A wind turbine blade fatigue life prediction platform and prediction method

Abstract

The application provides a wind turbine blade fatigue life prediction platform and a prediction method, and relates to the technical field of fatigue life prediction.The application firstly constructs a geometric model and an experimental test piece according to design parameters, obtains the limit fatigue cycle times under different stresses through a fatigue performance experiment, and draws an S-N curve for calibrating the geometric model.Secondly, stress values in the historical operation of the wind turbine blade are collected, the current damage condition is analyzed, and whether there is remaining fatigue life is preliminarily evaluated.Through the use of historical operation data, a fault prediction model is constructed to realize the prediction of the fault probability.Through the fault prediction model, the operation data at the current moment are predicted, and the influence of environmental data on the fatigue life is analyzed.Finally, through the comprehensive analysis of the damage condition, the fault probability and the environmental influence, the remaining fatigue life is calculated, and the state is judged to issue a safety or danger warning.

Description

Technical Field

[0001] This invention relates to the field of fatigue life prediction technology, specifically to a fatigue life prediction platform and method for wind turbine blades. Background Technology

[0002] With the rapid development of renewable energy, wind energy, as an important clean energy source, has been widely used. However, as a key component in wind power systems that withstands wind loads and environmental impacts, the prediction and management of wind turbine blade fatigue life has become increasingly important. Traditional methods for wind turbine blade fatigue analysis rely heavily on static tests and empirical formulas, lacking real-time monitoring and dynamic evaluation. This makes it difficult to accurately predict the fatigue state of the blades in actual operation, potentially leading to failures and safety hazards, and affecting the stability and economic benefits of wind power systems.

[0003] In recent years, with the development of computer technology and the application of advanced tools such as finite element analysis and computational fluid dynamics, blade design and fatigue analysis have become more precise. However, how to combine existing technologies to achieve real-time monitoring and comprehensive evaluation of multiple variables of wind turbine blades during actual operation, especially in dealing with complex wind speed changes and fatigue behavior under different environmental conditions, remains a challenge.

[0004] As a crucial component of wind power systems, wind turbine blades are exposed to complex conditions for extended periods, making them susceptible to fatigue damage. Traditional fatigue analysis methods typically rely on static tests and empirical formulas. However, these methods often fail to adequately account for the impact of dynamic load variations, environmental factors, and material properties on blade fatigue behavior in practical applications. Consequently, the lack of real-time monitoring and dynamic assessment tools introduces significant uncertainty into the prediction of wind turbine blade fatigue life, potentially leading to unexpected failures and downtime, thus affecting the economic benefits and safe operation of wind farms. Summary of the Invention

[0005] The purpose of this invention is to provide a wind turbine blade fatigue life prediction platform and prediction method to solve the problems mentioned in the background art.

[0006] A wind turbine blade fatigue life prediction platform includes:

[0007] The finite element analysis module is used to construct the geometric model and experimental specimen of the wind turbine blade based on the design parameters, conduct fatigue performance tests on the experimental specimen to obtain the ultimate fatigue cycle number under different stresses, plot the SN curve, perform finite element analysis on the geometric model, and calibrate the geometric model based on the SN curve.

[0008] The fatigue damage analysis module is used to collect the stress values ​​of wind turbine blades during historical operation, obtain the number of fatigue cycles of wind turbine blades under the stress values ​​during historical operation through finite element analysis, and analyze the damage status at the current moment based on the number of fatigue cycles.

[0009] The fault probability model construction module is used to acquire historical operating data of wind turbine blades, assign corresponding fault probabilities through expert scoring, take historical operating data of wind turbine blades as input, use the corresponding fault probabilities as labels, and build a fault prediction model based on machine learning model.

[0010] The real-time fault analysis module is used to collect the current operating data of the wind turbine blades and the environmental data of their location. The operating data is input into the trained fault prediction model to obtain the fault probability at the current moment and analyze the impact of the current environmental data on the fatigue life of the wind turbine blades.

[0011] The fatigue life prediction model is used to analyze the remaining fatigue life of the wind turbine blade at the current moment based on the damage status, failure probability, and environmental data of the wind turbine blade, and to determine whether to issue an early warning for the remaining fatigue life at the current moment.

[0012] Furthermore, the finite element analysis of the geometric model specifically includes:

[0013] Several experimental specimens of wind turbine blades were fabricated based on the design parameters of the wind turbine blades. Fatigue performance tests were conducted on the experimental specimens, with the blade root, blade tip, and blade middle section set as observation points. Different stress levels were applied to the observation points of each experimental model, and the ultimate fatigue cycle number and stress value at each stress level were recorded. The ultimate fatigue cycle number and stress value were fitted to obtain the SN curve. The equation of the fitted SN curve is expressed as:

[0014]

[0015] in, This represents the maximum number of fatigue cycles. Let be the stress value, and a and b be the fitting parameters, respectively.

[0016] The design parameters include the geometric data and material properties of the wind turbine blade. The geometric data includes the blade's length, width, thickness, cross-sectional shape, curvature, and camber. The material properties include the material used in the wind turbine blade and its mechanical properties, including elastic modulus, Poisson's ratio, shear modulus, tensile strength, and compressive strength. A geometric model of the blade is created based on the geometric data. Material properties are input, the boundary conditions at the blade root are defined as fixed, the mesh type is determined, loads are applied to the observation points of the geometric model, fatigue analysis is performed, and the number of fatigue cycles at the observation points is recorded. The results of the finite element analysis are compared with the SN curve. The absolute difference between the fatigue life in the SN curve at each observation point and the ultimate fatigue cycle count output by the finite element analysis is calculated. When the absolute difference is less than the error threshold, the geometric model calibration is considered complete.

