Method, system, device and readable medium for evaluating fatigue life of fan

By establishing a wind turbine fatigue load model and using the trained and validated model to assess wind turbine fatigue life, the problems of low efficiency and high cost in existing technologies are solved, and a fast and low-cost wind turbine fatigue life assessment is achieved.

CN112131753BActive Publication Date: 2024-11-01SHANGHAI ELECTRIC WIND POWER GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202011051645.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-09-29
Publication Date
2024-11-01
Estimated Expiration
2040-09-29

AI Technical Summary

Technical Problem

Existing methods for assessing the fatigue life of wind turbines are inefficient, costly in terms of hardware, require a large number of sensors and storage devices, and involve complex and time-consuming calculations.

Method used

By generating parameter combinations suitable for wind farms, a fatigue load model is established. The fatigue life of the wind turbine is assessed using the trained and validated model, reducing reliance on sensors and memory, and employing an explicit mathematical model for rapid assessment.

Benefits of technology

It greatly reduces computation time, lowers hardware costs, and enables efficient assessment of wind turbine fatigue life, applicable to real-time assessment of onshore and offshore wind turbines.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112131753B_ABST
    Figure CN112131753B_ABST
Patent Text Reader

Abstract

The present invention discloses a method, system, device and readable medium for evaluating the fatigue life of a wind turbine. The evaluation method includes: generating a parameter combination including an environmental parameter combination and a control parameter combination for a wind field applicable to the wind turbine, and obtaining equivalent fatigue load samples of the wind turbine under different parameter combinations for the entire life cycle to form first load sample data for model training and second load sample data for model verification; establishing a fatigue load model according to the parameter combination and the equivalent fatigue load sample, and training the fatigue load model using the first load sample data; verifying the trained fatigue load model using the second load sample data; using the environmental parameters and control parameters within the evaluation period as input, and evaluating the fatigue life occupied by the evaluation period through the verified fatigue load model to obtain the fatigue life of the wind turbine. The present invention improves the evaluation efficiency of the fatigue life of the wind turbine, and does not require additional hardware, thereby reducing hardware costs.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of wind power evaluation, and in particular to a method, system, device and readable medium for online real-time evaluation of wind turbine fatigue life through wind turbine monitoring data. Background Art

[0002] At present, the existing wind turbine fatigue life assessment needs to use the fatigue load time history data of the wind turbine components to obtain the vibration times of the component load in different amplitude ranges through rain flow statistics, and calculate the cumulative damage percentage of the wind turbine through the miner cumulative damage engineering model, so as to evaluate the fatigue life of the wind turbine.

[0003] The current method mainly targets the load of each component being evaluated, and it is necessary to install corresponding load sensors at the corresponding positions. If multiple components need to be tested, the number of sensors to be installed is huge, and the cost of sensors and collectors increases. In actual operation, if a load channel needs to be added, a new set of equipment needs to be prepared on the hardware. The evaluation of fatigue life requires the collection of load data for a certain period of time. Each load channel needs to be equipped with a data storage device of a certain capacity. When evaluating a large number of load channels, a larger storage medium is required to complete the data storage of each cycle. The collected load time history data needs to undergo rain flow processing and cumulative damage calculation to obtain an estimate of the equivalent fatigue life, and the above calculations are required for each load channel. Summary of the invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of low efficiency and high hardware cost in the prior art in evaluating the fatigue life of a fan, and to provide a method, system, device and readable medium for evaluating the fatigue life of a fan.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] A method for evaluating the fatigue life of a fan, comprising:

[0007] Generate a parameter combination of a wind farm applicable to the wind turbine, and obtain equivalent fatigue load samples of the wind turbine over its entire life cycle under different parameter combinations to form first load sample data for model training and second load sample data for model verification, wherein the parameter combination includes an environmental parameter combination and a control parameter combination;

[0008] Establishing a fatigue load model according to the parameter combination and the equivalent fatigue load sample, and training the fatigue load model using the first load sample data to form the trained fatigue load model;

[0009] using the second load sample data to verify the trained fatigue load model to form a verified fatigue load model; and,

[0010] The environmental parameters and control parameters within the evaluation period are used as inputs, and the fatigue life evaluation of the evaluation period is performed using the verified fatigue load model to obtain the fatigue life of the wind turbine.

