Wind driven generator blade overload and fatigue damage early warning method and device and medium

Abstract

The invention provides a wind driven generator blade overload and fatigue damage early warning method and device and a medium, and belongs to the field of wind power generation. The method comprises the steps of obtaining strain information of a blade; determining an accumulated fatigue damage index of the blade according to the strain information; determining whether a strain threshold is exceeded according to the strain information; determining whether the accumulated fatigue damage index exceeds an accumulated fatigue damage early warning threshold value or not according to the accumulated fatigue damage index; and when it is determined that the strain information exceeds a strain threshold value or the accumulated fatigue damage index exceeds an accumulated fatigue damage early warning threshold value, giving out blade overload or fatigue early warning. The early warning of exceeding the strain threshold value can prompt a user of the real-time load condition of each detection point on the fan blade, and the accumulated fatigue damage early warning can prompt the user of the accumulated damage condition of the fan blade, so that the user can maintain and troubleshoot the wind turbine generator according to the real-time load and the accumulated damage arrangement, and the service life of the wind turbine generator is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a method for early warning of overload and fatigue damage of wind turbine blades, a device for early warning of overload and fatigue damage of wind turbine blades, and a machine-readable storage medium. Background Art

[0002] Wind turbines convert wind energy into mechanical energy through the rotation of blades, and then convert it into electrical energy through generators. As a key component of wind turbines, the health of blades determines the power generation of wind turbines and the safety of the whole machine. In order to balance the aerodynamic shape and structural performance of blades, the blades of existing domestic wind turbines are all made of glass fiber or carbon fiber composite materials. This makes the blades prone to self-damage during operation when facing the invasion of the surrounding environment such as temperature, wind and sand, hail, typhoons, etc., such as cracking, sand holes, cracks, etc. At the same time, the stress state of the blades is extremely complex. During the rotation process, the blades are subjected to alternating cycles of external forces such as aerodynamic loads, gravity, centrifugal force, etc., making fatigue damage and stress damage to the blades inevitable. If these blade damages are not discovered, warned and repaired in time, as cracks, sand holes, etc. further expand, they may cause large-scale damage or even breakage of the blades, greatly affecting the power generation and life of the wind turbine, causing huge economic losses to the wind farm.

[0003] At present, the health monitoring of blades is still based on manual inspections. By formulating regular and special inspection plans, technical workers are arranged to climb high to conduct close inspections of blades. This method requires a large amount of manpower, is inefficient, and takes a long time. There are also certain operational safety risks during the manual inspection process. In addition, the wind turbine needs to be shut down during the manual inspection, which also has a certain negative impact on power generation. In order to reduce the labor cost required for blade monitoring and the power generation loss caused by shutdown during the inspection, the wind turbine blade inspection system based on drones has become a popular solution. This solution mainly diagnoses the damage of wind turbine blades based on high-definition photos of blades taken by ultra-high-pixel high-speed cameras carried by drones. However, this method can only monitor existing visible damage such as cracks and wrinkles on the surface of the blades. It is impossible to monitor and assess the risk of internal damage and potential damage to the blades, and it is also difficult to achieve real-time remote monitoring of the blade status.

[0004] Liu Xiaoying and others from Huazhong University of Science and Technology proposed a remote online monitoring system based on sound features and neural networks. This method uses outdoor microphones distributed around the wind turbine to collect sound signals generated by different wind turbine blades during operation, and transmits them to the trained BP neural network to judge the health status of the wind turbine blades and output the judgment results. This method places relatively high requirements on the noise reduction processing of the collected audio signals and the reliability of the BP neural network model. In order to obtain a neural network model with high prediction accuracy and a wide range of applications, the collection and establishment of the data set used to train the model should ideally be based on wind turbines in multiple scenarios, multiple states, and real wind farms, which requires long-term data accumulation. In addition, the outdoor microphone requires stable voltage support during operation, which is also a test for the power supply system.

