum points to obtain a central envelope line of the selected signal; decomposing the selected signal according to the central envelope line to obtain a plurality of electromagnetic components of the selected signal; continuing to decompose the remaining electromagnetic signals into a plurality of electromagnetic components.

[0007] In some embodiments, constructing a running state space of the medical instrument according to trend features of each electromagnetic component specifically includes: determining trend features of each electromagnetic component; screening a plurality of running state components of the medical instrument according to all trend features; combining all running state components into a running state space of the medical instrument.

[0008] In some embodiments, determining a spatial gradient field of magnetic field change on a common-mode choke current path according to a correlation relationship between each monitoring point in the running state space specifically includes: standardizing the running state space to obtain a standard running state space; determining a correlation relationship matrix between each monitoring point in the standard running state space; performing eigenvalue decomposition on the correlation relationship matrix to obtain an eigenvector matrix and an eigenvalue matrix; determining a spatial gradient field of magnetic field change on a common-mode choke current path according to a correlation relationship between each monitoring point in the running state space.

[0009] In some embodiments, determining a degradation constraint of saturation margin of an electromagnetic compatibility protection element in the medical instrument according to a time sequence change rate of magnetic field intensity in the spatial gradient field and the saturation current specifically includes: performing first-order derivation on the spatial gradient field to obtain a time sequence change rate matrix of magnetic field intensity; determining an aging feature of the electromagnetic compatibility protection element in the medical instrument based on the time sequence change rate matrix; determining a degradation constraint of saturation margin of the electromagnetic compatibility protection element in the medical instrument based on the saturation current and the aging feature.

[0010] In some embodiments, mapping the operation data into the dynamic slow feature of the long-term aging of the electromagnetic compatibility of the medical instrument in operation based on the degradation constraint specifically comprises: converting the operation data into an operation data matrix; mapping the operation data matrix into a slow feature matrix through the degradation constraint; decomposing the slow feature matrix into the dynamic slow feature of the long-term aging of the electromagnetic compatibility of the medical instrument in operation.

[0011] In some embodiments, performing time series mutation detection on the dynamic slow feature to obtain the failure time of the electromagnetic compatibility failure of the medical instrument specifically comprises: determining the autocorrelation sequence of the dynamic slow feature; determining the mutation point of the long-term aging through the autocorrelation sequence; segmenting and fitting the dynamic slow feature according to the mutation point, and then extracting the failure time of the electromagnetic compatibility saturation current failure of the medical instrument from the segmented and fitted result.

[0012] In some embodiments, the electromagnetic signals generated by the current flowing through each monitoring point are collected by a magnetic resistance sensor.

[0013] In some embodiments, the saturation current of the common mode choke coil in the medical instrument when the magnetic core is saturated is obtained by a Hall current sensor and a digital bridge tester.

[0014] In a second aspect, the present application provides a medical instrument fault intelligent diagnosis system, comprising: a collection module, configured to set multiple monitoring points on the circuit path of the common mode choke coil in the medical instrument, and collect electromagnetic signals generated by the current flowing through each monitoring point; a processing module, configured to decompose each electromagnetic signal into multiple electromagnetic components, construct an operation state space of the medical instrument according to the trend characteristics of each electromagnetic component, and determine the spatial gradient field of the magnetic field change on the current path of the common mode choke coil according to the correlation between each monitoring point in the operation state space; The processing module is further configured to obtain the saturation current of the common mode choke coil in the medical instrument when the magnetic core is saturated, and determine the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument according to the time series change rate of the magnetic field intensity in the spatial gradient field and the saturation current; The processing module is further configured to map the operation data into the dynamic slow feature of the long-term aging of the electromagnetic compatibility of the medical instrument in operation based on the degradation constraint; an execution module, configured to perform time series mutation detection on the dynamic slow feature to obtain the failure time of the electromagnetic compatibility failure of the medical instrument.

