Wind power plant wind measurement data abnormity identification method and system, equipment and medium

By establishing a standard library of power generation threshold range and secondary judgment of adjacent data, the error problem of abnormal identification of wind measurement data in wind farm stations is solved, more accurate data support is provided, and the safety production and scheduling management of wind farms is improved .

CN119025863APending Publication Date: 2024-11-26HUANENG DINGBIAN NEW ENERGY POWER GENERATION CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411174033.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-26
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

During the storage, processing and transmission of wind measurement data of wind farms, it is easy to have problems such as missing, repeated, missing, and wrong numbers, which affects the normal judgment of the equipment. It is difficult for the prior art to effectively identify abnormal data and normal fluctuation data.

Method used

By obtaining historical wind measurement data and power generation, a standard library for power generation power threshold range is established to determine whether the current data is within the threshold range. If it is not there, a secondary judgment of adjacent data is performed to determine whether the data is abnormal.

Benefits of technology

It reduces judgment errors, provides more accurate data support for the diagnosis of fan equipment, and improves the real-time and accuracy of data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119025863A_ABST
    Figure CN119025863A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of wind power plant data processing, in particular to a wind power plant wind measurement data anomaly identification method and system, equipment and a medium. Obtaining a generated power threshold range corresponding to the current wind measurement data through a standard library, if the first generated power is not in the generated power threshold range corresponding to the current wind measurement data, marking the current wind measurement data as to-be-identified wind measurement data, and obtaining second generated power of the wind measurement data at a plurality of adjacent moments of the to-be-identified wind measurement data, and according to whether the second generated power is within the corresponding generated power threshold range, whether the to-be-identified wind measurement data is normal is obtained. Through the method, secondary judgment is performed on the abnormal data, that is, secondary judgment is performed through adjacent data to judge whether the abnormal data are true abnormal data or conventional fluctuation data, so that judgment errors are reduced, and relatively accurate data support is provided for subsequent diagnosis of fan equipment.
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 farm data processing, and in particular to a method and system, equipment and medium for identifying abnormality in wind farm wind measurement data. Background Art

[0002] Wind farms have a huge amount of data and many types of data, covering all aspects of wind farm production. The access work is cumbersome and requires high refinement. Data faces various risks in the process of storage, processing, and transmission. As a result, the requirements for the control and monitoring of the station are becoming more and more stringent, and inevitably contain various problems such as missing, duplication, missing, and wrong numbers, which brings new challenges to the safe production and refined dispatching management of wind farms. At the same time, with the reform of power trading, the development of cross-provincial and cross-regional spot trading of new energy, and the promotion of new energy new goods trading within the province, higher requirements are put forward for the real-time and accuracy of new energy.

[0003] At present, the conventional method for supplementing wind measurement data is generally to collect historical data for neural network learning, and select abnormal data through the neural network. However, the data selected by this method is not necessarily abnormal data, but may also be normal fluctuating data, which will affect the subsequent judgment of whether the wind power related equipment is normal. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system, equipment and medium for identifying abnormalities in wind measurement data of a wind farm, so as to solve the above-mentioned problems in the prior art.

[0005] The embodiments of the present invention are implemented by the following technical solutions:

[0006] In a first aspect, the present invention provides a method for identifying abnormalities in wind farm wind measurement data, comprising:

[0007] Obtain multiple sets of historical wind measurement data and the historical power generation corresponding to the historical wind measurement data, extract the maximum historical power generation and the minimum historical power generation under the same historical wind measurement data through the historical wind measurement data and the historical power generation to obtain the power generation threshold range, and establish a standard library;

[0008] Obtain the current wind measurement data and the first power generation, obtain the power generation threshold range corresponding to the current wind measurement data through the standard library, and determine whether the first power is within the power generation threshold range;

[0009] If the first power generation is within the power generation threshold range corresponding to the current wind measurement data, it is judged to be normal;

[0010] If the first power generation power is not within the power generation power threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation power of the wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained. Based on whether the second power generation power is within the corresponding power generation power threshold range, it is determined whether the wind measurement data to be determined is normal.