[0005] Optical fiber strain sensors have gained more and more attention due to their high sensitivity, good electrical insulation performance, low transmission energy consumption, large transmission capacity and anti-electromagnetic interference. Song Tingxin and Li Jingli proposed a blade damage identification and early warning system based on fiber grating. This method determines whether the blade resonates based on the strain data collected by the grating, and determines the degree of damage based on deep learning. Similar to the above-mentioned solution by Liu Xiaoying et al., how to ensure that the deep learning model has the ability to accurately predict blade damage through strain requires in-depth thinking. Summary of the invention

[0006] The purpose of the embodiments of the present invention is to provide a method, device and medium for warning of overload and fatigue damage of wind turbine blades. The method calculates the cumulative fatigue damage index of the blades based on strain information, and issues warnings based on two situations: the single strain of the blade exceeds the strain threshold and the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold. The warning of exceeding the strain threshold can prompt the user of the real-time load condition of each detection point on the wind turbine blade, and the cumulative fatigue damage warning can prompt the user of the cumulative damage condition of the wind turbine blade, so that the user can arrange maintenance and inspection of the wind turbine set according to the real-time load and cumulative damage, thereby improving the service life of the set.

[0007] In order to achieve the above-mentioned object, the first aspect of the present invention provides a method for early warning of overload and fatigue damage of wind turbine blades, the method comprising: Obtaining the strain information of the blade; Determining a cumulative fatigue damage index of the blade according to the strain information; determining whether a strain threshold is exceeded according to the strain information; Determining whether a cumulative fatigue damage warning threshold is exceeded according to the cumulative fatigue damage index; When it is determined that the strain information exceeds the strain threshold or the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold, a blade overload or fatigue warning is issued.

[0008] According to the above technical means, the method calculates the cumulative fatigue damage index of the blade based on strain information, and issues warnings based on two situations: the single strain of the blade exceeds the strain threshold and the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold. The warning of exceeding the strain threshold can remind the user of the real-time load conditions of each detection point on the wind turbine blade, and the cumulative fatigue damage warning can remind the user of the cumulative damage conditions of the wind turbine blade, so that the user can arrange maintenance and inspection of the wind turbine according to the real-time load and cumulative damage, thereby improving the service life of the unit.

[0009] In some feasible embodiments, determining the cumulative fatigue damage index of the blade according to the strain information includes: generating a strain-time curve according to the strain information; determining a strain amplitude according to the strain-time curve; Obtaining fatigue life from a strain-fatigue life curve according to the strain amplitude; The fatigue damage index is calculated based on the fatigue life accumulation.

[0010] According to the above technical means, the strain amplitude can be determined according to the strain information, and then the fatigue life can be obtained according to the strain amplitude to calculate the fatigue damage index. The calculated fatigue damage index can better characterize the damage conditions at different key points of the blade.

[0011] In some feasible embodiments, calculating the fatigue damage index according to the fatigue life accumulation includes: The fatigue damage index is calculated based on the current fatigue life according to the Miner criterion.

[0012] In some feasible embodiments, determining the strain amplitude according to the strain-time curve includes: Determine the curvature of each point on the strain-time curve; The strain value of the curvature polarity change determined according to the curvature is the strain amplitude.

[0013] According to the above technical means, the strain value of the curvature polarity change on the strain-time curve corresponds to the peak value and the valley value on the strain-time curve, thereby the strain amplitude can be quickly determined.

[0014] In some feasible embodiments, the strain threshold is determined according to the limit strain value adopted in the blade design; and the strain-fatigue life curve is determined according to the Coffin-Manson model.

[0015] A second aspect of the present application provides a wind turbine blade overload and fatigue damage early warning device, the device comprising: The data acquisition system includes an optical fiber strain sensor and a signal processor. The optical fiber strain sensor is arranged at a key position of the blade to collect strain optical signals of the blade at the corresponding position. The signal processor is used to convert the strain optical signals collected by the optical fiber strain sensor into strain information. A data processing system is used to determine a cumulative fatigue damage index of a blade according to the strain information; determine whether a strain threshold is exceeded according to the strain information; determine whether a cumulative fatigue damage warning threshold is exceeded according to the cumulative fatigue damage index; and issue a blade overload or fatigue warning when it is determined that the strain information exceeds the strain threshold or the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold.

