CN-116412087-B - Abnormality detection method and related device for wind generating set

CN116412087BCN 116412087 BCN116412087 BCN 116412087BCN-116412087-B

Abstract

The application discloses an abnormality detection method and a related device for wind power generation sets, wherein the method comprises the steps of obtaining operation data of each wind power generation set in a wind power plant in a historical time period, processing the operation data to obtain a plurality of operation data sets, wherein each operation data set comprises operation data of each wind power generation set in a continuous time period, each wind power generation set is in a yaw state in the continuous time period, screening out a target operation data set of each wind power generation set in the yaw state from the plurality of operation data sets, searching out abnormal data deviating from a preset data range from the target operation data set, and determining the wind power generation set corresponding to the abnormal data as a wind power generation set with abnormal yaw vibration. The application solves the problem that yaw vibration is difficult to find.

Inventors

WANG CHENXU
ZHANG XINLI
LIU WEI
SUN JING
WANG JIA
CHEN GANG

Assignees

新疆金风科技股份有限公司
中国电建集团西北勘测设计研究院有限公司

Dates

Publication Date: 20260512
Application Date: 20211231

Claims (10)

1. An abnormality detection method for a wind turbine generator system, comprising: acquiring operation data of each wind generating set in a wind power plant in a historical time period; Processing the operation data to obtain a plurality of operation data sets, wherein each operation data set comprises the operation data of each wind generating set in a continuous time period, and each wind generating set is in a yaw state in the continuous time period; Screening out target operation data sets of the wind generating sets in a yawing state from a plurality of operation data sets; finding out abnormal data deviating from a preset data range from the target operation data set; And determining the wind generating set corresponding to the abnormal data as a wind generating set with abnormal yaw vibration.
2. The method of claim 1, wherein the operational data includes a yaw flag bit, a cable untwisting flag bit, and a yaw residual pressure, and wherein the screening the target operational data set for each of the wind turbine generator sets in a yawing state from the plurality of operational data sets comprises: Acquiring a yaw zone bit, a cable untwisting zone bit and a yaw residual pressure of each wind generating set in each operation data set; determining continuous yaw duration of each wind generating set in each continuous time period according to the yaw zone bit of each wind generating set; Selecting the operation data set with continuous yaw duration meeting a first preset condition, the cable-releasing zone bit meeting a second preset condition and the yaw residual pressure meeting a third preset condition as the target operation data set, wherein the first preset condition is that the continuous yaw duration of each wind generating set is longer than or equal to the preset duration in a continuous time period corresponding to the operation data set, the second preset condition is that each cable-releasing zone bit in the operation data set represents that each wind generating set is in a non-cable-releasing state, and the third preset condition is that each yaw residual pressure in the operation data set is smaller than a preset residual pressure threshold.
3. The method of claim 1, wherein the obtaining operational data for each wind turbine in the wind farm over the historical period of time comprises: acquiring SCADA data of each wind generating set in a historical time period; And eliminating the SCADA data with the unit running state being the maintenance state to obtain the running data.
4. The method of claim 1, wherein the operational data comprises vibration acceleration, and wherein the searching for abnormal data from the target operational data set that deviates from a predetermined data range comprises: calculating a statistical value corresponding to the vibration acceleration of each wind generating set in the continuous time period in the target operation data set, wherein the statistical value comprises at least one of a maximum value, a minimum value and a mean value; and searching an abnormal statistical value with the value not in a preset data range from the statistical value corresponding to the vibration acceleration, wherein the operation data to which the abnormal statistical value belongs is abnormal data.
5. The method of claim 4, wherein the searching for an abnormal statistic value with a value not in the preset data range from the statistic values corresponding to the vibration acceleration comprises: in a coordinate system with time as a first coordinate axis and vibration acceleration as a second coordinate axis, taking a statistical value corresponding to the vibration acceleration of the wind generating set in each continuous time period as input data to form a scatter diagram; capturing discrete points which are not in a preset data range in the scatter diagram, wherein the statistic value corresponding to the discrete points is an abnormal statistic value.
6. The method according to any one of claims 1 to 5, wherein after the determining the wind turbine generator set corresponding to the anomaly data as a wind turbine generator set having abnormal yaw vibration, the method further comprises: Acquiring a unit identifier of the wind generating unit with abnormal yaw vibration; And feeding back early warning information comprising the abnormal data and the unit identifier to an operation and maintenance terminal.
7. A yaw vibration anomaly detection device of a wind generating set, the device comprising: The acquisition module is used for acquiring the operation data of each wind generating set in the wind power plant in the historical time period; the processing module is used for processing the operation data to obtain a plurality of operation data sets, each operation data set comprises the operation data of each wind generating set in a continuous time period, and each wind generating set is in a yaw state in the continuous time period; The screening module is used for screening out target operation data sets of the wind generating sets in a yawing state from the operation data sets; The searching module is used for searching abnormal data deviating from a preset data range from the target operation data set; and the determining module is used for determining the wind generating set corresponding to the abnormal data as a wind generating set with abnormal yaw vibration.
8. A yaw vibration abnormality detection apparatus of a wind turbine generator system, the apparatus comprising a processor and a memory storing computer program instructions; The processor, when executing the computer program instructions, implements a yaw vibration anomaly detection method for a wind turbine generator set according to any one of claims 1-6.
9. A computer readable storage medium, wherein computer program instructions are stored on the computer readable storage medium, and when executed by a processor, the computer program instructions implement the yaw vibration anomaly detection method of the wind turbine generator set according to any one of claims 1 to 6.
10. A computer program product, characterized in that the computer program product has stored thereon computer program instructions, which when executed by a processor, implement the yaw vibration anomaly detection method of a wind turbine generator set according to any one of claims 1 to 6.

