A fan blade life assessment and stepwise utilization method and system

Abstract

This application provides a method and system for assessing the lifespan and tiered utilization of wind turbine blades. The method involves acquiring operational monitoring data and damage detection information of the wind turbine blades; based on the operational monitoring data, constructing a joint evaluation framework of a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics; determining the remaining lifespan of the wind turbine blades by cross-validating and weighted summation of the outputs of both models; generating targeted repair decisions based on the remaining lifespan and the damage type, location, and severity contained in the damage detection information; and performing repair treatment on the wind turbine blades according to these decisions; evaluating the performance of the repaired wind turbine blades; and classifying the blades into different tiered utilization levels based on the evaluation results and preset performance thresholds for corresponding reuse treatment. This approach improves the accuracy of lifespan assessment and the efficiency of tiered utilization.

Description

Technical Field

[0001] This application relates to the field of wind turbine technology, and in particular to a method and system for assessing the lifespan of wind turbine blades and their secondary utilization. Background Technology

[0002] With the rapid development of wind power technology, the life assessment and secondary utilization of wind turbine blades, as core components of wind turbine generators, have become a focus of industry attention. In existing technologies, wind turbine blade life assessment mainly relies on single operational data monitoring or empirical formula calculations, resulting in low accuracy and an inability to fully consider material fatigue accumulation and real-time damage factors. Simultaneously, the secondary utilization of retired blades is often limited to simple recycling or disposal, lacking a systematic repair decision-making and performance grading mechanism, leading to resource waste and increased environmental burden. Therefore, existing methods for wind turbine blade life assessment and secondary utilization struggle to achieve accurate prediction and efficient reuse, and overall utilization efficiency needs improvement. Summary of the Invention

[0003] This application provides a method and system for wind turbine blade life assessment and secondary utilization, which can improve the accuracy of life assessment and the efficiency of secondary utilization.

[0004] In a first aspect, this application provides a method for assessing the lifespan of wind turbine blades and their subsequent reuse, including: Acquire operational monitoring data and damage detection information for wind turbine blades; Based on the aforementioned operational monitoring data, a joint evaluation framework is constructed, consisting of a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics. By cross-validating and weighting the outputs of both models, the remaining lifespan of the wind turbine blades is determined. Based on the remaining lifespan and the damage type, location, and extent contained in the damage detection information, a targeted repair decision is generated, and the wind turbine blades are repaired according to the decision. The performance of the repaired wind turbine blades is evaluated, and based on the evaluation results and preset performance thresholds, the blades are divided into different tiers of utilization for corresponding reuse treatment.

[0005] In some embodiments, based on the operational monitoring data, a joint evaluation framework is constructed, comprising a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue properties, including: Extract real-time load spectra from the operational monitoring data, including time-domain or frequency-domain data of aerodynamic loads, gravity loads, and vibration loads; The material SN curve of the wind turbine blade is obtained to characterize the fatigue life of the material under different stress levels, as well as the preset damage judgment threshold. Based on the real-time load spectrum, the material SN curve, and the damage determination threshold, the cumulative damage value is calculated using Miner's rule or nonlinear damage theory, and is used as the output of the cumulative damage calculation model.

[0006] In some embodiments, a joint evaluation framework for constructing a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue properties, based on the operational monitoring data, further includes: The time-series prediction model is trained based on the operational monitoring data. The time-series prediction model uses a long short-term memory network or a gated recurrent unit to perform time-series analysis on historical operational data and outputs a remaining lifetime prediction value, which is expressed in time units.

[0007] In some embodiments, the remaining lifespan of the wind turbine blades is determined by cross-validating and weighting the outputs of both, including: The output of the time-series prediction model, the predicted remaining lifetime, and the output of the cumulative damage calculation model, the cumulative damage, are both normalized to the same evaluation dimension, such as the percentage of remaining lifetime. Perform a correlation analysis to verify the consistency between the two outputs; The weighting coefficients are determined based on the correlation results, and the final remaining lifetime is obtained by weighted comprehensive calculation.