[0017] The formula for converting the limit fatigue cycle count into the initial fatigue life is as follows:

[0018]

[0019] in, This refers to the initial fatigue life, expressed in hours. denoted as the limit fatigue cycle number, and f as the operating frequency.

[0020] Furthermore, the analysis of the damage to the wind turbine blades at the current moment specifically includes:

[0021] The stress values ​​of the wind turbine blades during historical operation are collected. The stress values ​​from each historical operation are used as input to perform finite element analysis on the geometric model, obtaining the output fatigue cycle count. The damage degree in each historical operation is calculated using the following formula:

[0022]

[0023] Where D(i) represents the damage degree under the i-th stress level in the historical operation, and N(i) represents the number of cycles under the i-th stress level in the historical operation. Let be the limit fatigue cycle number in the SN curve corresponding to the stress value of the wind turbine blade under the i-th stress level. Indexes for different stress levels;

[0024] The damage at each stress level is summed using the following formula:

[0025]

[0026] in, The total damage at the current moment. For each type of stress level, and ;

[0027] like This indicates that the wind turbine blades still have remaining fatigue life. If the stress conditions during historical operation have led to fatigue failure of the wind turbine blades, then the fatigue life of the wind turbine blades is determined to be 0, and a fatigue life danger warning is issued.

[0028] Furthermore, constructing the fault prediction model specifically includes:

[0029] The historical operating data includes stress, vibration, and blade temperature. The average stress, vibration, and blade temperature data at the observation points of the wind turbine blade are used as the stress, vibration, and blade temperature data for that wind turbine blade. The historical operating data is analyzed using an expert scoring method to assign corresponding failure probabilities. The historical operating data and corresponding failure probabilities are integrated into a sample set, which is then divided into a training set and a test set in a 7:3 ratio. The historical operating data is used as input to train a machine learning algorithm model, with the corresponding failure probabilities used as labels. The mean squared error is selected as the loss function. When the loss function is lower than a set threshold, the model training is considered complete. The threshold can be set to 0.01. After training, the historical operating data from the test set is input into the trained failure prediction model, and the mean absolute error and coefficient of determination are used to evaluate the model performance.

[0030] Furthermore, the analysis of the current operational and environmental data specifically includes:

[0031] The stress, vibration, and blade temperature at the current observation point are obtained, and the average values ​​are calculated as the stress, vibration, and blade temperature of the wind turbine blade at the current moment. Environmental data of the location of the wind turbine blade are obtained through the meteorological station. The operational data are input into the trained fault prediction model to obtain the fault probability predicted by the model.

[0032] The formula for calculating the environmental impact index is as follows: This analysis examines the impact of environmental data on the fatigue life of wind turbine blades.

[0033]

[0034] in, For environmental impact index, These are the data for temperature, humidity, and wind speed, respectively. These are the suitable values ​​for temperature, humidity, and wind speed, respectively. These are the influence coefficients for each item.

[0035] Furthermore, the analysis of the remaining fatigue life of the wind turbine blade at the current moment specifically includes:

[0036] The remaining fatigue life of wind turbine blades at the current moment is obtained by comprehensively analyzing the damage status, failure probability, and environmental data of the blades. The calculation formula is as follows:

[0037]

[0038] in, For the remaining fatigue life, Where is the initial fatigue life, D is the total damage degree, FEI is the environmental impact index, and CFP is the failure probability. These are the weight coefficients for the corresponding items. ;

[0039] The remaining fatigue life at the current moment is assessed. If the remaining fatigue life at the current moment is higher than the life threshold, the wind turbine blade is determined to be in a safe state, and monitoring of the wind turbine blade continues. If the remaining fatigue life at the current moment is lower than the life threshold, the wind turbine blade is determined to be in a state of fatigue failure, and a fatigue life danger warning is issued.

[0040] The present invention also provides a method for predicting the fatigue life of wind turbine blades. This method is executed by the aforementioned wind turbine blade fatigue life prediction platform, and the specific steps include:

[0041] Step 1: Construct the geometric model and experimental specimen of the wind turbine blade according to the design parameters, conduct fatigue performance tests on the experimental specimen to obtain the ultimate fatigue cycle number under different stresses, and plot the SN curve. Perform finite element analysis on the geometric model and calibrate the geometric model based on the SN curve.

[0042] Step 2: Collect the stress values ​​of the wind turbine blades during historical operation, obtain the number of fatigue cycles of the wind turbine blades under the stress values ​​during historical operation through finite element analysis, and analyze the damage status at the current moment based on the number of fatigue cycles.

[0043] Step 3: Obtain historical operating data of wind turbine blades, assign corresponding failure probabilities through expert scoring, use historical operating data of wind turbine blades as input, use corresponding failure probabilities as labels, and build a failure prediction model based on machine learning model;

[0044] Step 4: Collect the current operating data of the wind turbine blades and the environmental data of their location. Input the operating data into the trained fault prediction model to obtain the fault probability at the current moment and analyze the impact of the current environmental data on the fatigue life of the wind turbine blades.

[0045] Step 5: Based on the current damage status, failure probability, and environmental data of the wind turbine blades, analyze the remaining fatigue life of the wind turbine blades at the current moment, and determine whether to issue an early warning for the remaining fatigue life at the current moment.

