Equipment performance degradation evaluation method and device, storage medium and computer equipment
By transforming the accelerated degradation model into a constant stress model and fusing them, a practical degradation model is generated, which solves the problem of neglecting the multi-stress coupling effect in single-factor tests and achieves more accurate power equipment life prediction and reliability assessment.
Patent Information
- Application Number
- CN202511289892.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-09-10
- Publication Date
- 2025-12-05
AI Technical Summary
Existing technologies often focus on accelerated degradation tests based on a single factor, neglecting the actual impact of multi-stress coupling on the degradation of power equipment, resulting in low accuracy in life prediction and reliability assessment.
By acquiring the accelerated degradation model of the target device under each stress parameter, transforming it into a constant stress degradation model, and then fusing it with the initial degradation model to generate the actual degradation model, the combined effects of multiple stress coupling are taken into account.
It provides a more accurate assessment of equipment performance degradation, which can more realistically reflect the comprehensive degradation behavior of equipment under real multi-stress environments, providing a precise basis for equipment maintenance and life prediction.
Smart Images
Figure CN121069065A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of data analysis, and particularly relates to a device performance degradation evaluation method and device, a storage medium and a computer device. BACKGROUND
[0002] In testing the reliability of power equipment, in order to quickly evaluate and predict the degradation process of the equipment, an accelerated degradation test is usually used, that is, a test is carried out under a stress higher than the normal use condition, so as to obtain sufficient data in a short time. Although this method can shorten the test period, due to the complexity of the actual operating environment, the test result may be quite different from the degradation process under the real working condition.
[0003] At present, the research on the degradation of power equipment mainly focuses on the accelerated degradation test of a single factor. Although this simplified method is convenient to implement, it ignores the actual influence of the multi-stress coupling on the degradation of the equipment, resulting in low precision of the life prediction and reliability evaluation of the power equipment. SUMMARY
[0004] The present application aims to at least solve one of the above technical defects, in particular, the prior art mainly focuses on the accelerated degradation test of a single factor. Although this simplified method is convenient to implement, it ignores the actual influence of the multi-stress coupling on the degradation of the equipment, resulting in low precision of the life prediction and reliability evaluation of the power equipment.
[0005] In a first aspect, the present application provides a device performance degradation evaluation method, which comprises:
[0006] When at least one stress parameter corresponding to a target device is received, an accelerated degradation model corresponding to the target device under each stress parameter is obtained;
[0007] Each accelerated degradation model is converted into a constant stress degradation model to obtain a constant stress degradation model corresponding to each accelerated degradation model;
[0008] An initial degradation model of the target device is obtained, and each constant stress degradation model is fused according to the initial degradation model to obtain an actual degradation model corresponding to the target device;
[0009] Based on the actual degradation model, the performance parameter degradation rate of the target device is evaluated to obtain a degradation evaluation result.
[0010] In one of the embodiments, the conversion of each accelerated degradation model into a constant stress degradation model to obtain a constant stress degradation model corresponding to each accelerated degradation model comprises:
[0011] Calculate the activation energy of the target device under each stress parameter;
[0012] The acceleration factor of the target device under each stress parameter is determined based on the activation energy of the target device under each stress parameter.
[0013] Based on the acceleration factor corresponding to each stress parameter, the accelerated degradation model corresponding to each stress parameter is interpolated to obtain the corresponding constant stress degradation model.
[0014] In one embodiment, determining the acceleration factor of the target device under each stress parameter based on the activation energy of the target device under each stress parameter includes:
[0015] Obtain the various status parameters of the target device under normal use;
[0016] Based on each state parameter, each stress parameter, and the activation energy of the target device under each stress parameter, the acceleration factor of the target device under each stress parameter is calculated.
[0017] In one embodiment, the step of fusing various constant stress degradation models based on the initial degradation model to obtain the actual degradation model corresponding to the target device includes:
[0018] Using the performance parameter-time curve in the initial degradation model as the target curve, the performance parameter-time curves of each constant stress degradation model are fitted. Multiple fitting parameters are obtained when the performance parameter-time curves of the degradation model composed of each constant stress degradation model correspond as closely as possible to the target curve.
[0019] The actual degradation model corresponding to the target device is generated based on the fitting parameters and the degradation model.
[0020] In one embodiment, the various constant stress degradation models include a high-temperature degradation model, a high-humidity degradation model, and a high-pressure degradation model; the performance parameter-time curves of each constant stress degradation model are fitted according to the following formula:
[0021]
[0022] In the formula, Indicates performance parameters, Indicates time, Represents the Boltzmann constant. This represents the performance degradation rate in the high-temperature degradation model. This represents the performance degradation rate in the high-voltage degradation model. This represents the performance degradation rate in the high humidity degradation model. denotes an activation energy corresponding to a temperature parameter, 、 、 denotes a fitting parameter.
