Fan blade fracture risk assessment method, device, equipment, medium and product

Abstract

The invention relates to the technical field of electronics, and discloses a fan blade fracture risk assessment method, device and equipment, a medium and a product, and the method comprises the steps: determining a stress concentration target position through wind load time sequence data corresponding to different positions in a preset region of a fan blade; determining a brittleness index sequence of the target position according to the stress amplitude change information of the target position, and if one brittleness index value greater than a preset brittleness index threshold exists in the brittleness index sequence, determining a change trend of a material state of the target position based on the brittleness index sequence, and inputting the change trend into a pre-constructed fan blade micro-crack development model to simulate the crack propagation path of the target position to obtain crack simulation data, and evaluating the fracture risk of the fan blade based on the crack simulation data, thereby realizing accurate evaluation of the fracture risk of the fan blade. And the operation safety and reliability of the wind power equipment are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of electronic technology, and in particular to a method, device, equipment, medium and product for assessing the fracture risk of a wind turbine blade. Background Art

[0002] As core components of wind turbine systems, wind turbine blades' operational stability and safety are directly linked to the overall system's performance and lifespan. Blade fracture, particularly under extreme environments and long-term loads, has become a critical challenge impacting the development of the wind power industry. Blade fracture not only leads to equipment downtime and financial losses, but can also cause safety incidents, making effective risk assessment crucial.

[0003] Related technologies generally rely on regular manual inspections and basic vibration monitoring technology to identify blade damage and conduct risk assessments. Manual inspections are limited by labor costs and weather conditions, making continuous monitoring difficult. Traditional vibration monitoring typically compares monitored vibration data with vibration threshold data and assesses wind turbine blade operational risks based on the comparison results, which can easily lead to misjudgments. Therefore, existing wind turbine blade risk assessments have significant deficiencies in real-time and accuracy. Summary of the Invention

[0004] In view of this, the present invention provides a method, device, equipment, medium and product for assessing the fracture risk of wind blades to solve the problem that wind blade risk assessment in related technologies has significant deficiencies in real-time and accuracy.

[0005] In a first aspect, the present invention provides a method for assessing the fracture risk of a wind blade, the method comprising: obtaining wind load time series data corresponding to different positions in a preset area of ​​the wind blade; determining at least one target position among multiple positions based on the wind load time series data corresponding to the different positions, the target position being a stress concentration area in the preset area; determining a brittleness index sequence of the target position based on the stress amplitude change information of the target position, the stress amplitude change information of the target position being determined based on the wind load time series data of the target position; if there is a brittleness index value in the brittleness index sequence that is greater than a preset brittleness index threshold, determining a change trend of the material state of the target position based on the brittleness index sequence; inputting the change trend into a pre-constructed microcrack development model of a wind blade, so that the microcrack development model of the wind blade simulates the crack propagation path of the target position to obtain crack simulation data; and evaluating the fracture risk of the wind blade based on the crack simulation data to obtain an evaluation result.

[0006] The present invention provides a method for assessing the fracture risk of wind turbine blades. The method determines the target position of stress concentration through wind load time series data corresponding to different positions in a preset area of ​​the wind turbine blade, and determines the brittleness index sequence of the target position based on the stress amplitude change information of the target position. If there is a brittleness index value greater than a preset brittleness index threshold in the brittleness index sequence, the change trend of the material state of the target position is determined based on the brittleness index sequence, and the change trend is input into a pre-constructed micro-crack development model of the wind turbine blade to simulate the crack propagation path of the target position to obtain crack simulation data. The fracture risk of the wind turbine blade is assessed based on the crack simulation data, thereby achieving accurate assessment of the fracture risk of the wind turbine blade and effectively improving the safety and reliability of the operation of wind power equipment.

[0007] In an optional embodiment, based on the wind load time series data corresponding to different positions, at least one target position is determined among multiple positions, and the target position is a stress concentration area in a preset area. The step includes: performing Fourier transform on the wind load time series data of each position to obtain wind load spectrum data of the corresponding position; extracting the target frequency component greater than a preset frequency threshold in the wind load spectrum data of each position, and determining the abnormal signal sequence of the corresponding position based on the target frequency component; calculating the stress amplitude change information of the corresponding position based on the abnormal signal sequence of each position; and determining at least one target position among multiple positions based on the stress amplitude change information of each position and the preset stress amplitude threshold.

[0008] In an optional embodiment, the step of evaluating the fracture risk of a wind blade based on crack simulation data includes: obtaining measured crack data at a target position; using principal component analysis to fuse and reduce the crack simulation data and the measured crack data to obtain a principal eigenvector; inputting the principal eigenvector into a pre-constructed risk assessment model so that the risk assessment model outputs a risk value, and the risk assessment model is used to characterize the correlation between the principal eigenvector and the risk value; and evaluating the fracture risk of the wind blade based on the risk value.

[0009] In an optional embodiment, the fracture risk of a wind blade is evaluated based on a risk value, including: if the risk value is greater than a preset risk threshold, obtaining vibration monitoring data and first vibration characteristic data of a target position, the first vibration characteristic data being used to characterize the vibration characteristics of the wind blade during normal operation; processing the vibration monitoring data using a preset feature extraction method to obtain second vibration characteristic data of the target position; calculating the cosine similarity between the first vibration characteristic data and the second vibration characteristic data; and evaluating the fracture risk of the wind blade based on the cosine similarity.

[0010] In an optional embodiment, the fracture risk of the wind turbine blade is evaluated based on cosine similarity, including: if the cosine similarity is less than a preset similarity threshold, determining that the crack at the target position has entered the macro fracture stage; and controlling a preset alarm device to alarm.

