Fan blade identification data processing method and system

Abstract

The invention provides a fan blade identification data processing method and system. According to the method, vibration monitoring data and environment monitoring data of the fan blade are obtained, then the vibration monitoring data are corrected according to the environment monitoring data to generate vibration data to be recognized, then the structural safety state of the fan blade is determined according to the vibration data to be recognized, and the structural safety state of the fan blade is recognized through the correction process of the environment monitoring data. The influence of environmental factors on the vibration data is effectively reduced, and the accuracy of using the vibration data to be recognized for recognizing the structural defects of the fan blade is improved.

Description

Technical Field

[0001] The present application relates to data processing technology, and in particular to a method and system for processing wind turbine blade identification data. Background Art

[0002] With the continuous growth of global energy demand and increasing awareness of environmental protection, wind energy, as a clean, renewable energy source, has garnered widespread attention and application. As one of the primary methods for utilizing wind energy, wind power generation is continuously improving in terms of technology and efficiency. However, within wind power systems, turbine blades are key components, and their operating status directly impacts the performance and safety of the entire system.

[0003] During operation, wind turbine blades are affected by a variety of factors, including environmental factors such as wind speed, direction, temperature, and humidity, as well as internal factors such as the blade's structural characteristics, material aging, and fatigue damage. These factors can cause wind turbine blade vibration, and the intensity and characteristics of this vibration are closely related to the blade's structural safety status. Therefore, monitoring and analyzing wind turbine blade vibration data can effectively assess the blade's structural safety status, promptly identify potential defects and faults, and provide a critical basis for wind turbine equipment maintenance and management.

[0004] However, traditional methods for processing wind turbine blade vibration data often overlook the impact of environmental factors on vibration data. Under complex and changing environmental conditions, changes in environmental factors can lead to fluctuations and interference in vibration data, reducing the accuracy of vibration data in identifying defects in wind turbine blades. For example, a sudden change in wind speed can cause significant changes in vibration data, but these changes do not directly reflect the structural safety status of the blades, but are instead caused by external environmental factors. Therefore, without proper correction and processing of the vibration data, it is difficult to accurately extract the blade's own vibration information, which in turn affects the precise identification of the blade's structural safety status. Summary of the Invention

[0005] The present application provides a method and system for processing wind turbine blade identification data, which are used to effectively reduce the impact of environmental factors on vibration data, thereby improving the accuracy of the vibration data to be identified in identifying structural defects of the wind turbine blade itself.

[0006] In a first aspect, the present application provides a method for processing wind turbine blade identification data, comprising:

[0007] Obtain vibration monitoring data of wind turbine blades and environmental monitoring data;

[0008] Correcting the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified;

[0009] The structural safety status of the wind turbine blade is determined according to the vibration data to be identified.

[0010] In the above scheme, after acquiring vibration monitoring data and environmental monitoring data, the environmental monitoring data is used to correct the vibration monitoring data to generate the vibration data to be identified. This environmental monitoring data correction process effectively reduces the impact of environmental factors on the vibration data. Specifically, the extraction of vibration information from the wind turbine blade's structure and operation effectively improves the accuracy of the vibration data to be identified for identifying defects in the wind turbine blade itself. The corrected vibration data to be identified contains more accurate information about the wind turbine blade's vibration, enabling precise identification of the wind turbine blade's structural safety status.

[0011] Optionally, the environmental monitoring data includes: environmental wind speed data.

[0012] In the above scheme, ambient wind speed data is one of the key influencing parameters during the operation of the wind turbine. By incorporating ambient wind speed data into the wind turbine blade identification data processing process, the impact of blades on vibration under different wind speed conditions can be analyzed more accurately, thereby improving the accuracy of blade structural status identification.

[0013] Optionally, the modifying the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified includes:

[0014] Determine a correction coefficient from a preset data correction table according to the ambient wind speed data, wherein the preset data correction table is used to establish a mapping relationship between the ambient wind speed data and the correction coefficient;

[0015] The vibration monitoring data is corrected according to the correction coefficient to generate the vibration data to be identified.

[0016] In this solution, a mapping relationship between ambient wind speed data and correction coefficients is established by introducing a preset data correction table. This mapping relationship ensures accurate determination of the corresponding correction coefficients under varying wind speed conditions, based on experimental data and statistical analysis. By dynamically adjusting the correction coefficients based on ambient wind speed data, the impact of environmental factors on vibration data is effectively reduced, thereby enhancing the reliability of subsequent data identification. This helps improve the accuracy and timeliness of structural fault diagnosis for wind turbine blades and reduces misdiagnosis due to environmental factors.

[0017] Optionally, the correction coefficient is used to correct the amplitude in the vibration monitoring data, wherein the wind speed value in the ambient wind speed data is negatively correlated with the value of the correction coefficient.

[0018] In the above scheme, the vibration state of wind turbine blades is an important indicator for assessing their structural integrity and performance. However, changes in ambient wind speed can directly affect the vibration characteristics of the blades, leading to unnecessary fluctuations in the monitoring data. By introducing a correction factor and establishing a negative correlation with the ambient wind speed data—that is, the correction factor decreases as wind speed increases, and vice versa—the effect of wind speed on vibration amplitude is effectively quantified, achieving correction of the original vibration data. It is worth noting that fluctuations in ambient wind speed often lead to a large amount of noise in the vibration monitoring data, affecting the accuracy and reliability of data analysis. By dynamically adjusting the amplitude value, the vibration data can more accurately reflect the actual operating state of the blades, even in environments with variable wind speeds, thereby significantly improving data quality and analysis accuracy. Based on the corrected vibration data, a more accurate blade health monitoring model can be constructed to promptly identify potential structural problems such as fatigue and cracks.