[0011] In one embodiment of the present invention, establishing a standard library includes:

[0012] Identify the wind speed and direction of all historical wind measurement data and establish a standard plane;

[0013] The historical wind measurement data with the same wind speed and the same angle between the wind direction and the standard plane are determined as the same historical wind measurement data, and several groups of the same historical wind measurement data are obtained;

[0014] The power generation powers of the same group of historical wind measurement data are integrated and sorted to obtain the power generation power threshold range of the same group of historical wind measurement data.

[0015] In one embodiment of the present invention, establishing the standard plane includes:

[0016] Establish the spatial coordinate system of the fan location and extract the installation plane of the fan;

[0017] Select the surface that is perpendicular to the installation plane and parallel to the windward surface of the fan as the standard plane.

[0018] In one embodiment of the present invention, it further comprises:

[0019] Obtain a number of historical wind measurement data with the same wind speed but different wind directions, and determine whether the wind turbine receives a yaw signal when detecting the historical wind measurement data;

[0020] If the wind turbine receives a yaw signal, several historical wind measurement data with the same wind speed but different wind directions are classified as the same historical wind measurement data;

[0021] If the wind turbine does not receive the yaw signal, it will be grouped normally according to different historical wind measurement data.

[0022] In one embodiment of the present invention, the second power generation of wind measurement data of a plurality of adjacent moments of the wind measurement data to be identified comprises:

[0023] Obtain N adjacent wind measurement data occurring before the wind measurement data to be confirmed, and N adjacent wind measurement data occurring after the wind measurement data to be confirmed;

[0024]

[0025] Where N is the number of wind measurement data obtained before or after the wind measurement data to be identified, and V is the wind speed of the wind measurement data to be identified.

[0026] In one embodiment of the present invention, obtaining whether the wind measurement data to be determined is normal according to whether the second generated power is within the corresponding generated power threshold range includes:

[0027] If the second power generation is within the corresponding power generation threshold range, the wind measurement data to be determined is normal fluctuation data;

[0028] If the second power generation power is not within the corresponding power generation power threshold range, the second power generation power that is not within the corresponding power generation power threshold range is recorded, and whether the wind measurement data to be determined is normal is determined based on the sequence of occurrence times of the recorded second power generation power.

[0029] In one embodiment of the present invention, judging whether the wind measurement data to be determined is normal according to the sequence of the recorded occurrence times of the second generated power includes:

[0030] If the second recorded power generation occurs at equal time intervals, the wind measurement data to be determined is considered abnormal;

[0031] If the recorded second generated power appears randomly and irregularly, the wind measurement data to be determined is determined to be normal fluctuation data.

[0032] In a second aspect, the present invention further provides a wind farm wind measurement data anomaly identification system, comprising:

[0033] A standard library establishment module is configured to obtain multiple sets of historical wind measurement data and historical power generation corresponding to the historical wind measurement data, extract the maximum historical power generation and the minimum historical power generation under the same historical wind measurement data through the historical wind measurement data and the historical power generation to obtain the power generation threshold range, and establish a standard library;

[0034] An acquisition module is configured to acquire current wind measurement data and a first power generation, obtain a power generation threshold range corresponding to the current wind measurement data through a standard library, and determine whether the first power is within the power generation threshold range;

[0035] The judgment module is configured to judge that the first power generation power is normal if it is within the power generation power threshold range corresponding to the current wind measurement data; if the first power generation power is not within the power generation power threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation power of the wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained, and whether the wind measurement data to be determined is normal is determined based on whether the second power generation power is within the corresponding power generation power threshold range.

[0036] In a third aspect, the present invention further provides an electronic device, 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 method for identifying anomalies in wind farm wind measurement data when executing the computer program.

[0037] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned method for identifying abnormalities in wind measurement data of a wind farm is implemented.

