Remote monitoring and diagnosis system for linear accelerator operation status

Abstract

The present invention relates to the technical field of linear accelerators, and in particular to a remote monitoring and diagnosis system for the operating status of a linear accelerator. In the system of the present invention, it includes: a data acquisition unit, configured to acquire the operating parameters of the linear accelerator; a data association unit, configured to screen out each type of parameters in the operating parameters, and use one type of operating parameters as cause data, and then use other types of operating parameters as effect data, and perform a first data analysis on the cause data and the effect data to determine the correlation between the cause data and the other effect data, thereby obtaining the same number of data association groups as the number of types of operating parameters; a monitoring and diagnosis unit, configured to perform cross-analysis based on each data association group, obtain cross-analysis results, and determine whether a fault occurs based on the cross-analysis results. The system of the present invention can realize intelligent monitoring and diagnosis, and adopts a more efficient and accurate method to realize monitoring and diagnosis.

Description

Technical Field

[0001] The invention belongs to the technical field of linear accelerators, and in particular relates to a remote monitoring and diagnosis system for the operating status of a linear accelerator. Background Art

[0002] A linear accelerator usually refers to an accelerator that uses a high-frequency electromagnetic field to accelerate particles, and the trajectory of the accelerated particles is a straight line. A high-frequency linear accelerator (HLA) is a device that accelerates charged particles using a high-frequency electric field distributed along a straight track.

[0003] According to the type of accelerated particles, it can be divided into electron linear accelerator, proton linear accelerator, heavy ion linear accelerator and superconducting linear accelerator.

[0004] Various linear accelerators will inevitably malfunction due to various reasons during operation. After a malfunction occurs, it is particularly important to diagnose and monitor the linear accelerator equipment. Because there are many types of linear accelerator failures and the causes are countless, how to trace the source of the failure after it occurs is a technical problem that needs to be solved urgently. This can not only improve the efficiency of the use of the linear accelerator, because when a failure occurs, if the failure can be found and solved in a short time, it will significantly improve the efficiency of the use of the linear accelerator. On the other hand, it can also reduce the loss of the linear accelerator and extend the life of the linear accelerator.

[0005] In practice, fault monitoring and diagnosis often refers to fault judgment after the fault occurs. If the fault can be predicted based on the operating status of the linear accelerator before the fault occurs, it will provide a more complete idea for solving the above problems. Summary of the invention

[0006] The main purpose of the present invention is to provide a remote monitoring and diagnosis system for the operating status of a linear accelerator. The system of the present invention can realize intelligent monitoring and diagnosis, and adopts a more efficient and accurate method to realize monitoring and diagnosis.

[0007] The technical solution of the present invention is achieved in this way:

[0008] A remote monitoring and diagnosis system for the operation status of a linear accelerator, the system comprising: a data acquisition unit, configured to acquire the operation parameters of the linear accelerator; a data association unit, configured to screen out each type of parameters in the operation parameters, respectively select one type of operation parameters as cause data, and then select other types of operation parameters as effect data, perform a first data analysis on the cause data and the effect data to determine the correlation between the cause data and the other effect data, obtain strongly correlated effect data, weakly correlated effect data and uncorrelated effect data of the cause data, thereby obtaining data association groups of the same number as the number of types of the operation parameters; a monitoring and diagnosis unit, configured to perform cross-analysis based on each data association group to obtain a cross-analysis result, and determine whether a fault occurs based on the cross-analysis result, specifically comprising: The data association groups are put into a set, the affinities of different data association groups in the set are calculated, the data association groups whose affinity differences are within a set threshold range are fused, and a fused data association group consisting of two mutually related cause data and their corresponding effect data is obtained, and then affinity calculation is performed on the fused data association groups, and the data association groups whose affinity differences are within a set range are re-fused to obtain a secondary fused data association group, and the process is executed in a loop until a final fused data association group is obtained, and the affinity differences between the final fused data association groups exceed the set threshold range, and a preset association analysis model is used to perform a second data analysis on the final fused data association group to determine whether a fault occurs, and the fault type is determined according to the result of the second data analysis.

[0009] Furthermore, the operating parameters at least include: temperature, output dose, vacuum state value, water temperature, accuracy value and voltage value; the temperature includes: temperature inside the machine and temperature outside the machine; the voltage value includes:

[0010] Low voltage part value, high voltage part value and bus voltage value.

[0011] Furthermore, the data acquisition unit includes: a sensor part and a data conversion part; the sensor part includes a plurality of sensors of different types, each sensor being configured to sense a type of operating parameter of the linear accelerator; the data conversion part is configured to perform a range-unified operation on all the operating parameters sensed by the sensor part, so as to normalize the maximum and minimum values ​​of all types of operating parameters to within a set range.