[0019] Optionally, the preset data correction table includes a characteristic data mapping interval, and the wind speed value in the characteristic data mapping interval corresponds to a preset fixed correction coefficient.

[0020] In the above scheme, based on the experimental calibration of the resonant wind speed and the introduction of a preset fixed correction coefficient, by accurately matching the resonant wind speed, the special wind speed conditions that cause wind turbine blade resonance can be more effectively identified, thereby providing more reliable data support for risk assessment. This helps to timely discover and avoid potential safety hazards and improve the safety and stability of wind turbine operation.

[0021] Optionally, the preset data correction table includes a first data mapping interval, a second data mapping interval, and a third data mapping interval, the wind speed value interval in the second data mapping interval is between the maximum wind speed value in the first data mapping interval and the minimum wind speed value in the third data mapping interval, and the second data mapping interval is the characteristic data mapping interval;

[0022] The wind speed values ​​in the first data mapping interval and the third data mapping interval are negatively correlated with the value of the correction coefficient;

[0023] In the second data mapping interval, the wind speed value in the ambient wind speed data corresponds to a preset fixed correction coefficient.

[0024] In the above scheme, wind speed data is divided into three mapping intervals: a first data mapping interval, a second data mapping interval (characteristic data mapping interval), and a third data mapping interval. This interval division is designed based on the characteristics of wind speed's impact on wind turbine blade identification. It enables differentiated correction strategies to be adopted for different wind speed ranges, thereby improving the relevance and accuracy of data processing. Within the first and third data mapping intervals, the wind speed values ​​and the correction coefficient values ​​are set to have a negative correlation. This means that as wind speed increases (or decreases), the correction coefficient will decrease (or increase) accordingly. By adjusting the correction coefficient, this effect is mitigated, ensuring that the processed data truly reflects the actual structural state of the wind turbine blades. Furthermore, the second data mapping interval, serving as a characteristic data mapping interval, lies between the wind speed values ​​in the first and third intervals. Within this interval, the wind speed values ​​in the ambient wind speed data correspond to a preset fixed correction coefficient. This fixed correction strategy can more effectively identify the special wind speed conditions that trigger wind turbine blade resonance, thereby providing more reliable data support for risk assessment.

[0025] Optionally, the modifying the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified includes:

[0026] The vibration monitoring data is corrected according to the ambient wind speed data and a preset correction function to generate vibration data to be identified, wherein the preset correction function is a function used to determine a dynamic correction coefficient based on the wind speed value in the ambient wind speed data, and the correction function is used to correct the amplitude in the vibration monitoring data.

[0027] In the above scheme, wind speed is a crucial external factor during wind turbine blade operation, directly affecting the blade's vibration characteristics. This scheme employs a preset correction function that determines a dynamic correction coefficient based on the wind speed value in the ambient wind speed data. The introduction of this function enables dynamic adjustment of vibration monitoring data, enabling it to better reflect the actual vibration state under varying wind speed conditions. The core function of this correction function is to correct the amplitude in the vibration monitoring data. Amplitude is a key indicator in vibration monitoring data, directly reflecting the vibration intensity of the wind turbine blade. Variations in wind speed will also affect the blade's amplitude. Using this correction function, the monitored amplitude is adjusted accordingly based on the current wind speed value, eliminating interference caused by wind speed fluctuations and ensuring that the corrected amplitude data more closely reflects the blade's actual vibration conditions. It is worth noting that this amplitude correction approach enables rapid fault diagnosis, significantly improving diagnostic efficiency compared to traditional filtering algorithms. It is particularly suitable for preliminary fault diagnosis and screening in large-scale wind power plants.

[0028] In a second aspect, the present application provides a wind turbine blade identification data processing system, comprising:

[0029] An acquisition module is used to acquire vibration monitoring data of wind turbine blades and environmental monitoring data;

[0030] a processing module, configured to modify the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified;

[0031] The processing module is further configured to determine the structural safety status of the wind turbine blade based on the vibration data to be identified.

[0032] In a third aspect, the present application provides an electronic device, comprising:

[0033] processor; and,

[0034] a memory for storing executable instructions of the processor;

[0035] The processor is configured to perform any possible method described in the first aspect by executing the executable instructions.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.

[0037] The wind blade identification data processing method and system provided in the present application obtain vibration monitoring data and environmental monitoring data of the wind blade, then correct the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified, and then determine the structural safety status of the wind blade based on the vibration data to be identified. Through this environmental monitoring data correction process, the influence of environmental factors on the vibration data is effectively reduced, and the accuracy of the vibration data to be identified in identifying the structural defects of the wind blade itself is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0039] Figure 1 is a flow chart of a method for processing wind turbine blade identification data according to an exemplary embodiment of the present application;

[0040] Figure 2 is a flow chart of a method for processing wind turbine blade identification data according to another exemplary embodiment of the present application;

[0041] Figure 31 is a schematic structural diagram of a wind turbine blade identification data processing system according to an exemplary embodiment of the present application;

[0042] Figure 4 It is a structural diagram of an electronic device according to an exemplary embodiment of the present application.

[0043] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0044] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0045] To address the above-mentioned issues, the embodiments provided in this application aim to obtain vibration monitoring data and environmental monitoring data of wind turbine blades, and use the environmental monitoring data to correct the vibration monitoring data to generate vibration data to be identified, thereby accurately determining the structural safety status of the wind turbine blades. This effectively reduces the impact of environmental factors on the vibration data and improves the accuracy of the vibration data to be identified in identifying structural defects of the wind turbine blades themselves. The specific inventive concept is embodied in the following aspects:

[0046] Data Acquisition: Vibration sensors are installed on wind turbine blades to collect real-time vibration signals during operation. Vibration sensors can be accelerometers, displacement sensors, or velocity sensors. The collected vibration data includes key information such as timestamps, vibration amplitude, and vibration frequency. Environmental monitoring equipment, such as anemometers, wind vanes, thermometers, and hygrometers, are installed near wind turbines or on wind turbine blades to collect real-time data on environmental factors that affect the vibration characteristics of wind turbine blades, including wind speed, wind direction, temperature, and humidity. Ensure that the environmental monitoring data includes a timestamp to facilitate synchronization with the vibration monitoring data.

