阅读说明：本技术 风电机组的极端风况条件的预测方法、装置及设备 (Method, device and equipment for predicting extreme wind condition conditions of wind turbine generator ) 是由 徐洪雷 于 2020-06-28 设计创作，主要内容包括：本公开提供一种风电机组的极端风况条件的预测方法、装置及设备,所述方法包括：对测风塔风况数据进行处理以获得风况数据片段；基于所述风况数据片段中的风速与风况参数的联合概率分布,预测预定重现周期的风况参数；以及输出预测的所述预定重现周期的风况参数。(The present disclosure provides a method, an apparatus and a device for predicting an extreme wind condition of a wind turbine, wherein the method comprises: processing wind condition data of the anemometer tower to obtain a wind condition data segment; predicting a wind condition parameter of a predetermined reproduction period based on a joint probability distribution of wind speed and wind condition parameter in the wind condition data segment; and outputting the predicted wind condition parameters of the predetermined reproduction period.)

1. A method of predicting extreme wind conditions for a wind turbine, the method comprising:

processing wind condition data of the anemometer tower to obtain a wind condition data segment;

predicting a wind condition parameter of a predetermined reproduction period based on a joint probability distribution of wind speed and wind condition parameter in the wind condition data segment; and

and outputting the predicted wind condition parameters of the preset reproduction period.

2. The prediction method of claim 1, wherein the step of processing wind condition data of the anemometer tower comprises:

acquiring high-frequency sampling data of the anemometer tower, wherein the high-frequency sampling data comprises at least one variable of a timestamp, a wind speed and a wind direction;

determining whether the high frequency sampled data satisfies a predetermined condition;

and performing data segment cutting on the high-frequency sampling data meeting the preset condition at a preset time length to obtain the wind condition data segment.

3. The prediction method of claim 2, wherein the predetermined condition comprises a data integrity rate exceeding a predetermined threshold.

4. The prediction method of claim 1, wherein the wind condition parameters include at least one of a wind speed standard deviation, a wind speed variation magnitude, a wind direction variation magnitude, a wind shear value, and a wind farm load.

5. The prediction method according to claim 1, wherein the step of predicting the wind condition parameters of the predetermined reproduction period comprises:

determining a reliability indicator for the predetermined reproduction period based on a Gaussian probability function, wherein the reliability indicator is associated with a sum of squares of a first normative normal variable for a wind speed value and a second normative normal variable for a wind condition parameter;

calculating a function of the wind condition parameter with respect to wind speed by a joint probability distribution of the first and second standard normal variables;

predicting a wind condition parameter for the predetermined reproduction period based on the calculated function.

6. An apparatus for predicting extreme wind conditions of a wind turbine, comprising:

a data processing unit configured to process the anemometer tower wind condition data to obtain a wind condition data segment;

a data analysis unit configured to predict a wind condition parameter of a predetermined reproduction period based on a joint probability distribution of wind speed and the wind condition parameter in the wind condition data section; and

a data output unit configured to output the predicted wind condition parameters for the predetermined reproduction period.

7. The prediction apparatus of claim 6, wherein the data processing unit is configured to:

acquiring high-frequency sampling data of the anemometer tower, wherein the high-frequency sampling data comprises at least one variable of a timestamp, a wind speed and a wind direction;

determining whether the high frequency sampled data satisfies a predetermined condition;

and performing data segment cutting on the high-frequency sampling data meeting the preset condition at a preset time length to obtain the wind condition data segment.

8. The prediction apparatus of claim 7, wherein the predetermined condition comprises a data integrity rate exceeding a predetermined threshold.

9. The prediction apparatus of claim 6, wherein the wind condition parameters comprise at least one of a wind speed standard deviation, a wind speed variation magnitude, a wind direction variation magnitude, a wind shear value, and a wind farm load.