[0011] Optionally, the step of taking the environmental parameters and control parameters in the evaluation period as input and performing fatigue life evaluation of the evaluation period through the verified fatigue load model comprises:

[0012] Collect environmental parameters and control parameters during the assessment period;

[0013] Processing the environmental parameter and the control parameter to obtain representative values ​​of the environmental parameter and the control parameter;

[0014] The representative values ​​of the environmental parameters and the control parameters are used as inputs, and the fatigue life assessment of the assessment cycle is performed through the verified fatigue load model.

[0015] Optionally, the step of performing fatigue life assessment of the assessment cycle using the verified fatigue load model to obtain the fatigue life of the wind turbine includes:

[0016] The fatigue load is calculated by using the verified fatigue load model, and the wholeer coefficient is taken into account. The calculated fatigue load of the wind turbine over its entire life cycle is calculated according to the time probability of the evaluation period to obtain the fatigue life of the wind turbine during the evaluation period.

[0017] Optionally, after obtaining the fatigue life of the fan, the evaluation method further includes:

[0018] The fatigue life of the fan in the historical period is accumulated to obtain the cumulative fatigue life of the fan.

[0019] Optionally, the step of generating a parameter combination of a wind turbine applicable to a wind field includes:

[0020] The units that need to be load evaluated are selected, and the parameter variation range is set according to the site conditions of the unit design. The parameters are discretized within the variation range to generate a discrete combination of parameters suitable for the wind farm of the wind turbine.

[0021] Optionally, the environmental parameters include but are not limited to any one or more of wind speed, wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle and air density; and / or,

[0022] The control parameter includes a derating ratio.

[0023] A fan fatigue life assessment system, comprising:

[0024] A data generation module is configured to generate a parameter combination of a wind turbine applicable to a wind farm, and obtain equivalent fatigue load samples of the wind turbine over its entire life cycle under different parameter combinations to form first load sample data for model training and second load sample data for model verification, wherein the parameter combination includes an environmental parameter combination and a control parameter combination;

[0025] A model training module is configured to establish a fatigue load model according to a parameter combination and an equivalent fatigue load sample, and train the fatigue load model using the first load sample data to form a trained fatigue load model;

[0026] a model verification module, configured to verify the trained fatigue load model using the second load sample data to form a verified fatigue load model; and

[0027] The fatigue life assessment module is configured to use the environmental parameters and control parameters within the assessment period as inputs, and to perform fatigue life assessment of the assessment period through the verified fatigue load model to obtain the fatigue life of the wind turbine.

[0028] Optionally, the fatigue life assessment module is configured to:

[0029] Collect environmental parameters and control parameters during the assessment period;

[0030] Processing the environmental parameter and the control parameter to obtain representative values ​​of the environmental parameter and the control parameter;

[0031] The representative values ​​of the environmental parameters and the control parameters are used as inputs, and the fatigue life assessment of the assessment cycle is performed through the verified fatigue load model.

[0032] Optionally, the fatigue life assessment module is configured to: calculate the fatigue load through the verified fatigue load model, consider the whole coefficient, and calculate the calculated fatigue load of the wind turbine throughout its life cycle according to the time probability of the assessment period to obtain the fatigue life of the wind turbine in the assessment period.

[0033] Optionally, the fatigue life assessment module is further configured to: accumulate the fatigue life of the wind turbine in historical cycles to obtain the cumulative fatigue life of the wind turbine.

[0034] Optionally, the data generation module is configured to: select a unit that needs to be load evaluated, set a parameter variation range according to the site conditions of the unit design, and discretize the parameters within the variation range to generate a discrete combination of parameters suitable for the wind farm of the wind turbine.

[0035] Optionally, the environmental parameters include but are not limited to any one or more of wind speed, wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle and air density; and / or,

[0036] The control parameter includes a capacity reduction ratio.

[0037] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned method for evaluating fatigue life of a fan when executing the computer program.

[0038] A computer-readable medium stores computer instructions, which, when executed by a processor, implement the steps of the above-mentioned method for evaluating the fatigue life of a wind turbine.

[0039] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present invention.