[0046] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0047] This solution combines finite element analysis, fatigue damage analysis, and machine learning models to assess the fatigue state and remaining life of wind turbine blades in real time. The platform not only systematically analyzes design and material parameters to optimize blade design, but also learns from historical data to intelligently predict failure probabilities. This approach significantly improves the monitoring accuracy and response speed of wind turbines, effectively reduces the risk of failures due to fatigue damage, provides reliable assurance for the safe operation of wind power generation, and thus enhances the overall economic benefits and sustainability of wind power generation. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of the platform structure of the present invention;

[0049] Figure 2 This is a schematic diagram of the overall method flow of the present invention;

[0050] Figure 3 This is a graph showing the relationship between temperature and environmental impact index in this invention;

[0051] Figure 4 This is a graph showing the relationship between humidity and environmental impact index in this invention;

[0052] Figure 5 This is a graph showing the relationship between wind speed and environmental impact index in this invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0054] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0055] Example:

[0056] Please see Figure 1 This invention provides a wind turbine blade fatigue life prediction platform, comprising:

[0057] The finite element analysis module is used to construct the geometric model and experimental specimen of the wind turbine blade based on the design parameters, conduct fatigue performance tests on the experimental specimen to obtain the ultimate fatigue cycle number under different stresses, plot the SN curve, perform finite element analysis on the geometric model, and calibrate the geometric model based on the SN curve.

[0058] In this embodiment, the finite element analysis of the geometric model specifically includes:

[0059] Several experimental specimens of wind turbine blades were fabricated based on the design parameters of the wind turbine blades. Fatigue performance tests were conducted on the experimental specimens, with the blade root, blade tip, and blade middle section set as observation points. Different stress levels were applied to the observation points of each experimental model, and the ultimate fatigue cycle number and stress value at each stress level were recorded. The ultimate fatigue cycle number and stress value were fitted to obtain the SN curve. The equation of the fitted SN curve is expressed as:

[0060]

[0061] in, This refers to the ultimate fatigue cycle count, which is the maximum number of fatigue cycles a wind turbine blade can withstand under a given stress value. Let be the stress value, and a and b be the fitting parameters, which can be fitted using the least squares method.

[0062] The design parameters include the geometric data and material properties of the wind turbine blade. The geometric data includes the blade's length, width, thickness, cross-sectional shape (such as NACA series airfoils), curvature, and camber. The material properties include the materials used in the wind turbine blade (such as glass fiber, carbon fiber, composite materials, etc.) and mechanical properties, including elastic modulus, Poisson's ratio, shear modulus, tensile strength, and compressive strength. A geometric model of the blade is created based on the geometric data of the wind turbine blade. The material properties are input, the boundary conditions at the root of the wind turbine blade are defined as fixed, the mesh type is determined, loads are applied to the observation points of the geometric model, fatigue analysis is performed, and the number of fatigue cycles at the observation points is recorded. The results of the finite element analysis are compared with the SN curve. The absolute difference between the fatigue life in the SN curve and the limit fatigue cycle number output by the finite element analysis is calculated. When the absolute difference is less than the error threshold, the geometric model calibration is considered complete.

[0063] The formula for converting the limit fatigue cycle count into the initial fatigue life is as follows:

[0064]

[0065] in, This refers to the initial fatigue life, expressed in hours. The limit fatigue cycle number is given, and f is the operating frequency, which refers to the rotational frequency of the wind turbine.

[0066] This module ensures the accuracy of wind turbine blades by constructing geometric models and experimental specimens based on design parameters. Detailed geometric data and material property inputs allow the model to realistically reflect the stress conditions of the blades under actual operating conditions, thus improving the reliability of the analysis. The module's recording and analysis of the ultimate fatigue cycle count under different stress levels enables researchers to comprehensively understand the fatigue characteristics of materials in practical applications. By setting the root, tip, and middle of the blade as observation points, stress responses at different locations can be obtained, further enriching our understanding of fatigue performance. Fitting experimental data to form an SN curve model provides theoretical support for subsequent fatigue life prediction. The SN curve not only provides necessary parameters for fatigue analysis but also offers a convenient calculation method for practical engineering applications through mathematical modeling.

[0067] The fatigue damage analysis module is used to collect the stress values ​​of wind turbine blades during historical operation, obtain the number of fatigue cycles of wind turbine blades under the stress values ​​during historical operation through finite element analysis, and analyze the damage status at the current moment based on the number of fatigue cycles.

[0068] In this embodiment, analyzing the damage status of the wind turbine blades at the current moment specifically includes:

[0069] The stress values ​​of the wind turbine blades during historical operation are collected. The stress values ​​from each historical operation are used as input to perform finite element analysis on the geometric model, obtaining the output fatigue cycle count. The damage degree in each historical operation is calculated using the following formula:

[0070]

[0071] Where D(i) represents the damage degree under the i-th stress level in the historical operation, and N(i) represents the number of cycles under the i-th stress level in the historical operation. Let be the limit fatigue cycle number in the SN curve corresponding to the stress value of the wind turbine blade under the i-th stress level. Indexes for different stress levels;

[0072] The damage at each stress level is summed using the following formula:

[0073]

[0074] in, The total damage at the current moment. For each type of stress level, and ;

[0075] like This indicates that the wind turbine blades still have remaining fatigue life. If the stress conditions during historical operation have led to fatigue failure of the wind turbine blades, then the fatigue life of the wind turbine blades is determined to be 0, and a fatigue life danger warning is issued.

[0076] This module dynamically reflects the load the wind turbine blades bear during actual operation by collecting stress values ​​from historical data. This historical data-based analysis method makes damage calculation more practically meaningful, accurately reflecting the current fatigue state of the blades. The damage calculation formula intuitively represents the degree of fatigue damage to the blades under specific stress conditions. This proportional relationship reasonably reflects the fatigue performance of the material under different loads. By pre-setting the judgment of the total damage degree in historical operation, it can directly determine whether fatigue failure has occurred during historical operation. If it has, it means that the wind turbine blade has reached the limit of fatigue cycles during historical operation, and is considered to have reached fatigue failure. Therefore, it no longer judges the fatigue life under future stress conditions, and directly issues a fatigue life danger warning. This module can analyze and monitor the damage state of wind turbine blades in real time, providing timely safety warnings. When the fatigue life is detected to have dropped to a dangerous level, measures can be taken quickly, such as shutdown and maintenance, to avoid major failures and improve the safety of the wind turbine.