10. The prediction apparatus according to claim 6, wherein the step of predicting the wind condition parameters of the predetermined reproduction period comprises:

determining a reliability indicator for the predetermined reproduction period based on a Gaussian probability function, wherein the reliability indicator is associated with a sum of squares of a first normative normal variable for a wind speed value and a second normative normal variable for a wind condition parameter;

calculating a function of the wind condition parameter with respect to wind speed by a joint probability distribution of the first and second standard normal variables;

predicting a wind condition parameter for the predetermined reproduction period based on the calculated function.

11. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out a method of predicting extreme wind conditions of a wind turbine as set forth in any one of claims 1 to 5.

12. A computer device, characterized in that the computer device comprises:

a processor;

memory storing a computer program which, when executed by the processor, implements the method of predicting extreme wind conditions of a wind turbine as claimed in any one of claims 1 to 5.

Technical Field

The present disclosure relates to wind power generation technologies, and in particular, to a method, an apparatus, and a device for predicting an extreme wind condition of an operating environment of a wind turbine.

Background

The wind generating set needs to consider external environmental conditions and the running state of the set in the design process, wherein the external environmental conditions are divided into normal conditions and extreme conditions. Extreme external extreme wind conditions refer to wind conditions having a certain recurring period (e.g., one year or 50 years). Extreme wind conditions mainly include: extreme turbulence, extreme operating gusts, extreme operating coherent gusts, extreme wind shear, and extreme wind direction changes.

At present, the extreme wind condition parameters applied in the design of the wind generating set mainly come from a recommended formula in the IEC61400-1 standard. IEC61400-1 is an international universal standard in which the recommended formula is based on statistics, fits and assumptions from the limited meteorological data of the meteorological tower in the germany, usa and australia, but does not take into account the climatic conditions, topography and other conditions of a specific region (e.g. part of the china). As the diameter of the unit impeller grows, these extreme wind conditions parameters dominate the development of critical components of the unit.

At present, the design parameters of the wind generating set are set according to a recommended formula given in IEC61400-1 standard, so that the parameter setting of the extreme wind condition on flat terrain is too conservative, the parameter setting on complex terrain has risks, and the economy, competitiveness, reliability and the like of the set are greatly influenced and limited.

Disclosure of Invention

This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used as an aid in determining the scope of the claimed subject matter.

The method combines the inverse first-order reliability method with the high-frequency sampling data of the anemometer tower, is applied to calculation and prediction of extreme wind condition parameters, and can more accurately calculate the extreme wind condition at the position of the wind power plant, so that the current situation that the extreme wind condition parameters can only be calculated according to a standard recommended formula is broken through, and a new situation is opened for development and design of the wind turbine generator.

According to one aspect of the present disclosure, a method for predicting extreme wind conditions of a wind turbine includes: processing wind condition data of the anemometer tower to obtain a wind condition data segment; predicting a wind condition parameter of a predetermined reproduction period based on a joint probability distribution of wind speed and wind condition parameters in the wind condition data segment; and outputting the predicted wind condition parameters of the predetermined reproduction period.

According to an embodiment of the present disclosure, in the prediction method, the step of processing the wind condition data of the anemometer tower may include: acquiring high-frequency sampling data of the anemometer tower, wherein the high-frequency sampling data comprises at least one variable of a timestamp, a wind speed and a wind direction; determining whether the high frequency sampled data satisfies a predetermined condition; and performing data segment cutting on the high-frequency sampling data meeting the preset condition at a preset time length to obtain the wind condition data segment.

According to an embodiment of the present disclosure, in the prediction method, the predetermined condition includes that a data integrity rate exceeds a predetermined threshold.

According to an embodiment of the present disclosure, in the prediction method, the wind condition parameter may include at least one of a wind speed standard deviation, a wind speed variation amplitude, a wind direction variation amplitude, a wind shear value, and a wind turbine load.