[0023] In one of the embodiments, the performance parameter degradation rate of the target device is evaluated based on the actual degradation model to obtain a degradation evaluation result, which comprises:
[0024] The performance parameter degradation rate of the target device is obtained, and the predicted degradation rate of the target device at the current time is determined according to the actual degradation model;
[0025] If the difference between the performance parameter degradation rate and the predicted degradation rate is within a preset range, a degradation evaluation result that the performance parameter degradation rate of the target device matches the actual degradation model is generated;
[0026] If the difference between the performance parameter degradation rate and the predicted degradation rate is not within the preset range, a degradation evaluation result that the performance parameter degradation rate of the target device does not match the actual degradation model is generated.
[0027] In one of the embodiments, the method further comprises:
[0028] If the degradation evaluation results in the continuous N preset time windows are all that the performance parameter degradation rate of the target device matches the actual degradation model, the actual degradation model is corrected by using the performance parameter degradation rate of the target device in the N preset time windows;
[0029] If the degradation evaluation results in the continuous M preset time windows are all that the performance parameter degradation rate of the target device does not match the actual degradation model, an abnormal prompt is triggered.
[0030] In a second aspect, the present application provides a device performance degradation evaluation device, which comprises:
[0031] A parameter receiving module is configured to obtain an accelerated degradation model corresponding to each stress parameter of a target device when at least one stress parameter corresponding to the target device is received;
[0032] A model conversion module is configured to convert each accelerated degradation model into a constant stress degradation model respectively to obtain a constant stress degradation model corresponding to each accelerated degradation model;
[0033] A model fusion module is configured to obtain an initial degradation model of the target device, fuse each constant stress degradation model according to the initial degradation model, and obtain an actual degradation model corresponding to the target device;
[0034] a degradation evaluation module configured to evaluate the performance parameter degradation rate of the target device based on the actual degradation model, to obtain a degradation evaluation result.
[0035] In a third aspect, the present application provides a storage medium, wherein the storage medium stores computer readable instructions, and the computer readable instructions, when executed by one or more processors, cause the one or more processors to perform the steps of the device performance degradation evaluation method according to any one of the preceding embodiments.
[0036] In a fourth aspect, the present application provides a computer device, comprising: one or more processors, and a memory;
[0037] The memory stores computer readable instructions, and the one or more processors execute the computer readable instructions to perform the steps of the device performance degradation evaluation method according to any one of the preceding embodiments.
[0038] From the above technical solutions, the embodiments of the present application have the following advantages:
[0039] The device performance degradation evaluation method, device, storage medium and computer device provided by the present application obtain an accelerated degradation model corresponding to each stress parameter of a target device, and convert each accelerated degradation model into a constant stress degradation model, to obtain a constant stress degradation model corresponding to each accelerated degradation model. Then, an initial degradation model of the target device is obtained, and each constant stress degradation model is fused according to the initial degradation model, to obtain an actual degradation model corresponding to the target device. In this process, the accelerated degradation models under multiple single stress parameters are converted into constant stress degradation models and fused, which not only retains the independent degradation characteristics of each stress parameter, but also implicitly includes the nonlinear influence of multi-stress coupling through the fusion process based on the initial degradation model, so that the actual degradation model obtained finally can more accurately reflect the comprehensive degradation behavior of the device under a real multi-stress environment. When the degradation rate of a performance parameter of the device is evaluated based on the actual degradation model, since the actual degradation model has been calibrated by the initial data and has fused the multi-stress action mechanism, the evaluation result can more truly predict the reliability change of the device under actual complex working conditions, and provide a more accurate basis for device maintenance and life prediction. BRIEF DESCRIPTION OF DRAWINGS
[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.
[0041] Figure 1 A flowchart of a device performance degradation evaluation method provided by an embodiment of the present application is shown in FIG. 1.
[0042] Figure 2 A structural diagram of a device performance degradation evaluation apparatus provided by an embodiment of the present application is shown in FIG. 2.
[0043] Figure 3 An internal structure diagram of a computer device provided by an embodiment of the present application is shown in FIG. 3. DETAILED DESCRIPTION
[0044] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.
[0045] In one of the embodiments, the present application provides a device performance degradation evaluation method, and the following embodiments are described by taking the method applied to a server. It can be understood that the device performance degradation evaluation method can be performed by a single server, a server cluster composed of multiple servers, or a smart terminal device, and the present application does not make specific limitation on this.
[0046] As shown in FIG. 1, the present application provides a device performance degradation evaluation method, which comprises the following steps. Figure 1
[0047] S101: When at least one stress parameter corresponding to a target device is received, an accelerated degradation model of the target device under each stress parameter is obtained.
[0048] In the present step, when a user needs to perform performance degradation evaluation on a power device (i.e., a target device), the main factors affecting the performance and service life of the target device can be determined first, and then these factors are uploaded to the server as stress parameters. When the server receives at least one stress parameter corresponding to the target device, the accelerated degradation model of the target device under each stress parameter can be obtained.
[0049] In the present step, when a user needs to perform performance degradation evaluation on a power device (i.e., a target device), the main factors affecting the performance and service life of the target device can be determined first, and then these factors are uploaded to the server as stress parameters. When the server receives at least one stress parameter corresponding to the target device, the accelerated degradation model of the target device under each stress parameter can be obtained.
[0050] Specifically, in the process of obtaining the accelerated degradation model of the target device under each stress parameter, for each stress parameter, if the accelerated degradation model of the target device under the stress parameter already exists, the accelerated degradation model of the target device under the stress parameter can be directly obtained, and if the accelerated degradation model of the target device under the stress parameter does not exist, the relevant accelerated aging test can be performed, and the accelerated degradation model of the target device under the stress parameter is determined according to the test results.
[0051] S102: converting each accelerated degradation model into a constant stress degradation model to obtain a constant stress degradation model corresponding to each accelerated degradation model.
[0052] The constant stress degradation model is a model of natural degradation of device performance over time under normal use conditions, which reflects the long-term running state of the device without the influence of additional stress.
[0053] In this step, since the accelerated degradation model is detected under the condition of high stress parameters, the accelerated degradation model under each stress parameter needs to be converted into a constant stress degradation model according to the acceleration factor. The acceleration factor is used to reflect the proportional relationship between the performance degradation speed under the accelerated aging test condition and the performance degradation speed under the actual use condition. In addition, the degradation amount distribution parameter acceleration model reflecting the relationship between the degradation amount distribution parameter and the stress can be established, and the degradation amount distribution parameter value under the target stress can be extrapolated by using the model, so as to obtain the constant stress degradation model. The conversion mode of the constant stress degradation model can be selected according to the specific situation, which is not limited in the present application.
[0054] Specifically, in the case that the types of stress parameters are different, the acceleration factors of the power device can also be different, and therefore, when the acceleration factor is determined, the acceleration factors under different stress parameters can be calculated according to the activation energy under different stress parameters. The activation energy refers to the minimum energy required for the device to degrade or fail under different stress parameters.
[0055] S103: obtaining an initial degradation model of the target device, fusing each constant stress degradation model according to the initial degradation model to obtain an actual degradation model corresponding to the target device.
[0056] The initial degradation model refers to the corresponding relationship between the performance parameter and the time of the target device within the initial use period. The initial use period can be set to 10 days or longer, which is not limited in the present application. The actual degradation model refers to a model obtained by fitting and fusing each constant stress degradation model by comprehensively considering the degradation behavior of the device under the influence of various stress factors.
[0057] In this step, the performance parameters of the target device in the initial use period can be detected when the target device starts to be used, and after the performance parameter-time curve in the initial use period is obtained, the curve is taken as the initial degradation model. Then, the initial degradation model can be taken as the benchmark to fuse each constant stress degradation model, so as to ensure that the actual degradation model finally obtained can reflect the degradation behavior of the device under normal use conditions. In this way, the interaction of different stress factors can be considered comprehensively, and the actual degradation model reflecting the degradation behavior of the target device under actual use conditions can be obtained.
[0058] Specifically, the performance parameter-time curve is used to represent the case that the performance parameter changes with time, wherein the performance parameter includes but is not limited to absorption ratio, dielectric loss factor, apparent discharge amount, residual breakdown voltage, etc. In other words, the performance parameter-time curve can be composed of at least one of the absorption ratio-time curve, the dielectric loss factor-time curve, the apparent discharge amount-time curve, the residual breakdown voltage-time curve, etc.
[0059] S104: Based on the actual degradation model, the performance parameter degradation rate of the target device is evaluated to obtain a degradation evaluation result.
[0060] The performance parameter degradation rate refers to the speed of the performance parameter of the target device decreasing in a certain time, and the degradation evaluation result includes that the performance parameter degradation rate of the target device matches the actual degradation model and that the performance parameter degradation rate of the target device does not match the actual degradation model.
[0061] In this step, the performance parameter time series data (such as temperature, pressure, current, etc.) of the target device in operation can be obtained through real-time monitoring system or periodic detection, so as to determine the performance parameter degradation rate. Then, the current predicted degradation rate of the target device is determined according to the actual degradation model, and finally the degradation evaluation result is generated based on the performance parameter degradation rate and the predicted degradation rate.
[0062] In the above embodiment, the corresponding accelerated degradation model of the target device under each stress parameter is obtained, and each accelerated degradation model is converted into a constant stress degradation model respectively to obtain the constant stress degradation model corresponding to each accelerated degradation model. Then, the initial degradation model of the target device is obtained, and each constant stress degradation model is fused according to the initial degradation model to obtain the actual degradation model corresponding to the target device. In this process, by converting the accelerated degradation model under multiple single stress parameters into a constant stress degradation model and fusing, the independent degradation characteristics of each stress parameter are retained, and the nonlinear influence of the multi-stress coupling is implicitly included through the fusion process based on the initial degradation model, so that the final actual degradation model can more accurately reflect the comprehensive degradation behavior of the device under the real multi-stress environment. When evaluating the degradation rate of the performance parameter of the device based on the actual degradation model, since the actual degradation model has been calibrated by the initial data and has fused the multi-stress action mechanism, the evaluation result can more truly predict the reliability change of the device under the actual complex working condition, and provide a more accurate basis for device maintenance and life prediction.
[0063] In one of the embodiments, converting each accelerated degradation model into a constant stress degradation model respectively to obtain the constant stress degradation model corresponding to each accelerated degradation model comprises:
[0064] S1: The activation energy of the target device under each stress parameter is calculated respectively.
[0065] S2: The acceleration factor of the target device under each stress parameter is determined according to the activation energy of the target device under each stress parameter.
[0066] S3: The accelerated degradation model corresponding to each stress parameter is interpolated to obtain the corresponding constant stress degradation model based on the acceleration factor corresponding to each stress parameter.
[0067] The acceleration factor is used to reflect the proportional relationship between the performance degradation speed under the accelerated aging test condition and the performance degradation speed under the actual use condition.
[0068] In this embodiment, the activation energy of the target device under each stress parameter is calculated respectively, and the acceleration factor of the target device under each stress parameter is calculated based on the activation energy, so as to obtain the proportional relationship between the performance degradation speed under the accelerated aging test condition and the performance degradation speed under the actual use condition. Finally, according to the proportional relationship, the accelerated degradation model is converted into a constant stress degradation model by interpolating the accelerated degradation model corresponding to the stress parameter. In this way, the performance degradation of the device under normal use condition can be obtained from the accelerated degradation model. Through interpolation and model conversion, the constant stress degradation model is obtained, so as to predict the performance degradation of the device in the actual use environment.
[0069] Exemplarily, assuming that the acceleration factor is 10 years, the accelerated degradation model of 1 year time can be stretched into the constant stress degradation model of 10 years time, and at this time, the performance parameter-time curve corresponding to the accelerated degradation model can be interpolated to obtain the constant stress degradation model.
[0070] In one example, the activation energy is obtained by fitting the following curve:
[0071]
[0072] In the formula, represents the activation energy, represents the Boltzmann constant, represents the pre-exponential factor, represents the reciprocal of the stress parameter, represents the degradation rate of the corresponding performance parameter in the accelerated degradation model. The Boltzmann constant is usually taken as The pre-exponential factor is the intercept of the curve, and the physical meaning is the theoretical maximum value of the degradation rate when the stress parameter tends to infinity. / represents the slope of the curve. Specifically, the above curve is fitted with as the independent variable, as the dependent variable, and the activation energy is obtained.
[0073] In one embodiment, the acceleration factor of the target device under each stress parameter is determined according to the activation energy of the target device under each stress parameter, comprising:
[0074] S1: Obtain each state parameter of the target device under normal use.
[0075] S2: Calculate the acceleration factor of the target device under each stress parameter according to each state parameter, each stress parameter, and the activation energy of the target device under each stress parameter.
[0076] The state parameter refers to the stress parameter value of the target device under normal use conditions. The state parameter corresponds to the stress parameter one by one.
[0077] In the embodiment, the target device is periodically tested and monitored to record key performance indicators of the target device under normal operating conditions, etc. Then, the recorded data is used to analyze the performance variation of the target device and determine the state parameters of the target device under normal operating conditions. For example, for a power transformer, the temperature, humidity, and other state parameters of the power transformer under normal operating conditions can be obtained by monitoring the operating data of the power transformer under different loads and environmental conditions. When the state parameters of the target device under normal operating conditions are obtained, the acceleration factor of the target device under each stress parameter is calculated according to the state parameters, the stress parameters, and the activation energy of the target device under each stress parameter. This is used for subsequent conversion of the normal stress degradation model.
[0078] In one example, the acceleration factor of the target device under each stress parameter can be calculated according to the following expression:
[0079]
[0080] In the expression, represents the acceleration factor, represents the activation energy, represents the Boltzmann constant, represents the state parameter, represents the stress parameter, and exp represents the exponential function with the natural constant e as the base.
[0081] It can be understood that when the acceleration factor is calculated based on the above formula, the location, altitude, and climate environment of the target device are not the same, and the acceleration factor is not the same. Even the acceleration factor of the device in the same store in different seasons is not the same. Therefore, different acceleration factors can be calculated for different target devices, or acceleration factors can be calculated for the devices in the same store in different seasons.
[0082] For example, taking the temperature as the stress parameter, the temperatures of different power devices are not the same, and the temperature parameters of the power devices under actual conditions are also different. Therefore, the acceleration factors calculated for different power devices are different. It can be understood that the acceleration factors calculated for different state parameters of the same power device are also different. For example, the acceleration factors calculated for the temperature parameter, the humidity parameter, and the voltage parameter of the same power device are not the same.
[0083] In one embodiment, the initial degradation model is used to fuse each normal stress degradation model to obtain an actual degradation model corresponding to the target device, including:
[0084] S1: taking the performance parameter-time curve in the initial degradation model as a target curve, fitting the performance parameter-time curves of the various constant stress degradation models, and obtaining multiple fitting parameters when the performance parameter-time curve of the degradation model composed of the various constant stress degradation models corresponds to the target curve as much as possible;
[0085] S2: generating an actual degradation model corresponding to the target device according to the various fitting parameters and the degradation model.
[0086] In this embodiment, the performance parameter-time curve in the initial degradation model is taken as a target curve, and the performance parameter-time curves in the various constant stress degradation models are fitted, so that the performance parameter-time curves in the various constant stress degradation models are fitted to the corresponding performance parameter-time curves in the initial degradation model, for example, the performance parameter-time curves corresponding to the high-temperature degradation model, the high-humidity degradation model, and the high-pressure degradation model are fitted to the corresponding performance parameter-time curves in the initial degradation model. When the performance parameter-time curve of the degradation model composed of the various constant stress degradation models corresponds to the target curve as much as possible, the fitting parameters at this time are obtained, and then the fitting parameters are substituted into the degradation model to obtain an actual degradation model.
[0087] Specifically, by converting the acceleration degradation models under multiple single stress parameters into constant stress degradation models and fusing them, not only the independent degradation characteristics of each stress parameter are retained, but also the nonlinear effects of multi-stress coupling are implicitly included through the fusion process based on the initial degradation model, so that the actual degradation model obtained finally can more accurately reflect the comprehensive degradation behavior of the device under real multi-stress environment.
[0088] In one of the embodiments, the various constant stress degradation models include a high-temperature degradation model, a high-humidity degradation model, and a high-pressure degradation model; and the performance parameter-time curves of the various constant stress degradation models are fitted according to the following formula:
[0089]
[0090] In the formula, represents a performance parameter, represents time, represents a Boltzmann constant, represents a performance degradation rate in the high-temperature degradation model, represents a performance degradation rate in the high-pressure degradation model, represents a performance degradation rate in the high-humidity degradation model, represents an activation energy corresponding to a temperature parameter, , , represents a fitting parameter. a reference scaling factor representing a degradation rate, which determines the order of magnitude of the overall degradation rate. / a performance parameter-time curve of the actual degradation model.
[0091] In this embodiment, taking the performance parameter-time curve in the initial degradation model as the target curve, the performance parameter-time curve in each constant stress degradation model is fitted, i.e., the performance parameter-time curve in the final actual degradation model is made to be as close as possible to the target curve. Specifically, the initial degradation model is derived from short-term monitoring data (such as 10-day performance parameter changes) of the device in a real running environment, and reflects the actual degradation trend under the action of multiple stress couplings. By fitting, the performance parameter-time curve in the final actual degradation model is made to be as close as possible to the target curve. / as close as possible to the target curve. / Specifically, the initial degradation model is derived from short-term monitoring data (such as 10-day performance parameter changes) of the device in a real running environment, and reflects the actual degradation trend under the action of multiple stress couplings. By fitting, the performance parameter-time curve in the final actual degradation model is made to be as close as possible to the target curve. / As close as possible, each constant stress degradation model can be dynamically calibrated to the degradation behavior under the real complex environment. Moreover, the fitting process of the parameters n and m adaptively captures the nonlinear interaction (such as synergistic acceleration or inhibition) between the temperature (T), the voltage (V), and the humidity (RH). This data-driven parameter optimization indirectly reflects the actual degradation mechanism of the multiple stress couplings without explicitly modeling the complex coupling relationship.
[0092] In one of the embodiments, the performance parameter degradation rate of the target device is evaluated based on the actual degradation model, and a degradation evaluation result is obtained, including:
[0093] S1: Obtain the performance parameter degradation rate of the target device, and determine the predicted degradation rate of the target device at the current time according to the actual degradation model.
[0094] S2: If the difference between the performance parameter degradation rate and the predicted degradation rate is within a preset range, a degradation evaluation result that the performance parameter degradation rate of the target device matches the actual degradation model is generated.
[0095] S3: If the difference between the performance parameter degradation rate and the predicted degradation rate is not within the preset range, a degradation evaluation result that the performance parameter degradation rate of the target device does not match the actual degradation model is generated.
[0096] The preset range is an empirical value, which can be set and adjusted according to the actual situation. The present application does not make specific limitations thereto.
[0097] In the embodiment, the target device is determined to have a current predicted degradation rate according to the actual degradation model, and then the actual performance parameter degradation rate of the target device is obtained. The two are calculated by difference, and the corresponding degradation evaluation result is generated by judging whether the difference is within a preset range.
[0098] In one of the embodiments, the device performance degradation evaluation method further comprises:
[0099] S1: If the degradation evaluation results in the continuous N preset time windows are all that the performance parameter degradation rate of the target device matches the actual degradation model, the actual degradation model is corrected using the performance parameter degradation rate of the target device in the N preset time windows.
[0100] S2: If the degradation evaluation results in the continuous M preset time windows are all that the performance parameter degradation rate of the target device does not match the actual degradation model, an abnormal prompt is triggered.
[0101] Wherein, N and M are positive integers greater than 1. N and M can be set to 3, and the preset time window can be set to 24 hours, which is not limited here.
[0102] In the embodiment, on the one hand, when the performance parameter degradation rate of the power device matches the actual degradation model in the continuous N preset time windows, it indicates that the performance parameter degradation rate is within the normal range. However, since the actual degradation model is fitted, there may be a certain deviation from the actually detected performance parameter degradation rate. At this time, the actual degradation model can be corrected according to the performance parameter degradation rate, the error of the actual degradation model is reduced, and the accuracy of the actual degradation model is improved. On the other hand, since the actual degradation model is obtained by fitting, there may be a certain deviation between the performance parameter degradation rate and the predicted degradation rate in the actual degradation model. Therefore, when determining whether to output an abnormal prompt, the performance parameter degradation rate and the predicted degradation rate are not required to be completely consistent, but a certain error is allowed. Only when the difference between the performance parameter degradation rate and the predicted degradation rate in the continuous M preset time windows is not within the preset range, the abnormal prompt is output.
[0103] Exemplarily, the correction period is n time windows, for example, one month can be taken as the correction period. If the performance parameter degradation rate in one month matches the actual degradation model, the performance parameter degradation rate in one month is used to determine the performance parameter-time curve as the degradation model in one month, and then the actual degradation model is re-fitted according to the degradation model in one month to correct the parameters in the actual degradation model, thereby reducing the problem of inaccurate actual degradation model caused by changes in temperature, humidity, etc.
[0104] In addition, the actual degradation model can be corrected according to the performance parameter degradation rate in the latest N time windows when the change rate of the temperature and the humidity is greater than the preset change rate. For example, the actual degradation model can be corrected to reduce the inaccuracy of the actual degradation model caused by the change of the temperature and the humidity due to the weather change when the temperature and the humidity change greatly within 24 hours.
[0105] It should be understood that, although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow, these steps are not necessarily executed in sequence according to the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and these steps can be executed in other sequences. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence of these steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or steps or stages in other steps.
[0106] The device performance degradation evaluation device provided by the embodiments of the present application is described below. The device performance degradation evaluation device described below can be correspondingly referred to the device performance degradation evaluation method described above.
[0107] As shown in Figure 2 The present application provides a device performance degradation evaluation device 200, which comprises:
[0108] The parameter receiving module 201 is configured to obtain an acceleration degradation model corresponding to each stress parameter of the target device when at least one stress parameter corresponding to the target device is received.
[0109] The model conversion module 202 is configured to convert each acceleration degradation model into a constant stress degradation model respectively to obtain a constant stress degradation model corresponding to each acceleration degradation model.
[0110] The model fusion module 203 is configured to obtain an initial degradation model of the target device, fuse each constant stress degradation model according to the initial degradation model, and obtain an actual degradation model corresponding to the target device.
[0111] The degradation evaluation module 204 is configured to evaluate the performance parameter degradation rate of the target device based on the actual degradation model to obtain a degradation evaluation result.
[0112] In the above embodiment, the corresponding accelerated degradation model of the target device under each stress parameter is obtained, and each accelerated degradation model is converted into a constant stress degradation model respectively to obtain a constant stress degradation model corresponding to each accelerated degradation model. Then, the initial degradation model of the target device is obtained, and each constant stress degradation model is fused according to the initial degradation model to obtain the actual degradation model corresponding to the target device. In this process, by converting the accelerated degradation models under multiple single stress parameters into constant stress degradation models and fusing them, the independent degradation characteristics of each stress parameter are retained, and the nonlinear influence of the multi-stress coupling effect is implicitly included through the fusion process based on the initial degradation model, so that the final actual degradation model can more accurately reflect the comprehensive degradation behavior of the device under the real multi-stress environment. When evaluating the degradation rate of the performance parameter of the device based on the actual degradation model, since the actual degradation model has been calibrated by the initial data and has fused the multi-stress action mechanism, the evaluation result can more truly predict the reliability change of the device under the actual complex working condition, and provide a more accurate basis for device maintenance and life prediction.
[0113] In one of the embodiments, the model conversion module comprises:
[0114] The calculation sub-module is configured to calculate the activation energy of the target device under each stress parameter respectively;
[0115] The factor determination sub-module is configured to determine the acceleration factor of the target device under each stress parameter according to the activation energy of the target device under each stress parameter;
[0116] The model conversion sub-module is configured to perform interpolation processing on the accelerated degradation model corresponding to each stress parameter based on the acceleration factor corresponding to each stress parameter to obtain the corresponding constant stress degradation model.
[0117] In one of the embodiments, the factor determination sub-module comprises:
[0118] The parameter acquisition unit is configured to acquire each state parameter of the target device under normal use;
[0119] The calculation unit is configured to calculate the acceleration factor of the target device under each stress parameter according to each state parameter, each stress parameter, and the activation energy of the target device under each stress parameter.
[0120] In one of the embodiments, the model fusion module comprises:
[0121] a parameter determination sub-module configured to fit performance parameter-time curves of the constant stress degradation models to a performance parameter-time curve in the initial degradation model as a target curve, and obtain a plurality of fitting parameters when the performance parameter-time curve of the degradation model composed of the constant stress degradation models corresponds to the target curve as much as possible;
[0122] a model fusion sub-module configured to generate an actual degradation model corresponding to the target device according to the fitting parameters and the degradation model.
[0123] In one of the embodiments, the parameter adjustment sub-module comprises:
[0124]
[0125] wherein, represents a performance parameter, represents time, represents a Boltzmann constant, represents a performance degradation rate in a high-temperature degradation model, represents a performance degradation rate in a high-voltage degradation model, represents a performance degradation rate in a high-humidity degradation model, represents an activation energy corresponding to a temperature parameter, 、 、 represents a fitting parameter.
[0126] In one of the embodiments, the degradation evaluation module comprises:
[0127] a rate acquisition sub-module configured to acquire a performance parameter degradation rate of the target device, and determine a predicted degradation rate of the target device at a current time according to the actual degradation model;
[0128] a first generation sub-module configured to generate a degradation evaluation result that the performance parameter degradation rate of the target device matches the actual degradation model, if a difference between the performance parameter degradation rate and the predicted degradation rate is within a preset range;
[0129] a second generation sub-module configured to generate a degradation evaluation result that the performance parameter degradation rate of the target device does not match the actual degradation model, if the difference between the performance parameter degradation rate and the predicted degradation rate is not within the preset range.
[0130] In one of the embodiments, the device performance degradation evaluation apparatus further comprises:
[0131] a model correction module configured to correct the actual degradation model by using the performance parameter degradation rates of the target device in N preset time windows, if the degradation evaluation results in the N preset time windows are all that the performance parameter degradation rate of the target device matches the actual degradation model.
[0132] an abnormality prompting module, configured to trigger an abnormality prompt if the degradation evaluation results in the continuous M preset time windows are all inconsistent with the actual degradation model of the performance parameter degradation rate of the target device.
[0133] The division of each module in the device performance degradation evaluation apparatus is merely for illustration, and in other embodiments, the device performance degradation evaluation apparatus can be divided into different modules as needed to complete all or part of the functions of the device performance degradation evaluation apparatus. Each module in the device performance degradation evaluation apparatus can be implemented in whole or in part by software, hardware, and combinations thereof. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.
[0134] In one embodiment, the present application further provides a storage medium having computer readable instructions stored therein, and the computer readable instructions, when executed by one or more processors, cause the one or more processors to perform the steps of the device performance degradation evaluation method according to any one of the above embodiments.
[0135] In one embodiment, the present application further provides a computer device having computer readable instructions stored therein, and the computer readable instructions, when executed by one or more processors, cause the one or more processors to perform the steps of the device performance degradation evaluation method according to any one of the above embodiments.
[0136] As shown in Figure 3 , Figure 3 Fig. 3 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application. The computer device 300 can be provided as a server. As shown in Figure 3 , the computer device 300 includes a processing assembly 302, which further includes one or more processors, and a memory resource represented by a memory 301, for storing instructions executable by the processing assembly 302, such as an application program. The application program stored in the memory 301 can include one or more than one module each corresponding to a set of instructions. In addition, the processing assembly 302 is configured to execute the instructions to perform the device performance degradation evaluation method according to any one of the above embodiments.
[0137] The computer device 300 can further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 can operate based on an operating system stored in the memory 301, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.
[0138] Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. A specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0139] Finally, it should be noted that, in this document, the terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of another identical element in the process, method, article or device including the element. In this document, the singular forms "a", "an" and "the" can also include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / contain" or "have" and the like specify the presence of stated features, integers, steps, operations, components, parts or combinations thereof, but do not exclude the presence or addition of one or more other features, integers, steps, operations, components, parts or combinations thereof, and the term "and / or" used in the specification includes any and all combinations of the related listed items.
[0140] The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same and similar parts are referred to each other.
