Method for determining stability of device state signal and device therefor
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CNNC FUJIAN FUQING NUCLEAR POWER
- Filing Date
- 2023-06-02
- Publication Date
- 2026-05-12
AI Technical Summary
In equipment fault diagnosis, it is difficult to maintain consistency when manually judging the trend of equipment status signals, especially when the signals are unstable, and a large amount of manpower is required.
By employing a fuzzy evaluation model combined with state signal curves, the stability of the equipment is automatically analyzed. By acquiring the characteristic parameter deviation parameters of the equipment, the target membership function value is calculated using a Gaussian membership function to determine the stability level of the equipment.
It automates equipment stability analysis, saves manpower, maintains consistency in judgment criteria, reduces analysis errors, and provides early fault warning and diagnosis basis.
Smart Images
Figure CN116878887B_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of measurement technology, specifically relating to a method and apparatus for determining the stability of a device status signal. Background Technology
[0002] When diagnosing faults in equipment such as steam turbines, generators, pumps, or fans, on-site inspections require analyzing the trends of status signals such as vibration (which can be represented by changes in velocity, displacement, or acceleration), temperature, pressure, or flow rate. Currently, most methods involve using computers to plot status signal trend curves, with manual judgment of the trends based on these curves. When there are many status signals, it becomes difficult to judge each one manually, requiring a significant investment of manpower for trend analysis and judgment. Especially when the status signal trends are unstable, it is difficult to maintain consistency in the judgment criteria among different personnel. Summary of the Invention
[0003] In view of this, this application provides a method and apparatus for determining the stability of a device status signal. By using a fuzzy evaluation model to automatically analyze the stability of the device under test, manpower is saved and the determination criteria for stability analysis are kept consistent.
[0004] The first aspect of this application provides a method for determining the stability of a device status signal. This method includes: acquiring the status signal curve of the device under test (DUT) within a preset time period; and performing stability analysis on the DUT using a fuzzy evaluation model in conjunction with the status signal curve to determine the target stable state level of the DUT within the preset time period. The status signal curve is configured to reflect the trend of characteristic parameters of the DUT changing with operating time. The sub-factors of the fuzzy evaluation model include deviation parameters corresponding to the characteristic parameters. The evaluation set of the fuzzy evaluation model includes multiple preset stable state levels, which are divided according to multiple preset membership function values of the fuzzy evaluation model.
[0005] In the above scheme, by using a fuzzy evaluation model and combining it with state signal curves, stability analysis of the device under test is performed, thereby automatically determining the target stable state level of the device under test within a preset time period. This avoids the situation where there are too many state signals, resulting in too much workload for manual judgment or the need to invest a large number of personnel in analysis and judgment, thus saving manpower and laying the foundation for deep learning of signals.
[0006] In one specific embodiment of this application, the above-mentioned use of a fuzzy evaluation model and combined with a state signal curve to perform stability analysis on the device under test in order to determine the target stability level of the device under test within a preset time period includes: calculating the target membership function value corresponding to the state signal curve using a fuzzy evaluation model; and determining the target stability level of the device under test within a preset time period based on the target membership function value.
[0007] In one specific embodiment of this application, before calculating the target membership function value corresponding to the state signal curve using the fuzzy evaluation model, the determination method further includes: determining whether the rotational speed of the device under test is stable within a preset time period. The calculation of the target membership function value corresponding to the state signal curve using the fuzzy evaluation model includes: if the rotational speed of the device under test is stable within the preset time period, then calculating the target membership function value corresponding to the state signal curve using the fuzzy evaluation model.
[0008] In one specific embodiment of this application, the above-mentioned calculation of the target membership function value corresponding to the state signal curve using a fuzzy evaluation model if the rotational speed of the device under test is stable within a preset time period includes: if the rotational speed of the device under test is stable within a preset time period, dividing the state signal curve into multiple data analysis packages; calculating the deviation parameters corresponding to the feature parameters in the multiple data analysis packages; and determining the target membership function value corresponding to the state signal curve using a fuzzy evaluation model based on the deviation parameters corresponding to the feature parameters in the multiple data analysis packages.
[0009] In one specific embodiment of this application, the above-mentioned determination of the target membership function value corresponding to the state signal curve using a fuzzy evaluation model based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages includes: selecting the maximum deviation parameter from the deviation parameters corresponding to the feature parameters in multiple data analysis packages as a sub-factor of the fuzzy evaluation model; and calculating the target membership function value corresponding to the state signal curve using the fuzzy evaluation model based on the maximum deviation parameter.