[0015] The embodiments disclosed in the application have the following beneficial effects: In the medical instrument fault intelligent diagnosis method and system provided by the application, a plurality of monitoring points are arranged on the circuit path of the common mode choke coil in the medical instrument, and electromagnetic signals generated by the current flowing through each monitoring point are collected; each electromagnetic signal is decomposed into a plurality of electromagnetic components, an operation state space of the medical instrument is constructed according to the trend characteristics of each electromagnetic component, and a spatial gradient field of the magnetic field change on the current path of the common mode choke coil is determined according to the correlation between each monitoring point in the operation state space; the saturation current of the common mode choke coil in the medical instrument when the magnetic core is saturated is obtained, and the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument is determined according to the time sequence change rate of the magnetic field intensity in the spatial gradient field and the saturation current; the operation data of the medical instrument during operation is monitored in real time, the operation data is mapped into the dynamic slow feature of the long-term aging of the electromagnetic compatibility of the medical instrument during operation based on the degradation constraint, the time sequence mutation of the dynamic slow feature is detected, and the fault time of the electromagnetic compatibility failure of the medical instrument is obtained.

[0016] As can be seen, by decomposing and screening the electromagnetic signals, the application first eliminates the interference noise in the electromagnetic signals, and the remaining electromagnetic component signals are taken as the operation data to constitute the operation state space of the medical instrument, then the change of the internal electromagnetic field of the medical instrument during operation is analyzed (i.e. the time sequence change rate) through the correlation between each data in the operation state space, then the aging condition of the current common mode choke coil (i.e. the degradation constraint of the saturation margin) is comprehensively evaluated by combining the time sequence change rate and the saturation current of the common mode choke coil when the magnetic core is saturated, and the operation data of the medical instrument during operation is mapped into the slow feature of the long-term aging by the aging condition, the short-term change feature is eliminated, the slow aging condition of the electromagnetic compatibility protection element during long-term operation (i.e. the dynamic slow feature) is focused on, and the fault time of the electromagnetic compatibility failure of the medical instrument is identified through the dynamic slow feature. In summary, by using the scheme of the application, the long-term aging trend of the electromagnetic compatibility protection element of the medical instrument can be captured by excluding the influence of short-term rapid change data. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 is an exemplary flowchart of a medical instrument fault intelligent diagnosis method according to some embodiments of the application; Figure 2 is an exemplary flowchart of decomposing electromagnetic signals according to some embodiments of the application; Figure 3 is an exemplary flowchart of determining the degradation constraint according to some embodiments of the application; Figure 4is a structural schematic diagram of a medical instrument fault intelligent diagnosis system according to some embodiments of the present application; Figure 5 is a structural schematic diagram of a computer device for implementing a medical instrument fault intelligent diagnosis method according to some embodiments of the present application. DETAILED DESCRIPTION

[0018] In order to better understand the technical solutions of the present application, the technical solutions of the present application will be described in detail below in combination with the drawings of the specification and specific embodiments.

[0019] Reference Figure 1 The figure is an exemplary flowchart of a medical instrument fault intelligent diagnosis method according to some embodiments of the present application, which mainly includes the following steps: In step 101, a plurality of monitoring points are arranged on the circuit path of the common mode choke coil in the medical instrument, and electromagnetic signals generated by the current flowing through each monitoring point are collected.

[0020] When specifically implemented, the plurality of monitoring points arranged on the circuit path of the common mode choke coil in the medical instrument can be implemented in the following manner, i.e., a plurality of reluctance sensors are installed as monitoring points at a plurality of key positions on the circuit path of the common mode choke coil, and each monitoring point is labeled, i.e., all monitoring points are labeled as 1 to n, n being the total number of monitoring points, wherein the key positions can include the input terminal terminal at the common mode choke coil, the output terminal terminal, the vicinity of the magnetic core body, the cable shielding layer joint in series with the choke coil, and in other embodiments, the key positions can also include other positions on the circuit path of the common mode choke coil, which are not limited here.

[0021] It should be noted that the label of the monitoring point in the present application is only a means for facilitating the description of the subsequent implementation manner, and the size of the label does not limit the importance or other parameters of the monitoring point, i.e., all monitoring points can be randomly labeled as 1 to n, n being the total number of monitoring points.

[0022] When specifically implemented, collecting electromagnetic signals generated by the current flowing through each monitoring point can be implemented in the following manner, i.e., the sampling frequency of the reluctance sensor at each monitoring point is set to 1 kHz, the electromagnetic field intensity value in the running process of the medical instrument is collected through the reluctance sensor at each monitoring point, and all electromagnetic field intensity values collected by the reluctance sensor at each monitoring point are arranged in sequence according to the collection order, and each sequence obtained by the arrangement is respectively taken as the electromagnetic signal generated by the current flowing through each monitoring point in the running process of the medical instrument.