[0011] In an optional embodiment, the above method also includes: if it is determined according to the evaluation results that the crack at the target position has entered the macro-fracture stage, obtaining the operating data of the fan blade; inputting the operating data into a pre-built risk status identification model so that the risk status identification model outputs the risk status value of the fan blade; based on the risk status value being greater than a preset risk status threshold, sending a shutdown command to the fan where the fan blade is located.

[0012] In a second aspect, the present invention provides a device for assessing the fracture risk of a wind blade, the device comprising: a first acquisition module for acquiring wind load time series data corresponding to different positions in a preset area of ​​the wind blade; a first determination module for determining at least one target position among a plurality of positions based on the wind load time series data corresponding to different positions, the target position being a stress concentration area in the preset area; a second determination module for determining a brittleness index sequence of the target position based on the stress amplitude change information of the target position, the stress amplitude change information of the target position being determined based on the wind load time series data of the target position; a third determination module for determining a change trend of the material state of the target position based on the brittleness index sequence if there is a brittleness index value in the brittleness index sequence that is greater than a preset brittleness index threshold; a simulation module for inputting the change trend into a pre-constructed microcrack development model of a wind blade, so that the microcrack development model of the wind blade simulates the crack propagation path of the target position to obtain crack simulation data; an evaluation module for evaluating the fracture risk of the wind blade based on the crack simulation data to obtain an evaluation result.

[0013] In a third aspect, the present invention provides a computer device comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, computer instructions being stored in the memory, and the processor executing the method for assessing the fracture risk of wind blades according to the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the wind turbine blade fracture risk assessment method of the first aspect or any corresponding embodiment thereof.

[0015] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute the method for assessing the fracture risk of a wind turbine blade according to the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 is a flow chart of a method for assessing the risk of wind turbine blade fracture according to an embodiment of the present invention;

[0018] Figure 2 is a flow chart of another method for assessing the fracture risk of a wind turbine blade according to an embodiment of the present invention;

[0019] Figure 3 is a flow chart of another method for assessing the fracture risk of a wind turbine blade according to an embodiment of the present invention;

[0020] Figure 4 is a structural block diagram of a device for assessing the risk of wind turbine blade fracture according to an embodiment of the present invention;

[0021] Figure 5 Schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of the present invention.

[0023] Related technologies generally rely on regular manual inspections and basic vibration monitoring technology to identify blade damage and conduct risk assessments. Manual inspections are limited by labor costs and weather conditions, making continuous monitoring difficult. Traditional vibration monitoring typically compares monitored vibration data with vibration threshold data and assesses wind turbine blade operational risks based on the comparison results, which can easily lead to misjudgments. Therefore, existing wind turbine blade risk assessments have significant deficiencies in real-time and accuracy.

[0024] In view of this, a method for assessing the fracture risk of a wind turbine blade provided in an embodiment of the present application can be applied to a server to implement fracture risk assessment of a wind turbine blade. The method provided in an embodiment of the present application determines the target position of stress concentration through the wind load time series data corresponding to different positions in the preset area of ​​the wind turbine blade, determines the brittleness index sequence of the target position based on the stress amplitude change information of the target position, and if there is a brittleness index value greater than the preset brittleness index threshold in the brittleness index sequence, determines the change trend of the material state of the target position based on the brittleness index sequence, inputs the change trend into a pre-constructed micro-crack development model of the wind turbine blade to simulate the crack propagation path of the target position, obtains crack simulation data, and evaluates the fracture risk of the wind turbine blade based on the crack simulation data, thereby achieving an accurate assessment of the fracture risk of the wind turbine blade and effectively improving the safety and reliability of the operation of wind power equipment.

[0025] According to an embodiment of the present invention, an embodiment of a method for assessing the fracture risk of a wind blade is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] In this embodiment, a method for assessing the risk of wind turbine blade fracture is provided, which can be used in the above-mentioned server. Figure 1 FIG. 1 is a flow chart of a method for assessing the risk of fracture of a wind turbine blade according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0027] Step S101 : obtaining wind load time series data corresponding to different positions in a preset area of ​​a wind turbine blade.

[0028] For example, a wind turbine blade may be one that requires a fracture risk assessment. The preset area is a high-risk fracture area determined based on past experience. In the embodiment of the present application, the preset area may be an area 34 to 43 meters from the root of the wind turbine blade. Wind load data acquisition sensors are preset at different locations within the preset area to collect wind load time-series data at each location. In the embodiment of the present application, the wind load data acquisition sensors may include, but are not limited to, wind speed sensors (such as ultrasonic anemometers and propeller anemometers) and wind direction sensors. The wind load time-series data may include wind speed and wind direction time-series data.

[0029] Step S102 : determining at least one target position among a plurality of positions based on the wind load time series data corresponding to different positions, where the target position is a stress concentration area in a preset area.

[0030] For example, in the embodiment of the present application, the stress amplitude of the blade is different under different wind loads. The stress amplitude change at the corresponding position can be analyzed through the wind load time series data at each position, and at least one target position can be determined from multiple positions through the stress amplitude change. Specifically, the position where the stress amplitude change is greater than the preset value can be used as the target position. The embodiment of the present application does not limit the specific content of the preset value, and those skilled in the art can determine it according to their needs.

[0031] Step S103: determining a brittleness index sequence of the target position based on the stress amplitude change information of the target position.

[0032] For example, the stress amplitude change information at the target location is determined based on the wind load time series data at the target location. The brittleness index is calculated based on the stress amplitude change. Assuming the stress amplitude fluctuates between 0 and 100 MPa, the brittleness index formula is B = Δ / σ_max, where Δσ is the stress amplitude change and σ_max is the maximum stress value.

[0033] Step S104: If there is a brittleness index value in the brittleness index sequence that is greater than a preset brittleness index threshold, a change trend of the material state at the target position is determined based on the brittleness index sequence.