[0016] According to the above-mentioned technical means, the device calculates the cumulative fatigue damage index of the blade based on the strain information, and issues warnings according to two situations: the single strain of the blade exceeds the strain threshold and the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold. The warning of exceeding the strain threshold can remind the user of the real-time load condition of each detection point on the wind turbine blade, and the cumulative fatigue damage warning can remind the user of the cumulative damage condition of the wind turbine blade, so that the user can arrange maintenance and inspection of the wind turbine according to the real-time load and cumulative damage, thereby improving the service life of the unit.

[0017] In some feasible embodiments, determining the cumulative fatigue damage index of the blade according to the strain information includes: generating a strain-time curve according to the strain information; determining a strain amplitude according to the strain-time curve; Obtaining fatigue life from a strain-fatigue life curve according to the strain amplitude; The fatigue damage index is calculated based on the fatigue life accumulation.

[0018] According to the above technical means, the strain amplitude can be determined according to the strain information, and then the fatigue life can be obtained according to the strain amplitude to calculate the fatigue damage index. The calculated fatigue damage index can better characterize the damage conditions at different key points of the blade.

[0019] In some feasible embodiments, the key positions include at least a blade root, a blade tip, and a position of a blade with a maximum chord length.

[0020] According to the above technical means, the key positions can cover the positions on the blade that are prone to instability, fatigue damage and cracking.

[0021] In some feasible embodiments, the device further comprises: an interface display unit and a data cloud storage system; The interface display unit is connected to the data processing system and is used to visually display the strain at each key position of the blade and fatigue damage warning; The data cloud storage system is used to store strain thresholds, strain-fatigue life curves, and strain information collected by the data acquisition system, so that the data processing system can acquire and process them.

[0022] Based on the above technical means, the visualization display system can provide users with an intuitive blade display, allowing users to view the current and historical stress status of each blade in each wind turbine in the wind farm in real time. The data cloud storage system provides data support for early warning analysis.

[0023] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the wind turbine blade overload and fatigue damage early warning method.

[0024] Through the above technical scheme, the wind turbine blade overload and fatigue damage warning method provided by the present application calculates the cumulative fatigue damage index of the blade based on strain information, and issues warnings based on two situations: the single strain of the blade exceeds the strain threshold and the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold. The warning of exceeding the strain threshold can remind the user of the real-time load conditions of each detection point on the wind turbine blade, and the cumulative fatigue damage warning can remind the user of the cumulative damage conditions of the wind turbine blade, so that the user can arrange maintenance and inspection of the wind turbine according to the real-time load and cumulative damage, thereby improving the service life of the unit.

[0025] This method can be used to monitor the health status of blades in real time and remotely online, reducing the cost of manual inspections and the loss of power generation caused by wind turbine blade stoppage during inspections; the visual interface allows users to view the current and historical stress status of each blade in each wind turbine in the wind farm, and provides data support for whether the blades are cracked, the degree of cracking, and possible potential damage.

[0026] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 This is a flow chart of a method for early warning of overload and fatigue damage of wind turbine blades provided by one embodiment of the present invention; Figure 2 It is a schematic diagram of the cumulative fatigue damage calculation process provided by one embodiment of the present invention; Figure 3 The present invention is a block diagram of a wind turbine blade overload and fatigue damage early warning system provided in one embodiment of the present invention.

[0028] Description of Reference Numerals 1- Fiber optic strain sensor, 2- Data cloud storage system, 3- Data processing system, 4- Interface display unit. DETAILED DESCRIPTION

[0029] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0030] Figure 1 This is a flow chart of a method for early warning of overload and fatigue damage of wind turbine blades provided by one embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a method for early warning of overload and fatigue damage of wind turbine blades, the method comprising: S1: Obtaining strain information of the blade. In some feasible embodiments, the strain information of the blade is collected by optical fiber strain sensors distributed on the blade, converted into measured physical quantities by a signal processor and stored in a data cloud storage system. The method of the present application can directly read the strain information from the data cloud storage system. The strain information includes the strain amount and the acquisition time.

[0031] S2: Determine the cumulative fatigue damage index of the blade according to the strain information.

[0032] In some possible embodiments, Figure 2 As shown, determining the cumulative fatigue damage index of the blade according to the strain information includes: S201: Generate a strain-time curve according to the strain information. In the embodiment of the present application, the strain-time curve is generated with the strain amount as the ordinate and the time corresponding to the strain amount as the abscissa.

