Safety detection method, device and electronic equipment for wind turbine generator system

Abstract

The application provides a safety detection method and device of a wind turbine and electronic equipment, and relates to the technical field of safety detection of wind turbines, wherein the safety detection method of the wind turbine comprises the following steps: receiving detection data of different detection points of the wind turbine; performing feature extraction on the detection data of each detection point to determine inherent frequency characteristics of the detection point; extracting historical detection data, and determining an anomaly index according to the historical detection data and the inherent frequency characteristics; determining predicted inherent frequency characteristics based on the historical detection data, and obtaining inherent frequency deviation of the detection point according to the predicted inherent frequency characteristics and the inherent frequency characteristics; determining a detection result of the detection point according to the anomaly index and the inherent frequency deviation, and determining a safety detection result of the wind turbine based on the detection result of each detection point, so that real-time monitoring and fault detection of the wind turbine are realized, and the safety and reliability of the wind turbine are improved.

Description

Technical Field

[0001] This application relates to the field of wind turbine safety testing technology, and in particular to a method, apparatus and electronic equipment for wind turbine safety testing. Background Technology

[0002] The tower of a wind turbine is a load-bearing component, primarily serving a supporting role while absorbing vibrations. The tower bears complex and variable loads such as thrust, bending moment, and torque, causing it to sway and twist during operation. Furthermore, the tower is susceptible to tilting due to material changes, component failures, and ground settlement. Excessive tilting can disrupt the normal operation of the wind turbine and, in severe cases, lead to safety accidents. Therefore, real-time monitoring of wind turbine operation safety is essential to prevent such incidents. Summary of the Invention

[0003] This application aims to at least partially address one of the technical problems in the related art.

[0004] Therefore, the first objective of this application is to propose a safety testing method for wind turbine generators to achieve real-time testing of wind turbine generators and improve the accuracy of wind turbine generator safety testing.

[0005] The second objective of this application is to propose a safety detection device for wind turbine generators.

[0006] The third objective of this application is to propose an electronic device.

[0007] The fourth objective of this application is to provide a computer-readable storage medium.

[0008] The fifth objective of this application is to provide a computer program product.

[0009] To achieve the above objectives, the first aspect of this application proposes a safety testing method for wind turbine generators, comprising: Receives test data from different test points of the wind turbine during the current test cycle; Feature extraction is performed on the detection data at each detection point to determine the inherent frequency characteristics of the detection point; Historical detection data for historical detection cycles are extracted from the historical database, and the anomaly index of the detection point is determined based on the historical detection data and the inherent frequency characteristics of the detection point. Based on the historical detection data, the predicted inherent frequency characteristics of the detection point under the current detection cycle are determined, and the inherent frequency deviation of the detection point is obtained according to the predicted inherent frequency characteristics and the inherent frequency characteristics. Based on the anomaly index and the inherent frequency deviation, the detection results of the detection points are determined, and based on the detection results of each detection point, the safety detection results of the wind turbine are determined.

[0010] To achieve the above objectives, a second aspect of this application provides a safety detection device for wind turbine generators, comprising: The receiving module is used to receive the detection data of different detection points of the wind turbine in the current detection cycle; The first acquisition module is used to extract features from the detection data of each detection point and determine the inherent frequency features of the detection point. The second acquisition module is used to extract historical detection data of historical detection cycles from the historical database, and determine the anomaly index of the detection point based on the historical detection data and the inherent frequency characteristics of the detection point. The third acquisition module is used to determine the predicted inherent frequency characteristics of the detection point under the current detection cycle based on the historical detection data, and to obtain the inherent frequency deviation of the detection point according to the predicted inherent frequency characteristics and the inherent frequency characteristics. The safety detection module is used to determine the detection results of the detection points based on the anomaly index and the inherent frequency deviation, and to determine the safety detection results of the wind turbine based on the detection results of each detection point.

[0011] To achieve the above objectives, a third aspect of this application provides an electronic device comprising: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method described in the first aspect.

[0012] To achieve the above objectives, a fourth aspect of this application provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, are used to implement the method described in the first aspect.

[0013] To achieve the above objectives, the fifth aspect of this application provides a computer program product, including a computer product that, when executed by a processor, implements the method described in the first aspect.