[0010] In one specific embodiment of this application, the above-mentioned determination of the target membership function value corresponding to the state signal curve based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages using a fuzzy evaluation model includes: calculating multiple membership function values based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages using a fuzzy evaluation model; and determining the maximum membership function value among the multiple membership function values as the target membership function value corresponding to the state signal curve.
[0011] In one specific embodiment of this application, the membership function in the fuzzy evaluation model is a Gaussian membership function S. The Gaussian membership function S is... c and k are constants, x is a sub-factor of the fuzzy evaluation model, and y is the membership function value corresponding to the sub-factor.
[0012] A second aspect of this application provides a device for determining the stability of a device status signal. This device includes an acquisition module and an analysis module. The acquisition module acquires the status signal curve of the device under test (DUT) over a preset time period. The status signal curve is configured to reflect the trend of characteristic parameters of the DUT changing with operating time. The analysis module uses a fuzzy evaluation model and the status signal curve to perform stability analysis on the DUT to determine the target stable state level of the DUT over the preset time period. The sub-factors of the fuzzy evaluation model include deviation parameters corresponding to the characteristic parameters. The evaluation set of the fuzzy evaluation model includes multiple preset stable state levels, which are divided according to multiple preset membership function values of the fuzzy evaluation model.
[0013] A third aspect of this application provides a computer-readable storage medium storing executable instructions for a computer. When these executable instructions are executed by a processor, they implement a method for determining the stability of device status signals according to the first aspect of this application.
[0014] A fourth aspect of this application provides an electronic device including a processor and a memory. The processor is used to execute a method for determining the stability of device status signals according to the first aspect of this application. The memory is used to store executable instructions of the processor. Attached Figure Description
[0015] Figure 1 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to an embodiment of this application.
[0016] Figure 2 The figure shown is a schematic diagram of a Gaussian membership function provided in an embodiment of this application.
[0017] Figure 3 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application.
[0018] Figure 4 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application.
[0019] Figure 5 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application.
[0020] Figure 6 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application.
[0021] Figure 7 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to yet another embodiment of this application.
[0022] Figure 8 The figure shown is a schematic diagram of a state signal curve provided in an embodiment of this application.
[0023] Figure 9 The diagram shown is a schematic diagram of a state signal curve provided in another embodiment of this application.
[0024] Figure 10 The diagram shown is a block diagram of a device for determining the stability of a device status signal according to an embodiment of this application.
[0025] Figure 11 The diagram shown is a block diagram of an electronic device provided in one embodiment of this application. Detailed Implementation
[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0027] Figure 1 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to an embodiment of this application. The execution entity of this method for determining the stability of the device status signal can be a local or remote controller, processor, or server, etc., and this application does not specifically limit it. The following example uses a processor as the execution entity. Figure 1 As shown, the method for determining the stability of the device status signal includes the following steps.
[0028] S110: Acquire the status signal curve of the device under test (DUT) within a preset time period. The status signal curve is configured to reflect the trend of the characteristic parameters of the DUT changing with the running time.
[0029] In some embodiments, the processor can acquire the characteristic parameters of the device under test (DUT) at the current moment in real time, and then advance a certain period of time from the current moment to obtain the state signal curve within a preset time period. In other embodiments, the processor can also acquire the state signal curve of the DUT within a preset time period at preset intervals.
[0030] It should be noted that the device under test (DUT) can be any device that requires signal stability analysis. For example, the DUT can be a steam turbine, generator, pump, or fan.
[0031] Characteristic parameters can be any parameter that can change over time and reflect the stability of the state signal. For example, characteristic parameters can be velocity, displacement, acceleration, shaft vibration, bearing vibration, temperature, pressure, or flow rate.
[0032] The preset duration can be set according to actual needs. In some embodiments, the preset duration can also be referred to as the default value. For example, the preset duration can be 30 minutes, 1 hour, or 4 hours, etc.
[0033] S120: Using a fuzzy evaluation model and combining it with state signal curves, stability analysis is performed on the device under test (DUT) to determine the target stable state level of the DUT within a preset time period. The sub-factors of the fuzzy evaluation model include deviation parameters corresponding to feature parameters within the preset time period. The evaluation set of the fuzzy evaluation model includes multiple preset stable state levels, which are divided according to multiple preset membership function values of the fuzzy evaluation model.
