Wind turbine generator risk monitoring method and device based on extreme wind regime spectrum reconstruction

Abstract

The invention provides a wind turbine generator risk monitoring method and device based on extreme wind regime frequency spectrum reconstruction, and relates to the technical field of wind turbine generator risk monitoring, and the method comprises the steps: obtaining a first wind speed and a first wind direction of an environment where a target wind turbine generator is located, and a cabin position of the target wind turbine generator, obtaining a second wind speed, a second wind direction and turbulence intensity corresponding to each specified time window in a specified time period through a preset data processing model; target turbulence intensity is determined, target turbulence intensity time sequence data are constructed, wind speed time sequence data are constructed based on the second wind speed, and wind direction time sequence data are constructed based on the second wind direction; determining time-varying wind speed distribution corresponding to the target wind turbine generator according to the target turbulence intensity time sequence data and the wind speed time sequence data, and determining a main wind direction according to the wind direction time sequence data; and carrying out analogue simulation on the turbulence intensity at each wind turbine generator in the wind power plant simulation model based on the wind speed distribution and the main wind direction. According to the invention, transient simulation can be carried out on the wind power plant in allusion to extreme wind conditions.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbine risk monitoring, and specifically to a wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction, a wind turbine risk monitoring device based on extreme wind condition spectrum reconstruction, and a computer-readable storage medium. Background Art

[0002] At present, domestic wind farm development and design usually use commercial software WT and Windsim for micro-site selection simulation calculations, which have short calculation cycles and relatively stable accuracy. However, as the capacity of wind power development gradually increases, the proportion of large-scale units with high towers and long blades has increased significantly, which has higher requirements for the assessment of wind resources and needs to take into account both accuracy and calculation efficiency. At the same time, according to data statistics, the vast majority of wind turbines currently fail due to extreme wind conditions, but the existing conventional commercial software cannot perform transient simulation of extreme wind conditions and cannot obtain the wind resource conditions of wind turbines under extreme wind conditions. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide a wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction, a wind turbine risk monitoring device based on extreme wind condition spectrum reconstruction, and a computer-readable storage medium to solve the above problems.

[0004] In order to achieve the above-mentioned purpose, the first aspect of the present application provides a wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction, comprising: Acquire a first wind speed and a first wind direction of an environment in which the target wind turbine generator set is located and a nacelle position of the target wind turbine generator set within a specified time period; According to the wind speed, wind direction and cabin position in the specified time period, a second wind speed, a second wind direction and turbulence intensity corresponding to each specified time window in the specified time period are obtained through a preset data processing model; Determine a turbulence intensity greater than a first turbulence intensity threshold as a target turbulence intensity, construct target turbulence intensity time series data of all target turbulence intensities arranged in time, obtain a second wind speed and a second wind direction corresponding to each target turbulence intensity, and construct wind speed time series data of all second wind speeds arranged in time and wind direction time series data of all second wind directions arranged in time; Determine the time-varying wind speed distribution corresponding to the target wind turbine according to the target turbulence intensity time series data and the wind speed time series data, and determine the main wind direction according to the wind direction time series data; The simulation is performed on the turbulence intensity at each wind turbine in a pre-constructed wind farm simulation model based on the wind speed distribution and the main wind direction, and if the turbulence intensity at the current wind turbine is greater than a second turbulence intensity threshold, an alarm message is generated, wherein the first turbulence intensity threshold is greater than the second turbulence intensity threshold.

[0005] Optionally, after obtaining the second wind speed, the second wind direction and the turbulence intensity corresponding to each specified time window in the specified time period through a preset data processing model, the method further includes: Determine that among the acquired second wind speeds, a second wind speed that is less than the first wind speed threshold or greater than the second wind speed threshold is abnormal wind speed data, and determine that among the acquired second wind directions, a second wind direction that is less than the first angle threshold or greater than the second angle threshold is abnormal wind direction data; Deleting abnormal wind speed data and abnormal wind direction data from the acquired second wind speed and second wind direction; The first wind speed threshold is smaller than the second wind speed threshold, and the first angle threshold is smaller than the second angle threshold.