[0034] Exemplarily, the preset brittleness index threshold may include but is not limited to 1. The embodiment of the present application does not limit the specific content of the preset brittleness index threshold, and those skilled in the art can determine it according to needs. In the embodiment of the present application, if there is a brittleness index value greater than 1, it is preliminarily judged that the material state may have undergone slight changes. In order to further determine the preliminary change trend of the material state, a time series analysis method is used to perform sliding average processing on the brittleness index with a window size of 10 data points. It is found that the brittleness index shows a slow upward trend, indicating that the brittleness of the material may gradually increase. Through the above steps, combined with dynamic distribution characteristics, high-frequency abnormal signal separation and brittleness index calculation, the slight change trend of the material state is preliminarily determined.

[0035] Step S105 : inputting the change trend into a pre-built micro crack growth model of a wind turbine blade, so that the micro crack growth model of the wind turbine blade simulates the crack propagation path at the target position to obtain crack simulation data.

[0036] For example, in the embodiment of the present application, the micro crack development model of the wind turbine blade is established by finite element analysis software. First, the blade material is meshed using finite element analysis software, and the unit size is set to 1 mm to ensure that the stress distribution in the crack tip area can be accurately captured. By introducing the theory of linear elastic fracture mechanics, the stress intensity factor of the crack tip is calculated using the J integral algorithm. The initial crack length is 5 mm and the depth is 2 mm, simulating the crack expansion behavior under a uniform tensile stress of 100 MPa. During the simulation process, an adaptive mesh encryption technology is used. When the crack expansion step exceeds 2 mm, the mesh in the crack tip area is automatically encrypted to improve the calculation accuracy. Through iterative calculation, the evolution data of the crack length and depth are recorded in real time. For example, the crack length increases to 8 mm and the depth increases to 35 mm after 1000 iterations. At the same time, a Python script is used to automatically extract these data and generate a crack expansion path diagram to obtain crack simulation data.

[0037] Step S106 : evaluating the fracture risk of the wind turbine blade based on the crack simulation data to obtain an evaluation result.

[0038] For example, in an embodiment of the present application, the crack length and depth at different development stages are determined based on crack simulation data, and whether the wind turbine blade has a risk of fracture is evaluated based on the crack length and depth at different development stages. The embodiment of the present application does not limit the specific evaluation process, and those skilled in the art can determine it according to needs.

[0039] The present embodiment provides a method for assessing the fracture risk of wind blades. The method determines a target position of stress concentration through wind load time series data corresponding to different positions in a preset area of ​​the wind blade, and determines a brittleness index sequence of the target position based on stress amplitude change information at the target position. If there is a brittleness index value greater than a preset brittleness index threshold in the brittleness index sequence, the change trend of the material state at the target position is determined based on the brittleness index sequence. The change trend is input into a pre-constructed micro-crack development model of the wind blade to simulate the crack propagation path at the target position to obtain crack simulation data. The fracture risk of the wind blade is assessed based on the crack simulation data, thereby achieving accurate assessment of the fracture risk of the wind blade and effectively improving the safety and reliability of the operation of wind power equipment.

[0040] In this embodiment, a method for assessing the risk of wind turbine blade fracture is provided, which can be used in the above-mentioned server. Figure 2 FIG. 1 is a flow chart of a method for assessing the risk of fracture of a wind turbine blade according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0041] Step S201: Obtain the wind load time series data corresponding to different positions in the preset area of ​​the wind turbine blade. Figure 1Step S101 of the illustrated embodiment will not be described in detail here.

[0042] Step S202 : determining at least one target position among a plurality of positions based on the wind load time series data corresponding to different positions, where the target position is a stress concentration area in a preset area.

[0043] Specifically, the above step S202 includes:

[0044] Step S2021 , performing Fourier transform on the wind load time series data at each position to obtain wind load spectrum data at the corresponding position.

[0045] For example, in an embodiment of the present application, a fast Fourier transform (FFT) is performed on the time-domain wind load sequence data of each position, and the data is converted into the frequency domain to obtain the frequency spectrum (wind load spectrum data) of the corresponding position.

[0046] Step S2022 : extracting target frequency components greater than a preset frequency threshold from the wind load spectrum data at each location, and determining an abnormal signal sequence at the corresponding location based on the target frequency components.

[0047] Exemplarily, the preset frequency threshold may include but is not limited to 50 Hz. In an embodiment of the present application, the frequency spectrum obtained by FFT is analyzed to identify the frequency intervals and key frequency components where energy is concentrated. Low-frequency components (0-50 Hz) are usually related to wind field characteristics and normal operating conditions of blades; high-frequency components (>50 Hz) may contain abnormal signals (such as structural damage, sensor noise). The db4 wavelet basis function is used to perform a 5-layer multi-scale decomposition of the wind-load signal to decompose the signal into approximate components and detail components at different frequency levels. After decomposition, high-frequency abnormal signals are usually contained in the detail coefficients, in preparation for the subsequent extraction of high-frequency components. The fifth-layer detail coefficients are extracted from the five-layer decomposition results as the separated target frequency components. The frequency range corresponding to the fifth-layer detail coefficients is close to the local vibration frequency caused by blade structural abnormalities (such as fiber debonding and crack initiation), and can effectively capture the high-frequency characteristics related to material damage. By performing inverse Fourier transform on the target frequency components at each position and reconstructing them into time domain signals, a sequence of abnormal signals at the corresponding positions is obtained.

[0048] Step S2023: Calculate stress amplitude change information at the corresponding position based on the abnormal signal sequence at each position.