[0033] S202: Determine the strain amplitude according to the strain-time curve. In some feasible embodiments, determining the strain amplitude according to the strain-time curve includes: Determine the curvature of each point on the strain-time curve; The strain value of the curvature polarity change determined according to the curvature is the strain amplitude. The curvature polarity change refers to the curvature changing from positive to negative or from negative to positive. For example, if the curvature corresponding to the strain amount at the current moment is positive and the curvature corresponding to the strain amount at the next moment is negative, then the strain amount at the current moment is determined to be a strain amplitude; if the curvature corresponding to the strain amount at the current moment is negative and the curvature corresponding to the strain amount at the next moment is positive, then the strain amount at the current moment is determined to be a strain amplitude.

[0034] According to the above technical means, the strain value of the curvature polarity change on the strain-time curve corresponds to the peak value and the valley value on the strain-time curve, thereby the strain amplitude can be quickly determined.

[0035] S203: Obtain fatigue life from the strain-fatigue life curve according to the strain amplitude. In some feasible embodiments, the strain-fatigue life curve is determined according to the material at the corresponding key position, the horizontal coordinate of the strain-fatigue life curve is the fatigue life, and the vertical coordinate is the strain amount. The strain-fatigue life curve characterizes the total number of cycles that can be performed under the corresponding strain amplitude. The strain-fatigue life curve is determined according to the Coffin-Manson model. If the blade is subjected to component-level or full-scale fatigue testing, the strain-fatigue life curve is consistent with the test results. In an embodiment of the present application, the fatigue life is obtained by determining the point corresponding to the strain amplitude on the strain-fatigue life curve and determining the point corresponding to the strain amplitude according to the horizontal coordinate of the point corresponding to the strain amplitude.

[0036] S204: Calculating a fatigue damage index according to the fatigue life accumulation. In some feasible embodiments, calculating a fatigue damage index according to the fatigue life accumulation includes: The fatigue damage index is calculated based on the current fatigue life according to the Miner criterion. The current fatigue life represents the total number of cycles that can be performed under the current strain amplitude. The specific calculation formula is as follows: ; Where D is the fatigue damage index, D i-1 is the cumulative fatigue damage index before the current strain amplitude, is the current fatigue life. Theoretically, when D=0, it indicates that no fatigue damage has occurred; when D=1, it indicates that fatigue fracture has occurred at that position.

[0037] According to the above technical means, the strain amplitude can be determined according to the strain information, and then the fatigue life can be obtained according to the strain amplitude to calculate the fatigue damage index. The calculated fatigue damage index can better characterize the damage conditions at different key points of the blade.

[0038] S3: Determine whether the strain threshold is exceeded according to the strain information. In some feasible embodiments, the strain threshold is determined according to the limit strain value used in the blade design. It can be consistent with the limit strain value used in the blade structure design. It should be pointed out that if component-level or full-scale tests are carried out during the blade development stage, the strain thresholds at different positions can be determined in combination with the test results.

[0039] S4: Determine whether the cumulative fatigue damage warning threshold is exceeded according to the cumulative fatigue damage index. In some feasible embodiments, the cumulative fatigue damage warning threshold supports user customization.

[0040] S5: When it is determined that the strain information exceeds the strain threshold or the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold, a blade overload or fatigue warning is issued. In some feasible embodiments, the blade warning may include one or more of a sound warning, an indicator warning, or an interactive interface warning.

[0041] According to the above technical means, the method calculates the cumulative fatigue damage index of the blade based on strain information, and issues warnings based on two situations: the single strain of the blade exceeds the strain threshold and the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold. The warning of exceeding the strain threshold can remind the user of the real-time load conditions of each detection point on the wind turbine blade, and the cumulative fatigue damage warning can remind the user of the cumulative damage conditions of the wind turbine blade, so that the user can arrange maintenance and inspection of the wind turbine according to the real-time load and cumulative damage, thereby improving the service life of the unit.