[0012] Furthermore, the data association unit performs a first data analysis on the cause data and the effect data to determine the association between the cause data and other effect data, including: substituting the cause data into the following formula to calculate the output result: Among them, P iis the effect data, {} is the rounding operation, n is the number of effect data, S(x) is the change function of the cause data, || is the determinant operation, and F is the output result; the value of the calculated output result is compared with the set multiple judgment ranges, and the correlation between the cause data and other effect data is judged according to the comparison result; S(x)=x+Δx; wherein x is the cause data, Δx is the change value of the cause data, and is a set value.

[0013] Furthermore, the determination range includes: a first range, a second range and a third range; the first range, the second range and the third range must satisfy the following relationship:

[0014] Furthermore, when the output result is within a first range, the cause data and the effect data are determined to be strongly correlated, and strongly correlated effect data of the cause data is obtained; when the output result is within a second range, the cause data and the effect data are determined to be weakly correlated, and weakly correlated effect data of the cause data is obtained; when the output result is within a third range, the cause data and the effect data are determined to be uncorrelated, and uncorrelated effect data of the cause data is obtained.

[0015] Furthermore, the monitoring and diagnosis unit puts each data association group into a set, and the method for calculating the affinity of different data association groups in the set includes: substituting two data association groups into the following formula for differential calculation to obtain the differential calculation result: D = r ((T 1 *x 1 *R 1 -T 2 *x 2 *R 2 )); where D is the result of differential calculation, is the calculated affinity, and R 1 and R 2 are all single-row matrices formed by removing the data from the data association group; x 1 and x 2 All due to data, T 2 and T 1 are all correlation coefficients; r() is the operation for finding the rank of the matrix.

[0016] Furthermore, when the data association group is a strongly associated group, the association coefficient is 3; when the data association group is a weakly associated group, the association coefficient is 1; and when the data association group is an unassociated group, the association coefficient is 0.

[0017] Furthermore, the monitoring and diagnosis unit uses a preset association analysis model to perform a second data analysis on the final fused data association group, and the method for determining whether a fault occurs includes: setting a uniform change amount for each data value in the final fused data association group to obtain a change value corresponding to each data value in the final fused data group; then calculating the normalized mean between the change values, and determining whether a fault occurs based on the size of the normalized mean.

[0018] Furthermore, the normalized mean is calculated by arithmetic mean.

[0019] The remote monitoring and diagnosis system for the operation status of a linear accelerator of the present invention has the following beneficial effects: by associating and connecting the various data in the linear accelerator, when a subsequent fault occurs, cross-analysis can be performed through the relationship of the associated connections. This association method can not only improve efficiency, because after the data is associated, there is no need to analyze and judge all the data separately in the future, and the associated data can more accurately discover the relationship between the data, thereby obtaining more accurate results and achieving more precise fault monitoring and judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A schematic diagram of the system structure of a remote monitoring and diagnosis system for the operation status of a linear accelerator provided in an embodiment of the present invention;

[0021] Figure 2 A tree structure diagram of fault categories of a remote monitoring and diagnosis system for the operation status of a linear accelerator provided by an embodiment of the present invention;

[0022] Figure 3 A schematic diagram of a curve showing the relationship between the predicted value and the telemetered value of the temperature of the remote monitoring and diagnosis system for the operation status of a linear accelerator provided in an embodiment of the present invention;

[0023] Figure 4 A schematic diagram of a curve showing the relationship between the predicted value and the predicted value of the temperature of the remote monitoring and diagnosis system for the operation status of a linear accelerator provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0024] In the following description, specific details such as specific system structures, interfaces, and technologies are provided for illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the embodiments of the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the embodiments of the present invention.

[0025] The terms "system" and "network" are often used interchangeably herein. The terms "including" and "having" and any variations thereof in the specification, claims and drawings of the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0026] The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0027] Example 1