[0049] For example, in the present embodiment, the abnormal signal sequence at each location is divided into time windows (e.g., 100 data points, corresponding to 0.1 seconds), and the stress amplitude within each window is calculated. For example, if the abnormal signal value within a window fluctuates between 10 and 30 MPa, the stress amplitude is 20 MPa. Stress amplitude change information is determined based on the stress amplitudes within different windows.

[0050] Step S2024, determining at least one target position in the plurality of positions based on the stress amplitude variation information of each position and at a preset stress amplitude threshold value.

[0051] Exemplarily, in the embodiments of the present application, the determination of the target position needs to comprehensively consider the absolute value of the stress amplitude, the significance of the variation amplitude and the concentration of the spatial distribution. First, if the stress amplitude of a position continuously exceeds a preset absolute threshold value (such as 3 consecutive windows ≥ 120 MPa), the position is preliminarily included in the candidate target position. Second, if the rate of change of the stress amplitude of a position exceeds a preset dynamic threshold value (such as 30%), even if the amplitude does not reach the absolute threshold value, the position is also regarded as a potential risk position. The blade is divided into multiple regions along the length direction (such as the 34-43m region is further divided into 34-37m, 37-40m and 40-43m three segments), and the correlation of the stress amplitudes of adjacent positions is analyzed. Third, if the stress amplitudes of multiple adjacent positions in a region simultaneously exceed the threshold value or show obvious spatial aggregation characteristics (such as 5 consecutive monitoring points in the 37-40m region exceed the limit), the positions are determined as stress concentration target positions.

[0052] Step S203, determining a brittleness index sequence of the target position based on the stress amplitude variation information of the target position, the stress amplitude variation information of the target position being determined according to the wind load time series data of the target position. For details, please refer to Figure 1 Step S103 of the embodiment shown in FIG. 1 is not repeated here.

[0053] Step S204, if there is a brittleness index value greater than a preset brittleness index threshold value in the brittleness index sequence, determining a change trend of the material state of the target position based on the brittleness index sequence. For details, please refer to Figure 1 Step S104 of the embodiment shown in FIG. 1 is not repeated here.

[0054] Step S205, inputting the change trend into a pre-constructed micro-crack development model of the fan blade, so that the micro-crack development model of the fan blade simulates a crack propagation path of the target position to obtain crack simulation data. For details, please refer to Figure 1 Step S105 of the embodiment shown in FIG. 1 is not repeated here.

[0055] Step S206, evaluating the fracture risk of the fan blade based on the crack simulation data to obtain an evaluation result. For details, please refer to Figure 1 Step S106 of the embodiment shown in FIG. 1 is not repeated here.

[0056] In the embodiments, a fracture risk evaluation method of a fan blade is provided, which can be used in the server, Figure 3 is a flowchart of the fracture risk evaluation method of the fan blade according to the embodiments of the present application, as shown in Figure 3As shown, the process includes the following steps:

[0057] Step S301: Obtain the wind load time series data corresponding to different positions in the preset area of ​​the wind turbine blade. Figure 1 Step S201 of the illustrated embodiment will not be described in detail here.

[0058] Step S302: Based on the wind load time series data corresponding to different positions, determine at least one target position from multiple positions. The target position is a stress concentration area in the preset area. Figure 1 Step S202 of the illustrated embodiment will not be described in detail here.

[0059] Step S303: Determine the brittleness index sequence of the target location based on the stress amplitude variation information of the target location. The stress amplitude variation information of the target location is determined based on the wind load time series data of the target location. Figure 1 Step S203 of the illustrated embodiment will not be described in detail here.

[0060] Step S304: If there is a brittleness index value in the brittleness index sequence that is greater than a preset brittleness index threshold, the change trend of the material state at the target location is determined based on the brittleness index sequence. Figure 1 Step S204 of the illustrated embodiment will not be described in detail here.

[0061] Step S305: Input the change trend into the pre-built wind turbine blade micro crack development model, so that the wind turbine blade micro crack development model simulates the crack propagation path at the target position to obtain crack simulation data. Figure 1 Step S205 of the illustrated embodiment will not be described in detail here.

[0062] Step S306 : evaluating the fracture risk of the wind turbine blade based on the crack simulation data to obtain an evaluation result.

[0063] Specifically, the above step S306 includes:

[0064] Step S3061, obtaining measured crack data at the target position.

[0065] Illustratively, in the embodiment of the present application, the measured crack data is obtained by scanning the target position surface of the blade with a high-precision microscope. The measured crack data may include but is not limited to raw data such as the size, shape, and distribution of the crack.

[0066] Step S3062: Use principal component analysis to perform dimensionality reduction processing on the crack simulation data and the measured crack data to obtain a principal eigenvector.

[0067] For example, in the embodiment of the present application, the simulation data (crack simulation data, such as stress intensity factor K, expansion rate da / dN) and the measured data (measured crack data, such as crack geometry, oxide layer thickness) constitute a high-dimensional feature set (such as 100 dimensions). After dimensionality reduction by principal component analysis (PCA), principal component 1 (contribution rate 45%) that comprehensively reflects the correlation between crack length and K value, and principal component 2 (contribution rate 30%) that reflects the relationship between crack width and expansion rate are obtained. After dimensionality reduction, the first three principal components (cumulative contribution rate 90%) are retained, which not only compresses the data volume but also retains the key mapping relationship of "simulation-measurement".

[0068] Step S3063: input the main eigenvector into the anticipated risk assessment model so that the risk assessment model outputs a risk value. The risk assessment model is used to characterize the correlation between the main eigenvector and the risk value.

[0069] Exemplarily, the risk value is used to characterize the degree of impact of a crack on the overall structure of the blade. In an embodiment of the present application, based on the retained principal eigenvectors and combined with finite element analysis to simulate the stress distribution and residual strength of the blade under different crack states, a mapping relationship between crack characteristics and the degree of impact on the blade structure (risk value) is established. For example, an assessment model is constructed through regression analysis or machine learning algorithms, with the principal eigenvectors as input and the risk value of the degree of structural impact output, thereby constructing a risk assessment model.