[0014] The wind turbine safety inspection method, device, and electronic equipment provided in this application acquire inspection data from different inspection points of the wind turbine during the current inspection cycle, extract features from the inspection data to obtain the inherent frequency characteristics of the inspection points, obtain historical inspection data from a historical database, compare the historical inherent frequency characteristics of the historical inspection data with the inherent frequency characteristics of the current inspection cycle to determine the anomaly index of the current inspection point, further determine the inherent frequency deviation based on the predicted inherent frequency characteristics of the current inspection cycle and the actual collected inherent frequency characteristics, combine the inherent frequency deviation and the anomaly index to obtain the inspection results of the inspection points, and obtain the safety inspection results of the wind turbine based on the inspection results of the inspection points, thereby realizing real-time monitoring and fault detection of the wind turbine, improving the safety and reliability of the wind turbine, and reducing maintenance costs.

[0015] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0016] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart illustrating a safety testing method for a wind turbine provided in an embodiment of this application. Figure 2 This is a schematic diagram of a process for obtaining an anomaly index provided in an embodiment of this application; Figure 3 This is a schematic diagram of a process for obtaining the inherent frequency deviation provided in an embodiment of this application; Figure 4 This is a flowchart illustrating another safety testing method for wind turbine generators provided in an embodiment of this application. Figure 5 A logic flowchart of another safety detection method for wind turbine generators provided in an embodiment of this application; Figure 6 This is a schematic diagram of the structure of a safety detection device for a wind turbine provided in an embodiment of this application. Detailed Implementation

[0017] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0018] The following description, with reference to the accompanying drawings, describes a safety testing method, apparatus, and electronic device for wind turbine generators according to embodiments of this application.

[0019] Figure 1 This is a flowchart illustrating a safety testing method for wind turbine generators provided in an embodiment of this application. Figure 1 As shown, the method includes the following steps: S101 receives detection data from different detection points of the wind turbine during the current detection cycle.

[0020] In some embodiments, different detection points of the wind turbine can be key detection points at different locations on the tower and the tower base. In this embodiment, high-precision tilt sensors are installed at the top, middle and bottom of the tower and at the four corners of the tower base to detect the detection data of different detection points of the wind turbine.

[0021] In some embodiments, the detection cycle is the periodic cycle for conducting safety assessments of wind turbine units, such as every hour or half a day. The detection data detected by the high-precision tilt sensor within the detection cycle is received to ensure that it can accurately capture minute angle changes. Optionally, tilt data can be collected at 1-second intervals to obtain tilt data from different high-precision tilt sensors collected every second within the detection cycle, thereby obtaining detection data from different detection points.

[0022] In some embodiments, after the detection data is acquired, the detection data can be preprocessed, such as data cleaning, to remove noise and outliers caused by environmental factors, sensor errors, etc., so as to ensure the accuracy and reliability of the data.

[0023] Optionally, the detection data can be normalized to eliminate the dimensional differences between data at different time points, so that all data are on the same order of magnitude, which facilitates the analysis and comparison of the detection data.

[0024] S102, extract features from the detection data of each detection point to determine the inherent frequency characteristics of the detection point.

[0025] Alternatively, a fast Fourier transform or other signal processing methods can be used to extract the first-order natural frequency from the tilt data as the natural frequency feature of each detection point.

[0026] S103. Extract historical detection data for historical detection cycles from the historical database, and determine the anomaly index of the detection point based on the historical detection data and the inherent frequency characteristics of the detection point.

[0027] The historical database can be a database system with sufficient storage capacity to store detection data for historical detection periods; alternatively, historical detection data for multiple historical detection periods can be extracted from the historical database, such as historical detection data for the 10 historical detection periods closest to the current detection period.

[0028] Understandably, the first historical inherent frequency can be calculated based on the historical detection data of each historical detection period, thereby obtaining the historical inherent frequency characteristics of the historical detection data.

[0029] Optionally, historical detection cycles of the wind turbine's normal operating conditions can be selected to determine the historical inherent frequency characteristics of the historical detection cycles under normal conditions. Based on the historical inherent frequency characteristics under normal conditions and the inherent frequency characteristics of the current detection point, the anomaly index of the detection point can be determined. For example, the average value of the historical inherent frequency characteristics under normal conditions can be determined as the target inherent frequency characteristic. The difference between the target inherent frequency characteristic and the inherent frequency characteristic of the current detection point can be calculated as the anomaly index. The larger the difference, the greater the difference between the inherent frequency characteristics of the current detection point and the target inherent frequency characteristic, that is, the greater the deviation from normal, and the larger the corresponding anomaly index.