[0028] like Figure 1 and Figure 2 As shown, a remote monitoring and diagnosis system for the operation status of a linear accelerator, the system includes: a data acquisition unit, configured to acquire the operation parameters of the linear accelerator; a data association unit, configured to screen out each type of parameters in the operation parameters, respectively use one type of operation parameters as cause data, and then use other types of operation parameters as effect data, perform a first data analysis on the cause data and the effect data to determine the correlation between the cause data and the other effect data, obtain strong-correlated effect data, weak-correlated effect data and unrelated effect data of the cause data, thereby obtaining data association groups of the same number as the number of types of the operation parameters; a monitoring and diagnosis unit, configured to perform cross-analysis based on each data association group to obtain a cross-analysis result, and determine whether a fault occurs based on the cross-analysis result, specifically including: Each data association group is placed in a set, the affinity of different data association groups in the set is calculated, and the data association groups whose affinity difference is within a set threshold range are fused to obtain a fused data association group consisting of two mutually related cause data and their corresponding effect data. Affinity calculation is then performed on the fused data association groups, and the data association groups whose affinity difference is within a set range are re-fused to obtain a secondary fused data association group. This is repeated until a final fused data association group is obtained, and the affinity difference between the final fused data association groups exceeds the set threshold range. A preset association analysis model is used to perform a second data analysis on the final fused data association group to determine whether a fault occurs, and the fault type is determined based on the result of the second data analysis.

[0029] Specifically, the relationship between cause data and effect data can be understood as one is the independent variable in a function and the other is the dependent variable in a function. In practice, when a linear accelerator fails, there are many different reasons, which may be a single factor or multiple factors. After the failure occurs, if a certain data is abnormal, it often causes other operating parameters to be abnormal, and the two are highly correlated. However, there is no such correlation between some operating parameters.

[0030] It is very necessary to associate these data, which can not only improve the efficiency of subsequent data cross-analysis, but also improve the accuracy of fault analysis and judgment.

[0031] In the present invention, after establishing the data association group obtained by the data association, the affinity of the data association group is further calculated. The affinity of the data association group reflects whether the two data association groups are homologous, that is, the two data association groups reflect the same relationship. In this way, the complexity of subsequent processing can be reduced, and the amount of data processing can be further reduced.

[0032] Continuous iterative fusion can significantly reduce the types and amounts of data association groups that ultimately need to be processed and analyzed, thereby improving efficiency.

[0033] At the same time, due to the establishment of correlation, the false alarm rate can be reduced. In reality, false alarms in fault monitoring and diagnosis often occur due to abnormalities in a single data, which reduces the accuracy.

[0034] The fault type and judgment logic correspond to a tree structure, from the root node to the leaf node of the tree structure.

[0035] Example 2

[0036] refer to Figure 3 and Figure 4 Based on the previous embodiment, the operating parameters include at least: temperature, output dosage, vacuum state value, water temperature, accuracy value and voltage value; the temperature includes: temperature inside the machine and temperature outside the machine; the voltage value includes: low voltage part value, high voltage part value and bus voltage value.

[0037] Specifically, since the accelerator is a combination of technologies from multiple fields such as microwaves, electronics, computers, high-energy physics, mechanics, fluid mechanics, and heat exchange, it has many unique performance characteristics.

[0038] Low voltage part failure. Power short circuit and open circuit, generally caused by fuse, transformer, various power circuit components burning out, power cable and control cable and their adapters breaking or poor contact, mostly caused by cable wear between the rotating frame and the fixed base.

[0039] At the same time, the operation control switch fails, the switches of the console, hand control box, treatment bed, etc. have a certain service life, and they will also fail after a long time of use. Various faults may occur at any time during use of each control circuit, all of which constitute the main faults of the low-voltage circuit.

[0040] Low voltage part failure. Power short circuit and open circuit, generally caused by fuse, transformer, various power circuit components burning out, power cable and control cable and their adapters breaking or poor contact, mostly caused by cable wear between the rotating frame and the fixed base.

[0041] At the same time, the operation control switch fails, the switches of the console, hand control box, treatment bed, etc. have a certain service life, and they will also fail after a long time of use. Various faults may occur at any time during use of each control circuit, all of which constitute the main faults of the low-voltage circuit.

[0042] High-voltage part failure. Mainly in the thyristor in the modulation cabinet, due to long-term use, the gas pressure in the tube is too low, which will increase the tube pressure drop and overheat the anode; in the thyristor grid control circuit, the aging of the components or welding problems cause the grid to not work properly;

[0043] Linear accelerator failure analysis: Pulse modulator failure and high-voltage pulse transformer failure. This type of failure is generally caused by transformer insulation aging, resulting in high-voltage breakdown.

[0044] Mechanical failure: The machine head, frame, treatment bed and target moving parts show reduced accuracy, limit failure, loosening and falling off of locking and fixing parts, etc.