[0070] Step S3064: Evaluate the risk of wind turbine blade fracture based on the risk value.

[0071] For example, in an embodiment of the present application, the degree of impact of the blade crack on the overall structure is evaluated based on the risk value. For example, if the crack propagation rate is 1 micron / second and the residual strength of the blade is 80% of the original strength (risk value), it can be judged that the degree of impact of the crack on the overall structure of the blade is moderate and requires further monitoring and maintenance.

[0072] In some optional implementations, the above step S3064 includes:

[0073] Step a1: If the risk value is greater than a preset risk threshold, obtain vibration monitoring data and first vibration characteristic data of the target position. The first vibration characteristic data is used to characterize the vibration characteristics of the wind turbine blade during normal operation.

[0074] For example, the preset risk threshold can be determined based on experience. When the risk value is greater than the preset risk threshold, it can be determined that the impact of the crack on the overall structure of the blade is moderate and requires further monitoring and maintenance. At this time, the first vibration characteristic data of the blade during normal operation and the real-time vibration monitoring data of the target position are obtained. In the embodiment of the present application, the first vibration characteristic data is obtained by performing a PCA algorithm on the vibration data of the wind turbine blade during normal operation, including the first three principal components, which account for 45%, 30%, and 15%, respectively.

[0075] Step a2: Process the vibration monitoring data using a preset feature extraction method to obtain second vibration feature data of the target position.

[0076] Exemplarily, the preset feature extraction method may include, but is not limited to, a wavelet transform algorithm. In the embodiment of the present application, vibration monitoring data is collected by a sensor and decomposed using a wavelet transform to obtain time characteristics and frequency characteristics. The time characteristics and frequency characteristics are extracted from the decomposition results to obtain the main eigenvector, thereby obtaining second vibration characteristic data of the target location.

[0077] Step a3: Calculate the cosine similarity between the first vibration feature data and the second vibration feature data.

[0078] For example, the embodiment of the present application does not limit the calculation process of cosine similarity, and those skilled in the art can determine it according to needs.

[0079] Step a4: Evaluate the fracture risk of the wind turbine blades based on cosine similarity.

[0080] For example, if the cosine similarity is within the preset normal range, it means that there is no risk of breakage of the wind blade. When the cosine similarity is greater than the preset similarity threshold, it is determined that there is a risk of breakage of the wind blade. The embodiment of the present application does not limit the specific content of the preset normal range and the preset similarity threshold, and those skilled in the art can determine it according to needs.

[0081] In some optional implementations, the above step a4 includes:

[0082] Step a41: If the cosine similarity is less than a preset similarity threshold, it is determined that the crack at the target position has entered the macro fracture stage.

[0083] Step a42, controlling the preset alarm device to sound an alarm.

[0084] For example, the embodiment of the present application does not limit the specific content of the preset alarm device, as long as the alarm can be realized. In the embodiment of the present application, the preset similarity threshold may include but is not limited to 0.85. If the cosine similarity is less than 0.85, the vibration monitoring data is determined to be abnormal, and the crack at the target position has entered the macro-fracture stage. Further analysis of the time-frequency characteristics of the vibration monitoring data, if periodic impacts appear in the time domain, and the impact interval is less than 0.01 seconds, and at the same time, the overlap between the frequency domain features and the main eigenvector exceeds the preset threshold of 0.9, it can be further determined that the crack has entered the macro-fracture stage. At this point, the system automatically triggers an alarm and stores the analysis results in the database to provide data support for subsequent fault diagnosis.

[0085] In some optional embodiments, the above method further includes:

[0086] Step b1: If it is determined according to the evaluation result that the crack at the target position has entered the macro fracture stage, the operating data of the fan blade is obtained.

[0087] For example, in an embodiment of the present application, the operating data of the fan blade may include but is not limited to key features such as vibration frequency, temperature change, and stress distribution, for example, the vibration frequency is 45 Hz, the temperature is 85°C, and the stress distribution is 3 MPa.

[0088] Step b2: inputting the operating data into a pre-built risk status identification model, so that the risk status identification model outputs the risk status value of the wind turbine blade.

[0089] For example, in the embodiment of the present application, the risk status identification model is constructed by a support vector machine algorithm. The support vector machine algorithm is used to classify these features, the data is mapped to a high-dimensional space through a kernel function, and the hyperplane is optimized to achieve the best classification effect. During algorithm training, a historical data set is used for model training, in which fracture samples account for 20% and normal samples account for 80%. The parameters are adjusted through cross-validation, and the final classification accuracy is 92%. The model outputs the fracture risk probability (risk status value). When the probability exceeds the preset threshold of 75, it is judged to be a high-risk state.

[0090] Step b3: Based on the risk status value being greater than a preset risk status threshold, a shutdown instruction is sent to the wind turbine where the wind turbine blade is located.

[0091] For example, the preset risk status threshold can be determined based on demand. In this embodiment, the currently calculated risk status value is 82. If the threshold is exceeded, the system automatically triggers a shutdown command to prevent further equipment damage. This entire process is automated, eliminating the need for human intervention and ensuring timely and accurate decision-making.