[0040] The positive and progressive effects of the present invention are:

[0041] The fan fatigue life assessment method and system provided by the present invention can effectively realize the required fan component fatigue load assessment by utilizing the trained and verified fatigue load model, greatly shortening the calculation time and improving the assessment efficiency. In addition, there is no need to install sensors, collectors, and storage devices for each load that needs to be estimated, thereby greatly reducing the hardware cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The features and advantages of the present invention can be better understood after reading the detailed description of the embodiments of the present disclosure in conjunction with the following drawings. In the drawings, the components are not necessarily drawn to scale, and components with similar related properties or features may have the same or similar reference numerals.

[0043] Figure 1 The figure is a flow chart of a method for evaluating the fatigue life of a fan according to an embodiment of the present invention.

[0044] Figure 2 Schematic diagram of the distribution of fatigue load model.

[0045] Figure 3 It is a schematic structural diagram of a system for evaluating the fatigue life of a fan according to another embodiment of the present invention.

[0046] Figure 4 It is a schematic structural diagram of an electronic device for realizing a system for evaluating fatigue life of a fan according to another embodiment of the present invention. DETAILED DESCRIPTION

[0047] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0048] In order to overcome the above-mentioned defects that currently exist, the present embodiment provides a method for evaluating the fatigue life of a wind turbine, the evaluation method comprising: generating a parameter combination of a wind field applicable to the wind turbine, and obtaining equivalent fatigue load samples of the wind turbine over its entire life cycle under different parameter combinations to form first load sample data for model training and second load sample data for model verification, the parameter combination comprising an environmental parameter combination and a control parameter combination; establishing a fatigue load model according to the parameter combination and the equivalent fatigue load samples, and training the fatigue load model using the first load sample data to form the trained fatigue load model; verifying the trained fatigue load model using the second load sample data to form the verified fatigue load model; and, taking the environmental parameters and control parameters within the evaluation period as input, performing fatigue life evaluation of the evaluation period through the verified fatigue load model to obtain the fatigue life of the wind turbine.

[0049] In this embodiment, the trained and verified fatigue load model can be used to effectively realize the required fatigue load assessment of wind turbine components, greatly shortening the calculation time and improving the assessment efficiency. In addition, there is no need to install sensors, collectors, and storage devices for each load that needs to be estimated, thereby greatly reducing the hardware cost.

[0050] Preferably, as an embodiment, the online real-time evaluation method of the fatigue life of a wind turbine provided in this embodiment mainly includes two steps: establishment of a mathematical model of equivalent fatigue load of the wind turbine and online real-time fatigue life evaluation.

[0051] Through the above two links, real-time parameter variables are effectively provided, realizing the rapid evaluation of fan fatigue life.

[0052] Specifically, Figure 1 As shown, the evaluation method mainly includes the following steps:

[0053] Step 101: Generate a parameter combination of a wind turbine suitable for a wind field.

[0054] In this step, the unit that needs to be load evaluated is selected, and the parameter variation range is set according to the site conditions of the unit design. The parameters are discretized within the variation range to generate a parameter combination for the wind turbine that is suitable for the wind field. The parameter combination includes an environmental parameter combination and a control parameter combination.

[0055] In this embodiment, the establishment of the fatigue load model of the wind turbine throughout its life cycle is mainly divided into the processes of generating a fatigue load database of the unit, training the fatigue load model, and verifying the accuracy of the fatigue load model.

[0056] Step 102: Generate first load sample data and second load sample data.

[0057] In this step, equivalent fatigue load samples of the wind turbine over its entire life cycle under different parameter combinations are obtained to form first load sample data for model training and second load sample data for model verification.

[0058] The parameters are discretely combined to form input parameter samples, and load simulation software is used to simulate and form full life cycle equivalent fatigue load samples corresponding to the input parameter samples.

[0059] In this embodiment, the environmental parameters mainly include wind speed, wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle and air density. The environmental parameters can increase variables according to actual conditions, but at least include the variables mentioned above.

[0060] In this embodiment, the control parameter includes a capacity reduction ratio, but the control parameter is not specifically limited and can be adjusted and selected accordingly according to actual needs.