[0006] Optionally, the preset data processing model includes: a wind speed mapping submodel, a wind direction mapping submodel and a turbulence intensity calculation submodel; according to the wind speed, wind direction and cabin position in the specified time period, the second wind speed, second wind direction and turbulence intensity corresponding to each specified time window in the specified time period are obtained through the preset data processing model, including: Taking the first wind speed in the specified time period as input, obtaining the second wind speed corresponding to each specified time window in the specified time period through the wind speed mapping submodel; Taking the first wind direction and the position of the nacelle in the specified time period as input, the second wind direction corresponding to each of the specified time windows in the specified time period is obtained through the wind direction mapping submodel; Taking the first wind speed of the specified time period and the second wind speed corresponding to each specified time window in the specified time period as input, the turbulence intensity corresponding to each specified time window in the specified time period is obtained through the turbulence intensity calculation submodel.

[0007] Optionally, the wind speed mapping sub-model includes:

[0008] in, is the second wind speed corresponding to the specified window, v i is the wind speed at the ith second, n is the number of wind speeds in the specified time period, and m is the number of the specified time windows in the specified time period.

[0009] Optionally, the wind direction mapping sub-model includes:

[0010] in, is the second wind direction corresponding to the specified window, Y i is the wind direction at the ith second, P i is the cabin position angle at the i-th second.

[0011] Optionally, the turbulence intensity calculation sub-model includes:

[0012] in, is the turbulence intensity corresponding to the specified window.

[0013] Optionally, determining the main wind direction according to the wind direction time series data includes: determining the second wind direction having the largest number of occurrences in the wind direction time series data as the main wind direction; Determining the time-varying wind speed distribution corresponding to the target wind turbine generator set according to the target turbulence intensity time series data and the wind speed time series data, including: Determining a target turbulence intensity mean value of the target turbulence intensity time series data and a second wind speed mean value of the wind speed time series data; Performing Fourier transform on the wind speed time series data to obtain a frequency spectrum corresponding to the wind speed time series data, performing power spectrum density calculation on the frequency spectrum corresponding to the wind speed time series data to obtain energy distribution of the second wind speed at different frequencies, and determining peak frequencies corresponding to different energies; According to the peak frequencies corresponding to different energies of the wind speed time series data, the target turbulence intensity mean and the second wind speed mean, the time-varying wind speed distribution corresponding to the target wind turbine is obtained through a preset wind speed distribution model.

[0014] Optionally, the wind speed distribution model includes:

[0015] Where U(t) is the wind speed distribution that changes with time, m 2 is the number of peak frequencies, is the target turbulence intensity mean, is the second wind speed mean, L k is the velocity integral scale parameter, f i is the i-th peak frequency, S(f) is the atmospheric power spectral density function, rand(-π, π) represents a random number in the interval [-π, π], and t represents time.

[0016] In a second aspect of the present application, a wind turbine risk monitoring device based on extreme wind condition spectrum reconstruction is provided, comprising: A data acquisition module is configured to obtain a first wind speed and a first wind direction of an environment in which the target wind turbine is located and a nacelle position of the target wind turbine within a specified time period; The first data processing module is configured to obtain the second wind speed, the second wind direction and the turbulence intensity corresponding to each specified time window in the specified time period through a preset data processing model according to the wind speed, the wind direction and the position of the cabin in the specified time period; A second data processing module is configured to determine a turbulence intensity greater than a first turbulence intensity threshold as a target turbulence intensity, construct target turbulence intensity time series data of all target turbulence intensities arranged in time, obtain a second wind speed and a second wind direction corresponding to each target turbulence intensity, and construct wind speed time series data of all second wind speeds arranged in time and wind direction time series data of all second wind directions arranged in time; A third data processing module is configured to determine the time-varying wind speed distribution corresponding to the target wind turbine group according to the target turbulence intensity time series data and the wind speed time series data, and determine the main wind direction according to the wind direction time series data; The simulation module is configured to perform the simulation on the turbulence intensity at each wind turbine in a pre-constructed wind farm simulation model based on the wind speed distribution and the main wind direction, and generate an alarm message if the turbulence intensity at the current wind turbine is greater than a second turbulence intensity threshold, wherein the first turbulence intensity threshold is greater than the second turbulence intensity threshold.

[0017] In a third aspect of the present application, a computer-readable storage medium is provided, which stores a computer program which, when executed by a processor, causes the processor to execute the wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction as described above.

[0018] In a fourth aspect of the present application, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction when executing the computer program.