[0023] In step 102, each electromagnetic signal is decomposed into a plurality of electromagnetic components, an operation state space of the medical instrument is constructed according to trend characteristics of each electromagnetic component, and a spatial gradient field of magnetic field changes on the common mode choke current path is determined according to the correlation between each monitoring point in the operation state space.

[0024] In some embodiments, with reference to Figure 2 The figure is an exemplary flowchart for decomposing electromagnetic signals according to some embodiments of the present application, and the decomposition of each electromagnetic signal into a plurality of electromagnetic components can be achieved by the following steps: In step 1021, one electromagnetic signal is selected as a selected signal, and all maximum points and minimum points in the selected signal are marked; In step 1022, all maximum points and all minimum points are subjected to interpolation fitting to obtain a central envelope line of the selected signal; In step 1023, the selected signal is decomposed according to the central envelope line to obtain a plurality of electromagnetic components of the selected signal; In step 1024, the remaining electromagnetic signals are continuously decomposed into a plurality of electromagnetic components.

[0025] In a specific implementation, all maximum points and all minimum points are subjected to interpolation fitting to obtain a central envelope line of the selected signal, which can be achieved by the following manner, that is, first, all maximum points are arranged in time sequence, and a cubic spline interpolation method in the prior art is used to fit all maximum points to obtain an upper envelope line, all minimum points are also arranged in time sequence, and a cubic spline interpolation method in the prior art is used to fit all minimum points to obtain a lower envelope line, and then, an average curve of the upper envelope line and the lower envelope line is calculated as the central envelope line of the selected signal.

[0026] It should be noted that the central envelope line in the present application is a reference curve reflecting the overall trend of the electromagnetic signal in the fluctuation process.

[0027] In a specific implementation, the selected signal is decomposed according to the central envelope line to obtain a plurality of electromagnetic components of the selected signal, which can be achieved by the following manner, that is, an empirical mode decomposition method in the prior art is used, the central envelope line is removed as the mean value of the selected signal, and the screening condition of the intrinsic mode function is set to a difference between the number of extreme points and the number of zero-crossing points not more than 1, thereby obtaining a plurality of intrinsic mode functions of the selected signal, and each intrinsic mode function obtained is taken as an electromagnetic component of the selected signal.

[0028] In some embodiments, the operation state space of the medical instrument can be constructed according to the trend characteristics of each electromagnetic component by the following steps: The trend characteristics of each electromagnetic component are determined; determining a running state component of the medical instrument according to all the trend characteristics; combining all the running state components into a running state space of the medical instrument.

[0029] In a specific implementation, the trend characteristics of each electromagnetic component can be determined by calculating the Hurst index of each electromagnetic component using the rescaled range analysis method in the prior art, and taking the Hurst index of each electromagnetic component as the trend characteristic of each electromagnetic component.

[0030] It should be noted that the trend characteristic in the present application is a parameter value quantifying the continuous change tendency of the electromagnetic component in the time dimension.

[0031] In a specific implementation, the running state component of the medical instrument can be determined according to all the trend characteristics by setting the trend threshold to 0.5 according to the principle of the Hurst index, and taking the sum of all electromagnetic components whose trend characteristics differ from the trend threshold by less than 0.1 as the running state component of the medical instrument at each monitoring point.

[0032] It should be noted that the running state component in the present application is a comprehensive signal reflecting the stable change tendency of the electromagnetic characteristics of the medical instrument at the corresponding monitoring point.

[0033] It should be noted that the running state component in the present application is one-to-one corresponding to the monitoring point, that is, one monitoring point corresponds to one running state component.

[0034] In a specific implementation, all the running state components can be combined into a running state space of the medical instrument by arranging all the running state components into a matrix according to the labels of the monitoring points, that is, the running state component of the label i monitoring point is the i-th column in the matrix, and taking the obtained matrix as the running state space of the medical instrument.

[0035] It should be noted that the running state space in the present application is a collection of electromagnetic signal components comprehensively reflecting the electromagnetic running state of the common mode choke coil and the correlation relationship between the monitoring points.

[0036] In some embodiments, determining the spatial gradient field of the magnetic field change on the common mode choke coil current path according to the correlation relationship between the monitoring points in the running state space can be implemented by the following steps: standardizing the running state space to obtain a standard running state space; determining a correlation relationship matrix between the monitoring points in the standard running state space; performing eigenvalue decomposition on the correlation relationship matrix to obtain an eigenvector matrix and an eigenvalue matrix; The spatial gradient field of the magnetic field change on the common-mode choke current path is determined according to the correlation between the monitoring points in the operation state space.