[0061] According to actual needs, yaw error variables can be added. The discretization of environmental parameter variables is carried out according to the following ideas: select typical wind farm environmental parameters applicable to real wind turbines, screen the environmental parameter combinations of each point and each sector, and form discrete samples. The wind speed change range of the sample points is required to be from the cut-in wind speed to the cut-out wind speed, with an interval of 1m / s or 2m / s. At each wind speed, the wind speed standard deviation of the sample points should be distributed as evenly as possible, and include points near the minimum value of the wind speed standard deviation at that wind speed to points near the maximum value. The vertical wind shear, horizontal wind shear and inflow angle parameters should be distributed as evenly as possible, and the number of sample points at each wind speed should be no less than 40. For each sample point, the yaw error is discretized into 10 equally spaced points according to the design range of the unit; the air density is centered on the design value, and 4 points are set in the decreasing direction and the increasing direction, with a spacing of 0.1kg / m 3 .

[0062] Step 103: Establish a fatigue load model.

[0063] In this step, a fatigue load model is established based on parameter combinations and equivalent fatigue load samples.

[0064] A mapping relationship between parameter samples and full life cycle fatigue load samples is established to form a regression mathematical model.

[0065] In this embodiment, the equivalent fatigue load of the wind turbine over its entire life cycle is obtained through simulation, and the wholeer parameters of different components need to be considered. For the equivalent fatigue load model of the wind turbine over its entire life cycle, a mathematical model of the equivalent fatigue load over its entire life cycle is set for each wind speed, each air density, each derating ratio and each load type. The mathematical model is a multivariate linear model containing a constant term, and the independent variables include the standard deviation of wind speed, vertical wind shear, horizontal wind shear, inflow angle and yaw error. The fatigue load model can be applied to the load types of three moments and three forces in the orthogonal coordinate system of the blade root, rotating hub, fixed hub, yaw bearing, tower top section and tower bottom section.

[0066] Step 104: Use the first load sample data to train the fatigue load model.

[0067] In this step, the environmental variables and the control variables are used as independent variables, the equivalent fatigue load of the wind turbine throughout its life cycle is used as the dependent variable, and the fatigue load model is trained using the first load sample data to form the trained fatigue load model.

[0068] Step 105: Verify the fatigue load model using the second load sample data.

[0069] In this step, the trained fatigue load model is verified using the second load sample data to form the verified fatigue load model.

[0070] In this embodiment, the fatigue load is predicted by the fatigue load model using the second load sample data as input, and the wind turbine simulation software is also used to obtain the simulated full life cycle equivalent fatigue load results. By comparing the two, the fatigue load model is verified and adjusted. The trained and verified fatigue load model can be used for rapid assessment of fatigue life.

[0071] refer to Figure 2 The figure shows the distribution of the mathematical model of fatigue loads over the entire life cycle. The fatigue load assessment process over the entire life cycle uses environmental parameters and control parameters to calculate the fatigue loads of each component of the wind turbine under the parameter combination over the entire life cycle.

[0072] Step 106: Collect environmental parameters and control parameters within the evaluation period and the period duration.

[0073] In this step, the time history data of environmental variables within the evaluation period, the time series data of the wind turbine yaw error, the reduction ratio of the wind turbine operation within the period and the period duration are collected.

[0074] Step 107: Obtain representative values ​​of environmental parameters and control parameters.

[0075] In this step, the environmental parameter and the control parameter are processed to obtain representative values ​​of the environmental parameter and the control parameter.

[0076] Specifically, in this embodiment, when processing the collected parameters, the evaluation period should be less than or equal to 10 minutes (of course, not limited to this), and the wind speed and the derating ratio are processed by binning with reference to the discrete value of the wind speed in the fatigue load model, and the corresponding wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle, yaw error and air density can only be applied to the fatigue load model of the derating ratio at the wind speed. For each wind speed and each derating ratio, the wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle and yaw error are averaged, and the average value is used as the representative value.

[0077] Step 108: Using the representative value as input and utilizing the fatigue load model, obtain the fatigue life of the fan.

[0078] In this step, representative values ​​of the environmental parameters and the control parameters are used as inputs, and fatigue life evaluation of the evaluation cycle is performed through the verified fatigue load model.

[0079] Specifically, in this step, the fatigue load is calculated by using the verified fatigue load model, and the wholeer coefficient is taken into account. The calculated fatigue load of the wind turbine over its entire life cycle is calculated according to the time probability of the evaluation period to obtain the fatigue life of the wind turbine during the evaluation period.

[0080] Step 109: Accumulate the fatigue life of the fan in the historical period to obtain the cumulative fatigue life of the fan.