[0019] The embodiments provided in this application have the following beneficial effects: This application can perform more refined transient simulation of wind farms for extreme wind conditions, thereby evaluating the turbulence risk of wind turbines, which is conducive to monitoring risky units in advance and reducing safety hazards of units.

[0020] Other features and advantages of the embodiments or implementations of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings: Figure 1 A method flow chart of a wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to an embodiment of the present application is schematically shown; Figure 2 A schematic diagram of extreme wind conditions in an embodiment of the present application is schematically shown; Figure 3 A schematic diagram of the peak frequency of an embodiment of the present application is schematically shown; Figure 4 A schematic diagram of extreme wind conditions obtained by inversion according to an embodiment of the present application is schematically shown; Figure 5 A simulation diagram of an embodiment of the present application is schematically shown; Figure 6 A schematic block diagram of a wind turbine risk monitoring device based on extreme wind condition spectrum reconstruction according to an embodiment of the present application is schematically shown; Figure 7 A schematic diagram of the structure of a terminal device according to an embodiment of the present application is shown schematically.

[0022] Description of Reference Numerals 10-terminal device, 100-processor, 101-memory, 102-computer program. DETAILED DESCRIPTION

[0023] The specific implementation of the embodiment of the present application 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 embodiment of the present application, and is not used to limit the embodiment of the present application.

[0024] In order to solve the above problems, Figure 1 As shown, the first aspect of the present application provides a wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction, comprising: S100, obtaining a first wind speed and a first wind direction of an environment in which a target wind turbine is located and a nacelle position of the target wind turbine within a specified time period; S200, according to the wind speed, wind direction and cabin position in the specified time period, obtaining the second wind speed, second wind direction and turbulence intensity corresponding to each specified time window in the specified time period through a preset data processing model; S300, determining a turbulence intensity greater than a first turbulence intensity threshold as a target turbulence intensity, constructing target turbulence intensity time series data of all target turbulence intensities arranged in time, obtaining a second wind speed and a second wind direction corresponding to each target turbulence intensity, and constructing wind speed time series data of all second wind speeds arranged in time and wind direction time series data of all second wind directions arranged in time; S400, determining the time-varying wind speed distribution corresponding to the target wind turbine according to the target turbulence intensity time series data and the wind speed time series data, and determining the main wind direction according to the wind direction time series data; S500, simulating the turbulence intensity at each wind turbine in a pre-constructed wind farm simulation model based on wind speed distribution and main wind direction, and generating an alarm message if the turbulence intensity at the current wind turbine is greater than a second turbulence intensity threshold, wherein the first turbulence intensity threshold is greater than the second turbulence intensity threshold.

[0025] In this way, the present application can perform more refined transient simulation of wind farms for extreme wind conditions, thereby evaluating the turbulence risk of wind turbines, which is conducive to monitoring risky units in advance and reducing safety hazards of units.

[0026] In step S100, the target wind turbine group can be any wind turbine group in the wind farm, and the first wind speed, the first wind direction and the cabin position data of the target wind turbine group can be directly obtained through the SCADA (Supervisory Control And Data Acquisition) system of the wind farm, that is, the data acquisition and monitoring control system, wherein the specified time period can be within the past year. For example, the second-level measured data of the target wind turbine group in the past year is obtained through the SCADA system, that is, the wind speed, wind direction and cabin position corresponding to each second in the past year. Among them, the cabin position refers to the angle between the wind turbine cabin and the horizontal plane when the wind turbine of the wind turbine group is running. It can be understood that during the rotation of the wind turbine, the cabin will change due to the action of the torsional force, thereby producing different cabin positions, and the cabin position will have a certain impact on the performance and stability of the generator.

[0027] In step S200, the specified time window can be 1 minute, 10 minutes, etc. For example, the acquired first wind speed, first wind direction, cabin position and other data are synthesized and processed through the data processing model to generate the wind speed, wind direction and turbulence intensity data of the specified time window, such as every 10 minutes. In the present application, the preset data processing model includes: a wind speed mapping sub-model, a wind direction mapping sub-model and a turbulence intensity calculation sub-model; according to the wind speed, wind direction and cabin position in the specified time period, the second wind speed, second wind direction and turbulence intensity corresponding to each specified time window in the specified time period are obtained through the preset data processing model, including: S210, taking the first wind speed in the specified time period as input, obtaining the second wind speed corresponding to each specified time window in the specified time period through the wind speed mapping sub-model; the time series SCADA data of the target wind turbine group obtained can be expressed as: wind speed (v 1 , v 2 ...v n ), wind direction (Y 1 , Y 2 ...Y n ), cabin position (P 1 , P2...P n ), where v 1 represents the measured wind speed at the first sampling moment, Y 1 represents the measured wind direction at the first sampling moment, P 1 Represents the measured cabin position at the first sampling moment, that is, the wind speed, wind direction and cabin position at each sampling moment correspond one to one; the wind speed time series data can be mapped to the wind speed of a specified time window such as 10 minutes through the wind speed mapping submodel, wherein the wind speed mapping submodel includes:

[0028] in, is the average wind speed corresponding to the specified window, i.e. the second wind speed, v i is the wind speed at the ith second, n is the number of wind speeds in the specified period, and m is the number of specified time windows in the specified period; S220, taking the first wind direction and the position of the nacelle in the specified time period as input, the wind direction mapping sub-model is used to obtain the second wind direction corresponding to each specified time window in the specified time period; the wind direction mapping sub-model can map the wind direction time series data into the wind direction of the specified time window, such as 10 minutes, wherein the wind direction mapping sub-model includes:

[0029] in, is the average wind direction corresponding to the specified window, i.e. the second wind direction, Y i is the wind direction at the ith second, P i is the cabin position angle at the i-th second; S230, taking the first wind speed in the specified time period and the second wind speed corresponding to each specified time window in the specified time period as input, obtaining the turbulence intensity corresponding to each specified time window in the specified time period through the turbulence intensity calculation submodel; wherein the turbulence intensity calculation submodel includes:

[0030] in, is the turbulence intensity corresponding to the specified window.

[0031] Through the above steps, the 10-minute wind speed (ῡ 1 ,ῡ 2 ...ῡ m )、wind direction(Ŷ 1 ,Ŷ 2 ... m ) and turbulence intensity data (σ 1 ,σ 2 ... m ) In the present application, after obtaining the second wind speed, the second wind direction and the turbulence intensity corresponding to each specified time window in the specified time period through the preset data processing model, the method further includes: S240, determining that among the acquired second wind speeds, a second wind speed that is less than the first wind speed threshold or greater than the second wind speed threshold is abnormal wind speed data, and determining that among the acquired second wind directions, a second wind direction that is less than the first angle threshold or greater than the second angle threshold is abnormal wind direction data, wherein the first wind speed threshold is less than the second wind speed threshold, and the first angle threshold is less than the second angle threshold; in the present application, the first wind speed threshold is 3m / s, the second wind speed threshold is 30m / s, the first angle threshold is 0°, and the second angle threshold is 360°, that is, determining that the wind speed does not satisfy 3≤ῡ j ≤30m / s, wind direction does not meet 0°≤Ŷ j Data ≤360° are abnormal wind speed or direction; S250, deleting abnormal wind speed data and abnormal wind direction data from the acquired second wind speed and second wind direction, so as to delete data that does not meet the requirements and leave data with normal wind speed and wind direction, thereby eliminating the interference of abnormal data and improving the accuracy of subsequent simulation.

[0032] In step S300, the first turbulence intensity threshold is the turbulence intensity threshold for identifying extreme turbulence standard wind conditions defined in the IEC extreme turbulence standard. The present application extracts wind conditions exceeding the extreme turbulence standard from the turbulence intensity obtained according to the IEC extreme turbulence standard to analyze its spectral characteristics and invert the extreme wind speed curve with periodic changes of its spectral characteristics. Specifically, Figure 2 As shown, the present application determines the extreme turbulence of the target wind turbine at different wind speeds based on the model parameters, turbulence design standards, impeller diameter and other parameters of the target wind turbine and the extreme turbulence standards in the IEC standard, and uses this as a basis to screen the wind conditions that exceed the extreme turbulence standards, and integrates all wind condition fragments into continuous wind conditions to form a set of extreme wind condition time series wind speeds (u 1 ,u 2 ...u m1 )、wind direction(y 1 ,y 2 ...y m1 ) and turbulence intensity data (σ1 ,σ 2 ... m1 ), where m1 is less than m and m>10000 to ensure the accuracy of spectrum analysis.