[0008] In some embodiments, a targeted repair decision is generated based on the remaining lifetime and the damage type, location, and extent contained in the damage detection information, including: Assess structural safety constraints to ensure that the repaired structure meets the strength requirements of GB / T 25383 standard; Assess economic feasibility constraints to ensure that repair costs are lower than the cost of purchasing new blades or the benefits of cascade utilization. Assess process feasibility constraints to ensure that the location and extent of damage are compatible with existing repair techniques; Repair decisions are generated based on the remaining lifetime, damage detection information, and the three constraints.

[0009] In some embodiments, performing repair procedures on the wind turbine blades based on the decision includes: Crack damage can be repaired by filling or patching. Vacuum resin infusion was used to repair delamination damage; Surface corrosion can be repaired with a coating. The repair quality is monitored in real time during the repair process to ensure that it meets the constraints of structural safety, economic feasibility, and technological feasibility.

[0010] In some embodiments, a performance evaluation of the repaired wind turbine blades is performed, including: Perform structural strength assessment by measuring deflection and strain values ​​through static load tests; Perform aerodynamic performance evaluation and measure the lift-to-drag ratio through wind tunnel testing; Perform fatigue performance assessment by measuring the damage propagation rate through accelerated fatigue testing; Perform a sealing assessment and obtain results through waterproofing and corrosion resistance testing.

[0011] In some embodiments, based on the evaluation results and preset performance thresholds, the blades are divided into different utilization levels, including: The first-level tier is defined as a downgraded tier for low-wind-speed wind fields, with a threshold requirement that the core indicators be no less than 80% of the original indicators; The second-tier is defined as being converted into photovoltaic support structures or building sound barriers, with the threshold requirement only being static load-bearing capacity; The three-tiered crushing and recycling process is defined as a raw material for composite materials, with the threshold requirement only being the purity of the components. The classification is based on the assessment results and the corresponding scenario thresholds.

[0012] In some embodiments, acquiring operational monitoring data and damage detection information of wind turbine blades further includes: Real-time operational monitoring data is collected through sensors, including rotational speed, wind speed, and vibration data. Damage detection information is obtained through non-destructive testing techniques such as ultrasound or thermal imaging.

[0013] In some embodiments, constructing a joint evaluation framework further includes: When training the time-series prediction model, supervised learning is performed using historical damage data, and the model parameters are optimized through cross-validation.

[0014] In some embodiments, the corresponding reuse process is performed, including: For the first-stage blades, adjust the installation position to match the low-load environment; For the second-stage blades, cutting and modification are carried out; For the three-stage stepped blades, mechanical crushing and material separation are performed.

[0015] Secondly, this application provides a wind turbine blade life assessment and cascade utilization system, which includes: The data acquisition module is used to acquire operational monitoring data and damage detection information of the wind turbine blades; The processing module is used to construct a joint evaluation framework based on the operation monitoring data, which is a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics. By cross-validating and weighting the outputs of the two models, the remaining life of the wind turbine blades is determined. The processing module is also used to generate targeted repair decisions based on the remaining lifespan and the damage type, location and extent contained in the damage detection information, and to perform repair treatment on the wind turbine blades based on the decisions. The execution module is used to evaluate the performance of the repaired wind turbine blades and, based on the evaluation results and preset performance thresholds, classify the blades into different tiers of utilization levels to perform corresponding reuse processes.

[0016] Thirdly, this application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to acquire the code and execute the above-described method for wind turbine blade life assessment and secondary utilization.

[0017] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for wind turbine blade life assessment and secondary utilization.