According to an embodiment of the present disclosure, in the predicting method, the step of predicting the wind condition parameter of the predetermined reproduction period may include: determining a reliability indicator for the predetermined reproduction period based on a Gaussian probability function, wherein the reliability indicator is associated with a sum of squares of a first normative normal variable for a wind speed value and a second normative normal variable for a wind condition parameter; calculating a function of the wind condition parameter with respect to wind speed by a joint probability distribution of the first and second standard normal variables; predicting a wind condition parameter for the predetermined reproduction period based on the calculated function.

According to another aspect of the present disclosure, an apparatus for predicting extreme wind conditions of a wind turbine includes: a data processing unit configured to process the anemometer tower wind condition data to obtain a wind condition data segment; a data analysis unit configured to predict a wind condition parameter of a predetermined reproduction period based on a joint probability distribution of wind speed and the wind condition parameter in the wind condition data section; and a data output unit configured to output the predicted wind condition parameters for the predetermined reproduction period.

According to an embodiment of the present disclosure, in the prediction apparatus, the data processing unit may be configured to: acquiring high-frequency sampling data of the anemometer tower, wherein the high-frequency sampling data comprises at least one variable of a timestamp, a wind speed and a wind direction; determining whether the high frequency sampled data satisfies a predetermined condition; and performing data segment cutting on the high-frequency sampling data meeting the preset condition at a preset time length to obtain the wind condition data segment.

According to an embodiment of the present disclosure, in the prediction apparatus, the predetermined condition includes that a data integrity rate exceeds a predetermined threshold.

According to an embodiment of the present disclosure, in the prediction apparatus, the wind condition parameter may include at least one of a wind speed standard deviation, a wind speed variation amplitude, a wind direction variation amplitude, a wind shear value, and a wind turbine load.

According to an embodiment of the present disclosure, in the predicting device, the step of predicting the wind condition parameter of the predetermined reproduction period may include: determining a reliability indicator for the predetermined reproduction period based on a Gaussian probability function, wherein the reliability indicator is associated with a sum of squares of a first normative normal variable for a wind speed value and a second normative normal variable for a wind condition parameter; calculating a function of the wind condition parameter with respect to wind speed by a joint probability distribution of the first and second standard normal variables; predicting a wind condition parameter for the predetermined reproduction period based on the calculated function.

According to another aspect of the present disclosure, a computer readable storage medium storing a computer program which, when executed by a processor, implements a method of predicting extreme wind conditions of a wind turbine as described in any one of the above.

According to another aspect of the present disclosure, a computer device includes: a processor; a memory storing a computer program which, when executed by the processor, implements a method of predicting extreme wind conditions for a wind turbine as described in any one of the above.

Drawings

The above and other objects of exemplary embodiments of the present invention will become more apparent from the following detailed description taken in conjunction with the accompanying drawings which illustrate exemplary embodiments, wherein:

FIG. 1 is a flow diagram of a method of predicting extreme wind conditions, according to an embodiment;

FIG. 2 is a schematic diagram of a configuration of a prediction device for extreme wind conditions according to an embodiment;

FIG. 3 is a schematic illustration of the standard deviation of wind speed for a 50 year reproduction cycle;

FIG. 4 is a computer device for prediction of extreme wind conditions for a wind turbine according to an embodiment of the present disclosure.

Detailed Description

The following detailed description is provided to assist the reader in obtaining a thorough understanding of the methods, devices, and/or systems described herein. However, various changes, modifications, and equivalents of the methods, apparatus, and/or systems described herein will be apparent to those skilled in the art upon review of the disclosure of this application. For example, the order of operations described herein is merely an example, which is not limited to the order set forth herein, but rather, upon understanding the disclosure of the present application, changes may be made in addition to the operations which must occur in a particular order. Moreover, descriptions of features known in the art may be omitted for the sake of clarity and conciseness. In order that those skilled in the art will better understand the present invention, specific embodiments thereof will be described in detail below with reference to the accompanying drawings.

The wind condition parameters under the extreme wind condition are wind condition parameters with specific reproduction periods and corresponding occurrence probabilities, which cannot be obtained through actual tests but can be obtained only by calculation according to actual measurement data and by utilizing a probability distribution function.