[0033] In step S400, the main wind direction is determined according to the wind direction time series data, including: determining the second wind direction that appears most frequently in the wind direction time series data as the main wind direction; determining the time-varying wind speed distribution corresponding to the target wind turbine according to the target turbulence intensity time series data and the wind speed time series data, including: S410, averaging the target turbulence intensity in the target turbulence intensity time series data to determine the target turbulence intensity mean value of the target turbulence intensity time series data, and averaging the wind speed in the wind speed time series data to determine a second wind speed mean value of the wind speed time series data; S420, perform Fourier transform on the wind speed time series data to obtain the frequency spectrum corresponding to the wind speed time series data, perform power spectral density calculation on the frequency spectrum corresponding to the wind speed time series data, obtain the energy distribution of the second wind speed at different frequencies, and determine the peak frequencies corresponding to different energies; wherein, the steps of performing Fourier transform on the wind speed time series data to obtain the frequency spectrum corresponding to the wind speed time series data, and performing power spectral density calculation on the frequency spectrum corresponding to the wind speed time series data can be implemented by existing technologies, such as directly using MATLAB software, for example, using the fft function in MATLAB software to convert the wind speed time series data into frequency domain data, giving the frequency spectrum of the wind speed data, and then performing spectral analysis on the extreme wind speed series data by using MATLAB software to find the PSD, i.e., power spectral density (Power Spectral Density) peak value, and obtaining the peak frequencies (f 1 ,f 2 ...f m2 ),like Figure 3 As shown, the peak value refers to the highest power value at a specific frequency, and the power spectrum density can represent the energy distribution of a signal on each frequency component; wherein, the process of obtaining the peak frequency is a prior art and is not limited here; S430, according to the peak frequency corresponding to different energies of the wind speed time series data, the target turbulence intensity mean and the second wind speed mean, the time-varying wind speed distribution corresponding to the target wind turbine is obtained by a preset wind speed distribution model; the present application generates a non-IEC wind condition having its spectral characteristics and turbulence characteristics by inverse Fourier transform according to the peak frequency and average wind speed ū of different energies of the extreme wind condition time series and the atmospheric power spectral density function. Specifically, the wind speed distribution model of the present application includes:

[0034]

[0035] Where U(t) is the wind speed distribution that changes with time, m 2 is the number of peak frequencies, is the target turbulence intensity mean, is the second wind speed mean, L k is the velocity integral scale parameter, f i is the ith peak frequency, S(f) is the atmospheric power spectral density function, rand(-π, π) represents a random number in the interval [-π, π], and t represents time. In this application, the first 20 peak frequencies are selected for wind speed inversion, and the non-IEC standard wind conditions with periodic changes are formed in combination with the average wind speed as the input data for FLUENT simulation. The periodic boundary of the extreme wind condition U(t) obtained by inversion is as follows: Figure 4 shown.

[0036] In step S500, the present application simulates the turbulence risk of the wind turbine using FLUENT simulation software. Specifically, firstly, a simulation model of the wind farm is constructed according to the topographic map of the wind farm, and the grid division and simulation settings are determined, wherein the grid quality standards are: two-dimensional grid quality>0.7; grid positive slope ratio<200; Cront number<5. Among them, the FLUENT parameters can be configured as follows: select the ke turbulence model, perform steady-state simulation, set boundary conditions, determine the velocity inlet, pressure outlet and wall boundary, set monitoring points for the positions of each wind turbine in the wind farm, mainly monitor the time-varying curves of velocity and turbulence, initialize the calculation domain, set the time step and calculation step, use the time-varying wind speed distribution obtained in step S400, that is, the non-IEC wind speed curve, as the velocity inlet of the model, perform FLUENT numerical simulation calculations on the two-dimensional model at different positions of the whole field, simulate the main wind energy direction of extreme wind conditions for each wind turbine in the wind farm, and monitor the simulation results at each position in the wind farm, that is, the time-varying curves of wind speed and turbulence at each position, and judge the turbulence at the corresponding wind speed at the position according to the extreme turbulence standard in IEC. If it exceeds the extreme turbulence standard, it is considered that the unit is at risk and an alarm message is generated. If it is lower than the extreme turbulence standard, it is considered that the unit is risk-free. Figure 5 Shown is a wind condition cloud map at the wind turbine location and an example of a simulation of extreme shear values.