[0047] Data Correction: Based on historical data and statistical analysis methods, a model is constructed to model the impact of environmental factors on wind turbine blade vibration data. This model is used to correct the vibration monitoring data based on environmental monitoring data to eliminate interference from environmental factors. A correction coefficient can be determined from a preset data correction table based on ambient wind speed data. The preset data correction table establishes a mapping relationship between ambient wind speed data and the correction coefficient. The correction coefficient is used to correct the amplitude in the vibration monitoring data, and the wind speed values ​​in the ambient wind speed data are negatively correlated with the correction coefficient values. The preset data correction table also includes a characteristic data mapping interval, in which wind speed values ​​within this interval are mapped to preset fixed correction coefficients to more effectively identify specific wind speed conditions that trigger wind turbine blade resonance. Vibration monitoring data can also be corrected based on ambient wind speed data and a preset correction function. The preset correction function is used to determine a dynamic correction coefficient based on the wind speed values ​​in the ambient wind speed data. The correction function is used to correct the amplitude in the vibration monitoring data. The dynamic correction function can be a preset fitting function, such as a quadratic fitting function, which fits the operating amplitude in the vibration operating condition data to the simulated amplitude in the simulated operating condition data.

[0048] Condition Assessment: Feature extraction is performed on the vibration data to be identified, identifying key features that reflect the structural safety status of the wind turbine blades, such as the rate of change of vibration amplitude and vibration frequency distribution. A wind turbine blade structural safety status assessment model is constructed based on historical data and machine learning algorithms. This model can classify or score the structural safety status of the wind turbine blades based on the extracted feature data. The extracted feature data is input into the constructed safety status assessment model to obtain the structural safety status assessment results of the wind turbine blades. Based on the assessment results, the wind turbine blades are classified into different states, such as normal, warning, and fault, so that appropriate maintenance measures can be taken.

[0049] Figure 1 FIG. 1 is a flow chart of a method for processing wind turbine blade identification data according to an exemplary embodiment of the present application. Figure 1 As shown, the method provided in this embodiment includes:

[0050] S101. Obtain vibration monitoring data of wind turbine blades and environmental monitoring data.

[0051] Specifically, vibration sensors can be installed on wind turbine blades to collect real-time vibration signals during operation. These sensors can be accelerometers, displacement sensors, or velocity sensors, depending on the application requirements and cost considerations. The collected vibration data should include key information such as timestamps, vibration amplitude, and vibration frequency.

[0052] Additionally, environmental monitoring equipment, such as anemometers, wind vanes, thermometers, and hygrometers, can be installed near wind turbines or on wind turbine blades. These devices can collect real-time data on environmental factors that affect the vibration characteristics of wind turbine blades, including but not limited to wind speed, direction, temperature, and humidity. Environmental monitoring data should also include timestamps to facilitate synchronization with vibration monitoring data.

[0053] S102: Correct the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified.

[0054] Specifically, the vibration monitoring data and environmental monitoring data can be preprocessed, including data cleaning (removing outliers, missing values, etc.), data smoothing (reducing noise interference) and data standardization (unifying data format and dimension) and other steps.

[0055] Based on historical data and statistical analysis methods, a model is constructed to measure the impact of environmental factors on wind turbine blade vibration data. This model should be able to reflect the degree and patterns of influence of different environmental factors (such as wind speed, direction, temperature, and humidity) on vibration data. This model can be constructed using machine learning algorithms such as multivariate linear regression, neural networks, and support vector machines.

[0056] The constructed environmental factor correction model is then used to correct the real-time vibration monitoring data to eliminate the interference of environmental factors on the vibration data. The corrected vibration data is the vibration data to be identified, which more accurately reflects the actual vibration state of the wind turbine blades.

[0057] S103: Determine the structural safety status of the wind turbine blades according to the vibration data to be identified.

[0058] Specifically, feature extraction is performed on the vibration data to be identified, and key features that can reflect the safety status of the wind turbine blade structure are extracted, such as the vibration amplitude change rate, vibration frequency distribution, etc.

[0059] Next, a wind turbine blade structural safety status assessment model can be constructed based on historical data and machine learning algorithms. This model should be able to classify or score the structural safety status of wind turbine blades based on the extracted feature data. Specific construction methods can use algorithms such as decision trees, random forests, and deep learning.

[0060] The extracted feature data is fed into the constructed safety status assessment model to obtain the structural safety status assessment results of the wind turbine blades. Based on the assessment results, the wind turbine blades can be managed in a hierarchical manner, such as normal, warning, and fault status, so that appropriate maintenance measures can be taken.

[0061] In this embodiment, the vibration monitoring data and environmental monitoring data of the wind turbine blades are obtained, and then the vibration monitoring data is corrected according to the environmental monitoring data to generate vibration data to be identified, and then the structural safety status of the wind turbine blades is determined based on the vibration data to be identified. Through this correction process of the environmental monitoring data, the influence of environmental factors on the vibration data is effectively reduced, and the accuracy of the vibration data to be identified in identifying the structural defects of the wind turbine blades themselves is improved.

[0062] Figure 2 FIG. 1 is a flow chart of a method for processing wind turbine blade identification data according to another exemplary embodiment of the present application. Figure 2 As shown, the wind turbine blade identification data processing method provided in this embodiment includes:

[0063] S201. Obtain vibration monitoring data and environmental monitoring data of wind turbine blades.