[0037] In a specific implementation, the operation state space is standardized to obtain a standard operation state space, which can be implemented in the following manner: for each column of data in the operation state space, the mean and standard deviation of each column of data are calculated, then each column of data is subjected to Z-score standardization processing through the mean and standard deviation of each column of data, and the matrix composed of the processed columns of data is taken as the standard operation state space.

[0038] It should be noted that the standard operation state space in the present application is the operation state space after standardization processing.

[0039] In a specific implementation, the correlation matrix between the monitoring points in the standard operation state space can be implemented in the following manner: the covariance matrix of the standard operation state space is calculated, and the covariance matrix is taken as the correlation matrix between the monitoring points.

[0040] It should be noted that the correlation matrix in the present application is a collection of parameter values for measuring the degree of mutual influence between the electromagnetic signal change trends of the monitoring points of the medical device.

[0041] In a specific implementation, the spatial gradient field of the magnetic field change on the common-mode choke current path can be implemented in the following manner according to the correlation between the monitoring points in the operation state space: first, the operation state space is whitened through the eigenvector matrix and the eigenvalue matrix, that is, the square root of the inverse matrix of the eigenvalue matrix is first calculated, and the result is multiplied by the eigenvector matrix, then the multiplied result is multiplied by the operation state space, and the obtained result is taken as the whitened result of the operation state space, and the whitened result is taken as the spatial gradient field of the magnetic field change on the common-mode choke current path.

[0042] It should be noted that the spatial gradient field in the present application is a matrix describing the speed and direction of the change of the magnetic field intensity on the common-mode choke current path at different monitoring point positions when the medical device is working.

[0043] In step 103, the saturation current of the common-mode choke in the medical device when the magnetic core is saturated is obtained, and the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical device is determined according to the time sequence change rate of the magnetic field intensity in the spatial gradient field and the saturation current.

[0044] In a specific implementation, the saturation current of the common-mode choke coil in the medical instrument when the magnetic core is saturated can be obtained by the following method: a Hall current sensor is connected in series at the input and output of the common-mode choke coil, and a digital bridge tester is connected in parallel to monitor the inductance value. When the inductance value is monitored to decrease to 80% of the nominal inductance value, the current value at this time is recorded as the saturation current, wherein the nominal inductance value can be directly obtained from the product manual of the medical instrument.

[0045] In some embodiments, reference is made to Figure 3 The figure is an exemplary flow chart for determining the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument according to some embodiments of the present application. The degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument is determined according to the time rate of change of the magnetic field strength in the spatial gradient field and the saturation current in the present application, which can be achieved by the following steps: In step 1031, the spatial gradient field is first-order differentiated to obtain a time rate of change matrix of the magnetic field strength; In step 1032, the aging characteristics of the electromagnetic compatibility protection element in the medical instrument are determined based on the time rate of change matrix; In step 1033, the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument is determined based on the saturation current and the aging characteristics.

[0046] In a specific implementation, the spatial gradient field is first-order differentiated to obtain a time rate of change matrix of the magnetic field strength, which can be achieved by the following method: for each row of data in the spatial gradient field, each row of data is differentiated, wherein the time interval between adjacent two data in each row of data is the inverse of the sampling frequency of the magnetoresistance sensor at each monitoring point. In the present application, the sampling frequency is 1 kHz, i.e. the time interval between adjacent two data in each row of data is 0.001 seconds. The result of differentiating each row of data is rearranged by row, and the matrix obtained by rearrangement is taken as the time rate of change matrix of the magnetic field strength.

[0047] It should be noted that the time rate of change matrix in the present application is a collection of parameter values describing the speed of change of the magnetic field strength on the circuit path of the common-mode choke coil in the medical instrument over time at each monitoring point position.

[0048] In a specific implementation, determining the aging feature of the electromagnetic compatibility protection element in the medical instrument based on the saturation current and the time-varying rate matrix can be implemented in the following manner: first, eigenvalue decomposition is performed on the covariance matrix of the time-varying rate matrix to obtain an eigenvector matrix A of the time-varying rate matrix; then, an eigenvector matrix B and an eigenvalue matrix C obtained by eigenvalue decomposition of the running state space after standardization are obtained; then, according to the principle of slow feature analysis, the matrix A is multiplied by the-1 / 2 power of the matrix B, and the obtained matrix is multiplied by the matrix C, and the final multiplication result is taken as the aging feature of the electromagnetic compatibility protection element in the medical instrument.