[0081] In this embodiment, for each wind speed and each derating ratio, two groups of fatigue load models closest to the air density measurement value are selected, and the full life cycle fatigue load is calculated using these two groups of fatigue load models. The air density is linearly interpolated to obtain the full life cycle fatigue load 22 of the point.

[0082] The time occupied by each wind speed and each derating ratio is counted, and the whole-life cycle fatigue load of each wind speed and each derating ratio is weighted and summed according to time. The summation formula is shown below.

[0083]

[0084] T DEL : Equivalent fatigue life

[0085] F i,j : Full life cycle equivalent fatigue load of the i-th wind speed interval and the j-th derating ratio

[0086] Ti,j : The time of the jth derating ratio in the i-th wind speed interval

[0087] F d : Fatigue load design value

[0088] m: Material Wholeer coefficient

[0089] The wholeer coefficient in the fan fatigue load assessment in step 107 needs to be consistent with the wholeer coefficient in step 103. The assessment method can be embedded in the fan monitoring system through programming, so that the fatigue life of key positions of various components of the fan can be estimated at regular intervals.

[0090] In this embodiment, the online real-time fatigue life assessment link collects environmental parameters and records the time period within the assessment period, calculates the fatigue life of the assessment period through the full life cycle fatigue load mathematical model combined with the time of the assessment period, and accumulates the fatigue life of all periods. The safe service of the wind turbine requires that the accumulated fatigue life is less than the design fatigue life of the wind turbine.

[0091] The fan fatigue life assessment method provided in this embodiment has the following beneficial effects:

[0092] 1) The equivalent fatigue load model of the wind turbine's entire life cycle is an explicit mathematical model. It does not require iterative optimization calculations and takes a very short time to calculate, which greatly improves the evaluation efficiency.

[0093] 2) The evaluation method only needs to collect environmental parameter variables within the evaluation period, and there is no need to install sensors, collectors, storage devices, etc. for each load that needs to be estimated, thereby greatly saving hardware costs.

[0094] 3) The evaluation method can achieve the required fatigue load evaluation of wind turbine components through algorithm expansion without adding hardware.

[0095] 4) The evaluation method can be applied to a fan monitoring system, has a fast running speed, high calculation accuracy, and can realize online and real-time evaluation of fan fatigue life.

[0096] 5) The evaluation method can be used for real-time estimation of fatigue life of onshore and offshore wind turbines.

[0097] In order to overcome the above-mentioned defects currently existing, this embodiment provides a system for evaluating the fatigue life of a fan. The evaluation system utilizes the above-mentioned method for evaluating the fatigue life of a fan.

[0098] Specifically, as an embodiment, Figure 3As shown, the evaluation system mainly includes a data generation module 21, a model training module 22, a model verification module 23 and a fatigue life evaluation module 24.

[0099] The data generation module 21 is configured to generate parameter combinations suitable for wind farms of wind turbines, and obtain equivalent fatigue load samples of the wind turbine over its entire life cycle under different parameter combinations to form first load sample data for model training and second load sample data for model verification, wherein the parameter combinations include environmental parameter combinations and control parameter combinations.

[0100] Preferably, in this embodiment, the data generation module 21 is configured to select a unit that needs to be load evaluated, and set a parameter variation range according to the site conditions of the unit design, and discretize the parameters within the variation range to generate a discrete combination of parameters suitable for the wind farm of the wind turbine.

[0101] The model training module 22 is configured to establish a fatigue load model according to the parameter combination and the equivalent fatigue load sample, and train the fatigue load model using the first load sample data to form the trained fatigue load model.

[0102] The model verification module 23 is configured to verify the trained fatigue load model using the second load sample data to form the verified fatigue load model.

[0103] The fatigue life assessment module 24 is configured to use the environmental parameters and control parameters within the assessment period as inputs, and to perform fatigue life assessment of the assessment period using the verified fatigue load model to obtain the fatigue life of the wind turbine.

[0104] The fatigue life assessment module 24 is further configured to accumulate the fatigue life of the wind turbine in the historical cycles to obtain the cumulative fatigue life of the wind turbine.

[0105] Preferably, in this embodiment, the fatigue life assessment module 24 is configured to: collect environmental parameters and control parameters within an assessment period; process the environmental parameters and the control parameters to obtain representative values ​​of the environmental parameters and the control parameters; use the representative values ​​of the environmental parameters and the control parameters as input, and perform fatigue life assessment of the assessment period through the verified fatigue load model.