[0064] In this step, single-point vibration data can be acquired by vibration sensors installed at various monitoring positions on the wind turbine blade to form a single-point vibration data set. A characteristic vibration data set is then generated based on the single-point vibration data set, wherein the characteristic vibration data in the characteristic vibration data set is the processed data of the single-point vibration data set in the time domain. Vibration monitoring data is then generated based on the single-point vibration data set and the characteristic vibration data set. It is worth noting that the various monitoring positions can be arranged sequentially along the extension direction of the wind turbine blade, with the extension direction extending from the root of the wind turbine blade to the tip.

[0065] In the above scheme, first, single-point vibration data is obtained by using vibration sensors installed at various monitoring positions of the wind turbine blades to form a single-point vibration data set. This step is the basis for data acquisition. The vibration sensor can accurately capture the vibration conditions of the wind turbine blades at different positions and provide raw data for subsequent data processing. Secondly, a characteristic vibration data set is generated based on the single-point vibration data set. The characteristic vibration data in the characteristic vibration data set is the processed data of the single-point vibration data set in the time domain, which can be aligned in the time dimension. Thirdly, vibration monitoring data is generated based on the single-point vibration data set and the characteristic vibration data set. This step organically combines the single-point vibration data and the characteristic vibration data to form comprehensive and accurate vibration monitoring data. These data not only include the vibration conditions of the wind turbine blades at various positions, but also include characteristic vibration data, which provide comprehensive data support for the subsequent wind turbine blade status assessment.

[0066] Furthermore, monitoring locations can be arranged sequentially along the extension direction of the wind turbine blade, extending from the root to the tip. This arrangement ensures that the complete vibration of the wind turbine blade from root to tip is monitored, avoiding data loss caused by insufficient monitoring locations. At the same time, this arrangement can better reflect the vibration differences at different locations on the wind turbine blade, providing more detailed data support for subsequent condition assessment.

[0067] The generation of the above-mentioned characteristic vibration data set can be carried out by extracting the single-point vibration data of each monitoring position at each time node in the single-point vibration data set, and generating vibration data along the extension direction of the wind turbine blade with the corresponding time node as the identifier, wherein the characteristic vibration data set includes the vibration data corresponding to each time node.

[0068] First, single-point vibration data must be acquired from various monitoring locations on the wind turbine blades. These monitoring locations are typically distributed along the blade's extension to ensure comprehensive coverage of blade vibration. Vibration sensors installed on the blades can be used to collect single-point vibration data from each monitoring location in real time or periodically. This data may include information such as vibration amplitude, frequency, and phase. The collected single-point vibration data is stored in a database for subsequent processing and analysis.

[0069] In order to generate vibration data along the extension direction of the wind turbine blades, a series of time nodes need to be determined. These time nodes can be equally spaced or set according to actual needs. Specifically, a series of time nodes can be set based on the needs of data analysis and the vibration characteristics of the wind turbine blades. For example, a time node can be set every second, or a time node corresponding to the rotation cycle can be set according to the rotation speed of the blades. It is also necessary to ensure that the single-point vibration data of all monitoring locations are synchronized according to the same time node so that they can be accurately combined later.

[0070] For each time point, the corresponding single-point vibration data must be extracted from each monitoring location. Based on the set time point, the single-point vibration data for each monitoring location at that time point can be extracted from the database. The extracted single-point vibration data is verified to ensure data integrity and accuracy. Any missing or abnormal data requires appropriate processing or supplementation.

[0071] Next, the extracted single-point vibration data at each time point is combined along the blade extension direction to generate vibration data along the blade extension direction. For each time point, the single-point vibration data from each monitoring location is sorted and combined along the blade extension direction to form a vibration data curve along the blade extension direction. Each vibration data curve is assigned a unique timestamp or number based on the time point, allowing for accurate identification and differentiation of different vibration data curves.

[0072] Finally, the vibration data corresponding to all time nodes are combined to form a characteristic vibration data set. This can be accomplished by arranging and combining the vibration data curves for all time nodes in chronological order to construct a characteristic vibration data set containing the vibration data for each time node. This characteristic vibration data set is stored in a database and effectively managed and maintained to facilitate subsequent data analysis and processing.

[0073] In the above scheme, single-point vibration data is extracted from the single-point vibration data set for each time node and monitoring position. Ensure that the data of all monitoring positions at each time node are extracted completely and accurately. Using the corresponding time node as an identifier, the extracted single-point vibration data are combined according to the extension direction of the wind turbine blade. Vibration data along the extension direction of the blade are generated, which reflects the overall vibration condition of the blade at this time node. The spatial distribution information of the blade vibration is provided to characterize the vibration characteristics of the blade at different positions. The vibration data corresponding to all time nodes are combined together to form a characteristic vibration data set. The characteristic vibration data set contains the vibration information of the blade at each time node and is a comprehensive description of the vibration state of the blade. It provides comprehensive information on the time and space domains of the blade vibration, providing comprehensive data support for blade status monitoring and fault diagnosis.

[0074] S202: Correct the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified.

[0075] In one possible implementation, a correction coefficient may be determined from a preset data correction table based on the ambient wind speed data, wherein the preset data correction table is used to establish a mapping relationship between the ambient wind speed data and the correction coefficient. The vibration monitoring data is corrected based on the correction coefficient to generate the vibration data to be identified.