[0049] It should be noted that the aging feature in this application is a feature matrix quantifying the degree of performance degradation of the common-mode choke coil caused by long-term operation.

[0050] In a specific implementation, determining the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument based on the saturation current and the aging feature can be implemented in the following manner: first, the saturation margin of the electromagnetic compatibility protection element in the medical instrument is calculated, that is, the nominal value of the saturation current of the common-mode choke coil in the medical instrument when the magnetic core is saturated is obtained, which can be directly obtained from the product manual of the medical instrument; then, the relative error between the saturation current and the nominal value is recorded as the saturation margin q; then, eigenvalue decomposition is performed on the matrix corresponding to the aging feature, and the q upper quantile of all eigenvalues is taken as a threshold value; then, the eigenvectors with eigenvalues greater than the threshold value are removed, and the remaining eigenvectors and eigenvalues are reconstructed into a matrix, and the reconstructed matrix is taken as the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument.

[0051] It should be noted that the degradation constraint in this application is a mapping relationship matrix quantifying the influence degree of the saturation margin of the electromagnetic compatibility protection element on the running data after the attenuation of the aging process, through which the rapidly changing indicators in the running data can be removed, and only the data features reflecting the long-term aging of the saturation margin of the electromagnetic compatibility protection element are retained.

[0052] In step 104, the running data of the medical instrument during operation is monitored in real time, and the running data is mapped into a dynamic slow feature of long-term aging of electromagnetic compatibility of the medical instrument during operation based on the degradation constraint.

[0053] In a specific implementation, real-time monitoring of the running data of the medical instrument during operation can be implemented in the following manner: the electromagnetic field intensity values in the operation process of the medical instrument are collected by the magnetoresistance sensors at each monitoring point on the medical instrument, all electromagnetic field intensity values collected by the magnetoresistance sensors at each monitoring point are arranged in sequence according to the collection order, and each sequence obtained by the arrangement is taken as the running data of each monitoring point during the operation process of the medical instrument, wherein the sampling frequency of the magnetoresistance sensor at each monitoring point is set to 1 kHz.

[0054] In some embodiments, mapping the operation data into dynamic slow features of long-term aging of electromagnetic compatibility of medical devices in operation based on the degradation constraint can be implemented by the following steps: Converting the operation data into an operation data matrix; Mapping the operation data matrix into a slow feature matrix through the degradation constraint; Decomposing the slow feature matrix into dynamic slow features of long-term aging of electromagnetic compatibility of medical devices in operation.

[0055] In a specific implementation, converting the operation data into an operation data matrix can be implemented by the following manner: first, obtaining the labels of each monitoring point, and then arranging all the operation data into a matrix according to the labels of the monitoring points, that is, the operation data of the monitoring point with the label k is the kth column in the matrix, and the obtained matrix is taken as the operation data matrix.

[0056] It should be noted that the operation data matrix in the present application is a collection of real-time electromagnetic field intensity change data of medical devices classified and summarized according to monitoring points.

[0057] In a specific implementation, mapping the operation data matrix into a slow feature matrix through the mapping matrix in the degradation constraint can be implemented by the following manner: multiplying the mapping matrix in the degradation constraint with the operation data matrix, and taking the obtained result as the slow feature matrix.

[0058] It should be noted that the slow feature matrix in the present application is a collection of feature data focusing on long-term slow change rules of electromagnetic compatibility after the operation data is mapped through the degradation constraint, and the slow feature matrix is used to highlight the long-term slow change trend of electromagnetic characteristics caused by element aging.

[0059] In a specific implementation, decomposing the slow feature matrix into dynamic slow features of long-term aging of electromagnetic compatibility of medical devices in operation through the screening parameter in the degradation constraint can be implemented by the following manner: first, summing the slow feature matrix by column, and taking the sequence obtained by the summation as the dynamic slow features of long-term aging of electromagnetic compatibility of medical devices in operation.

[0060] It should be noted that the dynamic slow feature in the present application is time series data reflecting the long-term slow dynamic process of electromagnetic characteristics caused by aging of electromagnetic protection elements.