[0030] S104. Based on historical detection data, determine the predicted inherent frequency characteristics of the detection points under the current detection cycle, and obtain the inherent frequency deviation of the detection points based on the predicted inherent frequency characteristics and the inherent frequency characteristics.

[0031] In some embodiments, the intrinsic frequency features can be predicted based on a pre-trained prediction model. That is, historical detection data is input into the prediction model, and the prediction model predicts the predicted intrinsic frequency features of different detection points in the current detection period based on the historical intrinsic frequency features of the historical detection data.

[0032] Furthermore, the difference between the predicted intrinsic frequency characteristics and the actual intrinsic frequency characteristics under the current detection period can be determined, and this difference can be used as the intrinsic frequency deviation of the detection point.

[0033] S105. Based on the anomaly index and the deviation of the natural frequency, determine the detection results of the detection points, and based on the detection results of each detection point, determine the safety detection results of the wind turbine.

[0034] Optionally, the anomaly index and the natural frequency deviation can be added together or weighted to obtain a detection score. This detection score is used to determine whether there is an abnormal detection result at the current detection point. For example, if the detection score exceeds a preset threshold, the detection result at the current detection point of the wind turbine is determined to be abnormal. Conversely, if the detection score does not exceed the preset threshold, the detection result at the current detection point of the wind turbine is determined to be non-abnormal.

[0035] Furthermore, after obtaining the detection results of each detection point, the number of abnormal detection points can be counted. If the number of abnormal detection points is large, it is determined that the wind turbine has an operational abnormality. For example, in this embodiment, there are a total of 7 detection points. When there are 2 or more abnormal detection points, it is determined that the wind turbine has an operational abnormality, so as to improve the accuracy of safety detection of the wind turbine operation process.

[0036] In this embodiment, detection data from different detection points of the wind turbine during the current detection cycle are acquired. Feature extraction is performed on the detection data to obtain the first-order natural frequency of the detection point as the natural frequency feature. Historical detection data is obtained from the historical database. The historical natural frequency features of the historical detection data are compared with the natural frequency features of the current detection cycle to determine the anomaly index of the current detection point. Furthermore, the natural frequency deviation is determined based on the predicted natural frequency and the actual collected natural frequency features of the current detection cycle. Combining the natural frequency deviation and the anomaly index, the detection result of the detection point is obtained. Based on the detection result of the detection point, the safety detection result of the wind turbine is obtained, realizing real-time monitoring and fault detection of the wind turbine, improving the safety and reliability of the wind turbine, and reducing maintenance costs.

[0037] Based on the above embodiments, Figure 2 This is a schematic diagram illustrating a process for obtaining an anomaly index provided in an embodiment of this application. Figure 2 As shown, the method includes the following steps: S201, the first test data selected from historical test data for test points.

[0038] Understandably, the detection data corresponding to each detection point is selected from the historical detection data of all detection points as the corresponding first detection data.

[0039] S202, Based on the first detection data, determine the normal inherent frequency characteristics under normal conditions.

[0040] The historical testing data includes data on wind turbines operating normally and wind turbines operating abnormally at different testing points. Optionally, second testing data under normal conditions can be selected from the first testing data.

[0041] In some embodiments, the inherent frequency values ​​of at least two detection cycles can be determined based on the second detection data; alternatively, the inherent frequency value of each detection cycle can be determined by analyzing the second detection data of each detection cycle based on the Fourier transform algorithm, and the inherent frequency value is the inherent frequency value under normal conditions.

[0042] Furthermore, the average value of the natural frequency values ​​of at least two detection cycles can be determined as the normal natural frequency characteristic.

[0043] S203, determine the anomaly index of the detection point based on the difference between the inherent frequency characteristics and the normal inherent frequency characteristics.

[0044] Optionally, the absolute value of the difference between the inherent frequency characteristics and the normal inherent frequency characteristics can be calculated as the anomaly index of the detection point.

[0045] In other embodiments, the slope or acceleration of the detection data can be extracted as a trend, and the trend can be used as a correlation feature for the analysis of the anomaly index. For example, the trend can be used as a weighting coefficient and fused with the difference in inherent frequency features to obtain a more accurate anomaly index.