[0076] Specifically, the above-mentioned preset data correction table establishes a mapping relationship between the ambient wind speed data and the correction coefficient. This table is based on a large amount of experimental data and statistical analysis, and is intended to reflect the degree of influence on the wind turbine blade vibration data under different wind speed conditions. The correction table contains multiple data mapping intervals, each interval corresponds to a specific wind speed range and a corresponding correction coefficient. These intervals can be divided based on the influence of wind speed on the vibration characteristics of the wind turbine blades to ensure the accuracy and effectiveness of the correction. When real-time ambient wind speed data is obtained, the system will look up the correction coefficient corresponding to the wind speed value in the preset data correction table. The correction coefficient is used to quantify the degree of influence of wind speed on the amplitude in the vibration monitoring data. In the correction table, the wind speed value and the correction coefficient value usually show a negative correlation, that is, the greater the wind speed, the smaller the correction coefficient, to reflect the corresponding change in the blade vibration amplitude when the wind speed increases.

[0077] Once the correction factor is determined, the amplitude of the vibration monitoring data is corrected using this factor. This correction process typically involves multiplying the original amplitude by the correction factor to obtain the corrected amplitude. This step aims to eliminate the influence of ambient wind speed on the vibration monitoring data, ensuring that the corrected data better reflects the vibration characteristics of the wind turbine blades.

[0078] After amplitude correction, the resulting vibration data is identified. Compared to the original vibration monitoring data, this data more accurately reflects the actual vibration state of the wind turbine blades under different environmental conditions. This data will serve as input for subsequent condition assessments to determine the structural safety or operational status of the wind turbine blades.

[0079] Furthermore, a correction factor is used to correct the amplitude in the vibration monitoring data. The wind speed value in the ambient wind speed data is negatively correlated with the correction factor. The vibration state of wind turbine blades is an important indicator for assessing their structural integrity and performance. However, changes in ambient wind speed can directly affect the blade's vibration characteristics, leading to unnecessary fluctuations in the monitoring data. By introducing a correction factor and establishing a negative correlation with the ambient wind speed data—that is, the correction factor decreases as wind speed increases, and vice versa—this effectively quantifies the impact of wind speed on vibration amplitude and achieves correction of the original vibration data. It is worth noting that fluctuations in ambient wind speed often lead to significant noise in vibration monitoring data, affecting the accuracy and reliability of data analysis. By dynamically adjusting the amplitude value, the vibration data more accurately reflects the actual operating state of the blade, even in environments with fluctuating wind speeds, significantly improving data quality and analysis accuracy. Based on the corrected vibration data, a more accurate blade health monitoring model can be constructed to promptly identify potential structural issues such as fatigue and cracks.

[0080] Furthermore, the preset data correction table includes characteristic data mapping intervals, where wind speed values ​​within these intervals correspond to preset fixed correction coefficients. By accurately matching resonant wind speeds with experimentally calibrated resonant wind speeds, the introduction of preset fixed correction coefficients can more effectively identify specific wind speed conditions that trigger wind turbine blade resonance, providing more reliable data support for risk assessment. This helps to promptly identify and avoid potential safety hazards, thereby improving the safety and stability of wind turbine operations.

[0081] Furthermore, the preset data correction table includes a first data mapping interval, a second data mapping interval, and a third data mapping interval. The wind speed value interval in the second data mapping interval is between the maximum wind speed value in the first data mapping interval and the minimum wind speed value in the third data mapping interval. The second data mapping interval is a characteristic data mapping interval. Among them, the wind speed values ​​in the first data mapping interval and the third data mapping interval are negatively correlated with the values ​​of the correction coefficient. In the second data mapping interval, the wind speed values ​​in the ambient wind speed data correspond to the preset fixed correction coefficient. Among them, the wind speed data is divided into three mapping intervals: the first data mapping interval, the second data mapping interval (characteristic data mapping interval), and the third data mapping interval. This interval division method is designed based on the characteristics of the influence of wind speed on wind turbine blade identification, and can adopt differentiated correction strategies for different wind speed ranges, thereby improving the pertinence and accuracy of data processing. Among them, in the first data mapping interval and the third data mapping interval, the wind speed values ​​and the correction coefficient values ​​are set to be negatively correlated. This means that as the wind speed increases (or decreases), the correction coefficient will decrease (or increase) accordingly. By adjusting the correction coefficient to weaken this effect, it is ensured that the processed data can truly reflect the actual structural state of the wind turbine blades. In addition, the second data mapping interval, as a characteristic data mapping interval, is located between the wind speed values ​​of the first and third intervals. Within this interval, the wind speed value in the ambient wind speed data corresponds to a preset fixed correction coefficient. This fixed correction strategy can more effectively identify special wind speed conditions that cause wind turbine blade resonance, thereby providing more reliable data support for risk assessment.

[0082] Furthermore, the preset fixed correction coefficient is greater than the maximum correction coefficient in the first data mapping interval and the third data mapping interval, and the wind speed value in the second data mapping interval is determined based on the experimentally calibrated resonant wind speed of the wind turbine blade.

[0083] Specifically, wind turbine blades are calibrated experimentally to determine their resonance characteristics under different wind speed conditions. This step is typically performed in a laboratory or actual wind farm environment. Through simulation or actual measurement, the vibration response data of the wind turbine blades at different wind speeds is obtained to identify the specific wind speed conditions that cause the wind turbine blades to resonate, i.e., the resonant wind speed.

[0084] Based on the results of experimental calibration, combined with statistical analysis and engineering experience, a preset fixed correction coefficient is determined. This coefficient is set to be greater than the maximum correction coefficient in the first and third data mapping intervals. The selection of the preset fixed correction coefficient must take into account the specific vibration characteristics of the blade at resonant wind speeds to ensure more accurate correction of vibration monitoring data within this wind speed range. A larger correction coefficient can more effectively reduce the impact of wind speed on vibration data, especially when the blade is near resonance.