[0038] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0039] The method or system provided by the present invention mainly includes establishing a standard library; obtaining the power generation threshold range corresponding to the current wind measurement data through the standard library, if the first power generation is not within the power generation threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation of the wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained, and whether the wind measurement data to be determined is normal is determined based on whether the second power generation is within the corresponding power generation threshold range. Through the above method, a secondary judgment is made on the abnormal data, that is, another judgment is made through the adjacent data to determine whether the abnormal data is really abnormal or regular fluctuating data, so as to reduce the judgment error and provide relatively accurate data support for the subsequent diagnosis of wind turbine equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0042] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0043] The terms "first, second" and the like in the specification and claims of this application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The named or numbered process steps can be changed in the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0044] Please refer to Figure 1 The present invention provides a method for identifying abnormal wind data in a wind farm, comprising:

[0045] S101: Acquire multiple groups of historical wind measurement data and historical power generation corresponding to the historical wind measurement data, extract the maximum historical power generation and the minimum historical power generation under the same historical wind measurement data through the historical wind measurement data and the historical power generation to obtain a power generation threshold range, and establish a standard library;

[0046] In this embodiment, the historical wind measurement data mainly includes wind speed and wind direction. The collected historical wind measurement data can be data measured in multiple time periods, covering the normal wind speed and wind direction as much as possible, and recording the power generation of the wind turbine under the normal wind speed and wind direction.

[0047] S102: Acquire current wind measurement data and first power generation, obtain a power generation threshold range corresponding to the current wind measurement data through a standard library, and determine whether the first power is within the power generation threshold range;

[0048] In this embodiment, the power generation power of the same wind measurement data is integrated together to obtain a data group consisting of several power generation powers in the same wind measurement data. The maximum and minimum values ​​of the data group can be obtained by sorting the data group, and then the power generation power threshold range can be obtained.

[0049] S103: If the first power generation power is within the power generation power threshold range corresponding to the current wind measurement data, it is determined to be normal;

[0050] S104: If the first power generation power is not within the power generation power threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation power of wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained. Based on whether the second power generation power is within the corresponding power generation power threshold range, it is determined whether the wind measurement data to be determined is normal.

[0051] The method or system provided by the present invention mainly includes establishing a standard library; obtaining the power generation threshold range corresponding to the current wind measurement data through the standard library, if the first power generation is not within the power generation threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation of the wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained, and whether the wind measurement data to be determined is normal is determined based on whether the second power generation is within the corresponding power generation threshold range. Through the above method, a secondary judgment is made on the abnormal data, that is, another judgment is made through the adjacent data to determine whether the abnormal data is really abnormal or regular fluctuating data, so as to reduce the judgment error and provide relatively accurate data support for the subsequent diagnosis of wind turbine equipment.

[0052] In one embodiment of the present invention, establishing a standard library includes:

[0053] Identify the wind speed and wind direction of all historical wind measurement data and establish a standard plane; determine the historical wind measurement data with the same wind speed and the same angle between the wind direction and the standard plane as the same historical wind measurement data, and obtain several groups of the same historical wind measurement data; integrate and sort the power generation of the same group of the same historical wind measurement data to obtain the power generation threshold range of the same historical wind measurement data.

[0054] In this embodiment, the wind measurement data mainly includes wind speed and wind direction. In order to further improve the accuracy of the data, the wind measurement data with the same wind speed and wind direction cut-in angle are uniformly divided into groups.

[0055] Specifically, establishing the standard plane includes: establishing a spatial coordinate system for the location of the fan, extracting the installation plane of the fan; and selecting a surface perpendicular to the installation plane and parallel to the positive windward surface of the fan as the standard plane.

[0056] In this embodiment, the included angle is a smaller angle between the wind direction and the standard plane, that is, an acute angle.

[0057] In one embodiment of the present invention, it also includes: obtaining a number of historical wind measurement data with the same wind speed but different wind directions, and judging whether the wind turbine receives a yaw signal when detecting the historical wind measurement data; if the wind turbine receives a yaw signal, classifying the several historical wind measurement data with the same wind speed but different wind directions as the same historical wind measurement data; if the wind turbine does not receive a yaw signal, normal grouping is performed according to different historical wind measurement data.