[0018] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: This application constructs a joint evaluation framework combining a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics. By cross-validating and weighting the outputs of both models, the remaining life of wind turbine blades can be determined more accurately. Based on the remaining life and damage detection information, targeted repair decisions are generated and repair processes are executed, improving the repair efficiency and quality of the blades. After repair, the blades are reused in stages by classifying them into different utilization levels through performance evaluation and preset performance thresholds, thereby reducing resource waste and improving overall utilization efficiency. Attached Figure Description

[0019] Figure 1 This is an exemplary flowchart of a method for assessing the blade life of a wind turbine and its secondary utilization, as shown in some embodiments of the present invention. Figure 2 This is an exemplary flowchart illustrating the determination of the remaining life of a wind turbine blade according to some embodiments of the present invention. Figure 3 This is a schematic diagram of a wind turbine blade life assessment and cascade utilization system according to some embodiments of the present invention; Figure 4 This is a schematic diagram of the structure of a computer device for realizing a method for assessing the blade life of a wind turbine and its secondary utilization, as shown in some embodiments of the present invention. Detailed Implementation

[0020] To better understand the above technical solutions, a detailed description of the solutions will be provided below in conjunction with the accompanying drawings and specific implementation methods. (Reference)Figure 1 The figure is an exemplary flowchart of a method for assessing and reusing the blade life of a wind turbine according to some embodiments of the present invention. The method mainly includes the following steps: In step 101, the operation monitoring data and damage detection information of the wind turbine blades are obtained.

[0021] Among them, operation monitoring data refers to the real-time data records of wind turbine blades in the actual operating environment, such as rotational speed, wind speed, vibration data, etc. These data are used to reflect the load and fatigue state of the blades. In some embodiments, operation monitoring data, including rotational speed, wind speed and vibration data, are collected in real time by sensors; damage detection information is obtained by non-destructive testing technologies such as ultrasonic or thermal imaging. For example, ultrasonic testing can identify internal cracks, and thermal imaging can detect surface thermal anomalies, which will not be elaborated here.

[0022] It should be noted that the damage detection information in this invention includes damage type, damage location, and damage degree. This information can be obtained through regular inspections or online monitoring systems to form a spatiotemporally correlated dataset. The damage type can be, for example, cracks, delamination, corrosion, etc., the damage location can be, for example, the root, middle, or tip of the blade, etc., and the damage degree can be, for example, crack length and depth, etc., which will not be elaborated here.

[0023] In step 102, based on the operational monitoring data, a joint evaluation framework is constructed, consisting of a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics. By cross-validating and weighting the outputs of the two models, the remaining lifespan of the wind turbine blades is determined.

[0024] The joint evaluation framework refers to a hybrid evaluation system that combines a data-driven model (black box model) and a physical model (white box model). The data-driven time-series prediction model is one of the core models used in this application for the remaining life assessment of wind turbine blades, and it is obtained in the following manner: First, data preparation: collect wind turbine blade operation monitoring data (including speed, wind speed, vibration, etc.), clean and standardize the data, and combine it with historical damage data to form a training dataset; Secondly, model selection: Long Short-Term Memory Network (LSTM) or Gated Recurrent Unit (GRU) is selected as the core of the model to adapt to the extraction of time-related features of time series data; Secondly, training optimization: Supervised learning training is performed based on the training dataset, and model parameters (such as the number of hidden layer nodes and the learning rate) are optimized through cross-validation (e.g., k-fold). In specific implementation, supervised learning training uses wind turbine blade operation monitoring data with historical damage labels as the training set, allowing the model to learn the mapping relationship between historical operation data and remaining lifespan, completing the initial training; while k-fold cross-validation optimization divides the training set into k parts, uses k-1 parts for training and 1 part for validation in turn, repeats this k times, and takes the average performance to adjust the model parameters, avoid overfitting, and determine the optimal parameter combination, which will not be elaborated here; Finally, the output results are as follows: After training, the model performs time-series analysis on historical operating data and finally outputs the predicted value of the remaining blade life in units of time.