[0042] The second aspect of the present application provides a wind turbine blade overload and fatigue damage early warning device, such as Figure 3 As shown, the device comprises: The data acquisition system comprises an optical fiber strain sensor 1 and a signal processor, wherein the optical fiber strain sensor 1 is arranged at a key position of the blade and is used to collect strain optical signals of the blade at the corresponding position, and the signal processor is used to convert the strain optical signals collected by the optical fiber strain sensor 1 into strain information; The data processing system 3 is used to determine the cumulative fatigue damage index of the blade according to the strain information; determine whether the strain threshold is exceeded according to the strain information; determine whether the cumulative fatigue damage warning threshold is exceeded according to the cumulative fatigue damage index; and issue a blade overload or fatigue warning when it is determined that the strain information exceeds the strain threshold or the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold.

[0043] In some feasible embodiments, the optical fiber strain sensor 1 is distributed at the key position of the blade structure and is responsible for collecting the strain of the blade at this position. The optical fiber strain sensor 1 is arranged before the blade is molded, and the specific measurement point arrangement position needs to be combined with the blade test results or finite element analysis results. In some feasible embodiments, the key positions include but are not limited to the blade root, blade tip and the maximum chord length position of the blade body. The key positions can cover the positions on the blades that are prone to instability, fatigue damage and cracking. The measurement point positions on the blades of different units in the same wind farm are arranged in the same way, which can facilitate later data processing and visualization. The optical fiber strain sensor 1 is selectively arranged at the key position of the blade structure, which reduces the cost while maximizing the quality of the collected data and improving the reliability of damage assessment and blade damage warning based on the collected data.

[0044] According to the above-mentioned technical means, the device calculates the cumulative fatigue damage index of the blade based on the strain information, and issues warnings according to two situations: the single strain of the blade exceeds the strain threshold and the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold. The warning of exceeding the strain threshold can remind the user of the real-time load condition of each detection point on the wind turbine blade, and the cumulative fatigue damage warning can remind the user of the cumulative damage condition of the wind turbine blade, so that the user can arrange maintenance and inspection of the wind turbine according to the real-time load and cumulative damage, thereby improving the service life of the unit.

[0045] In some feasible embodiments, determining the cumulative fatigue damage index of the blade according to the strain information includes: generating a strain-time curve according to the strain information; determining a strain amplitude according to the strain-time curve; Obtaining fatigue life from a strain-fatigue life curve according to the strain amplitude; The fatigue damage index is calculated based on the fatigue life accumulation.

[0046] According to the above technical means, the strain amplitude can be determined according to the strain information, and then the fatigue life can be obtained according to the strain amplitude to calculate the fatigue damage index. The calculated fatigue damage index can better characterize the damage conditions at different key points of the blade.

[0047] In some feasible embodiments, the device further comprises: an interface display unit 4 and a data cloud storage system 2; The interface display unit 4 is connected to the data processing system 3 and is used to visually display the strain at each key position of the blade and fatigue damage warning; The data cloud storage system 2 is used to store strain thresholds, strain-fatigue life curves, and strain information collected by the data acquisition system, so that the data processing system can acquire and process them.

[0048] The data cloud storage system 2 is responsible for storing the collected data. In addition, the strain thresholds at different measuring points of the blade and the fatigue life under different stress amplitudes determined by the corresponding material strain-fatigue life curve are also stored in the data cloud storage system to provide data support for overload warning and calculation of cumulative fatigue damage.

[0049] The data processing system 3 interacts with the data cloud storage system 2 in real time: the strain information collected by the data acquisition system is read from the data cloud storage system, and after processing the strain information, the calculation results are stored in the data cloud storage system and visualized on the user interface. The data processing system is responsible for visualizing the strains at different key positions of the blade on the user interface and for damage warning. The user interface is convenient for users to view the health status of the blade. The visualization of the interface can be written based on the python language. The user interface allows users to customize the warning threshold of fatigue damage, and also allows users to view the number and time of historical overload warnings at each blade measurement point. Provide data support for evaluating the overall status of the blade.

[0050] Based on the above technical means, the visualization display system can provide users with an intuitive blade display, allowing users to view the current and historical stress status of each blade in each wind turbine in the wind farm in real time. The data cloud storage system provides data support for early warning analysis.

[0051] A third aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the wind turbine blade overload and fatigue damage early warning method.