[0092] Furthermore, by linking the shutdown command with the historical load data analysis, the operating mode parameters of the high-risk areas are optimized. First, the shutdown command and corresponding load data for each hour in the past year are collected, and the data are preprocessed using time series analysis methods, including denoising and missing value interpolation. Specifically, wavelet transform is used to remove high-frequency noise, and linear interpolation is used to fill in missing values. Next, wind load and stress characteristics are extracted. The wind load data is calculated through the original records of the wind speed sensor, combined with the air density and blade area, and the stress data is obtained through strain gauge measurement. The Pearson correlation coefficient is used to calculate the correlation between wind load and stress, and the correlation coefficient is 85, indicating that the two are significantly correlated. Further, the stress concentration area is analyzed using the fracture mechanics model. Through finite element analysis, it is found that the stress value in the root area of ​​a certain blade exceeds the safety threshold of 300MPa, and it is determined to be a high-risk area. The fracture mechanics model is constructed based on linear elastic fracture mechanics and fatigue fracture theory. First, the Paris formula parameters (C and m) and fracture toughness (KIC) were determined through material fatigue testing. A finite element mesh (1mm cell size) was then generated for the three-dimensional model of the 34-43m region of the blade. Boundary conditions such as root fixation and wind load application were set. After verification using laboratory crack growth data, Bayesian updating and recurrent neural networks were used to integrate real-time monitored data such as crack length and stress amplitude. The model parameters were iteratively optimized, ultimately forming a dynamic fracture mechanics model for high-risk areas for stress concentration analysis and safety threshold determination. Based on the above analysis, a genetic algorithm was used to optimize the operating mode parameters, with the goal of reducing the maximum stress value in the stress concentration area. Through iterative optimization, the optimal parameter combination was obtained, including a wind speed threshold of 15m / s and a blade angle adjustment step of 5 degrees. Ultimately, the maximum stress in the high-risk area was reduced to 250MPa, significantly improving operational safety. The entire analysis process was implemented using automated scripts to ensure the efficiency and accuracy of data processing and optimization.

[0093] After the optimization parameters are obtained, the data collected by the sensor is first filtered in real time using the Kalman filter algorithm, and the filter gain coefficient is set to 0.8 to reduce noise interference. Then, an adaptive filter is used to adjust the sensor acquisition frequency. The initial acquisition frequency is 100 Hz, and it is dynamically adjusted to between 50 Hz and 200 Hz according to the change in signal strength, ensuring that the acquisition frequency is increased in high signal intensity areas and reduced in low signal intensity areas, thereby optimizing data acquisition efficiency. In terms of signal processing weight adjustment, the minimum mean square error algorithm (LMS) is used to weight the signal. The initial value of the weight coefficient is 0.5, and it is gradually adjusted to between 0.3 and 0.7 through iterative calculation to enhance the sensitivity to brittle change and crack development signals. By performing time-frequency analysis on the filtered data, the frequency characteristics of the signal are extracted using short-time Fourier transform. The window function length is 256 sampling points, and the overlap rate is 50%. The frequency distribution diagram of the signal is obtained to further identify the characteristic frequencies of brittle change and crack development. Finally, the processed data is fed into a support vector machine classifier, using a radial basis function as the kernel and a regularization parameter, C, set to 100. This trained model classifies and predicts brittleness changes and crack development, yielding more accurate monitoring results. Throughout this process, data processing and analysis are automated, ensuring the real-time and accuracy of the monitoring strategy.

[0094] Finally, based on the monitoring data, the micro crack development model and key feature extraction process are iterated, and the fracture trend under future loads is predicted through a recurrent neural network, outputting a risk warning signal for long-term operation. Specifically, based on the monitoring data, the micro crack development model is first iteratively optimized. Assuming that the initial crack length is 1 mm, the finite element analysis is combined with the calculation formula of the stress intensity factor K to obtain the initial crack length. Where σ is the stress value and a is the crack length, the initial stress intensity factor is obtained as The Bayesian updating method is used to iteratively modify the model parameters in combination with the newly collected crack growth data, so that the parameters C and m of the crack growth rate da / dN are increased from the initial C=5×10 -12 , m=2 is updated to C=6×10 -12, m = 3. Next, key features of the crack image, such as crack length, width, and fractal dimension, were extracted through wavelet transform and principal component analysis. Taking crack length as an example, the extracted feature values ​​were 12 mm, width 0.15 mm, and fractal dimension 45. These features were used as input to construct a LSTM-based recurrent neural network model. The network structure contained 128 hidden units, the learning rate was set to 0.01, and training was performed using the Adam optimizer. After 10,000 iterations of training, the mean squared error of the model on the validation set was reduced to 0.001. The trained model was used to predict fracture trends under future loads. The input future stress spectrum had a mean of 150 MPa and a variance of 20 MPa. The prediction results showed that the crack length would reach a critical value of 5 mm after 10,000 cycles. Based on the prediction results, the system automatically generates a risk warning signal. When the crack length exceeds 4 mm, a yellow warning is triggered, and when it exceeds 45 mm, a red warning is triggered. Combined with the equipment operation history data, the remaining service life is calculated to be 8,500 cycles, providing a scientific basis for equipment maintenance.