[0058] In addition, in order to reduce data redundancy, data with the same wind speed but different wind directions are grouped again. When the wind speed is the same, if the wind turbine is yawed, the blades of the wind turbine will face the direction of the wind with the largest windward surface. Therefore, wind measurement data with the same wind speed and different wind directions but yawed can be grouped together to reduce the capacity of the entire database and improve the speed of subsequent judgment.

[0059] In one embodiment of the present invention, the second power generation of wind measurement data at a plurality of adjacent moments of the wind measurement data to be determined comprises: obtaining N adjacent wind measurement data occurring before the wind measurement data to be determined, and N adjacent wind measurement data occurring after the wind measurement data to be determined;

[0060]

[0061] Where N is the number of wind measurement data obtained before or after the wind measurement data to be identified, and V is the wind speed of the wind measurement data to be identified.

[0062] In this formula, the wind speed of the wind measurement data to be identified is obtained, the root is taken, and then rounded up to obtain the final result.

[0063] In one embodiment of the present invention, obtaining whether the wind measurement data to be determined is normal according to whether the second generated power is within the corresponding generated power threshold range includes:

[0064] If the second power generation is within the corresponding power generation threshold range, the wind measurement data to be determined is normal fluctuation data;

[0065] If the second power generation power is not within the corresponding power generation power threshold range, the second power generation power that is not within the corresponding power generation power threshold range is recorded, and whether the wind measurement data to be determined is normal is determined based on the sequence of occurrence times of the recorded second power generation power.

[0066] If the second generated power is not within the corresponding generated power threshold range, further judgment is required to determine whether the abnormal second generated power is a normal fluctuation or real abnormal data.

[0067] Specifically, judging whether the wind measurement data to be determined is normal according to the sequence of the recorded occurrence times of the second generated power includes:

[0068] If the second recorded power generation occurs at equal time intervals, the wind measurement data to be determined is considered abnormal;

[0069] In this embodiment, the equal moment intervals may be understood as the second generated power being recorded continuously or regularly.

[0070] If the recorded second generated power appears randomly and irregularly, the wind measurement data to be determined is determined to be normal fluctuation data.

[0071] In a second aspect, the present invention further provides a wind farm wind measurement data anomaly identification system, comprising:

[0072] A standard library establishment module is configured to obtain multiple sets of historical wind measurement data and historical power generation corresponding to the historical wind measurement data, extract the maximum historical power generation and the minimum historical power generation under the same historical wind measurement data through the historical wind measurement data and the historical power generation to obtain the power generation threshold range, and establish a standard library;

[0073] An acquisition module is configured to acquire current wind measurement data and a first power generation, obtain a power generation threshold range corresponding to the current wind measurement data through a standard library, and determine whether the first power is within the power generation threshold range;

[0074] The judgment module is configured to judge that the first power generation power is normal if it is within the power generation power threshold range corresponding to the current wind measurement data; if the first power generation power is not within the power generation power threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation power of the wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained, and whether the wind measurement data to be determined is normal is determined based on whether the second power generation power is within the corresponding power generation power threshold range.

[0075] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0076] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-On l yMemory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0077] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for identifying abnormalities in wind farm wind measurement data, characterized in that: include: Obtain multiple sets of historical wind measurement data and the historical power generation corresponding to the historical wind measurement data, extract the maximum historical power generation and the minimum historical power generation under the same historical wind measurement data through the historical wind measurement data and the historical power generation to obtain the power generation threshold range, and establish a standard library; Obtain the current wind measurement data and the first power generation, obtain the power generation threshold range corresponding to the current wind measurement data through the standard library, and determine whether the first power is within the power generation threshold range; If the first power generation is within the power generation threshold range corresponding to the current wind measurement data, it is judged to be normal; If the first power generation power is not within the power generation power threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation power of the wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained. Based on whether the second power generation power is within the corresponding power generation power threshold range, it is determined whether the wind measurement data to be determined is normal.

2. A method for identifying abnormalities in wind farm wind measurement data according to claim 1, characterized in that: The establishment of the standard library includes: Identify the wind speed and direction of all historical wind measurement data and establish a standard plane; The historical wind measurement data with the same wind speed and the same angle between the wind direction and the standard plane are determined as the same historical wind measurement data, and several groups of the same historical wind measurement data are obtained; The power generation powers of the same group of historical wind measurement data are integrated and sorted to obtain the power generation power threshold range of the same group of historical wind measurement data.