Description

Abnormality detection method and related device for wind generating set Technical Field The application belongs to the technical field of wind power generation, and more particularly to a method, apparatus, device, computer readable storage medium and computer program product for anomaly detection of a wind turbine generator set. Background Wind power plants operate in complex environments for a long time as heavy equipment that operates over a long period of time. The vibration condition of the wind generating set is an important index reflecting the stability of the wind generating set, and the vibration within the allowable range of the wind generating set is normal, but if the vibration is aggravated, the component is damaged, and even serious accidents occur. At present, in order to prevent abnormal vibration, a protection value is usually set, and when the vibration of the unit is too large to exceed the protection value, a protection stop is started so as to prevent the unit from being impacted excessively. However, in the yaw process of the unit, due to the arrangement of a sensor control protection algorithm, vibration can be filtered, so that part of vibration impact in the yaw process is filtered, and abnormal vibration in the yaw process is difficult to find. Disclosure of Invention The embodiment of the application provides an abnormality detection method and a related device for a wind generating set, which can solve the problem that yaw vibration abnormality is difficult to find in the prior art. In one aspect, an embodiment of the present application provides a method for detecting an abnormality of a wind turbine generator system, including: acquiring operation data of each wind generating set in a wind power plant in a historical time period; Processing the operation data to obtain a plurality of operation data sets, wherein each operation data set comprises operation data of each wind generating set in a continuous time period, and each wind generating set is in a yaw state in the continuous time period; screening out target operation data sets of each wind generating set in a yawing state from a plurality of operation data sets; searching abnormal data deviating from a preset data range from a target operation data set; and determining the wind generating set corresponding to the abnormal data as the wind generating set with abnormal yaw vibration. The method comprises the steps of selecting a target operation data set of each wind generating set in a yawing state from a plurality of operation data sets, wherein the target operation data set comprises a yawing zone bit, a cable-untying zone bit and a yawing residual pressure, and the method comprises the following steps: Acquiring a yaw zone bit, a cable untwisting zone bit and a yaw residual pressure of each wind generating set in each operation data set; according to the yaw zone bit of each wind generating set, determining the continuous yaw duration of each wind generating set in each continuous time period; selecting an operation data set with continuous yaw duration meeting a first preset condition, a cable-releasing zone bit meeting a second preset condition and yaw residual pressure meeting a third preset condition as a target operation data set, wherein the first preset condition is that the continuous yaw duration of each wind generating set is longer than or equal to the preset duration in a continuous time period corresponding to the operation data set, the second preset condition is that each cable-releasing zone bit in the operation data set represents that each wind generating set is in a non-cable-releasing state, and the third preset condition is that each yaw residual pressure in the operation data set is smaller than a preset residual pressure threshold. Optionally, acquiring operation data of each wind generating set in the wind farm in the historical time period includes: acquiring SCADA data of each wind generating set in a historical time period; And eliminating SCADA data with the unit running state being the maintenance state to obtain the running data. Optionally, the operation data includes vibration acceleration, and searching for abnormal data deviating from a preset data range from the target operation data set includes: Calculating a statistical value corresponding to vibration acceleration of each wind generating set in a continuous time period in a target operation data set, wherein the statistical value comprises at least one of a maximum value, a minimum value and a mean value; and searching an abnormal statistical value with the value not in a preset data range from the statistical value corresponding to the vibration acceleration, wherein the operation data to which the abnormal statistical value belongs is abnormal data. Optionally, searching for an abnormal statistic value with a value not in a preset data range from the statistic values corresponding to the vibration acceleration includes: in a coo