[0046] In this embodiment, second detection data under normal conditions is selected from historical detection data, and normal inherent frequency characteristics are determined based on the second detection data. The absolute value of the difference between the normal inherent frequency characteristics and the inherent frequency characteristics under the current detection cycle is used as the anomaly index of the detection point. The normal inherent frequency characteristics are used as a comparison benchmark to determine whether there is an anomaly in the current detection cycle, thereby improving the accuracy of obtaining the anomaly index.

[0047] Based on the above embodiments, Figure 3 This is a schematic diagram illustrating a process for obtaining the inherent frequency deviation provided in an embodiment of this application. Figure 3 As shown, the method includes the following steps: S301, determine the target detection data of the detection point under the target detection cycle from historical detection data.

[0048] The target detection period includes at least N consecutive detection periods preceding the current detection period, where N is an integer greater than or equal to 2. For example, assuming the current detection period is t=20 and N is 10, the target detection period is t-10 to t-1, meaning the 10th to 19th detection periods constitute the target detection period.

[0049] The detection data corresponding to the target detection cycle is defined as the target detection data.

[0050] S302, Obtain the pre-trained feature prediction model.

[0051] Optionally, the feature prediction model can be a model with time series analysis capabilities, such as the Auto-Regressive Moving Average (ARMA) model, which comprehensively considers the correlation and random fluctuations of historical observations and captures the characteristics of time series data better.

[0052] It is understandable that when training a feature prediction model, historical detection data is obtained as sample data, and the feature prediction model is trained based on the inherent frequency features of the sample data to obtain prediction results. Based on the prediction results and the true results corresponding to the sample data, the prediction deviation is determined, and the feature prediction model is fine-tuned according to the prediction deviation to obtain a pre-trained feature prediction model.

[0053] S303 inputs the target detection data into the pre-trained feature prediction model and outputs the predicted inherent frequency features of the detection points in the current detection period.

[0054] Understandably, based on the target detection data, the inherent frequency features of the target are obtained for each target detection period. The pre-trained feature prediction model makes predictions based on the inherent frequency features of the target and outputs the predicted inherent frequency features of the detection points in the current detection period.

[0055] S304. Based on the predicted natural frequency characteristics and the natural frequency characteristics, obtain the natural frequency deviation of the detection point.

[0056] Optionally, the deviation value between the predicted inherent frequency feature and the inherent frequency feature can be obtained; that is, the absolute value of the difference between the predicted inherent frequency and the inherent frequency feature can be calculated. The larger the absolute value of the difference, the greater the deviation. Correspondingly, the smaller the absolute value of the difference, the smaller the deviation. The inherent frequency deviation of the detection point is obtained based on the deviation value. In this embodiment, the deviation value is used as the inherent frequency deviation of the detection point.

[0057] In this embodiment, target detection data for the target detection period is determined from historical detection data. Based on the target detection data and the pre-trained feature prediction model, the predicted inherent frequency features for the current detection period are obtained. Based on the deviation between the actual inherent frequency features and the predicted inherent frequency features for the current detection period, the inherent frequency deviation of the detection point is determined to reflect whether the detection point deviates significantly from the normal trend, thereby improving the accuracy of subsequent anomaly analysis results.

[0058] Based on the above embodiments, Figure 4 This is a flowchart illustrating another safety testing method for wind turbine generators provided in an embodiment of this application. Figure 4 As shown, the method includes the following steps: S401 receives detection data from different detection points of the wind turbine during the current detection cycle.

[0059] In this application embodiment, the implementation method of step S401 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0060] S402, extract features from the detection data of each detection point to determine the inherent frequency characteristics of the detection point.

[0061] In this application embodiment, the implementation method of step S402 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0062] S403, the first test data for screening test points from historical test data.

[0063] In this application embodiment, the implementation method of step S403 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0064] S404, based on the first detection data, determine the normal inherent frequency characteristics under normal conditions.

[0065] In this application embodiment, the implementation method of step S404 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0066] S405, determine the anomaly index of the detection point based on the difference between the inherent frequency characteristics and the normal inherent frequency characteristics.

[0067] In this application embodiment, the implementation method of step S405 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0068] S406, determine the target detection data of the detection point under the target detection cycle from historical detection data.

[0069] In this application embodiment, the implementation method of step S406 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0070] S407, Obtain the pre-trained feature prediction model.

[0071] In this application embodiment, the implementation method of step S407 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0072] S408 inputs the target detection data into the pre-trained feature prediction model and outputs the predicted inherent frequency features of the detection points in the current detection period.