[0077] The fault probability model construction module is used to acquire historical operating data of wind turbine blades, assign corresponding fault probabilities through expert scoring, take historical operating data of wind turbine blades as input, use the corresponding fault probabilities as labels, and build a fault prediction model based on machine learning model.

[0078] In this embodiment, constructing the fault prediction model specifically includes:

[0079] Stress and vibration sensors are installed inside the upper center of the blade to obtain stress and vibration data. The historical operating data includes stress, vibration, and blade temperature. The average stress, vibration, and blade temperature data at the observation point of the wind turbine blade are used as the stress, vibration, and blade temperature data of that wind turbine blade. The historical operating data is analyzed using an expert scoring method to assign corresponding failure probabilities. The historical operating data and corresponding failure probabilities are integrated into a sample set, which is then divided into a training set and a test set in a 7:3 ratio. The historical operating data is used as input to train a machine learning algorithm model, with the corresponding failure probabilities as labels. The mean squared error is selected as the loss function. The model training is considered complete when the loss function is lower than a set threshold, which can be set to 0.01. After training, the historical operating data in the test set is input into the trained failure prediction model, and the mean absolute error and coefficient of determination are used to evaluate the model performance.

[0080] Machine learning algorithms can handle complex nonlinear relationships between input features and output. In wind turbine blade failure prediction, factors influencing failure occurrence (such as stress, vibration, and temperature) may have complex interactions. Machine learning models can learn from historical data to capture these relationships, thereby improving prediction accuracy. Through machine learning models, the system can continuously optimize and update itself based on new historical operational data. During the long-term operation of wind turbine blades, performance and failure modes may change with time and environmental variations. Machine learning models can quickly adapt to these changes, improving the accuracy of failure prediction. Furthermore, this model is suitable for handling large-scale, high-dimensional datasets, thus enabling more accurate failure predictions.

[0081] Input data includes stress, vibration, and blade temperature, parameters closely related to the operating status of wind turbine blades. Stress and vibration directly affect the fatigue performance and reliability of the blades, while temperature can affect the physical properties of the materials and fatigue life. Therefore, historical operating data can comprehensively reflect the working environment and condition of the blades. Stress is the force per unit area, typically caused by aerodynamic forces and gravity acting on the wind turbine blades during operation. Changes in wind speed, wind direction, blade weight, and centrifugal force caused by rotation all lead to varying degrees of stress on the blades. Higher stress can cause material fatigue, leading to cracks, deformation, or eventual failure. Repeated stress cycles (fatigue) accelerate material fatigue damage, increasing structural vulnerability. Therefore, continuous monitoring of stress levels is crucial for predicting blade failure. Vibration is the mechanical vibration of an object caused by external or internal forces. On wind turbine blades, vibration may originate from airflow, blade imbalance, structural defects, or malfunctions of other mechanical components. Excessive vibration can lead to fatigue damage, loosening or failure of connections. Especially at the blade-hub junction, vibration can accelerate the formation and propagation of fatigue cracks, leading to structural failure. Therefore, monitoring and analyzing vibration data helps identify potential faults in a timely manner. Blade temperature refers to the temperature of the wind turbine blade itself, which is typically affected by factors such as the external environment, the thermal conductivity of the blade material, and wind speed. Temperature changes affect the mechanical properties of the blade material; for example, the strength of some materials may decrease as the temperature rises. Furthermore, excessively high temperatures can cause material aging, deformation, or loss of elasticity, thereby increasing the risk of failure. By monitoring blade temperature, its operating condition and potential failure risks can be assessed. Therefore, using the above data as input can effectively determine whether wind turbine blades are faulty, making the constructed failure probability prediction model more accurate.

[0082] The expert scoring method, combined with machine learning models, reduces reliance on human experience by providing fault probability labels. Machine learning models, through data-driven prediction, lower the errors and uncertainties introduced by human judgment. The expert scoring method can categorize stress states into three levels (high, medium, low), vibration states into three levels (normal, abnormal frequency, severe vibration), and blade temperature states into normal, slightly high, and excessively high. A design scoring scale using a 1-5 rating system is then established, where 1 indicates extremely low risk (almost no chance of failure), 2 indicates low risk (occasional chance of failure), 3 indicates medium risk (some chance of failure), 4 indicates high risk (relatively high chance of failure), and 5 indicates extremely high risk (almost certain failure). Experts first determine the corresponding stress, vibration, and blade temperature states, then assign a design score based on these states. Finally, the scores for stress, vibration, and blade temperature are normalized, and a weighted sum of these scores yields the final fault probability. Blade temperature can be assigned the highest weight, stress a medium weight, and vibration the lowest weight. The criteria for probability determination are then given: a failure probability of 0-0.2 indicates low risk and a low probability of failure; a failure probability of 0.2-0.5 indicates medium risk and requires attention to the wind turbine blades; a failure probability of 0.5-0.8 indicates high risk and requires measures; and a failure probability of 0.8-1 indicates extremely high risk and a near certain failure, requiring immediate action.