[0025] Furthermore, the cumulative damage calculation model based on material fatigue characteristics in this application is the core physical model of the joint evaluation framework of this application, and it is obtained in the following manner: First, acquire the core input data: extract the real-time load spectrum (including time-domain / frequency-domain data of aerodynamic, gravity, and vibration loads) from the wind turbine blade operation monitoring data; at the same time, acquire the blade material SN curve (which characterizes the fatigue life of the material under different stress levels) and the preset damage judgment threshold.

[0026] Secondly, select a computational theory: adopt Miner's rule or nonlinear damage theory as the basis for calculating damage accumulation.

[0027] Finally, the calculation output results are as follows: Combining the above input data and calculation theory, the degree of damage accumulation of the blade during operation is quantified, and the dimensionless cumulative damage value is finally output, thus completing the model construction.

[0028] In some embodiments, the joint evaluation framework for constructing a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics, based on the operational monitoring data, can be implemented in the following manner: Extract real-time load spectra from the operational monitoring data, including time-domain or frequency-domain data of aerodynamic loads, gravity loads, and vibration loads; Obtain the material SN curve of the wind turbine blades to characterize the fatigue life of the material under different stress levels, as well as the preset damage judgment threshold. Based on the real-time load spectrum, the material SN curve, and the damage determination threshold, the cumulative damage value can be calculated using Miner's rule or nonlinear damage theory, and used as the output of the cumulative damage calculation model.

[0029] In some embodiments, the joint evaluation framework, which constructs a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue properties based on the operational monitoring data, further includes: The time-series prediction model is trained based on the operational monitoring data. The time-series prediction model uses a long short-term memory network or a gated recurrent unit to perform time-series analysis on historical operational data and outputs a remaining lifetime prediction value, which is expressed in time units.

[0030] In addition, when training the time-series prediction model, historical damage data is used for supervised learning, and the model parameters are optimized through cross-validation. For example, k-fold cross-validation can be used to evaluate the model's generalization ability, which will not be elaborated here.

[0031] It should be noted that the joint evaluation framework in this application adopts a hierarchical collaboration + module linkage structure, with the core divided into 4 levels to ensure the collaboration of the two models from data input to result output throughout the entire process. Parallel computing of the two models ensures efficiency, the fusion verification layer solves the limitations of a single model, and the feedback mechanism enables dynamic optimization of the framework.

[0032] The input data collaboration mechanism for the two models is based on the unification and sharing of input data. This ensures that the two models perform calculations based on data from the same source and standardized data, avoiding result deviations due to data differences. The specific process is as follows: 1. Unified data collection and cleaning: Raw operational data such as rotation speed, wind speed, and vibration are collected by sensors, and after filtering, outlier removal, and data completion, a standardized operational monitoring dataset is obtained; 2. Data allocation and sharing on demand: Allocation to the cumulative damage calculation model: real-time load spectrum (time-domain / frequency-domain data of aerodynamic load, gravity load, and vibration load) extracted from standardized data, material SN curves (pre-acquired fatigue characteristic data of blade materials), and preset damage judgment thresholds; Allocation to the time-series prediction model: standardized historical operating data and real-time operating data fragments; Shared constraints: Both use the same time dimension and have the same statistical caliber for load data.