[0045] Water circulation system failure. Water circulation is the key to ensuring the temperature stability of each appliance. After long-term use, the circulating water quality deteriorates, causing too much scale in the metal pipe to block the pipe; and failure of the temperature control circuit and refrigeration unit will cause the water temperature to be too high;

[0046] Common fault analysis of accelerator. Common fault analysis of accelerator. Water circulation pump leakage or water circulation pump motor failure, water circulation power weakening or disappearing, water circulation water movement joint leakage, etc. These faults will affect the normal operation and service life of the machine.

[0047] Vacuum system failure. The function of the vacuum system is to ensure that the accelerator tube, klystron and deflection magnetic field system maintain a high vacuum degree. It is an important means to ensure the service life of the above components. If there is a problem with the vacuum, the service life of the machine will be seriously shortened.

[0048] The main failure of the vacuum system is leakage, which is mostly due to damage to the waveguide window or leakage at the waveguide bend; the second is possible failure of the vacuum power supply electrical components; and the failure of the titanium ion pump system used for vacuum extraction is mainly due to leakage of the titanium pump high-voltage cable (due to aging of the insulation inside the titanium pump).

[0049] The output dose is unstable. The stability of the accelerated output dose directly affects the treatment effect, and there are many reasons that affect the stability of the output dose. Among them, damage to the attenuator between the RF driver and the klystron coaxial cable will cause the dose to become low and the microwave frequency to shift.

[0050] Analysis of the causes of linear accelerator failure. The presence of an operating frequency far from the resonance frequency will also cause the dose to become low; the modulator triggers the repetition frequency to deviate, the vacuum degree drops seriously, and the electron gun emits insufficiently, which will cause the dose rate to be unstable; the focusing current and deflection current deviation is too large, the ionization chamber system does not work properly, and the temperature rises. Faults such as these will cause fluctuations in the dose rate.

[0051] Computer software system failure. This is mainly caused by virus invasion due to operating system failure and computer instability caused by increased ambient temperature.

[0052] Computer hardware failure. Mainly due to dust inside the machine, abnormal heat exchange fan, and high temperature inside the machine, which causes the board to not work stably.

[0053] By comparing telemetry values ​​or predicted values ​​with actual values, existing technologies can generally perform a certain degree of fault analysis.

[0054] refer to Figure 3 and Figure 4 In the simulation, the temperature and bus voltage values ​​tend to change over time, and there may be deviations between the predicted and actual values.

[0055] Example 3

[0056] Based on the previous embodiment, the data acquisition unit includes: a sensor part and a data conversion part; the sensor part includes a plurality of sensors of different types, each sensor being configured to sense a type of operating parameter of the linear accelerator; the data conversion part is configured to perform a range-unified operation on all the operating parameters sensed by the sensor part, so as to normalize the maximum and minimum values ​​of all types of operating parameters to a set range.

[0057] Example 4

[0058] On the basis of the previous embodiment, the data association unit performs a first data analysis on the cause data and the effect data to determine the association between the cause data and other effect data. The method includes: substituting the cause data into the following formula to calculate the output result: Among them, P i is the effect data, {} is the rounding operation, n is the number of effect data, S(x) is the change function of the cause data, || is the determinant operation, and F is the output result; the value of the calculated output result is compared with the set multiple judgment ranges, and the correlation between the cause data and other effect data is judged according to the comparison result; S(x)=x+Δx; wherein x is the cause data, Δx is the change value of the cause data, and is a set value.

[0059] Specifically, in the correlation analysis of the present invention, the algorithm used is implemented based on the matrix composed of the effect data and the difference between the effect data and the cause data. In the process, the cause data has a change value, and the final output result is calculated by the change brought by the change value, which can significantly improve the accuracy.

[0060] Example 5

[0061] Based on the previous embodiment, the determination range includes: a first range, a second range and a third range; the first range, the second range and the third range must satisfy the following relationship:

[0062] Example 6

[0063] On the basis of the previous embodiment, when the output result is within the first range, the cause data and the effect data are determined to be strongly correlated, and strongly correlated effect data of the cause data is obtained; when the output result is within the second range, the cause data and the effect data are determined to be weakly correlated, and weakly correlated effect data of the cause data is obtained; when the output result is within the third range, the cause data and the effect data are determined to be uncorrelated, and uncorrelated effect data of the cause data is obtained.

[0064] Example 7

[0065] Based on the previous embodiment, the monitoring and diagnosis unit puts each data association group into a set, and the method for calculating the affinity of different data association groups in the set includes: substituting two data association groups into the following formula for differential calculation to obtain the differential calculation result: D = r ((T 1 *x 1 *R 1

[0066] T 2 *x 2 *R 2 )); where D is the result of differential calculation, is the calculated affinity, and R 1 and R 2 are all single-row matrices formed by removing the data from the data association group; x 1 and x 2 All due to data, T2 and T 1 Both are correlation coefficients; r() is the operation of calculating the rank of a matrix.