[0083] The performance of blade materials (such as composites) can degrade significantly at high temperatures. Increased temperature affects the strength, stiffness, and fatigue life of materials, thus high temperatures are often considered a key factor leading to material failure. Temperature changes cause thermal expansion and contraction, resulting in thermal stress. This thermal stress can exacerbate existing material defects, leading to crack propagation. Furthermore, high temperatures typically accelerate material aging and corrosion, affecting long-term safety. Therefore, the effects of temperature are direct and significant. Stress is a significant factor leading to fatigue cracks, especially under repeated loading. High stress levels make blade materials susceptible to fatigue damage. While stress is an important factor in the operation of wind turbine blades, its impact depends to some extent on other factors (such as temperature and environmental influences). Therefore, a moderate weight is given to reflect its importance while acknowledging the interaction of other factors. Although vibration also leads to fatigue and damage, its impact can be relatively small in many cases, especially under normal operating conditions. If wind turbines are well-designed and maintained, vibration problems are usually less frequent and manageable. The impact of vibration is also related to its frequency and amplitude; under normal operating conditions, wind turbine designs can generally withstand a certain level of vibration. Therefore, a lower weight is given to vibration.

[0084] The real-time fault analysis module is used to collect the current operating data of the wind turbine blades and the environmental data of their location. The operating data is input into the trained fault prediction model to obtain the fault probability at the current moment and analyze the impact of the current environmental data on the fatigue life of the wind turbine blades.

[0085] In this embodiment, the analysis of the current operational data and environmental data specifically includes:

[0086] The stress, vibration, and blade temperature at the current observation point are obtained, and the average values ​​are calculated as the stress, vibration, and blade temperature of the wind turbine blade at the current moment. Environmental data of the location of the wind turbine blade are obtained through the meteorological station. The operational data are input into the trained fault prediction model to obtain the fault probability predicted by the model.

[0087] The formula for calculating the environmental impact index is as follows: This analysis examines the impact of environmental data on the fatigue life of wind turbine blades.

[0088]

[0089] in, For environmental impact index, These are the data for temperature, humidity, and wind speed, respectively. These are the suitable values ​​for temperature, humidity, and wind speed, respectively. These are the influence coefficients for each item. .

[0090] By calculating the FEI (Fatigue Intake Index), the fatigue life of wind turbine blades under current environmental conditions can be assessed and predicted in a timely manner. In this formula, the independent variables are temperature, humidity, and wind speed. Ambient temperature affects the thermal expansion and contraction of materials, potentially leading to stress concentration at joints. Furthermore, high temperatures may induce thermal aging of materials, accelerating fatigue damage. High humidity environments may cause moisture accumulation on the blade surface, increasing the risk of corrosion, especially in the presence of microcracks or defects in the material. In addition, humidity variations also affect the mechanical properties of the blade material, particularly the hygroscopicity of composite materials, which can lead to performance degradation. Excessively high wind speeds may cause wind turbine blades to withstand ultimate loads, increasing stress and vibration. Simultaneously, strong winds may cause unpredictable vibrations or torsion of the blades, increasing the risk of fatigue failure. Furthermore, changes in wind speed may cause instability in aerodynamic loads, leading to a decline in the overall performance of the equipment.

[0091] When environmental conditions exceed suitable values, wind turbine blades may face a higher risk of fatigue. For example, high temperatures may cause a decline in material performance, excessively high or low humidity may affect the physical properties of the materials, and extreme wind speeds may lead to unbalanced loads and vibrations. FEI is directly proportional to the deviation from the suitable value. That is, if actual environmental conditions ( Deviation from suitable value ( The larger the value of the environmental impact index (FEI), the greater the negative impact of the environment on the fatigue life of the blades. Therefore, the deviation of environmental conditions from the optimal value is positively correlated with the FEI. If the actual environmental conditions are consistent with the optimal conditions, the FEI approaches 0, indicating that the environment has no significant impact on the fatigue life of wind turbine blades.

[0092] The optimal temperature is set at 25℃, which is the ideal operating temperature for wind turbine blade materials (usually composite materials), ensuring stable mechanical properties. Temperature has the most significant impact on material properties. High temperatures can lead to decreased material strength and accelerated aging, directly affecting the fatigue life of the blades. Therefore, assigning the highest weight to temperature is reasonable. The optimal humidity is set at 50%. 50% humidity typically strikes a balance between material stability and structural safety; excessively high or low humidity will affect material properties. Humidity has a relatively small impact on materials, mainly affecting hygroscopicity and durability. Although humidity changes affect the physical properties of materials, their impact is usually less significant than that of temperature, thus assigning a moderate weight. The optimal wind speed is set at 10 m / s. 10 m / s is the optimal operating wind speed for wind turbines, effectively generating energy without causing excessive mechanical load. The impact of wind speed is mainly reflected in mechanical load and vibration. In well-designed wind turbines, wind speeds within the normal range will not cause direct damage to the blades, therefore assigning the lowest weight to wind speed.

[0093] In this embodiment, the suitable temperature was set to 25℃, the suitable humidity to 50%, the suitable wind speed to 10m / s, the temperature weighting coefficient was set to 0.5, the humidity weighting coefficient was set to 0.3, and the wind speed weighting coefficient was set to 0.1. Environmental data of nine sets of wind turbine blade locations were collected and analyzed. The specific measurement data are shown in the table below:

[0094]

[0095] Reference Figures 3-5 As can be seen from the data in the table above, the environmental impact index decreases as the temperature approaches the suitable value. The collected sample temperature data ranges from below the suitable temperature value to above the suitable temperature value. Figure 3 It can also be seen that the environmental impact index gradually decreases and then gradually increases, reflecting that the closer to the suitable temperature value, the smaller the environmental impact index; the further away from the suitable temperature value, the larger the environmental impact index. Similarly, the collected sample humidity data ranges from below the suitable humidity value to above the suitable humidity value. Figure 4As can be seen, the environmental impact index gradually decreases and then gradually increases, reflecting that the closer to the suitable humidity value, the smaller the environmental impact index; the further away from the suitable humidity value, the larger the environmental impact index. Similarly, the collected sample wind speed data ranges from below the suitable wind speed value to above the suitable wind speed value, from... Figure 5 It can also be seen that the environmental impact index gradually decreases and then gradually increases, reflecting that the closer it is to the suitable wind speed value, the smaller the environmental impact index is, and the further it deviates from the suitable wind speed value, the larger the environmental impact index is.