[0033] Regarding the specific execution process of cross-validation, since cross-validation is the core of the joint framework, its purpose is to verify the reliability of the output results of the two models and provide a basis for subsequent weighted fusion. The specific steps are as follows: 1. Result Normalization: Convert the outputs of the two models to the same evaluation dimension (to avoid differences in units). For example: the time series prediction model outputs the remaining lifetime prediction value (e.g., 5 years), which is normalized to the remaining lifetime percentage (assuming a design life of 20 years, then the 5-year percentage is 25%); the cumulative damage calculation model outputs the cumulative damage value (e.g., 0.6, i.e., cumulative damage of 60%), which is normalized to the remaining lifetime percentage (1-0.6=40%). 2. Consistency Analysis: The consistency of the normalization results of the two models is verified using indicators such as Pearson correlation coefficient and mean squared error (MSE). If the Pearson correlation coefficient is ≥0.7, it is considered high consistency, indicating that the two models have the same trend in judging the blade state. If 0.5≤correlation coefficient<0.7, it is considered medium consistency, and it is necessary to check whether there is any deviation in the model input data or parameters. If the correlation coefficient<0.5, it is considered low consistency, triggering anomaly investigation, such as errors in load spectrum extraction, insufficient time series model training data, and mismatch between the material SN curve and the actual blade material. 3. Result Correction: For medium / low consistency scenarios, corrections can be made in the following ways: Temporal prediction model: Retraining by supplementing historical damage data and optimizing parameters such as the number of hidden layer nodes and learning rate of the Long Short-Term Memory Network (LSTM) / Gated Recurrent Unit (GRU); Cumulative damage calculation model: Re-verify the accuracy of the material's SN curve, or change the damage calculation theory, for example, from Miner's rule to nonlinear damage theory.

[0034] For the dynamic weighted fusion strategy (final remaining lifetime calculation), since the core of weighted fusion is to allocate weights based on consistent results, the output of the more reliable model will have a higher proportion. The specific implementation method is as follows: 1. Rules for determining weighting coefficients: Let the weight of the time series prediction model be ω1, and the weight of the cumulative damage calculation model be ω2 (ω1+ω2=1); when the correlation coefficient r≥0.7 (high consistency): ω1=r, ω2=1-r (e.g., if r=0.8, then ω1=0.8, ω2=0.2), that is, the higher the consistency, the more the weight allocation tends to be synergistic between the two. When 0.5 ≤ r < 0.7 (moderate consistency): ω1 = ω2 = 0.5 (average weight) to avoid the influence of single model bias on the results; When the correlation coefficient r < 0.5 (low consistency): the cumulative damage calculation model (ω2=0.7, ω1=0.3) is preferred because this model is based on the physical properties of materials, has stronger stability, and triggers iterative optimization of the model. 3. Calculation of final remaining lifetime: Based on the normalized remaining lifetime percentage, substitute into the weighted formula: that is, final remaining lifetime percentage = ω1 × normalized result of time series model + ω2 × normalized result of cumulative damage model. Then convert the percentage back to time unit. For example, if the percentage is 30% and the design life is 20 years, then the final remaining lifetime = 6 years.

[0035] The iterative optimization and closed-loop update of the framework are not static, but can be continuously optimized through result feedback and model tuning to ensure long-term evaluation accuracy, which will not be elaborated here.

[0036] It should be noted that the essence of the above joint framework is that the physical model (cumulative damage calculation) ensures reliability, and the data-driven model (time series prediction) improves sensitivity. Through the whole process of unified data input, parallel calculation of dual models, cross-validation consistency, dynamic weighted fusion, and closed-loop iterative optimization, the accuracy and stability of remaining life assessment are achieved, which solves the limitations of single models that ignore material properties or real-time data. This will not be elaborated here.

[0037] In some embodiments, reference Figure 2 As shown, the remaining lifespan of the wind turbine blades can be determined by cross-validating and weighting the outputs of both methods, as follows: In step 1021, the output remaining lifetime prediction value of the time series prediction model and the output cumulative damage value of the cumulative damage calculation model are normalized to the same evaluation dimension, such as the remaining lifetime percentage. In step 1022, a correlation analysis is performed to verify the consistency between the two outputs; In step 1023, weighting coefficients are determined based on the correlation results, and weighted comprehensive calculations are performed to obtain the final remaining lifetime.

[0038] It should be noted that the correlation analysis can use the Pearson correlation coefficient. If the coefficient is greater than 0.7, it is considered to have high consistency. The weighting coefficient can be dynamically adjusted. For example, the weights of the time series model can be a function of the correlation coefficient, which will not be elaborated here.