[0085] According to the experimentally calibrated resonant wind speed, the wind speed data is divided into multiple mapping intervals, including the first data mapping interval, the second data mapping interval (characteristic data mapping interval) and the third data mapping interval. The wind speed value interval of the second data mapping interval is determined based on the resonant wind speed. Usually, this interval will include the resonant wind speed and a wind speed range near it to ensure that the vibration characteristics of the blade in the resonant state can be accurately captured. Determine the upper and lower bounds of the second data mapping interval. The selection of upper and lower bounds requires comprehensive consideration of the resonant characteristics of the blades, the continuity of wind speed changes and the actual needs of data processing. In actual applications, these boundaries may be fine-tuned according to the specific wind turbine model, blade design and operating environment to ensure the accuracy and effectiveness of the correction process.

[0086] When real-time ambient wind speed data is acquired, the system first determines which data mapping interval the wind speed data belongs to. If the wind speed data falls within the second data mapping interval, the vibration monitoring data is directly corrected by applying a preset fixed correction factor. This fixed correction factor is used to correct the amplitude of the vibration monitoring data to eliminate the influence of ambient wind speed on the vibration data. This corrected amplitude data, combined with the corrected data from other non-resonant wind speed intervals, forms the vibration data to be identified, which is used for subsequent wind turbine blade condition assessment.

[0087] This correction process is typically implemented through software algorithms within the wind turbine blade identification data processing system. The system first acquires vibration and environmental monitoring data, then performs correction calculations based on a preset data correction table and experimentally calibrated resonant wind speeds. In practical applications, this correction process requires verification and optimization. By comparing the corrected vibration data with actual operating data, the accuracy and effectiveness of the corrected vibration data in reflecting the blade's true vibration state are evaluated. Based on the verification results, the preset fixed correction coefficient and the second data mapping interval settings are fine-tuned to further improve the accuracy and reliability of the correction process.

[0088] In another possible implementation, vibration monitoring data can be corrected based on ambient wind speed data and a preset correction function to generate vibration data to be identified. The preset correction function is used to determine a dynamic correction coefficient based on the wind speed value in the ambient wind speed data. This correction function is used to correct the amplitude in the vibration monitoring data. Wind speed is a crucial external factor in the operation of wind turbine blades, directly affecting their vibration characteristics. The above solution utilizes a preset correction function that determines a dynamic correction coefficient based on the wind speed value in the ambient wind speed data. The introduction of this function enables dynamic adjustment of the vibration monitoring data, enabling it to better reflect the actual vibration state under varying wind speed conditions. The core function of the correction function is to correct the amplitude in the vibration monitoring data. Amplitude is a key indicator in vibration monitoring data, directly reflecting the vibration intensity of the wind turbine blades. Changes in wind speed will also affect the blade amplitude. Using this correction function, the monitored amplitude can be adjusted accordingly based on the current wind speed value, eliminating interference caused by wind speed changes and ensuring that the corrected amplitude data more closely reflects the actual vibration state of the blades. It is worth noting that by correcting the amplitude, rapid fault diagnosis can be achieved. Compared with traditional filtering algorithms, the efficiency of diagnosis is greatly improved, and it is especially suitable for preliminary diagnosis and screening of faults in large-scale wind power plants.

[0089] It is worth noting that the above-mentioned dynamic correction function can be a preset fitting function, for example, a quadratic fitting function, which is used to fit the operating amplitude in the vibration operating condition data and the simulated amplitude in the simulation operating condition data, wherein the vibration operating condition data is the actual amplitude measurement value based on different environmental wind speeds, and the simulation operating condition data is the simulation amplitude theoretical value based on a windless environment, wherein the motion parameters of the wind turbine blades corresponding to the vibration operating condition data and the simulation operating condition data are the same.

[0090] A preset fitting function is used to match the actual measured vibration amplitudes with the simulated amplitudes in a windless environment. This matching is not a simple numerical correspondence, but rather a fit based on the trends and patterns of amplitude changes with wind speed. During the fitting process, the preset fitting function also takes into account the complex effects of wind speed on amplitude, such as nonlinear relationships and hysteresis effects, to ensure the accuracy and reliability of the fitting results.

[0091] It's worth noting that the motion parameters of the wind turbine blades corresponding to the vibration data and the simulation data are identical. This means that when performing amplitude fitting, we compare and analyze based on the same motion parameters. This setting eliminates the amplitude variation interference caused by differences in motion parameters, allowing the fitting results to more purely reflect the impact of wind speed on amplitude.

[0092] Using a preset fitting function as a dynamic correction function can significantly improve the accuracy of corrections to vibration monitoring data. Because the fitting function is based on a large amount of experimental data and theoretical analysis, it can more accurately describe the variation of amplitude with wind speed. In practical applications, when new vibration monitoring data is obtained, the corrected amplitude value can be quickly calculated using the preset fitting function, thereby obtaining more accurate vibration data to be identified. The introduction of the preset fitting function enhances the adaptability and robustness of the wind turbine blade identification data processing system. Regardless of how the ambient wind speed changes, the system can effectively correct the vibration data through the fitting function. This adaptability enables the system to operate stably in different wind field environments, providing reliable data support for the status assessment of wind turbine blades.

[0093] S203 : Determine a first state characteristic value of the wind turbine blade according to a set of single-point vibration data to be identified in the vibration data to be identified.

[0094] Specifically, the first state characteristic value of the wind blade is determined based on the single-point vibration data set to be identified in the vibration data to be identified, wherein the first state characteristic value is associated with the maximum amplitude of each monitoring point on the wind blade, and the single-point vibration data set to be identified is data corrected based on the single-point vibration data set.

[0095] First, a set of single-point vibration data to be identified is extracted from the corrected vibration data to be identified. This data is based on the original single-point vibration data set, which has been corrected to eliminate the influence of factors such as ambient wind speed and more accurately reflects the vibration conditions at each monitoring point on the wind turbine blade.