[0034] Specifically, the processor can obtain the sub-factors required by the fuzzy evaluation model from the state signal curve, and substitute these sub-factors into the fuzzy evaluation model to determine the target stable state level of the device under test within a preset time period.
[0035] It should be noted that the sub-factors of the fuzzy evaluation model can be one or more. Multiple preset stability state levels in the evaluation set of the fuzzy evaluation model can be set according to actual needs. For example, multiple preset stability state levels can be very stable, stable, relatively stable, and unstable, respectively. Alternatively, multiple preset stability state levels can be stability level 1, stability level 2, instability level 1, instability level 2, and instability level 3, respectively. Correspondingly, multiple preset membership function values can also be set according to actual needs for different feature parameters. Taking shaft vibration as an example, assuming multiple preset membership function values are -1, 0.5, and 0.8, the preset stability state level corresponding to a preset membership function value of -1 can be the excellent value H1, the preset stability state level corresponding to a preset membership function value of 0.5 can be the high vibration alarm value H2, and the preset stability state level corresponding to a preset membership function value of 0.8 can be the high vibration alarm value H3. That is, multiple preset stability state levels can be the excellent value H1, the high vibration alarm value H2, and the high vibration alarm value H3, respectively.
[0036] According to the technical solution provided in this application, by utilizing a fuzzy evaluation model and combining it with state signal curves, stability analysis is performed on the device under test (DUT). This automatically determines the target stable state level of the DUT within a preset time period, avoiding the excessive workload of manual judgment or the need for a large number of personnel to conduct analysis and judgment when there are too many state signals, thus saving manpower and laying the foundation for deep learning of signals. Furthermore, since multiple preset stable state levels are divided according to multiple preset membership function values of the fuzzy evaluation model, the judgment criteria of the fuzzy evaluation model remain consistent, thus avoiding the large analysis errors caused by the difficulty in maintaining consistency in the judgment criteria of different personnel during manual judgment.
[0037] The membership function in the fuzzy evaluation model can be determined using methods such as fuzzy statistics, expert experience, or assignment. The membership function only needs to reflect the degree of membership of the sub-factors to the preset stable state level in the evaluation set. For example, the membership function in the fuzzy evaluation model can be a subparabolic distribution function, a normal distribution function, or a Cauchy distribution function. Based on this, the embodiments of this application do not impose specific limitations on the membership function.
[0038] In fuzzy evaluation models, membership functions are categorized into three types: sparsely subsized, intermediate, and sparsely subsized. Careful research reveals that, when performing stability analysis on the equipment under test, sparsely subsized membership functions better reflect the degree of membership of sub-factors to the preset stability level in the evaluation set, thus reducing errors in the final evaluation results. Sparsely subsized membership functions can be further classified into various distributions, such as ascending semi-rectangular distribution, ascending semi-normal distribution, ascending semi-Cauchy distribution, ascending semi-trapezoidal distribution, or ascending ridge distribution.
[0039] In some embodiments, the membership function in the fuzzy evaluation model is a Gaussian membership function S. Therefore, using a Gaussian membership function S as the membership function can result in a very small error in the final evaluation result.
[0040] It should be noted that the Gaussian membership function S can be an ascending semi-normal distribution or an ascending semi-Cauchy distribution, etc.
[0041] In at least one embodiment of this application, the Gaussian membership function S is as follows (1). c and k are constants, x is a sub-factor of the fuzzy evaluation model, and y is the membership function value corresponding to the sub-factor. Thus, because the membership degree of each preset stable state level in the evaluation set corresponding to the sub-factor in this embodiment of the application matches the Gaussian membership function S to a high degree, the application of the Gaussian membership function S will result in a very small error in the final evaluation result.
[0042]
[0043] Figure 2The image shown is a schematic diagram of a Gaussian membership function provided in an embodiment of this application. Figure 2 As shown, the curve is a monotonically increasing function of the independent variable, that is, a membership function with a relatively large size. Figure 2 The horizontal axis represents the deviation parameter, which is the maximum characteristic parameter X within a preset time period. max With the minimum characteristic parameter X min The difference is represented by the ordinate, which is the membership function value corresponding to the deviation parameter. The c value is equivalent to the boundary value between the presence and absence of the deviation parameter, and the k value reflects the steepness of the curve; the larger the k value, the steeper the membership function curve. Figure 2 The value of c can be 70, and the value of k can be 0.128.