[0096] The fatigue life prediction model is used to analyze the remaining fatigue life of the wind turbine blade at the current moment based on the damage status, failure probability, and environmental data of the wind turbine blade, and to determine whether to issue an early warning for the remaining fatigue life at the current moment.

[0097] In this embodiment, analyzing the remaining fatigue life of the wind turbine blades at the current moment specifically includes:

[0098] The remaining fatigue life of wind turbine blades at the current moment is obtained by comprehensively analyzing the damage status, failure probability, and environmental data of the blades. The calculation formula is as follows:

[0099]

[0100] in, For the remaining fatigue life, Where is the initial fatigue life, D is the total damage degree, FEI is the environmental impact index, and CFP is the failure probability. These are the weight coefficients for the corresponding items. ;

[0101] The remaining fatigue life at the current moment is assessed. If the remaining fatigue life at the current moment is higher than the life threshold, the wind turbine blade is considered to be in a safe state, and monitoring of the wind turbine blade continues. If the remaining fatigue life at the current moment is lower than the life threshold, the wind turbine blade is considered to be in a state of fatigue failure, and a fatigue life danger warning is issued.

[0102] Remaining fatigue life (RFW) refers to the estimated time or service life that a wind turbine blade will be able to operate safely under current conditions after experiencing certain damage and environmental impacts. It is an important performance indicator used to determine whether wind turbine blades require maintenance or replacement. RFF assesses the current condition of wind turbine blades, ensuring maintenance is performed before fatigue occurs, reducing the risk of failure, and guaranteeing the safe operation of wind farms. Through RFF analysis, wind power operators can develop reasonable maintenance plans, optimize resource allocation, and improve economic efficiency. Real-time monitoring and forecasting can identify potential problems in advance, reducing economic losses caused by equipment failure.

[0103] Total damage reflects the degree of damage accumulation suffered by the blade during use. Higher damage results in a shorter remaining fatigue life. The Environmental Impact Index (FEI) represents the impact of current environmental conditions on the blade's fatigue life. More unfavorable environmental factors (e.g., high temperature, high humidity) result in a higher FEI value, further reducing the remaining fatigue life. Failure probability represents the likelihood of equipment failure; a higher failure probability means greater risk, thus reducing the remaining fatigue life. Increases in both total damage and failure probability directly reduce the remaining fatigue life through exponential decay. An increase in total damage is directly inversely correlated with remaining fatigue life; higher damage results in a shorter remaining fatigue life. The FEI affects remaining fatigue life through a logarithmic function; as the FEI increases... An increase in the value of [value] reduces the remaining fatigue life, demonstrating the inverse effect of environmental factors on blade performance. An increase in the probability of failure will also lead to a decrease in the remaining fatigue life, indicating that a greater failure risk results in a shorter safe operating time. This term represents the reduction in fatigue life of wind turbine blades due to cumulative damage. As the damage level D increases, the remaining fatigue life decays exponentially, indicating that the impact of each unit of damage on fatigue life is non-linear. This exponential decay relationship is highly consistent with materials fatigue theory, where the accumulation of damage has an increasingly significant impact on the material's load-bearing capacity and lifespan. Therefore, through... The form can accurately reflect the significant impact of the current damage status on the remaining fatigue life. This section quantifies the impact of environmental factors on the fatigue life of wind turbine blades. FEI represents the Environmental Impact Index, reflecting the influence of changes in environmental conditions such as temperature, humidity, and wind speed on blade performance. Expressing it as a logarithmic function allows the increase in environmental impact to gradually decrease over a large range, avoiding overly drastic effects. Using a logarithmic function linearizes the impact of environmental factors, especially when the FEI value is low, indicating a smaller impact on fatigue life; while as the FEI value increases, the impact gradually increases. This more reasonably reflects the changes in blade fatigue life under different environmental conditions, providing a smoother adjustment mechanism. This term reflects the impact of failure probability on the remaining fatigue life of wind turbine blades. As the failure probability (CFP) increases, the risk of equipment failure in the current state increases, leading to a decrease in remaining fatigue life. Using an exponentially decaying form to express the impact of failure probability on life, similar to the impact of damage degree, emphasizes the importance of failure risk in fatigue life. This form effectively simulates the sharp decline in the actual reliability and safety of the equipment under high failure probabilities, enhancing the model's sensitivity to risk. The initial fatigue life provides a reference baseline, and subsequent correction factors aim to reflect the impact of various factors in actual operation on this baseline, thereby adjusting for a more realistic remaining fatigue life. Multiplying these three correction factors together effectively integrates the combined effects of various influencing factors. The fatigue life of wind turbine blades is not a simple linear superposition but the result of the interaction of multiple factors; the product form more realistically reflects this complexity.