[0095] The method provided in the embodiments of the present application can also collect multidimensional load signals through a sensor array, convert the analog signals into digital signals using an analog-to-digital converter, and obtain raw load data. The raw load data is decomposed into frequency components using a Fourier transform to obtain the signal's frequency domain characteristic data. The frequency components of the wind load distribution are extracted from the frequency domain characteristic data to determine the dynamic change trend of the wind load. The frequency components of the stress distribution are extracted from the frequency domain characteristic data to determine the dynamic distribution characteristics of the fatigue stress. Based on the dynamic change trend of the wind load, a wavelet transform is used to separate the high-frequency and low-frequency signals to obtain the time-frequency distribution results of the wind load. Based on the dynamic distribution characteristics of the fatigue stress, the stress amplitude and number of cycles are calculated to obtain fatigue damage accumulation data. Based on the time-frequency distribution results of the wind load and the fatigue damage accumulation data, a support vector machine is used to classify the correlation between wind load and stress. Specifically, in the 34-43 meter area of ​​the wind turbine blade, a high-precision sensor array is deployed to collect multidimensional load signals in real time, including wind speed, wind direction, blade vibration, and other data. Data is acquired at a sampling rate of 1000 times per second to ensure that high-frequency dynamic changes are captured. Fourier transform is used to perform frequency domain analysis on the signal, convert the time domain signal into a frequency domain signal, and decompose different frequency components. For example, the collected vibration signal is decomposed into a frequency range of 0-500 Hz through the fast Fourier transform (FFT) algorithm, and the main frequency components such as 10 Hz, 50 Hz and 200 Hz are identified, corresponding to the first-order, second-order and third-order vibration modes of the blade, respectively. The amplitude and phase of these frequency components are further analyzed to calculate the dynamic distribution characteristics of the wind load. For example, at a frequency of 10 Hz, the wind load amplitude is 500 Newtons and the phase is 30 degrees, indicating the vibration amplitude and direction of the blade at this frequency. At the same time, combined with the finite element analysis model, the frequency domain data is mapped to the three-dimensional structure of the blade to calculate the fatigue stress distribution. The fatigue life of the blade in this area is evaluated through the stress-life curve (SN curve) and the Meiner damage accumulation theory. For example, calculations show that at a frequency of 50 Hz, the maximum stress on the blade surface is 200 MPa, with a fatigue damage accumulation rate of 0.01 per cycle, and a predicted fatigue life of 10^6 cycles in this area. Real-time monitoring and data analysis provide timely warnings of potential fatigue damage, optimizing blade design and maintenance strategies.

[0096] This embodiment also provides a device for assessing the risk of wind turbine blade fracture, which is used to implement the above-mentioned embodiments and preferred implementations. Details already described will not be repeated here. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0097] This embodiment provides a device for assessing the risk of wind turbine blade fracture. Figure 4 Shown, including:

[0098] The first acquisition module 401 is used to acquire wind load time series data corresponding to different positions in a preset area of ​​the wind turbine blade;

[0099] A first determining module 402 is configured to determine at least one target location from a plurality of locations based on wind load time series data corresponding to different locations, where the target location is a stress concentration area in a preset area;

[0100] A second determining module 403 is configured to determine a brittleness index sequence at the target location based on stress amplitude variation information at the target location, wherein the stress amplitude variation information at the target location is determined based on wind load time series data at the target location;

[0101] A third determining module 404 is configured to determine a change trend of the material state at the target location based on the brittleness index sequence if a brittleness index value in the brittleness index sequence is greater than a preset brittleness index threshold;

[0102] The simulation module 405 is used to input the change trend into a pre-built wind turbine blade micro crack growth model, so that the wind turbine blade micro crack growth model simulates the crack propagation path at the target position to obtain crack simulation data;

[0103] The evaluation module 406 is configured to evaluate the fracture risk of the wind turbine blade based on the crack simulation data to obtain an evaluation result.

[0104] In some optional implementations, the first determining module 402 includes:

[0105] The first processing submodule is used to perform Fourier transform on the wind load time series data at each position to obtain the wind load spectrum data at the corresponding position;

[0106] The first determination submodule is configured to extract target frequency components greater than a preset frequency threshold from the wind load spectrum data at each location, and determine an abnormal signal sequence at the corresponding location based on the target frequency components;

[0107] A calculation submodule is used to calculate the stress amplitude change information of the corresponding position based on the abnormal signal sequence at each position;

[0108] The second determination submodule is configured to determine at least one target position among a plurality of positions based on the stress amplitude change information of each position and a preset stress amplitude threshold.

[0109] In some optional implementations, the evaluation module 406 includes:

[0110] A first acquisition submodule is used to obtain measured crack data at a target location;

[0111] The second processing submodule is used to perform dimensionality reduction processing on the crack simulation data and the measured crack data using the principal component analysis method to obtain the main eigenvector;

[0112] A third determination submodule is used to input the main eigenvector into a pre-constructed risk assessment model so that the risk assessment model outputs a risk value, and the risk assessment model is used to characterize the correlation between the main eigenvector and the risk value;

[0113] The assessment submodule is used to assess the fracture risk of wind turbine blades based on the risk value.

[0114] In some optional embodiments, the evaluation submodule includes:

[0115] an acquiring unit, configured to acquire vibration monitoring data and first vibration characteristic data of the target position if the risk value is greater than a preset risk threshold, wherein the first vibration characteristic data is used to characterize vibration characteristics of the wind turbine blade during normal operation;

[0116] a processing unit, configured to process the vibration monitoring data using a preset feature extraction method to obtain second vibration feature data of the target position;

[0117] a calculation unit, configured to calculate a cosine similarity between the first vibration feature data and the second vibration feature data;

[0118] An evaluation unit is used to evaluate the fracture risk of wind turbine blades based on cosine similarity.

[0119] In some optional embodiments, the evaluation unit includes:

[0120] a determination subunit, for determining that the crack at the target position has entered the macro fracture stage if the cosine similarity is less than a preset similarity threshold;

[0121] The control subunit is used to control the preset alarm device to alarm.

[0122] In some optional embodiments, the above device further includes:

[0123] A second acquisition module is configured to acquire operating data of the fan blade if it is determined according to the evaluation result that the crack at the target position has entered the macro fracture stage;

[0124] a fourth determination module, configured to input the operating data into a pre-built risk status identification model, so that the risk status identification model outputs a risk status value of the wind turbine blade;

[0125] The sending module is used to send a shutdown instruction to the wind turbine where the wind turbine blade is located based on the risk state value being greater than a preset risk state threshold.

[0126] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0127] The wind blade fracture risk assessment device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0128] The embodiment of the present invention also provides a computer device having the above Figure 4 The device for assessing the fracture risk of a wind turbine blade is shown.