[0106] Specifically, the fatigue life assessment module 24 is configured to calculate the fatigue load through the verified fatigue load model, consider the whole coefficient, and calculate the calculated fatigue load of the wind turbine throughout its life cycle according to the time probability of the assessment period to obtain the fatigue life of the wind turbine in the assessment period.

[0107] In this embodiment, the environmental parameters mainly include wind speed, wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle and air density. The environmental parameters can increase variables according to actual conditions, but at least include the variables mentioned above.

[0108] In this embodiment, the control parameter includes a capacity reduction ratio, but the control parameter is not specifically limited and can be adjusted and selected accordingly according to actual needs.

[0109] The fan fatigue life evaluation system provided in this embodiment has the following beneficial effects:

[0110] 1) The equivalent fatigue load model of the wind turbine's entire life cycle is an explicit mathematical model. It does not require iterative optimization calculations and takes a very short time to calculate, which greatly improves the evaluation efficiency.

[0111] 2) The evaluation system only needs to collect environmental parameter variables within the evaluation period, and there is no need to install sensors, collectors, storage devices, etc. for each load that needs to be estimated, thereby greatly saving hardware costs.

[0112] 3) The evaluation system can achieve the required fatigue load evaluation of wind turbine components through algorithm expansion without adding hardware.

[0113] 4) The evaluation system can be applied to a fan monitoring system, has a fast operating speed, high calculation accuracy, and can realize online and real-time evaluation of the fatigue life of the fan.

[0114] 5) The evaluation system can be used for real-time estimation of fatigue life of onshore and offshore wind turbines.

[0115] Figure 4 The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method for evaluating the fatigue life of a fan in the above embodiment is implemented. Figure 4 The electronic device 30 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0116] like Figure 4 As shown, the electronic device 30 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0117] The bus 33 includes a data bus, an address bus, and a control bus.

[0118] The memory 32 may include a volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322 , and may further include a read-only memory (ROM) 323 .

[0119] The memory 32 may also include a program / utility 325 having a set (at least one) of program modules 324, such program modules 324 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0120] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the method for evaluating the fatigue life of a fan in the above embodiment of the present invention.

[0121] The electronic device 30 may also communicate with one or more external devices 34 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 35. Furthermore, the model generating device 30 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 36. Figure 4 As shown, the network adapter 36 communicates with other modules of the model-generated device 30 via the bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the model-generated device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0122] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0123] This embodiment further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method for evaluating the fatigue life of a wind turbine in the above embodiment are implemented.

[0124] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0125] In a possible implementation manner, the present invention may also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps in the method for evaluating the fatigue life of a wind turbine in the above embodiment.

[0126] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0127] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that this is only for illustration and the protection scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A method for evaluating the fatigue life of a fan, characterized in that: include: Generate a parameter combination of a wind farm applicable to the wind turbine, and obtain equivalent fatigue load samples of the wind turbine over its entire life cycle under different parameter combinations to form first load sample data for model training and second load sample data for model verification, wherein the parameter combination includes an environmental parameter combination and a control parameter combination; Establishing a fatigue load model according to the parameter combination and the equivalent fatigue load sample, and training the fatigue load model using the first load sample data to form the trained fatigue load model, wherein the fatigue load model is an explicit mathematical model; Verifying the trained fatigue load model using the second load sample data to form a verified fatigue load model; as well as, Taking the environmental parameters and control parameters in the evaluation period as input, the fatigue life evaluation of the evaluation period is performed through the verified fatigue load model to obtain the fatigue life of the wind turbine; The second load sample data is used as input to predict the fatigue load through the fatigue load model. At the same time, the wind turbine simulation software is also used to obtain the simulated full life cycle equivalent fatigue load results. By comparing the two, the fatigue load model is verified and adjusted.

2. The evaluation method according to claim 1, characterized in that: The step of taking the environmental parameters and control parameters in the evaluation period as input and evaluating the fatigue life of the evaluation period through the verified fatigue load model comprises: Collect environmental parameters and control parameters during the assessment period; Processing the environmental parameter and the control parameter to obtain representative values ​​of the environmental parameter and the control parameter; The representative values ​​of the environmental parameters and the control parameters are used as inputs, and the fatigue life assessment of the assessment cycle is performed through the verified fatigue load model.