[0104] Total damage is an important indicator for evaluating the current damage status of wind turbine blades. As service time increases, blades accumulate damage, leading to a reduction in their fatigue life. Therefore, The high weighting of damage level reflects its direct and significant impact on remaining fatigue life. Increased damage typically has a significant impact on structural safety. While environmental factors (such as temperature and humidity) are important for blade performance, their influence is usually less significant than that of direct structural damage. Therefore, The weight is set to be lower than and This is reasonable. The Environmental Impact Index (EI) influences remaining fatigue life through a logarithmic function, indicating that the impact of environmental factors is gradual rather than nonlinear. The Probability of Failure (CFP) represents the likelihood of equipment failure. While this factor also significantly affects the remaining fatigue life of blades, its impact is generally considered within the context of risk assessment under certain conditions. Compared to the degree of damage, the impact of the CFP is more random and indirect; therefore, it is set to be lower than [the CFP value]. But higher than That's reasonable. The probability of a malfunction directly affects safety, but the degree of its impact often complements the actual extent of damage.

[0105] Lifespan thresholds can be set based on historical data, such as the average remaining fatigue life of wind turbine blades in historical data. By comparing the remaining fatigue life with the preset lifespan threshold, it is possible to determine in real time whether the wind turbine blades are in a safe operating condition. If the remaining fatigue life is higher than the threshold, the system will prompt the equipment to continue safe operation; conversely, it will issue a fatigue life danger warning, prompting timely maintenance or replacement. This judgment mechanism ensures the safety of the wind turbine and reduces the risk of accidents due to equipment failure. By monitoring and predicting the remaining fatigue life in real time, wind power operators can more effectively develop maintenance and repair plans. This predictive method can help identify potential failure points and take measures in advance, thereby reducing unplanned downtime and maintenance costs.

[0106] Please see Figure 2 The present invention also provides a method for predicting the fatigue life of wind turbine blades. This method is executed by the aforementioned wind turbine blade fatigue life prediction platform, and the specific steps include:

[0107] Step 1: Construct the geometric model and experimental specimen of the wind turbine blade according to the design parameters, conduct fatigue performance tests on the experimental specimen to obtain the ultimate fatigue cycle number under different stresses, and plot the SN curve. Perform finite element analysis on the geometric model and calibrate the geometric model based on the SN curve.

[0108] Step 2: Collect the stress values ​​of the wind turbine blades during historical operation, obtain the number of fatigue cycles of the wind turbine blades under the stress values ​​during historical operation through finite element analysis, and analyze the damage status at the current moment based on the number of fatigue cycles.

[0109] Step 3: Obtain historical operating data of wind turbine blades, assign corresponding failure probabilities through expert scoring, use historical operating data of wind turbine blades as input, use corresponding failure probabilities as labels, and build a failure prediction model based on machine learning model;

[0110] Step 4: Collect the current operating data of the wind turbine blades and the environmental data of their location. Input the operating data into the trained fault prediction model to obtain the fault probability at the current moment and analyze the impact of the current environmental data on the fatigue life of the wind turbine blades.

[0111] Step 5: Based on the current damage status, failure probability, and environmental data of the wind turbine blades, analyze the remaining fatigue life of the wind turbine blades at the current moment, and determine whether to issue an early warning for the remaining fatigue life at the current moment.

[0112] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0113] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0115] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. A fatigue life prediction platform for wind turbine blades, characterized in that, include: The finite element analysis module is used to construct the geometric model and experimental specimen of the wind turbine blade based on the design parameters, conduct fatigue performance tests on the experimental specimen to obtain the ultimate fatigue cycle number under different stresses, plot the SN curve, perform finite element analysis on the geometric model, and calibrate the geometric model based on the SN curve. The fatigue damage analysis module is used to collect the stress values ​​of wind turbine blades during historical operation, obtain the number of fatigue cycles of wind turbine blades under the stress values ​​during historical operation through finite element analysis, and analyze the damage status at the current moment based on the number of fatigue cycles. The fault probability model construction module is used to acquire historical operating data of wind turbine blades, assign corresponding fault probabilities through expert scoring, take historical operating data of wind turbine blades as input, use the corresponding fault probabilities as labels, and build a fault prediction model based on machine learning model. The real-time fault analysis module is used to collect the current operating data of the wind turbine blades and the environmental data of their location. The operating data is input into the trained fault prediction model to obtain the fault probability at the current moment and analyze the impact of the current environmental data on the fatigue life of the wind turbine blades. The fatigue life prediction model is used to analyze the remaining fatigue life of the wind turbine blade at the current moment based on the damage status, failure probability and environmental data of the wind turbine blade at the current moment, and to determine whether to issue an early warning for the remaining fatigue life at the current moment. The finite element analysis of the geometric model specifically includes: Several experimental specimens of wind turbine blades were fabricated based on the design parameters of the wind turbine blades. Fatigue performance tests were conducted on the experimental specimens of the wind turbine blades. The root, tip, and middle of the blade were set as observation points. Different stress levels were applied to the observation points of each experimental model. The number of ultimate fatigue cycles and stress values ​​at each stress level were recorded. The number of ultimate fatigue cycles and stress values ​​were fitted to obtain the SN curve. The design parameters include the geometric data and material properties of the wind turbine blade. A geometric model of the blade is created based on the geometric data of the wind turbine blade. The material properties are input, the boundary conditions at the root of the wind turbine blade are defined as fixed, the mesh type is determined, loads are applied to the observation points of the geometric model, fatigue analysis is performed, and the number of fatigue cycles at the observation points is recorded in the output of the finite element analysis. The results of the finite element analysis are compared with the SN curve. The absolute difference between the fatigue life in the SN curve of each observation point and the limit fatigue cycle number output by the finite element analysis is calculated. When the absolute difference is less than the error threshold, the geometric model calibration is considered complete.