[0039] In step 103, a targeted repair decision is generated based on the remaining lifespan and the damage type, location, and extent contained in the damage detection information, and the wind turbine blades are repaired according to the decision.

[0040] Here, repair decision refers to a repair scheme generated based on multiple constraints. In some embodiments, generating a targeted repair decision based on the remaining lifetime and the damage type, location, and extent contained in the damage detection information specifically includes: Assess structural safety constraints to ensure that the repaired structure meets the strength requirements of GB / T 25383 standard; Assess economic feasibility constraints to ensure that repair costs are lower than the cost of purchasing new blades or the benefits of cascade utilization. Assess process feasibility constraints to ensure that the location and extent of damage are compatible with existing repair techniques; Repair decisions are generated based on the remaining lifetime, damage detection information, and the three constraints.

[0041] In some embodiments, performing repair treatment on the wind turbine blades based on the decision specifically includes: Crack damage can be repaired by filling or patching. Vacuum resin infusion was used to repair delamination damage; Surface corrosion can be repaired with a coating. The repair quality is monitored in real time during the repair process to ensure that it meets the constraints of structural safety, economic feasibility, and technological feasibility.

[0042] It should be noted that real-time monitoring can be achieved through embedded sensors or re-inspection technology, such as performing ultrasonic re-inspection immediately after repair, which will not be elaborated here.

[0043] In step 104, the performance of the repaired wind turbine blades is evaluated, and based on the evaluation results and preset performance thresholds, the blades are divided into different tiers of utilization to perform corresponding reuse treatment.

[0044] Among these, performance evaluation refers to multi-index system testing. In some embodiments, the performance evaluation of the repaired wind turbine blades specifically includes: Perform structural strength assessment by measuring deflection and strain values ​​through static load tests; Perform aerodynamic performance evaluation and measure the lift-to-drag ratio through wind tunnel testing; Perform fatigue performance assessment by measuring the damage propagation rate through accelerated fatigue testing; Perform a sealing assessment and obtain results through waterproofing and corrosion resistance testing.

[0045] In some embodiments, classifying the blades into different utilization levels based on the evaluation results and preset performance thresholds specifically includes: The first-level tier is defined as a downgraded tier for low-wind-speed wind fields, with a threshold requirement that the core indicators be no less than 80% of the original indicators; The second-tier is defined as being converted into photovoltaic support structures or building sound barriers, with the threshold requirement only being static load-bearing capacity; The three-tiered crushing and recycling process is defined as a raw material for composite materials, with the threshold requirement only being the purity of the components. The classification is based on the assessment results and the corresponding scenario thresholds.

[0046] In some embodiments, performing the corresponding reuse process specifically includes: For the first-stage blades, adjust the installation position to match the low-load environment; For the second-stage blades, cutting and modification are carried out; For the three-stage stepped blades, mechanical crushing and material separation are performed.

[0047] Furthermore, in another aspect of the present invention, in some embodiments, the present invention provides a system for assessing and reusing the blade life of a wind turbine, with reference to... Figure 3 The figure is a schematic diagram of a wind turbine blade life assessment and secondary utilization system according to some embodiments of the present invention. The wind turbine blade life assessment and secondary utilization system includes: a data acquisition module 301, a processing module 302, and an execution module 303, which are described below: The data acquisition module 301 in this invention is mainly used to acquire the operation monitoring data and damage detection information of the wind turbine blades. Processing module 302, in this invention, is mainly used to construct a joint evaluation framework of a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics based on the operation monitoring data. By cross-validating and weighting the outputs of the two, the remaining life of the wind turbine blades is determined. It should be noted that the processing module 302 described in this application is also used to generate a targeted repair decision based on the remaining lifespan and the damage type, location and extent contained in the damage detection information, and to perform repair processing on the wind turbine blades based on the decision. The execution module 303 in this invention is mainly used to evaluate the performance of the repaired wind turbine blades, and to classify the blades into different tiers of utilization based on the evaluation results and preset performance thresholds, so as to perform corresponding reuse processing.