[0129] See also Figure 5 , Figure 5 is a structural diagram of a computer device provided by an optional embodiment of the present invention, such as Figure 5 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components utilize different buses to communicate with each other and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of a GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories. Equally, multiple computer devices can be connected, and each device provides part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 5 A processor 10 is taken as an example.

[0130] The processor 10 may be a central processing unit, a network processor, or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0131] The memory 20 stores instructions that can be executed by at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiment.

[0132] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created based on the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0133] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0134] The computer device further includes a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0135] The embodiment of the present invention also provides a computer-readable storage medium. The above-mentioned method according to the embodiment of the present invention can be implemented in hardware, firmware, or implemented as a computer code that can be recorded in a storage medium, or implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and downloaded through a network and will be stored in a local storage medium, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state drive, etc.; further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that a computer, a processor, a microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor or hardware, the method shown in the above embodiment is implemented.

[0136] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0137] Although the embodiments of the present invention have been described with reference to the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention. Such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A method for assessing the fracture risk of a wind turbine blade, characterized in that: The method comprises: Obtain wind load time series data corresponding to different positions in a preset area of ​​the wind turbine blade; Determining at least one target position among the plurality of positions based on the wind load time series data corresponding to the different positions, wherein the target position is a stress concentration area in a preset area; determining a brittleness index sequence at the target location based on stress amplitude variation information at the target location, wherein the stress amplitude variation information at the target location is determined based on wind load time series data at the target location; If there is a brittleness index value in the brittleness index sequence that is greater than a preset brittleness index threshold, determining a change trend of the material state at the target position based on the brittleness index sequence; Inputting the change trend into a pre-built micro crack growth model of a wind turbine blade, so that the micro crack growth model of the wind turbine blade simulates the crack propagation path at the target position to obtain crack simulation data; The fracture risk of the wind turbine blade is evaluated based on the crack simulation data to obtain an evaluation result.

2. The method according to claim 1, characterized in that The step of determining at least one target position from a plurality of positions based on the wind load time series data corresponding to the different positions, wherein the target position is a stress concentration area in a preset area, comprises: Performing Fourier transform on the wind load time series data at each position to obtain wind load spectrum data at the corresponding position; Extracting a target frequency component greater than a preset frequency threshold from the wind load spectrum data at each location, and determining an abnormal signal sequence at the corresponding location based on the target frequency component; Calculate the stress amplitude change information at the corresponding position based on the abnormal signal sequence at each position; At least one target position is determined among the plurality of positions based on the stress amplitude variation information of each position and a preset stress amplitude threshold.

3. The method according to claim 1 or 2, characterized in that The step of evaluating the fracture risk of the wind turbine blade based on the crack simulation data includes: Obtain measured crack data at the target location; Using principal component analysis to perform dimensionality reduction processing on the crack simulation data and the measured crack data to obtain a principal eigenvector; Inputting the main eigenvector into a pre-constructed risk assessment model so that the risk assessment model outputs a risk value, wherein the risk assessment model is used to characterize the correlation between the main eigenvector and the risk value; The fracture risk of the wind turbine blade is assessed based on the risk value.

4. The method according to claim 3, characterized in that Evaluating the fracture risk of the wind turbine blade based on the risk value includes: If the risk value is greater than a preset risk threshold, obtaining vibration monitoring data and first vibration characteristic data at the target location, where the first vibration characteristic data is used to characterize vibration characteristics of the wind turbine blade during normal operation; Processing the vibration monitoring data using a preset feature extraction method to obtain second vibration feature data of the target position; calculating a cosine similarity between the first vibration feature data and the second vibration feature data; The fracture risk of the wind turbine blade is evaluated based on the cosine similarity.

5. The method according to claim 4, characterized in that Evaluating the fracture risk of the wind turbine blade based on the cosine similarity includes: If the cosine similarity is less than a preset similarity threshold, it is determined that the crack at the target position has entered the macro fracture stage; Control the preset alarm device to alarm.

6. The method according to claim 5, characterized in that The method further comprises: If it is determined according to the evaluation result that the crack at the target position has entered the macro fracture stage, obtaining operating data of the fan blade; Inputting the operating data into a pre-built risk status identification model so that the risk status identification model outputs a risk status value of the wind turbine blade; Based on the risk state value being greater than a preset risk state threshold, a shutdown instruction is sent to the wind turbine where the wind turbine blade is located.

7. A device for assessing the risk of wind turbine blade fracture, characterized in that: The device comprises: The first acquisition module is used to obtain wind load time series data corresponding to different positions in a preset area of ​​the wind turbine blade; A first determining module is configured to determine at least one target position from a plurality of positions based on the wind load time series data corresponding to the different positions, wherein the target position is a stress concentration area in a preset area; a second determining module, configured to determine a brittleness index sequence of the target location based on stress amplitude variation information of the target location, wherein the stress amplitude variation information of the target location is determined according to wind load time series data of the target location; a third determining module, configured to determine a change trend of the material state at the target position based on the brittleness index sequence if a brittleness index value in the brittleness index sequence is greater than a preset brittleness index threshold; a simulation module, configured to input the change trend into a pre-built micro crack growth model of a wind turbine blade, so that the micro crack growth model of the wind turbine blade simulates the crack propagation path at the target position to obtain crack simulation data; An evaluation module is used to evaluate the fracture risk of the wind turbine blade based on the crack simulation data to obtain an evaluation result.

8. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the wind turbine blade fracture risk assessment method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the wind turbine blade fracture risk assessment method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions, wherein the computer instructions are used to cause a computer to execute the wind turbine blade fracture risk assessment method according to any one of claims 1 to 6.

Images