[0061] In step 105, time series mutation detection is performed on the dynamic slow features to obtain a failure time of electromagnetic compatibility failure of the medical device.

[0062] In some embodiments, time series mutation detection is performed on the dynamic slow features to obtain a failure time of electromagnetic compatibility failure of the medical device can be implemented by the following steps: determining a self-correlation sequence of the dynamic slow feature; determining a mutation point of long-term aging through the self-correlation sequence; segment fitting the dynamic slow feature according to the mutation point, and extracting a failure time of the electromagnetic compatibility saturation current capacity of the medical instrument from a result of the segment fitting.

[0063] In a specific implementation, the determining of the self-correlation sequence of the dynamic slow feature can be implemented in the following manner: the self-correlation coefficients of the long-term aging data under different time lags are calculated by using the Pearson self-correlation coefficient method in the prior art, all the self-correlation coefficients are arranged according to the size of the time lags, and the arranged sequence is taken as the self-correlation sequence of the dynamic slow feature.

[0064] In a specific implementation, the determining of the mutation point of long-term aging through the self-correlation sequence can be implemented in the following manner: all the self-correlation coefficients in the self-correlation sequence are compared with a preset correlation threshold in sequence, the time lag corresponding to the first self-correlation coefficient less than the correlation threshold is recorded as t, and then the tth data in the sequence of the dynamic slow feature is found, and the data is taken as the mutation point of long-term aging.

[0065] In a specific implementation, the segment fitting of the dynamic slow feature according to the mutation point, and the extracting of the failure time of the electromagnetic compatibility saturation current capacity of the medical instrument from the result of the segment fitting can be implemented in the following manner: the two data segments before and after the mutation point are fitted by using the least square algorithm in the prior art respectively, and the intersection point of the two fitted curves is taken as the failure time of the electromagnetic compatibility saturation current capacity of the medical instrument.

[0066] In addition, another aspect of the present application, in some embodiments, the present application provides a medical instrument failure intelligent diagnosis system, referring to Figure 4 The figure is a structure schematic diagram of a medical instrument failure intelligent diagnosis system according to some embodiments of the present application, the medical instrument failure intelligent diagnosis system 400 includes a collection module 401, a processing module 402 and an execution module 403, which are described as follows: The collection module 401 is mainly used for setting multiple monitoring points on the circuit path of the common-mode choke coil in the medical instrument, collecting electromagnetic signals generated by the current flowing through each monitoring point; The processing module 402 is mainly used for decomposing each electromagnetic signal into multiple electromagnetic components, constructing an operation state space of the medical instrument according to the trend characteristics of each electromagnetic component, and determining a spatial gradient field of the magnetic field change on the current path of the common-mode choke coil according to the correlation relationship between each monitoring point in the operation state space. It should be noted that the processing module 402 is further configured to acquire a saturation current of the common mode choke coil in the medical instrument when a magnetic core of the common mode choke coil is saturated, and determine a degradation constraint of a saturation margin of an electromagnetic compatibility protection element in the medical instrument according to a time sequence variation rate of a magnetic field intensity in the spatial gradient field and the saturation current. It should be noted that the processing module 402 is further configured to monitor running data of the medical instrument in real time, and map the running data to a dynamic slow feature of long-term aging of electromagnetic compatibility of the medical instrument in running based on the degradation constraint. The execution module 403 is mainly configured to perform time sequence mutation detection on the dynamic slow feature, and obtain a failure time of electromagnetic compatibility failure of the medical instrument.

[0067] In addition, the present application further provides a computer device, which comprises a memory and a processor, the memory stores code, and the processor is configured to acquire the code and execute the medical instrument failure intelligent diagnosis method described above.

[0068] In some embodiments, with reference to Figure 5 , the figure is a structural schematic diagram of a computer device for implementing the medical instrument failure intelligent diagnosis method according to some embodiments of the present application. The medical instrument failure intelligent diagnosis method in the above embodiments can be implemented by the computer device shown in Figure 5 , which comprises at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0069] The processor 501 can be a general central processing unit (CPU) or an application specific integrated circuit (ASIC).

[0070] The communication bus 502 can be used to transmit information between the above components.