[0044] It should be noted that the values of c and k can be set based on expert experience, relevant national and corporate standards. The values of c and k can be specifically set for different characteristic parameters.
[0045] Figure 3 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application. Figure 3 The embodiment shown is Figure 1 A specific embodiment of the illustrated example. For example... Figure 3 As shown, with Figure 1 The difference in the illustrated embodiment is that S121 and S122 are Figure 1 A specific implementation of S120 in the illustrated embodiment.
[0046] S110: Acquire the status signal curve of the device under test (DUT) within a preset time period. The status signal curve is configured to reflect the trend of the characteristic parameters of the DUT changing with the running time.
[0047] S121: Calculate the target membership function value corresponding to the state signal curve using a fuzzy evaluation model.
[0048] In some embodiments, the processor can obtain each feature parameter within a preset time period from the state signal curve, obtain the deviation parameter corresponding to the feature parameter within the preset time period by calculating the difference between the maximum and minimum feature parameters within the preset time period, and substitute the deviation parameter into the membership function of the fuzzy evaluation model to calculate the target membership function value.
[0049] It should be noted that the deviation parameter can also be the ratio of the difference between the maximum and minimum characteristic parameters to the minimum characteristic parameter.
[0050] S122: Determine the target stability level of the device under test within a preset time period based on the target membership function value.
[0051] Specifically, the processor can compare the target membership function value with the preset membership function value to determine the preset stable state level (i.e., the target stable state level) corresponding to the target membership function value.
[0052] According to the technical solution provided in the embodiments of this application, the target membership function value corresponding to the state signal curve is calculated by using a fuzzy evaluation model, and the target stability level of the device under test within a preset time period is determined based on the target membership function value. Thus, the stability of the device under test can be automatically calculated and analyzed by combining the state signal curve and according to the criteria in the fuzzy evaluation model. The target stability level of the device under test within a preset time period can be determined directly without manual operation, further saving manpower.
[0053] In some embodiments, after step S121, the processor can directly output the target membership function value corresponding to the state signal curve. The target stable state level of the device under test within a preset time period is determined manually based on the target membership function value. Since multiple preset stable state levels are divided according to multiple preset membership function values of the fuzzy evaluation model, the target stable state level of the device under test within a preset time period is also uniquely determined when the target membership function value is determined. This can avoid large analysis errors caused by the difficulty in maintaining consistency in the judgment criteria of different personnel.
[0054] Careful study revealed that, using vibration data as a characteristic parameter for analysis, the stability characteristics of the device under test (DUT) can be calculated. Under normal conditions, the vibration should be relatively stable. If instability or fluctuations occur, it indicates a potential equipment malfunction. This characteristic can be used for early fault warning, fault analysis, and diagnosis. For example, it can be used to diagnose friction and thermal deformation, serving as a crucial basis for fault diagnosis. Vibration stability analysis requires examining data over a period of time, which users can preset as needed. Changes in rotational speed will cause changes in vibration. Therefore, when performing stability analysis on the DUT, the rotational speed typically needs to remain stable within the preset time period.
[0055] Figure 4 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application. Figure 4 The embodiment shown is Figure 3 A specific embodiment of the illustrated example. For example... Figure 4 As shown, with Figure 3 The difference in the illustrated embodiment is that, before S121, the determination method further includes step S115. S1211 is... Figure 3 A specific implementation of S121 in the illustrated embodiment.
[0056] S110: Acquire the status signal curve of the device under test (DUT) within a preset time period. The status signal curve is configured to reflect the trend of the characteristic parameters of the DUT changing with the running time.
[0057] S115: Determine whether the rotational speed of the device under test is stable within a preset time period.
[0058] In some embodiments, the processor can acquire the rotational speed data of the device under test (DUT) at the current moment in real time, advance a certain period of time from the current moment to obtain the rotational speed data of the DUT within a preset time period, and then determine whether the rotational speed is stable within the preset time period based on the rotational speed data. In other embodiments, the processor can acquire the rotational speed data of the DUT within a preset time period at preset intervals, and then determine whether the rotational speed is stable within the preset time period based on the rotational speed data.