3. A method for identifying abnormalities in wind farm wind measurement data according to claim 2, characterized in that: The establishing of the standard plane comprises: Establish the spatial coordinate system of the fan location and extract the installation plane of the fan; Select the surface that is perpendicular to the installation plane and parallel to the windward surface of the fan as the standard plane.

4. A method for identifying abnormalities in wind farm wind measurement data according to claim 2, characterized in that: Also includes; Obtain a number of historical wind measurement data with the same wind speed but different wind directions, and determine whether the wind turbine receives a yaw signal when detecting the historical wind measurement data; If the wind turbine receives a yaw signal, several historical wind measurement data with the same wind speed but different wind directions are classified as the same historical wind measurement data; If the wind turbine does not receive the yaw signal, it will be grouped normally according to different historical wind measurement data.

5. The method for identifying abnormality in wind farm wind measurement data according to claim 1, characterized in that: The second power generation power of obtaining wind measurement data of a plurality of adjacent moments of the wind measurement data to be identified includes: Obtain N adjacent wind measurement data occurring before the wind measurement data to be confirmed, and N adjacent wind measurement data occurring after the wind measurement data to be confirmed; Where N is the number of wind measurement data obtained before or after the wind measurement data to be identified, and V is the wind speed of the wind measurement data to be identified.

6. A method for identifying abnormalities in wind farm wind measurement data according to claim 1, characterized in that: The obtaining whether the wind measurement data to be determined is normal according to whether the second generated power is within the corresponding generated power threshold range includes: If the second power generation is within the corresponding power generation threshold range, the wind measurement data to be determined is normal fluctuation data; If the second power generation power is not within the corresponding power generation power threshold range, the second power generation power that is not within the corresponding power generation power threshold range is recorded, and whether the wind measurement data to be determined is normal is determined based on the sequence of occurrence times of the recorded second power generation power.

7. A method for identifying abnormalities in wind farm wind measurement data according to claim 1, characterized in that: The determining whether the wind measurement data to be determined is normal according to the sequence of the occurrence times of the recorded second generated power comprises: If the second recorded power generation occurs at equal time intervals, the wind measurement data to be determined is considered abnormal; If the recorded second generated power appears randomly and irregularly, the wind measurement data to be determined is determined to be normal fluctuation data.

8. A wind farm wind measurement data anomaly identification system, characterized in that: include: A standard library establishment module is configured to obtain multiple sets of historical wind measurement data and historical power generation corresponding to the historical wind measurement data, extract the maximum historical power generation and the minimum historical power generation under the same historical wind measurement data through the historical wind measurement data and the historical power generation to obtain the power generation threshold range, and establish a standard library; An acquisition module is configured to acquire current wind measurement data and a first power generation, obtain a power generation threshold range corresponding to the current wind measurement data through a standard library, and determine whether the first power is within the power generation threshold range; The judgment module is configured to judge that the first power generation power is normal if it is within the power generation power threshold range corresponding to the current wind measurement data; if the first power generation power is not within the power generation power threshold range corresponding to the current wind measurement data, it is marked as wind measurement data to be determined, and the second power generation power of the wind measurement data at several adjacent moments of the wind measurement data to be determined is obtained, and whether the wind measurement data to be determined is normal is determined based on whether the second power generation power is within the corresponding power generation power threshold range.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, a method for identifying abnormalities in wind farm wind measurement data according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, a method for identifying abnormalities in wind measurement data of a wind farm according to any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Abnormal data identification method and device for wind power data

    CN115730695A

  • Wind power prediction method and device, equipment and storage medium

    CN116388148A

  • Progressive short-term wind power prediction method and system based on deep learning

    CN116579492A

  • Regional wind power cluster power prediction method based on space-time multiple clustering algorithm

    CN117277286A

  • Wind power prediction method and device, medium and electronic equipment

    CN117973743A