[0071] The memory 503 can be a readonly memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM), or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable readonly memory (EEPROM), a compact disc readonly memory (CDROM) or other optical disk storage, a magneto-optical disk storage, a magnetic disk or other magnetic storage device, or any other medium capable of storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory 503 can exist independently, and is connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0072] The memory 503 is configured to store program codes for implementing the solutions of the present application, and the processor 501 is configured to execute the program codes stored in the memory 503. The program codes can include one or more software modules. The medical instrument fault intelligent diagnosis method in the above-described embodiments can be implemented by one or more software modules in the program codes of the processor 501 and the memory 503.

[0073] The communication interface 504 is configured to communicate with other devices or communication networks, such as an Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc., using any transceiver-like mechanism.

[0074] In a specific implementation, as an example, the computer device can include a plurality of processors, each of which can be a single CPU processor or a multi-CPU processor. The processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (for example, computer program instructions).

[0075] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In specific implementation, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0076] In addition, the present application also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the intelligent fault diagnosis method for medical devices described above.

[0077] In summary, in the intelligent fault diagnosis method and system for medical devices disclosed by the embodiments of the present application, first, a plurality of monitoring points are arranged on the circuit path of the common-mode choke coil in the medical device, and the electromagnetic signals generated by the current flowing through each monitoring point are collected; each electromagnetic signal is decomposed into a plurality of electromagnetic components, an operating state space of the medical device is constructed according to the trend characteristics of each electromagnetic component, and a spatial gradient field of the magnetic field change on the current path of the common-mode choke coil is determined according to the correlation between each monitoring point in the operating state space; the saturation current of the common-mode choke coil in the medical device when the magnetic core is saturated is obtained, and the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical device is determined according to the time sequence change rate of the magnetic field intensity in the spatial gradient field and the saturation current; the operating data of the medical device during operation is monitored in real time, the operating data is mapped into the dynamic slow feature of the long-term aging of the electromagnetic compatibility of the medical device during operation based on the degradation constraint; and the time sequence mutation of the dynamic slow feature is detected to obtain the fault time of the electromagnetic compatibility failure of the medical device.

[0078] As can be seen, by decomposing and screening the electromagnetic signals, the present application first eliminates the interference noise in the electromagnetic signals, and the remaining electromagnetic component signals are taken as the operating data to constitute the operating state space of the medical device, then the change of the internal electromagnetic field of the medical device during operation is analyzed (i.e. the time sequence change rate) through the correlation between each data in the operating state space, then the aging condition of the current common-mode choke coil (i.e. the degradation constraint of the saturation margin) is comprehensively evaluated by combining the time sequence change rate and the saturation current of the common-mode choke coil when the magnetic core is saturated, and the operating data of the medical device during operation is mapped into the slow feature of the long-term aging through the aging condition, the short-term change feature is eliminated, the slow aging condition of the electromagnetic compatibility protection element during long-term operation (i.e. the dynamic slow feature) is focused on, and the fault time of the electromagnetic compatibility failure of the medical device is identified through the dynamic slow feature. In summary, by using the scheme of the present application, the long-term aging trend of the electromagnetic compatibility protection element of the medical device can be captured while excluding the influence of short-term rapid change data.

[0079] While the preferred embodiments of the application have been described, additional variations and modifications can be made to these embodiments by those skilled in the art once they have the benefit of the present disclosure without departing from the spirit and scope of the application. Accordingly, it is intended that such additions and modifications be included within the scope of the application. It is the following claims, including any amendments thereto, which define the scope of the application.

[0080] Obviously, numerous modifications and variations of the present application are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims and their equivalents, the application can be practiced otherwise than as specifically described.

Claims

1. A method for intelligent diagnosis of medical instrument failure, characterized in that, The method comprises the following steps: A plurality of monitoring points are arranged on the circuit path of the common mode choke in the medical instrument, and electromagnetic signals generated by the current flowing through each monitoring point are collected; Each electromagnetic signal is decomposed into a plurality of electromagnetic components, and an operating state space of the medical instrument is constructed according to the trend characteristics of each electromagnetic component, and a spatial gradient field of the magnetic field change on the current path of the common mode choke is determined according to the correlation between each monitoring point in the operating state space; The saturation current of the common mode choke in the medical instrument when the magnetic core is saturated is obtained, and the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument is determined according to the time sequence change rate of the magnetic field intensity in the spatial gradient field and the saturation current; Real-time monitoring of the operating data of the medical instrument during operation, mapping the operating data into the dynamic slow feature of the long-term aging of the electromagnetic compatibility of the medical instrument during operation based on the degradation constraint; The time sequence mutation of the dynamic slow feature is detected to obtain the failure time of the electromagnetic compatibility failure of the medical instrument.