[0073] In this application embodiment, the implementation method of step S408 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0074] S409, based on the predicted natural frequency characteristics and the natural frequency characteristics, obtain the natural frequency deviation of the detection point.

[0075] In this application embodiment, the implementation method of step S409 can be implemented in any of the various embodiments of this disclosure, and no limitation is made here, nor will it be described in detail.

[0076] S410 determines the detection results of the detection points based on the anomaly index and the inherent frequency deviation, and determines the safety detection results of the wind turbine based on the detection results of each detection point.

[0077] Optionally, in this embodiment, the anomaly index and the inherent frequency deviation are weighted and summed to obtain the first safety score of the detection point. Different weights can be assigned to the anomaly index and the inherent frequency deviation based on historical data and expert experience, taking into account the sensitivity of the data to the fault type, so as to ensure the accuracy of the first safety score.

[0078] Based on the first safety score and the preset scoring threshold, the detection result of the detection point is determined. If the first safety score is greater than or equal to the preset scoring threshold, the detection result of the detection point is determined to be abnormal. If the first safety score is less than the preset scoring threshold, the detection result of the detection point is determined to be non-abnormal.

[0079] Optionally, the number of detection points with abnormal results can also be counted; if the number of detection points is greater than or equal to the preset number, the safety test result of the wind turbine is determined to be abnormal; if the number of detection points is less than the preset number, the safety test result of the wind turbine is determined to be normal operation.

[0080] In some embodiments, when an abnormality is detected in the wind turbine, an alarm signal can be issued to notify maintenance personnel to take timely measures for troubleshooting and repair, thereby providing detailed fault diagnosis information and maintenance suggestions, including fault type, location, severity and possible maintenance measures, to achieve real-time monitoring and fault detection of the wind turbine, improve the safety and reliability of the wind turbine and reduce maintenance costs.

[0081] In this embodiment, detection data from different detection points of the wind turbine under the current detection cycle are acquired. Feature extraction is performed on the detection data to obtain the first-order natural frequency of the detection point as the natural frequency feature. Second detection data under normal conditions is selected from historical detection data to determine the normal natural frequency feature. The absolute value of the difference between the normal natural frequency feature and the natural frequency feature under the current detection cycle is used as the anomaly index of the detection point to improve the accuracy of the anomaly index acquisition. Target detection data for the target detection cycle is determined from historical detection data. Based on the target detection data and the pre-trained feature prediction model, the predicted natural frequency feature for the current detection cycle is obtained. Based on the deviation between the actual natural frequency feature and the predicted natural frequency feature under the current detection cycle, the natural frequency deviation of the detection point is determined to reflect whether the detection point deviates significantly from the normal trend. The natural frequency deviation and the anomaly index are weighted and summed to obtain the detection result of the detection point. The safety detection result of the wind turbine is obtained based on the detection result of the detection point, realizing real-time monitoring and fault detection of the wind turbine, improving the safety and reliability of the wind turbine, and reducing maintenance costs.

[0082] Figure 5 This is a logical flowchart of another wind turbine safety inspection method provided in this application embodiment; high-precision tilt sensors are deployed on the wind turbine tower and tower base, and the detection data collected by the high-precision tilt sensors is received. Based on the detection data, inherent frequency characteristics are obtained; historical detection data is extracted from a historical database; an anomaly index is determined based on the historical detection data and inherent frequency characteristics; a pre-trained feature prediction model is obtained; predicted inherent frequency feature values ​​are obtained based on the historical detection data and the feature prediction model; inherent frequency deviation is determined based on the predicted inherent frequency feature values ​​and inherent frequency feature values; the detection results of the detection points are determined based on the inherent frequency deviation and the anomaly index; the safety inspection result of the wind turbine is determined based on the detection results of all detection points; and an alarm and suggestions are issued based on the safety inspection result, achieving more accurate and timely wind turbine safety inspection.

[0083] To achieve the above embodiments, this application also proposes a safety detection device for wind turbine generators.