[0048] In addition, the present invention also provides a computer device, the computer device including a memory and a processor, the memory storing code, the processor being configured to acquire the code and execute the above-described method for assessing the blade life of a wind turbine and its secondary utilization.

[0049] In some embodiments, reference Figure 4 This figure is a schematic diagram of the structure of a computer device for implementing a method for assessing and reusing the blade life of a wind turbine, according to some embodiments of the present invention. The methods in the above embodiments can be implemented through... Figure 4 The computer device shown is used to implement this, and the computer device 400 includes at least one processor 401, a communication bus 402, a memory 403, and at least one communication interface 404.

[0050] The processor 401 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the blade life assessment and cascade utilization method of the wind turbine in this invention.

[0051] The communication bus 402 may include a path for transmitting information between the aforementioned components.

[0052] The memory 403 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or it may be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CDROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. The memory 403 may exist independently and be connected to the processor 401 via a communication bus 402. The memory 403 may also be integrated with the processor 401.

[0053] The memory 403 stores program code for executing the present invention, and its execution is controlled by the processor 401. The processor 401 executes the program code stored in the memory 403. The program code may include one or more software modules. In the above embodiments, the determination of the remaining lifetime can be achieved by the processor 401 and one or more software modules in the program code in the memory 403.

[0054] Communication interface 404 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0055] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single CPU) processor or a multi-core (multi CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0056] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This embodiment of the invention does not limit the type of computer device.

[0057] In addition, the present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-described method for assessing the blade life of a wind turbine and its secondary utilization.

[0058] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0059] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for assessing the lifespan of wind turbine blades and for their tiered utilization, characterized in that, Includes the following steps: Acquire operational monitoring data and damage detection information for wind turbine blades; Based on the aforementioned operational monitoring data, a joint evaluation framework is constructed, consisting of a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics. By cross-validating and weighting the outputs of both models, the remaining lifespan of the wind turbine blades is determined. Based on the remaining lifespan and the damage type, location, and extent contained in the damage detection information, a targeted repair decision is generated, and the wind turbine blades are repaired according to the decision. The performance of the repaired wind turbine blades is evaluated, and based on the evaluation results and preset performance thresholds, the blades are divided into different tiers of utilization for corresponding reuse treatment.

2. The method for assessing and utilizing wind turbine blade life according to claim 1, characterized in that, Based on the aforementioned operational monitoring data, a joint evaluation framework is constructed, comprising a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue properties, including: Extract real-time load spectra from the operational monitoring data, including time-domain or frequency-domain data of aerodynamic loads, gravity loads, and vibration loads; The material SN curve of the wind turbine blade is obtained to characterize the fatigue life of the material under different stress levels, as well as the preset damage judgment threshold. Based on the real-time load spectrum, the material SN curve, and the damage determination threshold, the cumulative damage value is calculated using Miner's rule or nonlinear damage theory, and is used as the output of the cumulative damage calculation model.

3. The method for assessing and utilizing wind turbine blade life according to claim 1, characterized in that, Based on the aforementioned operational monitoring data, a joint evaluation framework is constructed, comprising a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue properties. This framework further includes: The time-series prediction model is trained based on the operational monitoring data. The time-series prediction model uses a long short-term memory network or a gated recurrent unit to perform time-series analysis on historical operational data and output a predicted value for remaining lifetime.

4. The method for assessing and utilizing wind turbine blade life according to claim 1, characterized in that, The process of determining the remaining lifespan of the wind turbine blades by cross-validating and weighting the outputs of both methods includes: The remaining lifetime prediction value of the time-series prediction model and the cumulative damage value of the cumulative damage calculation model are both normalized to the same evaluation dimension. Perform a correlation analysis to verify the consistency between the two outputs; The weighting coefficients are determined based on the correlation results, and the final remaining lifetime is obtained by weighted comprehensive calculation.