2. The method of claim 1, wherein, The decomposition of each electromagnetic signal into a plurality of electromagnetic components specifically comprises: An electromagnetic signal is selected as a selected signal, and all maximum points and minimum points in the selected signal are marked; All maximum points and all minimum points are interpolated and fitted to obtain the central envelope line of the selected signal; The selected signal is decomposed according to the central envelope line to obtain a plurality of electromagnetic components of the selected signal; The remaining electromagnetic signals are continuously decomposed into a plurality of electromagnetic components.

3. The method of claim 1, wherein, The construction of the operating state space of the medical instrument according to the trend characteristics of each electromagnetic component specifically comprises: The trend characteristics of each electromagnetic component are determined; A plurality of operating state components of the medical instrument are screened out according to all trend characteristics; All operating state components are combined into the operating state space of the medical instrument.

4. The method of claim 1, wherein, The determination of the spatial gradient field of the magnetic field change on the current path of the common mode choke according to the correlation between each monitoring point in the operating state space specifically comprises: The operating state space is standardized to obtain a standard operating state space; The correlation matrix between each monitoring point in the standard operating state space is determined; The correlation matrix is subjected to eigenvalue decomposition to obtain an eigenvector matrix and an eigenvalue matrix; The spatial gradient field of the magnetic field change on the current path of the common mode choke is determined according to the correlation between each monitoring point in the operating state space.

5. The method of claim 1, wherein, The determination of the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument according to the time sequence change rate of the magnetic field intensity in the spatial gradient field and the saturation current specifically comprises: The spatial gradient field is subjected to first-order derivation to obtain a time sequence change rate matrix of the magnetic field intensity; The aging characteristics of the electromagnetic compatibility protection element in the medical instrument are determined based on the time sequence change rate matrix; The degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument is determined based on the saturation current and the aging characteristics.

6. The method of claim 1, wherein, The mapping of the operating data into the dynamic slow feature of the long-term aging of the electromagnetic compatibility of the medical instrument during operation based on the degradation constraint specifically comprises: The operating data is converted into an operating data matrix; The operating data matrix is mapped into a slow feature matrix through the degradation constraint; The slow feature matrix is decomposed into a dynamic slow feature of long-term aging of electromagnetic compatibility of the medical instrument in operation.

7. The method of claim 1, wherein, The dynamic slow feature is subjected to time sequence mutation detection to obtain a failure time of electromagnetic compatibility failure of the medical instrument, specifically including: autocorrelation sequence of the dynamic slow feature is determined; a mutation point of long-term aging is determined through the autocorrelation sequence; the dynamic slow feature is segmented and fitted according to the mutation point, and then a failure time of electromagnetic compatibility saturation current failure of the medical instrument is extracted from the segmented fitting result.

8. The method of claim 1, wherein, The electromagnetic signals generated by the current flowing through each monitoring point are collected by the magnetic resistance sensor.

9. The method of claim 1, wherein, The saturation current of the common mode choke coil in the medical instrument when the magnetic core is saturated is obtained by the Hall current sensor and the digital bridge tester.

10. An intelligent diagnosis system for medical instrument failure, characterized in that, It includes: a collection module for setting multiple monitoring points on the circuit path of the common mode choke coil in the medical instrument, collecting electromagnetic signals generated by the current flowing through each monitoring point; a processing module for decomposing each electromagnetic signal into multiple electromagnetic components, constructing an operating state space of the medical instrument according to the trend characteristics of each electromagnetic component, and determining the spatial gradient field of the magnetic field change on the current path of the common mode choke coil according to the correlation between each monitoring point in the operating state space; The processing module is also used to obtain the saturation current of the common mode choke coil in the medical instrument when the magnetic core is saturated, and to determine the degradation constraint of the saturation margin of the electromagnetic compatibility protection element in the medical instrument according to the time sequence change rate of the magnetic field intensity in the spatial gradient field and the saturation current; The processing module is also used to monitor the operating data of the medical instrument in operation in real time, and to map the operating data into a dynamic slow feature of long-term aging of electromagnetic compatibility of the medical instrument in operation based on the degradation constraint; An execution module is used to perform time sequence mutation detection on the dynamic slow feature to obtain a failure time of electromagnetic compatibility failure of the medical instrument.

Images