[0059] For example, the criterion for determining whether the rotational speed of the device under test is stable can be whether the fluctuation range of the rotational speed is within a preset amplitude range, such as ±50 r / min. If the fluctuation range of the rotational speed is within the preset amplitude range for a preset duration, then it can be determined that the rotational speed of the device under test is stable within the preset duration.
[0060] If the preset duration is 30 minutes, and the duration of the stable speed range is less than 30 minutes, then the stable speed range is considered too short to be analyzed and the characteristic value corresponding to the stable speed range cannot be extracted. In this case, the stability analysis of the device under test can be terminated.
[0061] S1211: If the rotational speed of the device under test is stable within a preset time period, the target membership function value corresponding to the state signal curve is calculated using a fuzzy evaluation model.
[0062] In some embodiments, if the rotational speed of the device under test is unstable within a preset time period, the stability analysis of the device under test is terminated.
[0063] S122: Determine the target stability level of the device under test within a preset time period based on the target membership function value.
[0064] According to the technical solution provided in the embodiments of this application, by comprehensively considering the stability of rotational speed and the stability of state signals when performing stability analysis on the device under test, the judgment result is more accurate and effective.
[0065] Figure 5 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application. Figure 5 The embodiment shown is Figure 4 A specific embodiment of the illustrated example. For example... Figure 5 As shown, with Figure 4The difference in the illustrated embodiment is that steps S1211a to S1211c are Figure 4 A specific implementation of step S1211 in the illustrated embodiment.
[0066] S110: Acquire the status signal curve of the device under test (DUT) within a preset time period. The status signal curve is configured to reflect the trend of the characteristic parameters of the DUT changing with the running time.
[0067] S115: Determine whether the rotational speed of the device under test is stable within a preset time period.
[0068] S1211a: If the rotational speed of the device under test is stable within a preset time period, the status signal curve will be divided into multiple data analysis packages.
[0069] It should be noted that multiple data analysis packages can be obtained by dividing a preset duration into multiple time periods, which can be done according to the actual situation of the state signal curve.
[0070] S1211b: Calculate the deviation parameters corresponding to the feature parameters in multiple data analysis packages.
[0071] Specifically, the processor can calculate the deviation parameters corresponding to the feature parameters in each of the multiple data analysis packages.
[0072] For example, the deviation parameter x corresponding to the feature parameter can be the maximum feature parameter X within the time period corresponding to the data analysis package. max With the minimum characteristic parameter X min The difference, i.e., x = X max -X min .
[0073] S1211c: Based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages, the target membership function value corresponding to the state signal curve is determined using a fuzzy evaluation model.
[0074] According to the technical solution provided in the embodiments of this application, by dividing the state signal curve within a preset time period into multiple data analysis packages, obtaining the deviation parameters corresponding to the multiple data analysis packages respectively, and then determining the target membership function value based on the deviation parameters corresponding to the multiple data analysis packages, compared with directly setting the state signal curve within a preset time period as a single data analysis package, this avoids the large change in characteristic parameters when the preset time period is too long, which would cause a large error in the stability analysis results. This is beneficial to improving the accuracy of the target membership function value determination, thereby improving the accuracy of the stability analysis results.
[0075] Figure 6 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to another embodiment of this application. Figure 6 The embodiment shown is Figure 5 A specific embodiment of the illustrated example. For example... Figure 6 As shown, with Figure 5 The difference in the illustrated embodiment is that steps S1211c-1 and S1211c-2 are Figure 5 A specific implementation of step S1211c in the illustrated embodiment.
[0076] S1211c-1: Select the parameter with the largest deviation from the deviation parameters corresponding to the feature parameters in multiple data analysis packages as the sub-factor of the fuzzy evaluation model.
[0077] S1211c-2: The target membership function value corresponding to the state signal curve is calculated based on the maximum deviation parameter using a fuzzy evaluation model.
[0078] Specifically, the processor can substitute the maximum deviation parameter among the deviation parameters corresponding to the feature parameters in multiple data analysis packages into the fuzzy evaluation model to calculate the target membership function value (taking shaft vibration as an example, it is equivalent to taking the maximum value of the fluctuation amplitude change in all data analysis packages as the evaluation basis) in order to realize the stability analysis of the device under test.
[0079] Figure 7 The diagram shown is a flowchart illustrating a method for determining the stability of a device status signal according to yet another embodiment of this application. Figure 7 The embodiment shown is Figure 5 A specific embodiment of the illustrated example. For example... Figure 7 As shown, with Figure 5 The difference in the illustrated embodiment is that steps S1211c-3 and S1211c-4 are Figure 5 A specific implementation of step S1211c in the illustrated embodiment.