5. The method for assessing and utilizing wind turbine blade life according to claim 1, characterized in that, The step of generating targeted repair decisions based on the remaining lifespan and the damage type, location, and extent contained in the damage detection information includes: Assess structural safety constraints to ensure that the repaired structure meets the strength requirements of GB / T 25383 standard; Assess economic feasibility constraints to ensure that repair costs are lower than the cost of purchasing new blades or the benefits of cascade utilization. Assess process feasibility constraints to ensure that the location and extent of damage are compatible with existing repair techniques; Repair decisions are generated based on the remaining lifetime, damage detection information, and the three constraints.

6. The method for assessing and reusing wind turbine blade life according to claim 5, characterized in that, The repair process for the wind turbine blades based on this decision includes: Crack damage can be repaired by filling or patching. Vacuum resin infusion was used to repair delamination damage; Surface corrosion can be repaired with a coating. The repair quality is monitored in real time during the repair process to ensure that it meets the constraints of structural safety, economic feasibility, and technological feasibility.

7. The method for assessing and utilizing wind turbine blade life according to claim 1, characterized in that, The performance evaluation of the repaired wind turbine blades includes: Perform structural strength assessment by measuring deflection and strain values ​​through static load tests; Perform aerodynamic performance evaluation and measure the lift-to-drag ratio through wind tunnel testing; Perform fatigue performance assessment by measuring the damage propagation rate through accelerated fatigue testing; Perform a sealing assessment and obtain results through waterproofing and corrosion resistance testing.

8. The method for assessing and reusing wind turbine blade life according to claim 1, characterized in that, The process of classifying blades into different utilization levels based on evaluation results and preset performance thresholds includes: The first-level tier is defined as a downgraded tier for low-wind-speed wind fields, with a threshold requirement that the core indicators be no less than 80% of the original indicators; The second-tier is defined as being converted into photovoltaic support structures or building sound barriers, with the threshold requirement only being static load-bearing capacity; The three-tiered crushing and recycling process is defined as a raw material for composite materials, with the threshold requirement only being the purity of the components. The classification is based on the assessment results and the corresponding scenario thresholds.

9. The method for assessing and utilizing wind turbine blade life according to claim 1, characterized in that, The acquisition of operational monitoring data and damage detection information of wind turbine blades also includes: Real-time operational monitoring data is collected through sensors, including rotational speed, wind speed, and vibration data. Damage detection information is obtained through non-destructive testing techniques.

10. The method for assessing and reusing wind turbine blade life according to claim 1, characterized in that, The construction of the joint evaluation framework also includes: When training the time-series prediction model, supervised learning is performed using historical damage data, and the model parameters are optimized through cross-validation.

11. The method for assessing and utilizing wind turbine blade life according to claim 1, characterized in that, The execution of the corresponding reuse process includes: For the first-stage blades, adjust the installation position to match the low-load environment; For the second-stage blades, cutting and modification are carried out; For the three-stage stepped blades, mechanical crushing and material separation are performed.

12. A system for assessing the lifespan of wind turbine blades and for their reuse, characterized in that, include: The data acquisition module is used to acquire operational monitoring data and damage detection information of the wind turbine blades; The processing module is used to construct a joint evaluation framework based on the operation monitoring data, which is a data-driven time-series prediction model and a cumulative damage calculation model based on material fatigue characteristics. By cross-validating and weighting the outputs of the two models, the remaining life of the wind turbine blades is determined. The processing module is also used to generate targeted repair decisions based on the remaining lifespan and the damage type, location and extent contained in the damage detection information, and to perform repair treatment on the wind turbine blades based on the decisions. The execution module is used to evaluate the performance of the repaired wind turbine blades and, based on the evaluation results and preset performance thresholds, classify the blades into different tiers of utilization to perform corresponding reuse processes.

Images