Wind generating set blade abnormal recognition method and device
A technology for wind turbines and abnormality identification, applied in wind turbines, wind turbine monitoring, engines, etc., can solve problems such as blade problem lag, failure to detect blade abnormalities in time, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0029] In this embodiment, a method for identifying abnormality of blades of a wind power generating set is provided, which is used for safety monitoring of the operating state of the wind power generating set. Crack and affect the aerodynamic performance of the blade or the balance of the impeller operation, so as to find the abnormal blade in time.
[0030] The method for identifying abnormality of blades of wind power generators in this embodiment, the flow chart is as follows figure 1 shown, including the following steps:
[0031] S11. Obtain operating parameter data of the wind power generating set, where the operating parameter data at least includes a Y-direction acceleration value.
[0032] The operation parameter selection historical data of the wind power generation unit described in this embodiment can be the historical data of recording the operation situation of the wind power generation unit within a period of time. The data includes at least the acceleration va...
Embodiment 2
[0045] In this embodiment, a method for identifying abnormality of blades of a wind power generating set is provided. The usage scenario is the same as that in Embodiment 1, and the flow chart is as follows figure 2 As shown, the method includes the following steps:
[0046] S21. Obtain operating parameter data of the wind power generating set, where the operating parameter data at least includes an acceleration value in the Y direction.
[0047] The operating parameter data of the wind power generating set input here is on-site transient operating data, which can be real-time data or pre-stored historical data. For example, the data sampling frequency is 1 / 7Hz, also known as 7-second data or 7s data, that is, every 7 seconds, the central monitoring system will record the instantaneous values of different variable signals during the operation of the unit as required for real-time or historical data storage down. The basic variable signals contained in the on-site detectio...
specific Embodiment approach
[0071] Specific implementation methods include as follows:
[0072] 1) Select the data of the small wind speed segment (5-8m / s) of the unit, divide the bins according to the wind speed every 0.5m / s, and select the bins with abnormally obvious amplitude of the acceleration signal of the cabin through data training, and use this program to detect the bin data , the target parameter reference value and the target difference threshold also need to be determined during the data training process.
[0073] 2) Select the data of the high-power segment of the unit (greater than or equal to (rated power-200kW)), divide the bins according to the power of 50kW, and select the bins with abnormally obvious amplitude of the acceleration signal of the cabin through data training, and use this program to detect the bin data , the target parameter reference value and the target difference threshold in the algorithm also need to be determined during the data training process.
[0074] 3) Select...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap