Generator insulation life evaluation method based on sliding window incremental damage

Abstract

The invention discloses a generator insulation life evaluation method based on sliding window incremental damage, and the method comprises the steps: obtaining original monitoring data, including voltage, current and temperature, of a stator winding of a hydro-generator; preprocessing the original monitoring data to obtain standardized data; a sliding window with a fixed time length is adopted, characteristic quantities used for representing the insulation state are extracted from the standardized data, and the characteristic quantities at least comprise voltage characteristics and temperature characteristics; based on the characteristic quantity, an insulation damage increment in each sliding window is calculated through an electric stress and thermal stress coupled increment damage model; cumulatively calculating the insulation damage increment of each sliding window to obtain a cumulative damage value; and evaluating the health state of stator insulation according to the accumulated damage value, and predicting the residual life. According to the method, additional sensors are not needed, deployment is easy and convenient, the method is adaptive to low-computing-power edge equipment, the insulation degradation speed can be accurately reflected, and a high-practicability solution is provided for online insulation monitoring and service life management of the water-turbine generator set.

Description

Technical Field

[0001] This application relates to the field of stator insulation condition monitoring and life assessment technology for hydro-generators, and more specifically, to a generator insulation life assessment method based on sliding window incremental damage. Background Technology

[0002] The stator insulation of a hydro-generator is a core component that ensures the long-term safe operation of the unit. Its performance degradation is mainly caused by the combined effects of electrical and thermal stress. Statistical data shows that about 70% of hydro-generator shutdown failures are directly related to stator insulation aging. Therefore, accurate assessment of insulation life is crucial to reducing the risk of failure.

[0003] Existing insulation life assessment technologies have three major drawbacks: (1) Lag in static feature extraction: Traditional methods directly calculate static statistics from voltage, current and temperature data, which cannot capture the dynamic trend of insulation degradation. For example, when the operating conditions change suddenly, the static statistics need several hours to reflect the parameter changes, which leads to the delay of degradation signals; while when the operating conditions are stable, it is difficult to identify the slow decay of insulation performance.

[0004] (2) Limitations of single-factor models: Most existing models only consider a single stress and ignore the coupling effect of electro-thermal stress. In actual operation, voltage increase will aggravate partial discharge, thereby accelerating the thermal aging rate; temperature increase will reduce the dielectric strength of insulation, forming an "electro-thermal vicious cycle".

[0005] (3) Inefficiency of offline testing: Traditional methods rely on periodic offline tests, which cannot achieve continuous monitoring. Insulation degradation often has "abrupt nodes" (such as a sudden increase in partial discharge), which are difficult to capture by offline testing, making it easy to miss the best maintenance time. In addition, the power plant needs to be shut down during the testing process, which affects the power generation efficiency of the power plant.

[0006] Therefore, there is an urgent need for an online insulation life assessment method that is simple to implement in engineering and has an accurate model, in order to address the pain points of existing technologies. Summary of the Invention

[0007] To address the aforementioned issues, this application provides a generator insulation life assessment method based on sliding window incremental damage, aiming to solve problems such as static feature lag, inaccurate single-factor modeling, inefficient offline detection, and difficulty in deploying dynamic windows in the prior art.

[0008] The first aspect of this invention provides a method for evaluating generator insulation life based on sliding window incremental damage, comprising: Obtain raw monitoring data of the stator windings of the hydro-generator, including voltage, current, and temperature; The raw monitoring data is preprocessed to obtain standardized data; Using a sliding window of fixed duration, feature quantities for characterizing the insulation state are extracted from the standardized data, and the feature quantities include at least voltage and temperature features. Based on the aforementioned characteristic quantities, the incremental insulation damage within each sliding window is calculated using an incremental damage model that couples electrical stress and thermal stress; the cumulative insulation damage increment of each sliding window is calculated to obtain the cumulative damage value. The health status of the stator insulation is assessed based on the cumulative damage value, and its remaining lifetime is predicted based on the health status.

[0009] In one optional implementation, the use of a sliding window of fixed duration specifically refers to: The window duration is set to 30 seconds, and the sliding step size is equal to the window duration. Each window contains 30 data points obtained at a sampling frequency of 1Hz.

[0010] In one optional implementation, the preprocessing of the raw monitoring data includes noise reduction, normalization, time synchronization, and outlier identification.

[0011] In one alternative implementation, the voltage characteristics include the average voltage and peak voltage within a sliding window; the temperature characteristics include the average temperature and rate of temperature rise within a sliding window.

[0012] In one optional implementation, the incremental damage model based on the coupling of electrical and thermal stress calculates the insulation damage increment within each sliding window, including: Calculate the electrical stress damage increment based on the average voltage within the sliding window:

[0013] in, This represents the increment of electrical stress damage. The electrical aging coefficient, The average voltage within the window. Where is the rated voltage of the motor, and n is the electrical aging index; Calculate the thermal stress damage increment based on the average temperature within the sliding window:

[0014] in, Let A be the thermal stress damage increment, and A be the pre-exponential factor. Activation energy for insulating materials, The gas constant is The average temperature within the window; Calculate the total damage increment within the sliding window based on the electrical stress damage increment and the thermal stress damage increment:

[0015] in, This represents the increment of insulation damage.

[0016] In one optional implementation, the cumulative damage value is obtained by accumulating the insulation damage increment of each sliding window, as shown in the following formula:

[0017] Where k is the total number of sliding windows.

[0018] In one optional implementation, assessing the health status of the stator insulation based on the cumulative damage value specifically involves: If the cumulative damage value D ≤ 0.2, it is assessed as a normal state; If 0.2 < cumulative damage value D ≤ 0.4, it is assessed as a mild degradation state; If 0.4 < cumulative damage value D ≤ 0.7, it is assessed as a moderate degradation state; If 0.7 < cumulative damage value D < 1.0, it is assessed as a severely degraded state; If the cumulative damage value D ≥ 1.0, it is assessed as insulation failure.

[0019] A second aspect of this invention provides a generator insulation life assessment system based on sliding window incremental damage, the system comprising: The data acquisition module is used to acquire raw monitoring data of the stator winding of the hydro-generator, including voltage, current and temperature; The preprocessing module is used to preprocess the raw monitoring data to obtain standardized data; The feature extraction module is used to extract feature quantities for characterizing the insulation state from the standardized data using a sliding window of fixed duration. The feature quantities include at least voltage features and temperature features. The damage calculation module is used to calculate the insulation damage increment within each sliding window based on the aforementioned characteristic quantity using an incremental damage model that couples electrical and thermal stress; to accumulate the insulation damage increments of each sliding window to obtain a cumulative damage value; and The monitoring and evaluation module is used to assess the health status of the stator insulation based on the cumulative damage value, and predict its remaining life based on the health status.

[0020] A third aspect of the present invention provides an electronic device, characterized in that it includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements a generator insulation life assessment method based on sliding window incremental damage.

[0021] A fourth aspect of the present invention provides a computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, a method for evaluating the insulation life of a generator based on sliding window incremental damage is provided.

[0022] This application has at least the following advantages or beneficial effects: (1) Low engineering deployment cost: This invention reuses the existing monitoring platform of the power station, without the need to install additional sensors, which greatly saves hardware investment; the fixed parameter sliding window design simplifies the algorithm logic, does not require complex computing power support, can be directly adapted to low computing power edge devices, reduces deployment, debugging and operation and maintenance costs, and has a low threshold for engineering implementation.

[0023] (2) High assessment accuracy: The electric-thermal dual-factor coupled incremental damage model is constructed to accurately characterize the "vicious cycle" mechanism of the interaction between electric and thermal stress, overcome the limitations of the traditional single-factor model, and the assessment results are more in line with the actual physical process of insulation degradation, significantly improving the accuracy and reliability of the assessment.

[0024] (3) Strong real-time performance: The feature parameters and damage values ​​are updated every 30 seconds by using a 30-second fixed-duration sliding window, which can quickly respond to insulation degradation signals, effectively solve the lag problem of traditional static feature extraction, realize online continuous monitoring, and facilitate the capture of degradation “mutation nodes”.

[0025] (4) Highly practical: The insulation status is divided into four levels and the remaining life is quantified, providing an intuitive basis for operation and maintenance decisions. Targeted maintenance strategies can be formulated, which can avoid the waste of resources due to over-maintenance and prevent the risk of failure caused by untimely maintenance, thereby improving the scientific and economical operation and maintenance of the power plant. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of a generator insulation life assessment method based on sliding window incremental damage proposed in an embodiment of this application; Figure 2 This is a structural diagram of a generator insulation life assessment system based on sliding window incremental damage proposed in an embodiment of this application; Figure 3 This is a schematic diagram of a fixed-parameter sliding window proposed in an embodiment of this application; Figure 4 This is a cumulative damage trend diagram based on an embodiment of the present application, showing the electro-thermal dual-factor damage. Figure 5 This is a data flow diagram of the evaluation system module proposed in one embodiment of this application; Figure 6 This is a schematic diagram of an electronic device according to this application. Detailed Implementation

[0028] 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, 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.

[0029] Please refer to Figure 1 , Figure 1 This is a flowchart of a generator insulation life assessment method based on sliding window incremental damage, proposed in one embodiment of this application. Figure 1 As shown, a generator insulation life assessment method based on sliding window incremental damage includes: S100: Acquire raw monitoring data of the stator windings of the hydro generator, including voltage, current and temperature; In this embodiment, raw monitoring data such as voltage, current, and temperature of the stator winding are collected from the existing online monitoring platform of the hydropower station via the OPC UA protocol, without the need for additional sensor installation.

[0030] S200: The raw monitoring data is preprocessed to obtain standardized data; Specifically, the preprocessing of the raw monitoring data includes noise reduction, normalization, time synchronization, and outlier identification.

[0031] In this embodiment, S210: The noise reduction process uses a sliding median filtering method to smooth data fluctuations through a fixed window (the window size is 5 sampling points) to eliminate non-operating noise; S220: The normalization process uses the min-max method to map the data to the [0,1] interval; S230: The time synchronization processing uses linear interpolation to unify all monitored quantities to a 1Hz time axis; S240: Outlier identification and processing is based on the 3σ criterion, which removes extreme data that exceed the data "mean ± 3 times the standard deviation" and replaces them with adjacent valid data through interpolation to ensure data continuity.

[0032] S300: Using a fixed-duration sliding window, extract characteristic quantities for characterizing the insulation state from the standardized data, the characteristic quantities including at least voltage and temperature characteristics; Specifically, such as Figure 3 As shown, the fixed-duration sliding window is specifically set as follows: the window duration is set to 30 seconds, the sliding step is equal to the window duration, and each window contains 30 data points obtained at a sampling frequency of 1Hz.

[0033] In this embodiment, the window duration is set to 30 seconds, covering 30 1Hz sampling points. A fixed-parameter sliding window is used to extract features characterizing insulation degradation, such as mean voltage, peak voltage, mean temperature, temperature rise rate, mean current, and variance. Among these features, the current feature is used to determine the stability of the operating condition and does not directly participate in the damage model.

[0034] S400: Based on the aforementioned characteristic quantity, the insulation damage increment within each sliding window is calculated using an incremental damage model that couples electrical stress and thermal stress; the insulation damage increment of each sliding window is accumulated to obtain the cumulative damage value. Specifically, the incremental damage model based on the coupling of electrical and thermal stress calculates the insulation damage increment within each sliding window, including: S410: Calculate the electrical stress damage increment based on the average voltage within the sliding window:

[0035] in, This represents the increment of electrical stress damage. The electrical aging coefficient, The average voltage within the window. Where is the rated voltage of the motor, and n is the electrical aging index; S420: Calculate the thermal stress damage increment based on the average temperature within the sliding window:

[0036] in, Let A be the thermal stress damage increment, and A be the pre-exponential factor. Activation energy for insulating materials, The gas constant is The average temperature within the window; S430: Calculate the total damage increment within the sliding window based on the electrical stress damage increment and the thermal stress damage increment:

[0037] in, This represents the increment of insulation damage. In this embodiment, based on the physical coupling mechanism of electrical stress and thermal stress mutually aggravating insulation aging, a simplified engineering superposition method is adopted to integrate the damage contributions of the two factors, which not only reflects the synergistic effect of the two factors, but also adapts to the deployment requirements of low computing power.

[0038] S440: The cumulative damage increment of each sliding window is calculated to obtain the cumulative damage value, and the specific formula is as follows:

[0039] Where k is the total number of sliding windows.

[0040] S500: Assess the health status of the stator insulation based on the cumulative damage value, and predict its remaining lifetime based on the health status.

[0041] Specifically, assessing the health status of the stator insulation based on the cumulative damage value includes: If the cumulative damage value D ≤ 0.2, it is assessed as a normal state; If 0.2 < cumulative damage value D ≤ 0.4, it is assessed as a mild degradation state; If 0.4 < cumulative damage value D ≤ 0.7, it is assessed as a moderate degradation state; If 0.7 < cumulative damage value D < 1.0, it is assessed as a severely degraded state; If the cumulative damage value D ≥ 1.0, it is assessed as insulation failure.

[0042] In this embodiment, the health status is divided based on cumulative damage, the remaining lifespan is calculated, and the results are displayed through a web interface (supporting power plant operation and maintenance personnel to view). An audible and visual alarm is triggered when the condition is "severely degraded".

[0043] Please refer to Figure 2 , Figure 2 This is a structural diagram of a generator insulation life assessment system based on sliding window incremental damage, as proposed in an embodiment of this application. Figure 2 As shown in the figure, this disclosure also provides a generator insulation life assessment system based on sliding window incremental damage. The system includes: a data acquisition module 201, a preprocessing module 202, a feature extraction module 203, a damage calculation module 204, and a monitoring and assessment module 205; wherein, Data acquisition module 201 is used to acquire raw monitoring data of the stator winding of the hydro generator, including voltage, current and temperature; Preprocessing module 202 is used to preprocess the raw monitoring data to obtain standardized data; Feature extraction module 203 is used to extract feature quantities for characterizing insulation state from the standardized data using a sliding window of fixed duration, wherein the feature quantities include at least voltage features and temperature features; Damage calculation module 204 is used to calculate the insulation damage increment within each sliding window based on the characteristic quantity using an incremental damage model coupling electrical stress and thermal stress; to accumulate the insulation damage increment of each sliding window to obtain a cumulative damage value; and The monitoring and evaluation module 205 is used to evaluate the health status of the stator insulation based on the cumulative damage value and predict its remaining life based on the health status.

[0044] In this embodiment, as Figure 5 As shown, the connection relationship and data flow of the five modules are illustrated.

[0045] This disclosure also provides an electronic device, please refer to... Figure 6 , Figure 6 This is a schematic diagram of an electronic device illustrated in an embodiment of this disclosure. For example... Figure 6 As shown, the electronic device 100 includes a memory 110 and a processor 120. The memory 110 and the processor 120 are connected via a bus for communication. The memory 110 stores a computer program that can run on the processor 120 to implement the steps in the generator insulation life assessment method based on sliding window incremental damage disclosed in this embodiment.

[0046] The disclosed embodiments also provide a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by a processor of a computer device, enables the computer device to perform steps in the generator insulation life assessment method based on sliding window incremental damage as described in the embodiments of this disclosure.

[0047] Example This embodiment uses a generator-transformer unit of a large hydropower station as the application object. This unit has been operating stably for 5 years. The stator insulation uses epoxy resin-mica composite insulation (design life 30 years), and the insulation is currently in a normal aging state, with an initial cumulative damage value D0=0.15 (consistent with the normal aging level after 5 years of operation). The unit's rated voltage is 15.75kV, and its normal operating parameters are stable: stator line voltage 15.6-15.7kV, stator phase current 2750-2850A, and stator core temperature 74-76℃. This embodiment is based entirely on a second-level time dimension, reusing the power station's existing 1Hz sampling frequency monitoring system. Through data from a typical 30-minute operating period, it fully demonstrates the process of insulation damage accumulation and health status assessment, ensuring a high degree of consistency with actual operation and maintenance scenarios.

[0048] S100: Through the data acquisition module of the evaluation system of this invention, the power plant's SCADA system is connected via the OPC UA protocol to collect second-level operating data of the unit from 14:00:00 to 14:30:00 (a total of 30 minutes, 1800 seconds) on a normal operating day, including stator line voltage, stator phase current, and stator core temperature. During this period, the unit operates stably with small parameter fluctuations. The following are typical data for the first 6 seconds (the data trend is consistent throughout): Table 1

[0049] S200: The system preprocessing module standardizes 30-minute-level data to eliminate minor power grid interference and sensor drift, ensuring data reliability. The specific steps are as follows: S210 Denoising Processing: For voltage and current data, a 5-point sliding median filter (window size of 5 sampling points, adapted to a 1Hz sampling frequency) is used to smooth high-frequency impulse noise. Taking the voltage data (15.65, 15.66, 15.64, 15.65, 15.67) from 14:00:00 to 14:00:04 as an example, after sorting, it becomes (15.64, 15.65, 15.65, 15.66, 15.67). Taking the median of 15.65, the filtered result is 15.65, 15.65, 15.65, 15.66, 15.66kV. For temperature data, a 3-point sliding median filter is used to smooth out minute drifts of ±0.1℃. After filtering, the temperature is stabilized at 75.2-75.3℃ without disrupting the original data trend.

[0050] S220 normalization: The min-max algorithm is used to map the data to the [0,1] interval to eliminate dimensional differences. The specific formula is as follows:

[0051] Wherein, voltage X min =15.5kV, X max =15.9kV, if 15.65kV is normalized, it becomes: (15.65-15.5) / (15.9-15.5)=0.375; Current X min =2700A、X max =2900A, such as 2800A, after normalization is: (2800-2700) / (2900-2700)=0.5; Temperature X min =72℃, X max =78℃, if 75.2℃ is normalized, it becomes: (75.2-72) / (78-72)=0.53.

[0052] S230 Time Synchronization: The power plant monitoring system has a timestamp accuracy of ≤1ms. The timestamps of voltage, current, and temperature data are fully aligned, eliminating the need for additional time calibration through linear interpolation and directly outputting standardized data.

[0053] S240 outlier removal: Based on the baseline range of 5 years of historical operating data of the unit (voltage 15.5-15.9kV, current 2700-2900A, temperature 72-78℃), all data within 30 minutes are within the normal range, and there are no extreme outliers caused by sensor failure or grid disturbance, so no removal is required to ensure data continuity.

[0054] S300: The system's sliding window feature extraction module uses a fixed parameter window to extract core features characterizing insulation degradation. The specific operation is as follows: S310 window parameter configuration: The window duration is set to 30 seconds (corresponding to 30 1Hz sampling points), balancing feature stability and real-time monitoring requirements; the sliding step size is 30 seconds, with no overlap between adjacent windows (e.g., window 1 is 14:00:00-14:00:30, window 2 is 14:00:30-14:01:00), and the parameters are fixed throughout to adapt to stable power plant operation conditions. A total of 60 sliding windows are divided within 30 minutes (1800 seconds ÷ 30 seconds / window = 60).

[0055] S320 Feature Calculation: Taking window 10 (14:04:30-14:05:00) as an example, based on the preprocessed standardized data, the core features are calculated as shown in the table below: Table 2

[0056] Among them, the current characteristics are only used for judging the stability of the operating condition and are not directly involved in the damage model calculation.

[0057] S400: such as Figure 4 As shown, the cumulative trend chart of electrical-thermal dual-factor damage is plotted, with the horizontal axis representing operating time (days) and the vertical axis representing cumulative damage. Three curves are labeled: electrical damage, thermal damage, and total damage, along with the health status grading threshold. The system lifetime damage calculation module loads the electrical-thermal dual-factor coupled incremental damage model, calculates the damage increment for each window, and accumulates it. The specific process is as follows: Based on the material properties and experimental fitting results of epoxy resin-mica composite insulation, the following model parameters are applied: Electrical stress parameters: , , ; Thermal stress parameter: , , ; Time parameter: (Window duration converted to hours).

[0058] Calculation of single-window damage increment: Taking the 10th window as an example, the average window voltage U_avg = 15.66 kV, and the window temperature T = 75.2 °C = 348.35 K. The calculation is as follows: Electrical stress damage increment of S410: ; Thermal stress damage increment of S420: ;

[0059] Total single-window damage increment of S430:

[0060] Damage accumulation of S440: There are 60 windows in total within 30 minutes,[[ID=—]] Total damage increment ; Cumulative damage after 30 minutes: ; Add the initial cumulative damage , and it is still in a normal state. The decision is output through the health assessment module.

[0061] S500: Through the system health assessment module, based on the damage accumulation result and dynamic threshold, complete the determination of the insulation health status and output the operation and maintenance suggestions: Determination of health status: Based on the design life of epoxy resin mica composite insulation and the industry operation and maintenance standards, set the dynamic threshold for health status classification: normal state (D ≤ 0.2), mild degradation (0.2 < D ≤ 0.4), moderate degradation (0.4 < D ≤ 0.7), severe degradation (0.7 < D < 1). When D ≥ 1, it is determined that the insulation fails. In this embodiment, the cumulative damage after 30 minutes < 0.2, it is determined that the stator insulation is in a normal state; the core basis is that the damage increment within 30 minutes is only 1.758 × 10 -6 , indicating that the current operating parameters are stable, and the insulation damage accumulation under the electro-thermal stress coupling is extremely slow, which is consistent with the normal aging expectation of the unit's 5-year operation.

[0062] Operation and maintenance suggestions: Monitoring frequency: Maintain the existing quarterly insulation inspection frequency of the power station, and review the cumulative damage value every 3 months through the evaluation system of this invention to track changes in insulation status in real time; Parameter monitoring: Focus on monitoring the stator core temperature. If the temperature continues to exceed 78°C, the operating status of the cooling system should be checked in time. Voltage and current fluctuations should be controlled within the existing range. Life planning: Based on the current aging rate, it is expected that the unit will enter the mild degradation stage in 10 years (15 years of operation). It is recommended to start the preparation of the overhaul plan at that time and plan maintenance resources in advance.

[0063] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, electronic devices, and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0067] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0068] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0069] The above provides a detailed description of a generator insulation life assessment method based on sliding window incremental damage. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and its core ideas. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for evaluating the insulation life of a generator based on sliding window incremental damage, characterized in that, include: Obtain raw monitoring data of the stator windings of the hydro-generator, including voltage, current, and temperature; The raw monitoring data is preprocessed to obtain standardized data; Using a sliding window of fixed duration, feature quantities for characterizing the insulation state are extracted from the standardized data, and the feature quantities include at least voltage and temperature features. Based on the aforementioned characteristic quantities, the incremental insulation damage within each sliding window is calculated using an incremental damage model that couples electrical stress and thermal stress. The cumulative damage value is obtained by accumulating the insulation damage increment of each sliding window; The health status of the stator insulation is assessed based on the cumulative damage value, and its remaining lifetime is predicted based on the health status.

2. The generator insulation life assessment method based on sliding window incremental damage according to claim 1, characterized in that, The fixed-duration sliding window is specifically described as follows: The window duration is set to 30 seconds, and the sliding step size is equal to the window duration. Each window contains 30 data points obtained at a sampling frequency of 1Hz.

3. The generator insulation life assessment method based on sliding window incremental damage according to claim 1, characterized in that, The preprocessing of the raw monitoring data includes noise reduction, normalization, time synchronization, and outlier identification.

4. The generator insulation life assessment method based on sliding window incremental damage according to claim 1, characterized in that, The voltage characteristics include the average voltage and peak voltage within the sliding window; the temperature characteristics include the average temperature and the rate of temperature rise within the sliding window.

5. The generator insulation life assessment method based on sliding window incremental damage according to claim 1, characterized in that, The incremental damage model based on the coupling of electrical and thermal stress calculates the insulation damage increment within each sliding window, including: Calculate the electrical stress damage increment based on the average voltage within the sliding window: in, This represents the increment of electrical stress damage. The electrical aging coefficient, The average voltage within the window. Where is the rated voltage of the motor, and n is the electrical aging index; Calculate the thermal stress damage increment based on the average temperature within the sliding window: in, Let A be the thermal stress damage increment, and A be the pre-exponential factor. Activation energy for insulating materials, The gas constant is... The average temperature within the window; Calculate the total damage increment within the sliding window based on the electrical stress damage increment and the thermal stress damage increment: in, This represents the increment of insulation damage.

6. The generator insulation life assessment method based on sliding window incremental damage according to claim 5, characterized in that, The cumulative damage value is obtained by accumulating the insulation damage increment of each sliding window, as shown in the following formula: Where k is the total number of sliding windows.

7. The generator insulation life assessment method based on sliding window incremental damage according to claim 1, characterized in that, The assessment of the health status of the stator insulation based on the cumulative damage value specifically includes: If the cumulative damage value D ≤ 0.2, it is assessed as a normal state; If 0.2 < cumulative damage value D ≤ 0.4, it is assessed as a mild degradation state; If 0.4 < cumulative damage value D ≤ 0.7, it is assessed as a moderate degradation state; If 0.7 < cumulative damage value D < 1.0, it is assessed as a severely degraded state; If the cumulative damage value D ≥ 1.0, it is assessed as insulation failure.

8. The generator insulation life assessment system based on sliding window incremental damage according to any one of claims 1-7, characterized in that, The system includes: The data acquisition module is used to acquire raw monitoring data of the stator winding of the hydro-generator, including voltage, current and temperature; The preprocessing module is used to preprocess the raw monitoring data to obtain standardized data; The feature extraction module is used to extract feature quantities for characterizing the insulation state from the standardized data using a sliding window of fixed duration. The feature quantities include at least voltage features and temperature features. The damage calculation module is used to calculate the insulation damage increment within each sliding window based on the aforementioned characteristic quantity using an incremental damage model that couples electrical and thermal stress; to accumulate the insulation damage increments of each sliding window to obtain a cumulative damage value; and The monitoring and evaluation module is used to assess the health status of the stator insulation based on the cumulative damage value, and predict its remaining life based on the health status.

9. An electronic device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the generator insulation life assessment method based on sliding window incremental damage as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the generator insulation life assessment method based on sliding window incremental damage as described in any one of claims 1 to 7.

Images