[0067] Example 8

[0068] On the basis of the previous embodiment, when the data association group is a strong association group, the correlation coefficient takes the value of 3; when the data association group is a weak association group, the value is 1; when the data association group is a non - association group, the value is 0.

[0069] Example 9

[0070] On the basis of the previous embodiment, the method for the monitoring and diagnosis unit to use a preset association analysis model to perform a second - time analysis on the final fusion data association group to determine whether a fault occurs includes: setting a unified change amount for each data value in the final fusion data association group to obtain the corresponding change value for each data value in the final fusion data group; then calculating the normalized mean value between the change values, and determining whether a fault occurs according to the magnitude of the normalized mean value.

[0071] Example 10

[0072] On the basis of the previous embodiment, the calculation method of the normalized mean value is obtained by arithmetic mean.

[0073] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the above - mentioned division of each functional module is used as an example. In actual applications, the above - mentioned functions can be allocated to different functional modules according to needs, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0074] In several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical functional division, and there can be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point, the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms.

[0075] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0076] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0077] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0078] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. Remote monitoring and diagnosis system for the operation status of linear accelerator, It is characterized in that The system comprises: a data acquisition unit configured to acquire the operating parameters of the linear accelerator; a data association unit configured to screen out each type of parameters in the operating parameters, respectively select one type of operating parameters as cause data, and then select other types of operating parameters as effect data, perform a first data analysis on the cause data and the effect data to determine the correlation between the cause data and the other effect data, obtain strong-correlated effect data, weak-correlated effect data and unrelated effect data of the cause data, thereby obtaining data association groups of the same number as the number of types of the operating parameters; a monitoring and diagnosis unit configured to perform cross-analysis based on each data association group to obtain a cross-analysis result, and determine whether a fault occurs based on the cross-analysis result, specifically comprising: placing each data association group into a In a set, the affinities of different data association groups in the set are calculated, and the data association groups whose affinity differences are within a set threshold range are fused to obtain a fused data association group consisting of two mutually related cause data and their corresponding effect data. Affinity calculation is then performed on the fused data association groups, and the data association groups whose affinity differences are within a set range are re-fused to obtain a secondary fused data association group. This is performed in a loop until a final fused data association group is obtained, and the affinity differences between the final fused data association groups exceed the set threshold range. A preset association analysis model is used to perform a second data analysis on the final fused data association group to determine whether a fault occurs, and the type of fault is determined based on the result of the second data analysis.

2. The system according to claim 1, It is characterized in that The operating parameters include at least: temperature, output dosage, vacuum state value, water temperature, accuracy value and voltage value; the temperature includes: temperature inside the machine and temperature outside the machine; the voltage value includes: low voltage part value, high voltage part value and bus voltage value.

3. The system according to claim 2, It is characterized in that The data acquisition unit includes: a sensor part and a data conversion part; the sensor part includes a plurality of sensors of different types, each sensor is configured to sense a type of operating parameter of the linear accelerator; the data conversion part is configured to perform a range uniform operation on all the operating parameters sensed by the sensor part, so as to normalize the maximum and minimum values ​​of all types of operating parameters to a set range.

4. The system according to claim 3, It is characterized in that The monitoring and diagnosis unit puts each data association group into a set, and the method for calculating the affinity of different data association groups in the set includes: substituting two data association groups into the following formula for differential calculation to obtain the differential calculation result: D = r ((T 1 *x 1 *R 1 -T 2 *x 2 *R 2 )); where D is the result of differential calculation, is the calculated affinity, and R 1 and R 2 are all single-row matrices formed by removing the data from the data association group; x 1 and x 2 All due to data, T 2 and T 1 are all correlation coefficients; r() is the operation for finding the rank of the matrix.

5. The system according to claim 4, It is characterized in that When the data association group is a strong association group, the association coefficient is 3; when the data association group is a weak association group, the association coefficient is 1; when the data association group is an unassociated group, the association coefficient is 0.

6. The system according to claim 5, It is characterized in that The monitoring and diagnosis unit uses a preset association analysis model to perform a second data analysis on the final fused data association group. The method for determining whether a fault occurs includes: setting a unified change amount for each data value in the final fused data association group to obtain a change value corresponding to each data value in the final fused data group; then calculating the normalized mean between the change values, and determining whether a fault occurs based on the size of the normalized mean.

7. The system according to claim 6, It is characterized in that The normalized mean value is calculated by arithmetic mean.

Images