[0141] The foregoing description of the disclosed embodiments enables a person skilled in the art to make or use the application. Modifications of these embodiments will occur to persons of skill in the art, and that the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method of evaluating degradation of performance of a device, characterized by, The method comprises: When at least one stress parameter corresponding to the target device is received, an accelerated degradation model corresponding to the target device under each stress parameter is obtained; Each accelerated degradation model is converted into a constant stress degradation model to obtain a constant stress degradation model corresponding to each accelerated degradation model; An initial degradation model of the target device is obtained, and each constant stress degradation model is fused according to the initial degradation model to obtain an actual degradation model corresponding to the target device; The performance parameter degradation rate of the target device is evaluated based on the actual degradation model to obtain a degradation evaluation result.
2. The method of claim 1, wherein, The conversion of each accelerated degradation model into a constant stress degradation model to obtain a constant stress degradation model corresponding to each accelerated degradation model comprises: The activation energy of the target device under each stress parameter is calculated respectively; The acceleration factor of the target device under each stress parameter is determined according to the activation energy of the target device under each stress parameter; Each accelerated degradation model corresponding to each stress parameter is subjected to interpolation processing based on the acceleration factor corresponding to each stress parameter to obtain a corresponding constant stress degradation model.
3. The method of claim 2, wherein, The determination of the acceleration factor of the target device under each stress parameter according to the activation energy of the target device under each stress parameter comprises: The state parameters of the target device under normal use are obtained; The acceleration factor of the target device under each stress parameter is calculated according to the state parameters, the stress parameters, and the activation energy of the target device under each stress parameter.
4. The method of claim 1, wherein The fusion of each constant stress degradation model according to the initial degradation model to obtain an actual degradation model corresponding to the target device comprises: The performance parameter-time curve in the initial degradation model is taken as a target curve, and the performance parameter-time curves of each constant stress degradation model are fitted, a plurality of fitting parameters are obtained when the performance parameter-time curve of the degradation model composed of each constant stress degradation model corresponds to the target curve as much as possible in the fitting, and the actual degradation model corresponding to the target device is generated according to each fitting parameter and the degradation model. Each constant stress degradation model comprises a high-temperature degradation model, a high-humidity degradation model, and a high-pressure degradation model; 5. The method of claim 4, wherein The performance parameter-time curve of each constant stress degradation model is fitted according to the following formula: The evaluation of the performance parameter degradation rate of the target device based on the actual degradation model to obtain a degradation evaluation result comprises: wherein denotes a performance parameter, denotes time, denotes the Boltzmann constant, denotes a performance degradation rate in the high temperature degradation model, denotes a performance degradation rate in the high voltage degradation model, denotes a performance degradation rate in the high humidity degradation model, denotes an activation energy corresponding to the temperature parameter, , , denotes a fitting parameter.
6. The method of claim 1, wherein The performance parameter degradation rate of the target device is obtained, and the predicted degradation rate of the target device at the current time is determined according to the actual degradation model; If the difference between the performance parameter degradation rate and the predicted degradation rate is within a preset range, a degradation evaluation result that the performance parameter degradation rate of the target device matches the actual degradation model is generated; If the difference between the performance parameter degradation rate and the predicted degradation rate is not within the preset range, a degradation evaluation result that the performance parameter degradation rate of the target device does not match the actual degradation model is generated. The method further comprises:
7. The method of claim 1 to 6, wherein If the degradation evaluation results in the continuous N preset time windows are all that the performance parameter degradation rate of the target device matches the actual degradation model, the actual degradation model is corrected by using the performance parameter degradation rate of the target device in the N preset time windows. If the degradation evaluation results in the continuous M preset time windows are all that the performance parameter degradation rate of the target device does not match the actual degradation model, an abnormal prompt is triggered.
8. An apparatus performance degradation evaluation device, characterized by comprising: The device comprises: a parameter receiving module, configured to acquire an accelerated degradation model corresponding to each stress parameter of the target device when at least one stress parameter corresponding to the target device is received; a model conversion module, configured to convert each accelerated degradation model into a constant stress degradation model respectively to obtain a constant stress degradation model corresponding to each accelerated degradation model; a model fusion module, configured to acquire an initial degradation model of the target device, and fuse each constant stress degradation model according to the initial degradation model to obtain an actual degradation model corresponding to the target device; a degradation evaluation module, configured to evaluate the performance parameter degradation rate of the target device based on the actual degradation model to obtain a degradation evaluation result.
9. A storage medium characterized by: The storage medium has computer readable instructions stored therein, and the computer readable instructions are executed by one or more processors to make the one or more processors execute the steps of the device performance degradation evaluation method in any one of claims 1 to 7.
10. A computer device, comprising: comprise: one or more processors, and a memory; the memory has computer readable instructions stored therein, and the computer readable instructions are executed by the one or more processors to execute the steps of the device performance degradation evaluation method in any one of claims 1 to 7.