[0037] like Figure 6 As shown, in a second aspect of the present application, a wind turbine risk monitoring device based on extreme wind condition spectrum reconstruction is provided, comprising: Obtaining a first wind speed, a first wind direction, and a nacelle position of the target wind turbine generator set in an environment where the target wind turbine generator set is located within a specified time period; According to the wind speed, wind direction and cabin position in the specified time period, the second wind speed, second wind direction and turbulence intensity corresponding to each specified time window in the specified time period are obtained through a preset data processing model; Determine a turbulence intensity greater than a first turbulence intensity threshold as a target turbulence intensity, construct target turbulence intensity time series data of all target turbulence intensities arranged in time, obtain a second wind speed and a second wind direction corresponding to each target turbulence intensity, and construct wind speed time series data of all second wind speeds arranged in time and wind direction time series data of all second wind directions arranged in time; Determine the time-varying wind speed distribution corresponding to the target wind turbine according to the target turbulence intensity time series data and wind speed time series data, and determine the main wind direction according to the wind direction time series data; The turbulence intensity at each wind turbine in the pre-built wind farm simulation model is simulated based on the wind speed distribution and the main wind direction. If the turbulence intensity at the current wind turbine is greater than the second turbulence intensity threshold, an alarm message is generated, wherein the first turbulence intensity threshold is greater than the second turbulence intensity threshold.

[0038] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0039] In a third aspect of the present application, a computer-readable storage medium is provided, which stores a computer program which, when executed by a processor, causes the processor to execute the wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction as described above.

[0040] In a fourth aspect of the present application, a terminal device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction when executing the computer program.

[0041] like Figure 7 FIG. 1 is a schematic diagram of a terminal device provided in an embodiment of the present application. Figure 7As shown, the terminal device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the above method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the above device embodiments are implemented.

[0042] Exemplarily, the computer program 102 may be divided into one or more modules / units, one or more modules / units are stored in the memory 101, and are executed by the processor 100 to complete the present application. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 102 in the terminal device 10.

[0043] The terminal device 10 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art will appreciate that Figure 7 It is only an example of the terminal device 10 and does not constitute a limitation of the terminal device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0044] The processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0045] The memory 101 may be an internal storage unit of the terminal device 10, such as a hard disk or memory of the terminal device 10. The memory 101 may also be an external storage device of the terminal device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the terminal device 10. Further, the memory 101 may also include both an internal storage unit of the terminal device 10 and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the terminal device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0046] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0047] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0048] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction, characterized in that: include: Acquire a first wind speed and a first wind direction of an environment in which the target wind turbine generator set is located and a nacelle position of the target wind turbine generator set within a specified time period; According to the wind speed, wind direction and cabin position in the specified time period, a second wind speed, a second wind direction and turbulence intensity corresponding to each specified time window in the specified time period are obtained through a preset data processing model; Determine a turbulence intensity greater than a first turbulence intensity threshold as a target turbulence intensity, construct target turbulence intensity time series data of all target turbulence intensities arranged in time, obtain a second wind speed and a second wind direction corresponding to each target turbulence intensity, and construct wind speed time series data of all second wind speeds arranged in time and wind direction time series data of all second wind directions arranged in time; Determine the time-varying wind speed distribution corresponding to the target wind turbine according to the target turbulence intensity time series data and the wind speed time series data, and determine the main wind direction according to the wind direction time series data; The simulation is performed on the turbulence intensity at each wind turbine in a pre-constructed wind farm simulation model based on the wind speed distribution and the main wind direction, and if the turbulence intensity at the current wind turbine is greater than a second turbulence intensity threshold, an alarm message is generated, wherein the first turbulence intensity threshold is greater than the second turbulence intensity threshold.

2. The wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to claim 1 is characterized in that: After obtaining the second wind speed, the second wind direction and the turbulence intensity corresponding to each specified time window in the specified time period through the preset data processing model, the method further includes: Determine that among the acquired second wind speeds, a second wind speed that is less than the first wind speed threshold or greater than the second wind speed threshold is abnormal wind speed data, and determine that among the acquired second wind directions, a second wind direction that is less than the first angle threshold or greater than the second angle threshold is abnormal wind direction data; Deleting abnormal wind speed data and abnormal wind direction data from the acquired second wind speed and second wind direction; The first wind speed threshold is smaller than the second wind speed threshold, and the first angle threshold is smaller than the second angle threshold.