Currently, the wind power industry calculates such wind condition parameters based on formulas recommended in IEC standards, which are set only by referring to a limited number of wind condition data in a short time in a few countries such as the united states, australia, germany, and the like. The validity of such extreme wind condition parameters needs to be further verified under the conditions of complex terrain and various climates in China.

Definition of technical terms

Joint probability distribution: joint probability distribution, referred to as joint distribution for short, is the probability distribution of a random vector composed of two or more random variables.

High frequency data: the returned data (generally second-level data) with high sampling frequency is collected by a wind measuring device and a data collector.

FIG. 1 is a flow diagram of a method of predicting extreme wind conditions according to one embodiment of the present disclosure. As shown in fig. 1, in step 101, wind condition data of a wind measuring tower is subjected to data processing to obtain a wind condition data segment.

Step 101 may include performing a data read operation. For example, anemometer tower high frequency sampling data is acquired. According to the embodiment of the present disclosure, the read data may be high-frequency sampling data (generally, second-level data) acquired by a wind measuring tower, and the data may be set to contain a timestamp, a wind speed, a wind direction, and other variables.

In step 101, an operation of determining whether the high frequency sample data satisfies a predetermined condition may be further included. According to an embodiment of the present disclosure, the predetermined condition includes the data integrity rate exceeding a predetermined threshold.

For example, a data integrity rate determination operation may be performed to determine whether the data integrity rate of the high frequency sampled data is met. A typical judging expression is as follows:

in equation (1), P represents the data integrity rate, and in the embodiment of the present disclosure, the threshold satisfying the data integrity rate condition may be set to be 85%, or 90%, or 95%, or even higher, but is not limited thereto, when the threshold satisfying the data integrity rate condition is set to be higher, the number of wind condition data segments satisfying the condition is smaller, so in specific implementation, the threshold satisfying the data integrity rate may be set according to a specific application scenario. If the judgment result of the formula (1) is 'yes', the data integrity rate condition is met, and the operation of the next step can be carried out; if "no," the analysis of this data is stopped.

In addition, in step 101, operations of performing segment cutting and preprocessing may be further included. For example, data segment cutting is performed on the high-frequency sampling data satisfying the predetermined condition for a predetermined length of time to obtain a wind condition data segment. In order to perform pattern recognition on the time series data points in a specific time period, the data read in step 101 needs to be segmented according to a specific time length, which is typically 10 minutes. For example, the data sampling period of an automatic digital condition monitoring System (SCADA) is 1s, and the number of points per wind condition data segment is 600. And then, judging the data integrity rate of the wind condition data fragments obtained by cutting again, and carrying out the next processing on the fragments meeting the data integrity rate condition by the judging method.

In step 102, a wind condition parameter for a predetermined reproduction period is predicted based on a joint probability distribution of wind speed and wind condition parameter in the segment of wind condition data.

The different reproduction periods can be customized as desired, for example, 1 year, 5 years, 10 years, 20 years, 30 years, 50 years, etc. The wind condition parameters may include: wind speed standard deviation, wind speed variation amplitude, wind direction variation amplitude, wind shear value, wind turbine load, etc., and may also include sea state conditions.

According to the embodiments of the present disclosure, in predicting the wind condition parameters of different reproduction periods based on the joint probability distribution of the wind speed and each wind condition parameter in the wind condition data segment, first, the reliability index of the predetermined reproduction period may be determined based on the gaussian probability function. Wherein the reliability indicator is associated with a sum of squares of a first normative normal variable for a wind speed value and a second normative normal variable for a wind condition parameter. Secondly, a function of the wind condition parameter with respect to the wind speed is calculated through a joint probability distribution of the first normal variable and the second normal variable. Thirdly, the wind condition parameters of the predetermined reproduction period are predicted based on the calculated function.