[0096] For each monitoring point in the single-point vibration data set to be identified, its maximum amplitude over a period of time is calculated. This maximum amplitude is a key indicator for evaluating the vibration intensity of the blade at that monitoring point. Based on the maximum amplitude of all monitoring points, a comprehensive indicator is calculated as the first state eigenvalue. This eigenvalue can be the average, maximum, or other statistical value of the maximum amplitude. The specific choice depends on the structural characteristics of the blade and the evaluation requirements. The first state eigenvalue reflects the maximum intensity of vibration at each monitoring point on the blade and is one of the important indicators for evaluating the safety status of the blade structure.

[0097] S204 : Determine a second state characteristic value of the wind turbine blade according to a set of characteristic vibration data to be identified in the vibration data to be identified.

[0098] Specifically, the second state characteristic value of the wind blade is determined based on the characteristic vibration data set to be identified in the vibration data to be identified, wherein the second state characteristic value is associated with the overall vibration energy of the wind blade, and the characteristic vibration data set to be identified is data corrected based on the characteristic vibration data set.

[0099] A set of characteristic vibration data to be identified is extracted from the corrected vibration data to be identified. These data are the result of correction based on the original characteristic vibration data set, and more accurately reflect the overall vibration characteristics of the wind turbine blade. Spectral analysis or time domain analysis is performed on the characteristic vibration data set to be identified, and the vibration energy of the blade in the entire frequency domain or time domain is calculated. This vibration energy is a key indicator for evaluating the overall vibration intensity of the blade. Based on the calculated vibration energy, a comprehensive indicator is determined as the second-state eigenvalue. This eigenvalue can be the total value of the vibration energy, the energy value within a specific frequency band, or other related indicators. The second-state eigenvalue reflects the overall vibration energy of a blade and is another important indicator for evaluating the structural safety status of each blade.

[0100] In the above scheme, the interference of external factors (such as wind speed) on the vibration data is eliminated through the revised single-point vibration data set, so that the first state characteristic value can more accurately reflect the actual vibration intensity of each monitoring point on the blade. The first state characteristic value, as a comprehensive indicator of the local vibration intensity of the blade, provides an important basis for evaluating the structural safety status of the blade. The revised characteristic vibration data set further eliminates the interference of external factors on the vibration data, so that the second state characteristic value can more accurately reflect the overall vibration intensity of the blade. The second state characteristic value, as a comprehensive indicator of the overall vibration intensity of the blade, complements the first state characteristic value and provides more comprehensive information for a comprehensive assessment of the structural safety status of the blade. By comprehensively analyzing the first state characteristic value and the second state characteristic value, the structural safety status of the blade can be more comprehensively assessed, which improves the accuracy and reliability of the assessment. The grading of the assessment results provides clear guidance for operation and maintenance personnel, which helps to take necessary maintenance and management measures in a timely manner to ensure the safe operation of the wind turbine.

[0101] Furthermore, the second state eigenvalue can be determined by performing frequency domain analysis on the set of characteristic vibration data to be identified to determine the amplitude distribution at different frequencies. The energy spectrum under each different amplitude distribution is calculated to generate an energy spectrum set, which is used to characterize the amplitude energy at the corresponding frequency. A target energy range is determined based on the energy spectrum set, and the target energy range includes at least the energy spectrum with the highest amplitude energy in the energy spectrum set. The second state eigenvalue is determined based on the target energy range.

[0102] It's worth noting that the characteristic vibration data set to be identified is converted from the time domain to the frequency domain, and the amplitude distribution at different frequencies is obtained through Fourier transform or other frequency domain analysis methods. Frequency domain analysis can reveal hidden frequency components in the vibration signal, which are often closely related to the blade's natural frequency, external excitation frequency, and other factors. Frequency domain analysis clearly demonstrates the distribution of the vibration signal in the frequency domain, providing a foundation for subsequent energy spectrum calculations.

[0103] After obtaining the amplitude distribution, the energy spectrum for each different amplitude distribution is calculated. The energy spectrum is a function of the square of the amplitude and the frequency, representing the amplitude energy at the corresponding frequency. The energy spectrum is calculated for the amplitude distribution at all frequencies to generate an energy spectrum set. The energy spectrum intuitively reflects the energy distribution of the vibration signal in the frequency domain, providing an important basis for evaluating the overall vibration intensity of the blade. The energy spectrum set contains information on the blade's vibration energy at different frequencies, providing comprehensive data support for the subsequent determination of the target energy range.

[0104] The energy spectrum set is analyzed to determine the energy spectrum with the highest amplitude energy, along with several adjacent energy spectra, which together constitute the target energy range. The target energy range includes at least the energy spectrum with the highest amplitude energy in the energy spectrum set to ensure that the primary energy components of the blade vibration are captured. By determining the target energy range, the primary energy components of the blade vibration can be focused on, while minor or noise components are ignored, improving the accuracy of feature value extraction. Determining the target energy range helps identify the dominant frequency in blade vibration, providing key information for blade structural safety assessment.

[0105] Within the target energy range, the energy spectrum is further analyzed and processed, such as by calculating the average, maximum, or weighted summation, to determine the second-state eigenvalue. This second-state eigenvalue characterizes the blade's overall vibration energy level and is a key indicator for assessing the blade's structural safety. By determining the second-state eigenvalue within the target energy range, the overall vibration energy level of the blade can be more accurately reflected, improving the reliability of the structural safety assessment.

[0106] S205 : Determine the structural safety state of the wind turbine blade according to the first state characteristic value and the second state characteristic value.

[0107] If it is determined that the first state characteristic value is greater than the preset first characteristic threshold and / or the second state characteristic value is greater than the preset second characteristic threshold, it is determined that the structural safety state of the wind turbine blade is an abnormal state.