[0052] Through the above technical scheme, the wind turbine blade overload and fatigue damage warning method provided by the present application calculates the cumulative fatigue damage index of the blade based on strain information, and issues warnings based on two situations: the single strain of the blade exceeds the strain threshold and the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold. The warning of exceeding the strain threshold can remind the user of the real-time load conditions of each detection point on the wind turbine blade, and the cumulative fatigue damage warning can remind the user of the cumulative damage conditions of the wind turbine blade, so that the user can arrange maintenance and inspection of the wind turbine according to the real-time load and cumulative damage, thereby improving the service life of the unit.

[0053] This method can be used to monitor the health status of blades in real time and remotely online, reducing the cost of manual inspections and the loss of power generation caused by the wind turbine stopping its blades during inspections. The visual interface allows users to view the current and historical stress status of each blade in each wind turbine in the wind farm, and provides data support for whether the blades are cracked, the degree of cracking, and possible potential damage.

[0054] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0055] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0056] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A wind turbine blade overload and fatigue damage early warning method, characterized in that: The method comprises: Obtaining the strain information of the blade; Determining a cumulative fatigue damage index of the blade according to the strain information; determining whether a strain threshold is exceeded according to the strain information; Determining whether a cumulative fatigue damage warning threshold is exceeded according to the cumulative fatigue damage index; When it is determined that the strain information exceeds the strain threshold or the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold, a blade overload or fatigue warning is issued.

2. The wind turbine blade overload and fatigue damage early warning method according to claim 1 is characterized in that: Determining the cumulative fatigue damage index of the blade according to the strain information includes: generating a strain-time curve according to the strain information; determining a strain amplitude according to the strain-time curve; Obtaining fatigue life from a strain-fatigue life curve according to the strain amplitude; The fatigue damage index is calculated based on the fatigue life accumulation.

3. The wind turbine blade overload and fatigue damage early warning method according to claim 2 is characterized in that: The fatigue damage index calculated based on the fatigue life accumulation includes: The fatigue damage index is calculated based on the current fatigue life according to the Miner criterion.

4. The wind turbine blade overload and fatigue damage early warning method according to claim 2 is characterized in that: Determining the strain amplitude according to the strain-time curve includes: Determine the curvature of each point on the strain-time curve; The strain value of the curvature polarity change determined according to the curvature is the strain amplitude.

5. The wind turbine blade overload and fatigue damage early warning method according to claim 2, characterized in that: The strain threshold is determined according to the limit strain value adopted in the blade design; and the strain-fatigue life curve is determined according to the Coffin-Manson model.

6. A wind turbine blade overload and fatigue damage early warning device, characterized in that: The device comprises: The data acquisition system includes an optical fiber strain sensor and a signal processor. The optical fiber strain sensor is arranged at a key position of the blade to collect strain optical signals of the blade at the corresponding position. The signal processor is used to convert the strain optical signals collected by the optical fiber strain sensor into strain information. A data processing system is used to determine a cumulative fatigue damage index of a blade according to the strain information; determine whether a strain threshold is exceeded according to the strain information; determine whether a cumulative fatigue damage warning threshold is exceeded according to the cumulative fatigue damage index; and issue a blade overload or fatigue warning when it is determined that the strain information exceeds the strain threshold or the cumulative fatigue damage index exceeds the cumulative fatigue damage warning threshold.

7. The wind turbine blade overload and fatigue damage early warning device according to claim 6, characterized in that: Determining the cumulative fatigue damage index of the blade according to the strain information includes: generating a strain-time curve according to the strain information; determining a strain amplitude according to the strain-time curve; Obtaining fatigue life from a strain-fatigue life curve according to the strain amplitude; The fatigue damage index is calculated based on the fatigue life accumulation.

8. The wind turbine blade overload and fatigue damage early warning device according to claim 6, characterized in that: The key positions include at least the blade root, the blade tip and the position of the maximum chord length of the blade body.

9. The wind turbine blade overload and fatigue damage early warning device according to claim 6, characterized in that: The device also includes: an interface display unit and a data cloud storage system; The interface display unit is connected to the data processing system and is used to visually display the strain at each key position of the blade and fatigue damage warning; The data cloud storage system is used to store strain thresholds, strain-fatigue life curves, and strain information collected by the data acquisition system, so that the data processing system can acquire and process them.

10. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling the machine to execute the wind turbine blade overload and fatigue damage early warning method according to any one of claims 1 to 5.

Images