Step 102 will be described in detail below with reference to the standard deviation of wind speed as an example. V is defined as the wind speed, and σ is defined corresponding to the average wind speed in the 10-minute data segment acquired in step 101_VAssuming that the standard deviation of the wind speed of the 50-year reproduction period needs to be calculated, the reliability index is as follows:

wherein the content of the first and second substances,is the inverse of the Gaussian probability function, T_tIs the fragment duration (here 10min), T_rIs the total time length, n_mIs the number of fragments in a year.

This reliability index is the radius of the circle in the standard normal space, so:

where u1 and u2 represent the first normalized normal variable and the second normalized normal variable, respectively, and u1 and u2 are obtained by converting physical variables in consideration of correlation, for example: rosenblatt transform. At this time, the wind speed and the standard deviation can be expressed as follows:

the present disclosure is not limited to the joint probability distribution of wind speed and its standard deviation represented by equation (4), and the joint probability distribution may also be implemented by means of IFORM, SORM, or the like, for example.

According to IEC 61400-1: 2019 Standard, wind speed and standard deviation follow the Weibull distribution, so wind speed and standard deviation can be expressed as:

wherein A is a proportional parameter and k is a shape parameter. For example, the fitting relationship of the wind speed to the above two parameters, a (v) and k (v), can be obtained by fitting the measured data.

Then:

the formula (6) can be substituted into the formula (3) to be solved, and the wind speed standard deviation of the 50-year reproduction period can be obtained.

FIG. 3 is a schematic of the standard deviation of wind speed for a 50 year reproduction cycle. In fig. 3, the curve represents the standard deviation of a 50 year reproduction cycle and the scatter represents the measured data points.

According to the same calculation method, wind condition parameters such as wind speed standard deviation values, wind speed change amplitude values, wind direction change amplitude values, wind shearing parameters and wind generating set loads in different reproduction periods can be obtained.

In step 103, the result of step 102 is outputted, that is, the predicted wind condition parameter of the predetermined reproduction period is outputted.

FIG. 2 is a schematic diagram of a configuration of an extreme wind condition prediction device according to one embodiment of the present disclosure.

As shown in fig. 2, the device for predicting the wind condition parameters of the extreme wind condition mainly includes a data processing unit 100, a data analyzing unit 200, and a data output unit 300. The above units can perform data interaction through the bus to execute respective functions. In addition, each unit can also independently operate. The data processing unit 100 may be configured to process the anemometer tower wind condition data to obtain a wind condition data segment; the data analysis unit 200 may be configured to predict the wind condition parameters for a predetermined recurrence period based on a joint probability distribution of wind speed and wind condition parameters in the segment of wind condition data; the data output unit 300 may be configured to output the predicted wind condition parameters for the predetermined reproduction period. The present disclosure is not limited thereto and more functional modules may be included in each unit.

The data processing unit 100 may be used to obtain anemometer tower high frequency sampling data. Wherein the high frequency sampled data includes at least one variable of a time stamp, a wind speed, and a wind direction. The data processing unit 100 may read the high frequency sampling data from a wind tower of the wind turbine, and may also read the high frequency sampling data from real-time data of a main controller of the wind turbine. The high frequency sampling data may include time stamp, wind speed and wind direction data, for example, may be a data string, a data packet, a data array, and the like.

Furthermore, the data processing unit 100 may be further configured to determine whether the high frequency sampled data satisfies a predetermined condition. For example, the predetermined condition includes the data integrity rate exceeding a predetermined threshold. That is, the data processing unit 100 may perform data integrity check on the read high frequency sample data.

In addition, the data processing unit 100 may be further configured to perform data segment cutting on the high-frequency sampled data satisfying the predetermined condition for a predetermined length of time to obtain a wind condition data segment.

The data analysis unit 200 may predict the corresponding wind condition parameters for a predetermined recurrence period (e.g., 1 year, 5 years, 10 years, 20 years, 30 years, or 50 years, etc.) based on the joint probability distribution of the wind speed and each wind condition parameter in the segment of wind condition data. The wind condition parameters comprise at least one of wind speed standard deviation, wind speed change amplitude, wind direction change amplitude, wind shearing value, wind turbine load, sea condition and the like. The joint probability distribution processing may be implemented in an R environment or a matlab environment.