3. The wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to claim 1 is characterized in that: The preset data processing model includes: a wind speed mapping sub-model, a wind direction mapping sub-model and a turbulence intensity calculation sub-model; according to the wind speed, wind direction and cabin position in the specified time period, the second wind speed, second wind direction and turbulence intensity corresponding to each specified time window in the specified time period are obtained through the preset data processing model, including: Taking the first wind speed in the specified time period as input, obtaining the second wind speed corresponding to each specified time window in the specified time period through the wind speed mapping submodel; Taking the first wind direction and the position of the nacelle in the specified time period as input, the second wind direction corresponding to each of the specified time windows in the specified time period is obtained through the wind direction mapping submodel; Taking the first wind speed of the specified time period and the second wind speed corresponding to each specified time window in the specified time period as input, the turbulence intensity corresponding to each specified time window in the specified time period is obtained through the turbulence intensity calculation submodel.

4. The wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to claim 3 is characterized in that: The wind speed mapping sub-model includes: in, is the second wind speed corresponding to the specified window, v i is the wind speed at the ith second, n is the number of wind speeds in the specified time period, and m is the number of the specified time windows in the specified time period.

5. The wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to claim 4 is characterized in that: The wind direction mapping sub-model includes: in, is the second wind direction corresponding to the specified window, Y i is the wind direction at the ith second, P i is the cabin position angle at the i-th second.

6. The wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to claim 5 is characterized in that: The turbulence intensity calculation sub-model includes: in, is the turbulence intensity corresponding to the specified window.

7. The wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to claim 1 is characterized in that: Determining the main wind direction according to the wind direction time series data includes: determining the second wind direction having the largest number of occurrences in the wind direction time series data as the main wind direction; Determining the time-varying wind speed distribution corresponding to the target wind turbine generator set according to the target turbulence intensity time series data and the wind speed time series data, including: Determining a target turbulence intensity mean value of the target turbulence intensity time series data and a second wind speed mean value of the wind speed time series data; Performing Fourier transform on the wind speed time series data to obtain a frequency spectrum corresponding to the wind speed time series data, performing power spectrum density calculation on the frequency spectrum corresponding to the wind speed time series data to obtain energy distribution of the second wind speed at different frequencies, and determining peak frequencies corresponding to different energies; According to the peak frequencies corresponding to different energies of the wind speed time series data, the target turbulence intensity mean and the second wind speed mean, the time-varying wind speed distribution corresponding to the target wind turbine is obtained through a preset wind speed distribution model.

8. The wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction according to claim 7 is characterized in that: The wind speed distribution model comprises: Where U(t) is the wind speed distribution over time, m2 is the number of peak frequencies, is the target turbulence intensity mean, is the second wind speed mean, L k is the velocity integral scale parameter, f i is the ith peak frequency, S(f) is the atmospheric power spectral density function, rand(-π, π) represents a random number in the interval [-π, π], and t represents time.

9. A wind turbine risk monitoring device based on extreme wind condition spectrum reconstruction, characterized in that: include: A data acquisition module is configured to obtain a first wind speed and a first wind direction of an environment in which the target wind turbine is located and a nacelle position of the target wind turbine within a specified time period; The first data processing module is configured to obtain the second wind speed, the second wind direction and the turbulence intensity corresponding to each specified time window in the specified time period through a preset data processing model according to the wind speed, the wind direction and the position of the cabin in the specified time period; A second data processing module is configured to determine a turbulence intensity greater than a first turbulence intensity threshold as a target turbulence intensity, construct target turbulence intensity time series data of all target turbulence intensities arranged in time, obtain a second wind speed and a second wind direction corresponding to each target turbulence intensity, and construct wind speed time series data of all second wind speeds arranged in time and wind direction time series data of all second wind directions arranged in time; A third data processing module is configured to determine the time-varying wind speed distribution corresponding to the target wind turbine group according to the target turbulence intensity time series data and the wind speed time series data, and determine the main wind direction according to the wind direction time series data; The simulation module is configured to perform the simulation on the turbulence intensity at each wind turbine in a pre-constructed wind farm simulation model based on the wind speed distribution and the main wind direction, and generate an alarm message if the turbulence intensity at the current wind turbine is greater than a second turbulence intensity threshold, wherein the first turbulence intensity threshold is greater than the second turbulence intensity threshold.

10. A computer-readable storage medium storing a computer program which, when executed by a processor, causes the processor to execute the wind turbine risk monitoring method based on extreme wind condition spectrum reconstruction as claimed in any one of claims 1 to 8.

Images