[0108] The preset first and second characteristic thresholds described above serve as a benchmark for determining the structural safety status of wind turbine blades. The calculated first characteristic value is compared with the preset first characteristic threshold, while the second characteristic value is compared with the preset second characteristic threshold. By setting clear thresholds, an objective and quantitative standard is provided for determining the structural safety status of wind turbine blades.

[0109] When the first state characteristic value exceeds a preset first characteristic threshold and / or the second state characteristic value exceeds a preset second characteristic threshold, the wind turbine blade's structural safety status is determined to be abnormal. Identification of abnormal conditions is based on analysis of blade vibration data and can indicate possible structural damage or performance degradation. Early detection of abnormal conditions can prevent more serious consequences of blade damage, such as turbine downtime and accidents, thereby reducing maintenance costs and operational risks.

[0110] Once the structural safety status of the wind turbine blades is determined to be abnormal, appropriate maintenance measures can be taken immediately, such as shutting down the machine for inspection, repairing or replacing the blades. Through timely maintenance, the wind turbine can be ensured to operate in good condition, improving its safety and reliability.

[0111] Figure 3 FIG. 1 is a schematic diagram of a wind turbine blade identification data processing system according to an exemplary embodiment of the present application. Figure 3 As shown, the wind turbine blade identification data processing system 300 provided in this embodiment includes:

[0112] An acquisition module 310 is used to acquire vibration monitoring data of wind turbine blades and environmental monitoring data;

[0113] The processing module 320 is configured to modify the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified;

[0114] The processing module 320 is further configured to determine the structural safety status of the wind turbine blade according to the vibration data to be identified.

[0115] Figure 4 FIG. 1 is a schematic diagram of the structure of an electronic device according to an exemplary embodiment of the present application. Figure 4 As shown, this embodiment provides an electronic device 400 including: a processor 401 and a memory 402; wherein:

[0116] The memory 402 is used to store computer programs, and the memory may also be a flash memory.

[0117] The processor 401 is configured to execute the execution instructions stored in the memory to implement each step in the above method. For details, please refer to the relevant description in the above method embodiment.

[0118] Optionally, the memory 402 may be independent or integrated with the processor 401 .

[0119] When the memory 402 is a device independent of the processor 401, the electronic device 400 may further include:

[0120] The bus 403 is used to connect the memory 402 and the processor 401 .

[0121] This embodiment further provides a readable storage medium, in which a computer program is stored. When at least one processor of an electronic device executes the computer program, the electronic device executes the methods provided in the various aforementioned embodiments.

[0122] This embodiment further provides a program product, which includes a computer program stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and at least one processor can execute the computer program to cause the electronic device to implement the methods provided in the various embodiments described above.

[0123] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present application that follow the general principles of the present application and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered merely as exemplary, and the true scope and spirit of the present application are indicated by the claims.

[0124] It should be understood that the present application is not limited to the exact structure described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for processing wind turbine blade identification data, characterized in that: include: Obtain vibration monitoring data of wind turbine blades and environmental monitoring data; Correcting the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified; The structural safety status of the wind turbine blade is determined according to the vibration data to be identified.

2. The wind turbine blade identification data processing method according to claim 1, characterized in that: The environmental monitoring data includes: environmental wind speed data.

3. The method for processing wind turbine blade identification data according to claim 2, characterized in that: The step of correcting the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified includes: Determine a correction coefficient from a preset data correction table according to the ambient wind speed data, wherein the preset data correction table is used to establish a mapping relationship between the ambient wind speed data and the correction coefficient; The vibration monitoring data is corrected according to the correction coefficient to generate the vibration data to be identified.

4. The method for processing wind turbine blade identification data according to claim 3, characterized in that: The correction coefficient is used to correct the amplitude in the vibration monitoring data, wherein the wind speed value in the ambient wind speed data is negatively correlated with the value of the correction coefficient.

5. The wind turbine blade identification data processing method according to claim 3, characterized in that: The preset data correction table includes a characteristic data mapping interval, and the wind speed values ​​in the characteristic data mapping interval correspond to preset fixed correction coefficients.

6. The method for processing wind turbine blade identification data according to claim 5, characterized in that: The preset data correction table includes a first data mapping interval, a second data mapping interval, and a third data mapping interval, wherein the wind speed value interval in the second data mapping interval is between the maximum wind speed value in the first data mapping interval and the minimum wind speed value in the third data mapping interval, and the second data mapping interval is the characteristic data mapping interval; The wind speed values ​​in the first data mapping interval and the third data mapping interval are negatively correlated with the value of the correction coefficient; In the second data mapping interval, the wind speed value in the ambient wind speed data corresponds to a preset fixed correction coefficient.

7. The method for processing wind turbine blade identification data according to claim 2, characterized in that: The step of correcting the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified includes: The vibration monitoring data is corrected according to the ambient wind speed data and a preset correction function to generate vibration data to be identified, wherein the preset correction function is a function used to determine a dynamic correction coefficient based on the wind speed value in the ambient wind speed data, and the correction function is used to correct the amplitude in the vibration monitoring data.

8. A wind turbine blade identification data processing system, characterized in that: include: An acquisition module is used to acquire vibration monitoring data of wind turbine blades and environmental monitoring data; a processing module, configured to modify the vibration monitoring data according to the environmental monitoring data to generate vibration data to be identified; The processing module is further configured to determine the structural safety status of the wind turbine blade based on the vibration data to be identified.

9. An electronic device, characterized in that: include: processor; as well as, a memory for storing executable instructions of the processor; The processor is configured to perform the method according to any one of claims 1 to 7 by executing the executable instructions.

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

Images