[0080] S1211c-3: Using a fuzzy evaluation model, multiple membership function values are calculated based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages.
[0081] S1211c-4: Determine the maximum membership function value among multiple membership function values as the target membership function value corresponding to the state signal curve.
[0082] Specifically, the processor can substitute the deviation parameters corresponding to the feature parameters in multiple data analysis packages into the fuzzy evaluation model to calculate multiple membership function values, and determine the largest membership function value among the multiple membership function values as the target membership function value, so as to realize the stability analysis of the device under test.
[0083] Figure 8 The diagram shown is a schematic representation of a state signal curve provided in an embodiment of this application. For example, as... Figure 8As shown, the device under test is a steam turbine, the x-axis represents the running time, and the y-axis represents the shaft vibration. Assuming c = 0 and k = 0.033, the Gaussian membership function S adaptively becomes the following formula (2). This state signal curve can reflect the vibration characteristics of the device under test, and the signal fluctuation alarm value can be set according to the vibration characteristics of the device under test.
[0084]
[0085] refer to Figure 8 Assuming a preset duration of 30,000 seconds, and the rotational speed remains stable between 0 and 30,000 seconds, the state signal curve can be divided into three data analysis packages: 0-10,000 seconds (package 1), 10,000-20,000 seconds (package 2), and 20,000-30,000 seconds (package 3, corresponding to...). Figure 5 Step S1211a) in the illustrated embodiment. The vibration signal trend shows that the shaft vibration continuously increases within 0s-10000s, and then the vibration falls back. The fluctuation amplitude corresponding to data analysis package 1 is x = 112μm - 22μm = 90μm (corresponding to...). Figure 5 In step S1211b) of the illustrated embodiment, substituting x into the above formula (2) yields that the membership function value (also known as the unstable eigenvalue) corresponding to data analysis package 1 is 0.90. Within 10000s-20000s, the fluctuation amplitude x corresponding to data analysis package 2 is 66μm-46μm=20μm (corresponding to...). Figure 5 In step S1211b) of the illustrated embodiment, substituting x into the above formula (2) yields a membership function value of -0.03 for data analysis package 2. Within 20000s-30000s, the fluctuation amplitude x corresponding to data analysis package 3 is 82μm-65μm=17μm. Substituting x into the above formula (2) yields a membership function value of -0.14 for data analysis package 3. To obtain the target membership function value within 0s to 30000s, the largest fluctuation amplitude of 90μm can be selected from fluctuation amplitudes of 90μm, 20μm, and 17μm as x value, and the membership function value corresponding to the largest fluctuation amplitude of 90μm, 0.90, can be confirmed as the target membership function value (corresponding to...). Figure 6 In the illustrated embodiment, steps S1211c-1 and S1211c-2 can also be used to select the largest membership function value (0.90) from the membership function values of 0.90, -0.03, and -0.14 as the target membership function value (corresponding to...). Figure 7 Steps S1211c-3 and S1211c-4 in the illustrated embodiment.
[0086] Figure 9 The diagram shown is a schematic representation of a state signal curve provided in another embodiment of this application. For example, as... Figure 9As shown, the device under test is the main pump in the nuclear power unit, the x-axis represents the running time, and the y-axis represents the shaft vibration. Assuming c = 10 and k = 0.045, the Gaussian membership function S adaptively becomes the following formula (3).
[0087]
[0088] refer to Figure 9 The vibration fluctuates between 0 min and 1500 min, but the amplitude is small, with a fluctuation range of approximately 12 μm (x) and a membership function value of -0.83. After 1500 min, the vibration fluctuates significantly, with a fluctuation range of approximately 100 μm (x) and a membership function value of 0.96 between 1500 min and 3000 min.
[0089] Figure 10 The diagram shows a block diagram of a device for determining the stability of a device status signal according to an embodiment of this application. The device 10 includes an acquisition module 11 and an analysis module 12. The acquisition module 11 acquires the status signal curve of the device under test (DUT) within a preset time period. The status signal curve is configured to reflect the trend of the characteristic parameters of the DUT changing with operating time. The analysis module 12 uses a fuzzy evaluation model and combines it with the status signal curve to perform stability analysis on the DUT to determine the target stable state level of the DUT within the preset time period. The sub-factors of the fuzzy evaluation model include deviation parameters corresponding to the characteristic parameters, and the evaluation set of the fuzzy evaluation model includes multiple preset stable state levels, which are divided according to multiple preset membership function values of the fuzzy evaluation model.
