Wind Turbine Yaw Calibration via Data Mining
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The wind power industry faces inaccuracies in wind measurement due to improper calibration and operational errors, leading to inherent wind alignment errors in wind turbines, which result in suboptimal generator output.
Innovation Solution
A method and device for automatically calibrating wind alignment errors using historical operation data analysis, involving data mining and dimensionality reduction to identify inherent wind alignment errors and adjust yaw system parameters, thereby enhancing self-adaptive capabilities and output performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If manual calibration method is used to install the wind vane, then the calibration process can be completed with simple equipment, but the absolute zero position of the wind vane may not be parallel to the centerline of the nacelle due to improper calibration method and operator errors
Solution Approach 1:
The system performs automatic calibration using historical operation data and data mining algorithms. The yaw system automatically identifies the inherent wind alignment error and adjusts the zero position parameter without requiring manual intervention, making the system self-correcting and eliminating operator errors.
Solution Approach 2:
The system uses historical operation data including wind alignment errors and output performance to continuously refine the calibration. By analyzing the relationship between wind alignment error and power output, the system provides feedback to automatically adjust the wind vane zero position, improving accuracy through iterative optimization.
2Device complexity
If manual calibration by operators is used, then equipment and installation costs can be reduced, but operation errors and maintenance errors may cause wind alignment errors
Solution Approach 1:
The patent replaces manual mechanical calibration with an automated data-driven system. Instead of relying on operators to physically adjust the wind vane, the system uses data mining algorithms to analyze historical operation data and automatically calculates the correction needed, substituting human operation with automated computational processing.
Solution Approach 2:
The system performs self-diagnosis and self-correction by analyzing its own historical operation data. The yaw system automatically identifies calibration errors and adjusts itself without requiring external intervention from operators or maintenance personnel, improving reliability through autonomous operation.
3Ease of operation
If traditional calibration methods are used, then installation process can be simplified, but extreme conditions such as typhoon may disturb the wind vane zero position
Solution Approach 1:
The system performs preliminary calibration by analyzing historical operation data collected under various conditions including extreme weather. By pre-processing this data to identify the optimal zero position, the system prepares the calibration parameters in advance, making the installation process simpler while ensuring stability against future disturbances.
Solution Approach 2:
The calibration system is designed to be dynamic and adaptive rather than static. It continuously monitors operation data and can recalibrate the wind vane zero position in response to changes in operating conditions or disturbances from extreme weather, maintaining stability through adaptive adjustment.
4Manufacturing precision
If automatic calibration using historical data analysis is implemented, then wind alignment error can be accurately identified and corrected, but data processing complexity and computational requirements increase
Solution Approach 1:
The system extracts only the essential features from historical operation data that are relevant to wind alignment calibration. By focusing on key parameters such as wind direction, yaw angle, and power output, the system avoids processing unnecessary data, reducing computational complexity while maintaining calibration accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided are a method and device for automatically calibrating a wind alignment error of a wind power generation unit. The method comprises: obtaining historical operation data of a target unit within a preset time period; removing abnormal data from the historical operation data of the target unit; performing dimensionality reduction processing on target data and determining a curve representing a relationship between wind alignment error and output performance by means of data obtained after the dimensionality reduction processing; determining an inherent wind alignment error by means of the curve representing the relationship between wind alignment error and output performance; and correcting zero parameters in a yaw system of the target unit on the basis of the inherent wind alignment error. The device has multiple modules, and the function of each of the modules corresponds to the method. According to the above method and device, historical operation data of a wind generation unit is utilized, and an inherent wind alignment error of a yaw system of a target unit is automatically identified by data exploration and analysis, so that zero parameters in the yaw system of the target unit can be automatically adjusted according to the inherent wind alignment error, enhancing the adaptability of the yaw system of the unit and improving the actual output performance of the unit.