[0084] Figure 6 This is a schematic diagram of the structure of a safety detection device for a wind turbine provided in an embodiment of this application. Figure 6 As shown, the safety detection device 600 for the wind turbine includes: The receiving module 601 is used to receive the detection data of different detection points of the wind turbine in the current detection cycle; The first acquisition module 602 is used to extract features from the detection data of each detection point and determine the inherent frequency features of the detection point. The second acquisition module 603 is used to extract historical detection data of historical detection cycles from the historical database, and determine the anomaly index of the detection point based on the historical detection data and the inherent frequency characteristics of the detection point. The third acquisition module 604 is used to determine the predicted inherent frequency characteristics of the detection point under the current detection cycle based on historical detection data, and to obtain the inherent frequency deviation of the detection point based on the predicted inherent frequency characteristics and the inherent frequency characteristics. The safety detection module 605 is used to determine the detection results of the detection points based on the anomaly index and the inherent frequency deviation, and to determine the safety detection results of the wind turbine based on the detection results of each detection point.

[0085] Furthermore, in one possible implementation of this application embodiment, the second acquisition module 603 includes: The first test data of the test points is selected from historical test data; Based on the first detection data, the normal inherent frequency characteristics under normal conditions are determined; The anomaly index of the detection point is determined based on the difference between the inherent frequency characteristics and the normal inherent frequency characteristics.

[0086] Furthermore, in one possible implementation of this application embodiment, the second acquisition module 603 includes: Filter the second test data under normal conditions from the first test data; Based on the second detection data, determine the inherent frequency values ​​for at least two detection cycles; The average value of the natural frequency values ​​from at least two detection cycles is determined as the normal natural frequency characteristic.

[0087] Furthermore, in one possible implementation of this application embodiment, the third acquisition module 604 includes: Determine the target detection data of the detection point in the target detection period from the historical detection data. The target detection period includes at least N consecutive detection periods before the current detection period, where N is an integer greater than or equal to 2. Obtain a pre-trained feature prediction model; The target detection data is input into the pre-trained feature prediction model, which outputs the predicted inherent frequency features of the detection points in the current detection period.

[0088] Furthermore, in one possible implementation of this application embodiment, the third acquisition module 604 includes: Obtain the deviation between the predicted intrinsic frequency feature and the intrinsic frequency feature; The inherent frequency deviation of the detection point is obtained based on the deviation value.

[0089] Furthermore, in one possible implementation of this application embodiment, the security detection module 605 includes: The first safety score of the detection point is obtained by weighted summation of the anomaly index and the deviation of the inherent frequency. The detection results of the detection points are determined based on the first safety score and the preset scoring threshold.

[0090] Furthermore, in one possible implementation of this application embodiment, the security detection module 605 includes: The number of detection points with abnormal results is counted. If the number of detection points is greater than or equal to the preset number, the safety inspection result of the wind turbine is determined to be abnormal. If the number of testing points is less than the preset number, the safety test result of the wind turbine is determined to be normal operation.

[0091] It should be noted that the foregoing explanation of the safety testing method embodiment for wind turbines also applies to the safety testing device for wind turbines in this embodiment, and will not be repeated here.

[0092] In this embodiment, detection data from different detection points of the wind turbine during the current detection cycle are acquired. Feature extraction is performed on the detection data to obtain the first-order natural frequency of the detection point as the natural frequency feature. Second detection data under normal conditions are selected from historical detection data to determine the normal natural frequency feature. The absolute value of the difference between the normal natural frequency feature and the natural frequency feature under the current detection cycle is used as the anomaly index of the detection point to improve the accuracy of the anomaly index acquisition. Target detection data for the target detection cycle is determined from historical detection data. Based on the target detection data and a pre-trained feature prediction model, the predicted natural frequency feature for the current detection cycle is obtained. Based on the deviation between the actual natural frequency feature and the predicted natural frequency feature under the current detection cycle, the natural frequency deviation of the detection point is determined to reflect whether the detection point deviates significantly from the normal trend. The natural frequency deviation and the anomaly index are weighted and summed to obtain the detection result of the detection point. The safety detection result of the wind turbine is obtained based on the detection result of the detection point, realizing real-time monitoring and fault detection of the wind turbine, improving the safety and reliability of the wind turbine, and reducing maintenance costs.

[0093] To implement the above embodiments, this application also proposes an electronic device, including: a processor and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0094] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0095] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0096] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in this application all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0097] It should be noted that personal information collected from users should be used for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. Furthermore, such collection / sharing should only be conducted after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization that includes authorization of relevant user information before the user uses the function. In addition, any necessary steps must be taken to protect and safeguard access to such personal information data and ensure that others with access to personal information data comply with their privacy policies and procedures.