[0090] In at least one embodiment of this application, the analysis module 12 is further configured to calculate the target membership function value corresponding to the state signal curve using a fuzzy evaluation model; and determine the target stability state level of the device under test within a preset time period based on the target membership function value.
[0091] In at least one embodiment of this application, the analysis module 12 is further used to determine whether the rotation speed of the device under test is stable within a preset time period; if the rotation speed of the device under test is stable within the preset time period, the target membership function value corresponding to the state signal curve is calculated using a fuzzy evaluation model.
[0092] In at least one embodiment of this application, the analysis module 12 is further configured to divide the state signal curve into multiple data analysis packages if the rotational speed of the device under test is stable within a preset time period; calculate the deviation parameters corresponding to the feature parameters in the multiple data analysis packages; and determine the target membership function value corresponding to the state signal curve using a fuzzy evaluation model based on the deviation parameters corresponding to the feature parameters in the multiple data analysis packages.
[0093] In at least one embodiment of this application, the analysis module 12 is further configured to select the maximum deviation parameter as a sub-factor of the fuzzy evaluation model from the deviation parameters corresponding to the feature parameters in multiple data analysis packages; and use the fuzzy evaluation model to calculate the target membership function value corresponding to the state signal curve based on the maximum deviation parameter.
[0094] In at least one embodiment of this application, the analysis module 12 is further configured to use a fuzzy evaluation model to calculate multiple membership function values based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages; and to determine the maximum membership function value among the multiple membership function values as the target membership function value corresponding to the state signal curve.
[0095] In at least one embodiment of this application, the membership function in the fuzzy evaluation model is a Gaussian membership function S. The Gaussian membership function S is... c and k are constants, x is a sub-factor of the fuzzy evaluation model, and y is the membership function value corresponding to the sub-factor.
[0096] It should be noted that since the determination device 10 includes all the technical features of the determination method provided in the embodiments of this application, the technical effects of the technical features in the determination device 10 can be referred to the description of the determination method in the embodiments of this application, and will not be repeated here.
[0097] Figure 11 The diagram shown is a block diagram of an electronic device provided in one embodiment of this application.
[0098] Reference Figure 11 The electronic device 20 includes a processor 21 and a memory 22. The memory 22 stores instructions executable by the processor 21, such as application programs. There can be one or more processors 21. The application programs stored in the memory 22 can include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 21 is configured to execute instructions to perform the aforementioned method for determining the stability of device status signals.
[0099] Electronic device 20 may also include a power supply component configured for power management, a wired or wireless network interface configured to connect electronic device 20 to a network, and an input / output (I / O) interface. Electronic device 20 can operate on an operating system, such as Windows Server, stored in memory 22. TM Mac OSX TM Unix TM Linux TM FreeBSD TM Or similar.
[0100] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the aforementioned electronic device 20, enables the electronic device 20 to execute a method for determining the stability of a device state signal. This determination method is executed by a proxy program and includes: acquiring the state signal curve of the device under test (DUT) over a preset time period; and performing a stability analysis on the DUT using a fuzzy evaluation model in conjunction with the state signal curve to determine a target stable state level of the DUT over the preset time period. The state signal curve is configured to reflect the trend of characteristic parameters of the DUT changing with operating time. The sub-factors of the fuzzy evaluation model include deviation parameters corresponding to the characteristic parameters. The evaluation set of the fuzzy evaluation model includes multiple preset stable state levels, which are divided according to multiple preset membership function values of the fuzzy evaluation model.
[0101] Those skilled in the art will recognize that the algorithmic steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0102] In the several embodiments provided in this application, it should be understood that the disclosed determination method and determination device can be implemented in other ways. For example, the determination device embodiments described above are merely illustrative. For example, the division of modules is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.
[0103] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program verification codes, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0104] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the determination device and electronic device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0105] It should be noted that the combination of the technical features in the embodiments of this application is not limited to the combination methods described in the embodiments of this application or the combination methods described in specific embodiments. All technical features described in this application can be freely combined or combined in any way, unless they contradict each other.