2. The wind turbine blade fatigue life prediction platform according to claim 1, characterized in that, The equation for the fitted SN curve is expressed as: in, This represents the maximum number of fatigue cycles. Let be the stress value, and a and b be the fitting parameters, respectively. Geometric data includes the blade's length, width, thickness, cross-sectional shape, curvature, and camber. Material properties include the materials used in the wind turbine blade and their mechanical properties, including elastic modulus, Poisson's ratio, shear modulus, tensile strength, and compressive strength. The formula for converting the limit fatigue cycle count into the initial fatigue life is as follows: in, This refers to the initial fatigue life, expressed in hours. denoted as the limit fatigue cycle number, and f as the operating frequency.

3. The wind turbine blade fatigue life prediction platform according to claim 1, characterized in that, The analysis of the damage to the wind turbine blades at the current moment specifically includes: The stress values ​​of the wind turbine blades during historical operation are collected. The stress values ​​from each historical operation are used as input to perform finite element analysis on the geometric model, obtaining the output fatigue cycle count. The damage degree in each historical operation is calculated using the following formula: Where D(i) represents the damage degree under the i-th stress level in the historical operation, and N(i) represents the number of cycles under the i-th stress level in the historical operation. Let be the limit fatigue cycle number in the SN curve corresponding to the stress value of the wind turbine blade under the i-th stress level. Indexes for different stress levels; The damage at each stress level is summed using the following formula: in, The total damage at the current moment. Let be the total number of stress levels, and ; like This indicates that the wind turbine blades still have remaining fatigue life. If the stress conditions during historical operation have led to fatigue failure of the wind turbine blades, then the fatigue life of the wind turbine blades is determined to be 0, and a fatigue life danger warning is issued.

4. The wind turbine blade fatigue life prediction platform according to claim 1, characterized in that, Constructing the fault prediction model specifically includes: The historical operating data includes stress, vibration, and blade temperature. The average stress, vibration, and blade temperature data at the observation points of the wind turbine blade are used as the stress, vibration, and blade temperature data for that wind turbine blade. The historical operating data is analyzed using an expert scoring method to assign corresponding failure probabilities. The historical operating data and corresponding failure probabilities are integrated into a sample set, which is then divided into a training set and a test set in a 7:3 ratio. The historical operating data is used as input to train a machine learning algorithm model, with the corresponding failure probabilities used as labels. The mean squared error is selected as the loss function. When the loss function is lower than a set threshold, the model training is considered complete. The threshold can be set to 0.

01. After training, the historical operating data from the test set is input into the trained failure prediction model, and the mean absolute error and coefficient of determination are used to evaluate the model performance.

5. The wind turbine blade fatigue life prediction platform according to claim 1, characterized in that, The analysis of current operational and environmental data specifically includes: The stress, vibration, and blade temperature at the current observation point are obtained, and the average values ​​are calculated as the stress, vibration, and blade temperature of the wind turbine blade at the current moment. Environmental data of the location of the wind turbine blade are obtained through the meteorological station. The operational data are input into the trained fault prediction model to obtain the fault probability predicted by the model. The formula for calculating the environmental impact index is as follows: This analysis examines the impact of environmental data on the fatigue life of wind turbine blades. in, For environmental impact index, These are the temperature, humidity, and wind speed data, respectively. These are the suitable values ​​for temperature, humidity, and wind speed, respectively. These are the influence coefficients for each item.

6. The wind turbine blade fatigue life prediction platform according to claim 1, characterized in that, The analysis of the remaining fatigue life of the wind turbine blades at the current moment specifically includes: The remaining fatigue life of wind turbine blades at the current moment is obtained by comprehensively analyzing the damage status, failure probability, and environmental data of the blades. The calculation formula is as follows: in, For the remaining fatigue life, Where is the initial fatigue life, D is the total damage degree, FEI is the environmental impact index, and CFP is the failure probability. These are the weight coefficients for the corresponding items. ; The remaining fatigue life at the current moment is assessed. If the remaining fatigue life at the current moment is higher than the life threshold, the wind turbine blade is determined to be in a safe state, and monitoring of the wind turbine blade continues. If the remaining fatigue life at the current moment is lower than the life threshold, the wind turbine blade is determined to be in a state of fatigue failure, and a fatigue life danger warning is issued.

7. A method for predicting the fatigue life of wind turbine blades, characterized in that, The method for predicting the fatigue life of a wind turbine blade is executed by the wind turbine blade fatigue life prediction platform described in any one of claims 1-6, and the specific steps include: Step 1: Construct the geometric model and experimental specimen of the wind turbine blade according to the design parameters, conduct fatigue performance tests on the experimental specimen to obtain the ultimate fatigue cycle number under different stresses, and plot the SN curve. Perform finite element analysis on the geometric model and calibrate the geometric model based on the SN curve. Step 2: Collect the stress values ​​of the wind turbine blades during historical operation, obtain the number of fatigue cycles of the wind turbine blades under the stress values ​​during historical operation through finite element analysis, and analyze the damage status at the current moment based on the number of fatigue cycles. Step 3: Obtain historical operating data of wind turbine blades, assign corresponding failure probabilities through expert scoring, use historical operating data of wind turbine blades as input, use corresponding failure probabilities as labels, and build a failure prediction model based on machine learning model; Step 4: Collect the current operating data of the wind turbine blades and the environmental data of their location. Input the operating data into the trained fault prediction model to obtain the fault probability at the current moment and analyze the impact of the current environmental data on the fatigue life of the wind turbine blades. Step 5: Based on the current damage status, failure probability, and environmental data of the wind turbine blades, analyze the remaining fatigue life of the wind turbine blades at the current moment, and determine whether to issue an early warning for the remaining fatigue life at the current moment.

Images