3. The evaluation method according to claim 2, characterized in that: The step of evaluating the fatigue life occupied by the evaluation cycle through the verified fatigue load model to obtain the fatigue life of the wind turbine includes: The fatigue load is calculated by using the verified fatigue load model, and the wholeer coefficient is taken into account. The calculated fatigue load of the wind turbine over its entire life cycle is calculated according to the time probability of the evaluation period to obtain the fatigue life of the wind turbine during the evaluation period.

4. The evaluation method according to claim 3, characterized in that: After obtaining the fatigue life of the fan, the evaluation method further includes: The fatigue life of the fan in the historical period is accumulated to obtain the cumulative fatigue life of the fan.

5. The evaluation method according to claim 1, characterized in that: The step of generating a parameter combination of a wind turbine applicable to a wind field comprises: The units that need to be load evaluated are selected, and the parameter variation range is set according to the site conditions of the unit design. The parameters are discretized within the variation range to generate a discrete combination of parameters suitable for the wind farm of the wind turbine.

6. The evaluation method according to any one of claims 1 to 5, characterized in that: The environmental parameters include any one or more of wind speed, wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle and air density; and / or, The control parameter includes a derating ratio.

7. A fan fatigue life assessment system, characterized in that: include: A data generation module is configured to generate a parameter combination of a wind turbine applicable to a wind farm, and obtain equivalent fatigue load samples of the wind turbine over its entire life cycle under different parameter combinations to form first load sample data for model training and second load sample data for model verification, wherein the parameter combination includes an environmental parameter combination and a control parameter combination; a model training module, configured to establish a fatigue load model according to a parameter combination and an equivalent fatigue load sample, and train the fatigue load model using the first load sample data to form a trained fatigue load model, wherein the fatigue load model is an explicit mathematical model; a model verification module, configured to verify the trained fatigue load model using the second load sample data to form a verified fatigue load model; as well as, A fatigue life assessment module is configured to use environmental parameters and control parameters within an assessment period as inputs, and to perform fatigue life assessment of the assessment period through the verified fatigue load model to obtain the fatigue life of the wind turbine; The model verification module also uses the second load sample data as input to predict the fatigue load through the fatigue load model. It also uses the wind turbine simulation software to obtain the simulated full life cycle equivalent fatigue load results. By comparing the two, the fatigue load model is verified and adjusted.

8. The evaluation system according to claim 7, characterized in that The fatigue life assessment module is configured to: Collect environmental parameters and control parameters during the assessment period; Processing the environmental parameter and the control parameter to obtain representative values ​​of the environmental parameter and the control parameter; The representative values ​​of the environmental parameters and the control parameters are used as inputs, and the fatigue life assessment of the assessment cycle is performed through the verified fatigue load model.

9. The evaluation system according to claim 8, characterized in that The fatigue life assessment module is configured to calculate the fatigue load through the verified fatigue load model, consider the whole coefficient, and calculate the calculated fatigue load of the wind turbine throughout its life cycle according to the time probability of the assessment period to obtain the fatigue life of the wind turbine in the assessment period.

10. The evaluation system according to claim 9, characterized in that The fatigue life assessment module is further configured to: accumulate the fatigue life of the wind turbine in historical cycles to obtain the cumulative fatigue life of the wind turbine.

11. The evaluation system according to claim 9, characterized in that The data generation module is configured to: select a unit that needs to be load evaluated, set a parameter variation range according to the site conditions of the unit design, and discretize the parameters within the variation range to generate a discrete combination of parameters suitable for the wind farm of the wind turbine.

12. The evaluation system according to any one of claims 7 to 11, characterized in that: The environmental parameters include any one or more of wind speed, wind speed standard deviation, vertical wind shear, horizontal wind shear, inflow angle and air density; and / or, The control parameter includes a derating ratio.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method for evaluating the fatigue life of a wind turbine as claimed in any one of claims 1 to 6 are implemented.

14. A computer readable medium having computer instructions stored thereon, characterized in that: When the computer instructions are executed by a processor, the steps of the method for evaluating the fatigue life of a wind turbine as claimed in any one of claims 1 to 6 are implemented.