[0098] This application is intended to provide an implementation scheme for users to selectively prevent the use or access to their personal information data. Specifically, this disclosure is intended to provide hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, risks can be minimized by restricting data collection and deleting data. Furthermore, where applicable, such personal information is de-identified to protect user privacy.

[0099] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0100] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0101] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0102] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0103] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0104] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0105] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0106] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A safety inspection method for wind turbine generators, characterized in that, The method includes: Receives test data from different test points of the wind turbine during the current test cycle; Feature extraction is performed on the detection data at each detection point to determine the inherent frequency characteristics of the detection point; Historical detection data for historical detection cycles are extracted from the historical database, and the anomaly index of the detection point is determined based on the historical detection data and the inherent frequency characteristics of the detection point. Based on the historical detection data, the predicted inherent frequency characteristics of the detection point under the current detection cycle are determined, and the inherent frequency deviation of the detection point is obtained according to the predicted inherent frequency characteristics and the inherent frequency characteristics. Based on the anomaly index and the inherent frequency deviation, the detection results of the detection points are determined, and based on the detection results of each detection point, the safety detection results of the wind turbine are determined.

2. The method according to claim 1, characterized in that, Based on the historical detection data and the inherent frequency characteristics of the detection points, the anomaly index of the detection points is determined, including: Filter the first detection data of the detection point from the historical detection data; Based on the first detection data, the normal inherent frequency characteristics under normal conditions are determined; The anomaly index of the detection point is determined based on the difference between the inherent frequency characteristics and the normal inherent frequency characteristics.

3. The method according to claim 2, characterized in that, The step of determining the normal inherent frequency characteristics under normal conditions based on the first detection data includes: Filter the second detection data under normal conditions from the first detection data; Based on the second detection data, determine the inherent frequency values ​​for at least two detection cycles; The average value of the intrinsic frequency values ​​of the at least two detection cycles is determined as the normal intrinsic frequency feature.

4. The method according to any one of claims 1-3, characterized in that, The step of determining the predicted inherent frequency characteristics of the detection points in the current detection period based on the historical detection data includes: The target detection data of the detection point under the target detection period is determined from the historical detection data. The target detection period includes at least N consecutive detection periods before the current detection period, where N is an integer greater than or equal to 2. Obtain a pre-trained feature prediction model; The target detection data is input into a pre-trained feature prediction model, which outputs the predicted inherent frequency features of the detection points in the current detection period.

5. The method according to claim 4, characterized in that, The step of obtaining the intrinsic frequency deviation of the detection point based on the predicted intrinsic frequency features and the intrinsic frequency features includes: Obtain the deviation between the predicted intrinsic frequency feature and the intrinsic frequency feature; The inherent frequency deviation of the detection point is obtained based on the deviation value.

6. The method according to claim 1, characterized in that, The step of determining the detection result of the detection point based on the anomaly index and the inherent frequency deviation includes: The first security score of the detection point is obtained by weighted summation of the anomaly index and the inherent frequency deviation. The detection result of the detection point is determined based on the first security score and the preset scoring threshold.

7. The method according to claim 6, characterized in that, Based on the detection results at each of the aforementioned detection points, the safety inspection results of the wind turbine are determined, including: Count the number of detection points when the detection result is abnormal; If the number of detection points is greater than or equal to the preset number, the safety inspection result of the wind turbine is determined to be abnormal. If the number of detection points is less than the preset number, the safety test result of the wind turbine is determined to be normal operation.

8. A safety detection device for wind turbine generators, characterized in that, include: The receiving module is used to receive the detection data of different detection points of the wind turbine in the current detection cycle; The first acquisition module is used to extract features from the detection data of each detection point and determine the inherent frequency features of the detection point. The second acquisition module is used to extract historical detection data of historical detection cycles from the historical database, and determine the anomaly index of the detection point based on the historical detection data and the inherent frequency characteristics of the detection point. The third acquisition module is used to determine the predicted inherent frequency characteristics of the detection point under the current detection cycle based on the historical detection data, and to obtain the inherent frequency deviation of the detection point according to the predicted inherent frequency characteristics and the inherent frequency characteristics. The safety detection module is used to determine the detection results of the detection points based on the anomaly index and the inherent frequency deviation, and to determine the safety detection results of the wind turbine based on the detection results of each detection point.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

Images