According to an embodiment of the present disclosure, the data analysis unit 200 may determine the reliability index of the predetermined reproduction period based on a gaussian probability function. Wherein the reliability indicator is associated with a sum of squares of a first normative normal variable for a wind speed value and a second normative normal variable for a wind condition parameter; calculating a function of the wind condition parameter with respect to wind speed by a joint probability distribution of the first and second standard normal variables; predicting a wind condition parameter for the predetermined reproduction period based on the calculated function.

The data output unit 300 may output a wind condition parameter predicted for a predetermined reproduction period, based on which the design of the wind turbine may be guided.

FIG. 4 is a computer device for prediction of extreme wind conditions for a wind turbine provided in accordance with an embodiment of the present disclosure.

The computer device includes a processor and a memory. The memory is for storing a computer program. The computer program is executed by a processor causing the processor to execute the method of prediction of extreme wind conditions of a wind turbine according to the invention.

As shown in fig. 4, the apparatus may include a processor 401 and a memory 402 storing computer program instructions.

Specifically, the processor 401 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured as one or more Integrated circuits implementing embodiments of the present invention.

Memory 402 may include mass storage for data or instructions. By way of example, and not limitation, memory 402 may include a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, tape, or Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 402 may include removable or non-removable (or fixed) media, where appropriate. The memory 402 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 402 is a non-volatile solid-state memory. In a particular embodiment, the memory 402 includes Read Only Memory (ROM). Where appropriate, the ROM may be mask-programmed ROM, Programmable ROM (PROM), Erasable PROM (EPROM), Electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory or a combination of two or more of these.

The processor 401, by reading and executing computer program instructions stored in the memory 402, implements any of the above described embodiments of a method for predicting extreme wind conditions for a wind turbine.

In one example, the computer devices described above may also include a communication interface 403 and a bus 404. As shown in fig. 4, the processor 401, the memory 402, and the communication interface 403 are connected via a bus 404 to complete communication therebetween.

The communication interface 403 is mainly used for implementing communication between modules, devices, units and/or devices in the embodiment of the present invention.

The bus 404 may comprise hardware, software, or both for coupling the above-described components to one another. For example, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus X10 may include one or more buses, where appropriate. Although specific buses have been described and shown in the embodiments of the invention, any suitable buses or interconnects are contemplated by the invention.

The wind generating set controller can execute the wind generating set operation control method in the embodiment of the invention, so as to realize the prediction method and the device of the extreme wind condition of the wind generating set described in conjunction with fig. 1 to 3.

According to the embodiment described above, the extreme wind condition parameters can be calculated more accurately according to historical wind speed and wind direction data, and the economic efficiency, competitiveness and reliability of the unit are improved on the basis of ensuring the safety of the unit. A universal solution is provided for extreme parameters, which can be used for calculating any environmental parameter and load of the wind generating set, thereby realizing the probability design of the set as a whole, such as loads with different reproduction periods, sea waves, ocean currents and the like.

According to an exemplary embodiment of the present invention, there is also provided a computer-readable storage medium storing a computer program. The computer readable storage medium stores a computer program which, when executed by a processor, causes the processor to perform the method of predicting extreme wind conditions of a wind turbine according to the invention. The computer readable recording medium is any data storage device that can store data read by a computer system. Examples of the computer-readable recording medium include: read-only memory, random access memory, read-only optical disks, magnetic tapes, floppy disks, optical data storage devices, and carrier waves (such as data transmission through the internet via wired or wireless transmission paths).

Although a few embodiments have been shown and described, it would be appreciated by those skilled in the art that changes may be made in these embodiments without departing from the principles and spirit of the disclosure, the scope of which is defined in the claims and their equivalents.