[0106] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications or equivalent substitutions made within the spirit and principles of this application should be included within the protection scope of this application.
Claims
1. A method for determining the stability of a device status signal, characterized in that, Acquire the status signal curve of the device under test within a preset time period, wherein the status signal curve is configured to reflect the trend of the characteristic parameters of the device under test changing with the running time; By using a fuzzy evaluation model and combining it with the state signal curve, a stability analysis is performed on the device under test to determine the target stable state level of the device under test within the preset time period. The sub-factors of the fuzzy evaluation model include the deviation parameters corresponding to the feature parameters. The evaluation set of the fuzzy evaluation model includes multiple different preset stable state levels, which are divided according to multiple preset membership function values of the fuzzy evaluation model.
2. The determination method according to claim 1, characterized in that, The step of using a fuzzy evaluation model and combining it with the state signal curve to perform stability analysis on the device under test (DUT) to determine the target stability level of the DUT within the preset time period includes: The target membership function value corresponding to the state signal curve is calculated using a fuzzy evaluation model. The target stability level of the device under test within the preset time period is determined based on the target membership function value.
3. The determination method according to claim 2, characterized in that, Before calculating the target membership function value corresponding to the state signal curve using the fuzzy evaluation model, the determination method further includes: Determine whether the rotational speed of the device under test is stable within the preset time period; The step of calculating the target membership function value corresponding to the state signal curve using a fuzzy evaluation model includes: If the rotational speed of the device under test is stable within the preset time period, the target membership function value corresponding to the state signal curve is calculated using a fuzzy evaluation model.
4. The determination method according to claim 3, characterized in that, If the rotational speed of the device under test remains stable within the preset time period, the calculation of the target membership function value corresponding to the state signal curve using the fuzzy evaluation model includes: If the rotational speed of the device under test is stable within the preset time period, the state signal curve is divided into multiple data analysis packages. Calculate the deviation parameters corresponding to the feature parameters in the multiple data analysis packages; Based on the deviation parameters corresponding to the feature parameters in the multiple data analysis packages, the target membership function value corresponding to the state signal curve is determined using a fuzzy evaluation model.
5. The determination method according to claim 4, characterized in that, The step of determining the target membership function value corresponding to the state signal curve using a fuzzy evaluation model based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages includes: The largest deviation parameter is selected as a sub-factor of the fuzzy evaluation model from the deviation parameters corresponding to the feature parameters in the multiple data analysis packages. The target membership function value corresponding to the state signal curve is calculated using a fuzzy evaluation model based on the maximum deviation parameter.
6. The determination method according to claim 4, characterized in that, The step of determining the target membership function value corresponding to the state signal curve using a fuzzy evaluation model based on the deviation parameters corresponding to the feature parameters in multiple data analysis packages includes: Multiple membership function values are calculated using a fuzzy evaluation model based on the deviation parameters corresponding to the feature parameters in the multiple data analysis packages. The largest membership function value among the multiple membership function values is determined as the target membership function value corresponding to the state signal curve.
7. The determination method according to any one of claims 1 to 6, characterized in that, The membership function in the fuzzy evaluation model is a Gaussian membership function S, and the Gaussian membership function S is... Where c and k are constants, x is a sub-factor of the fuzzy evaluation model, and y is the membership function value corresponding to the sub-factor.
8. A device for determining the stability of a device status signal, characterized in that, include: The acquisition module is used to acquire the status signal curve of the device under test within a preset time period, wherein the status signal curve is configured to reflect the trend of the characteristic parameters of the device under test changing with the running time. The analysis module is used to perform stability analysis on the device under test using a fuzzy evaluation model and in conjunction with the state signal curve, so as to determine the target stable state level of the device under test within the preset time period. The sub-factors of the fuzzy evaluation model include the deviation parameters corresponding to the feature parameters, and the evaluation set of the fuzzy evaluation model includes multiple different preset stable state levels. The multiple preset stable state levels are divided according to multiple preset membership function values of the fuzzy evaluation model.
9. A computer-readable storage medium having executable instructions stored thereon, characterized in that, When the executable instructions are executed by the processor, they implement a method for determining the stability of the device status signal as described in any one of claims 1 to 7.
10. An electronic device, characterized in that, include: A processor for executing a method for determining the stability of a device status signal as described in any one of claims 1 to 7; as well as Memory for storing the executable instructions of the processor.