Wind Turbine Azimuth Drivetrain Wear Detection by Variation Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wind turbines experience wear in the azimuth steering drivetrain, leading to variations in azimuth pointing direction, which can cause excessive forces on the main drivetrain components, resulting in accelerated wear or damage, particularly to the gearbox, and existing monitoring systems fail to effectively detect these issues in a timely manner.
Innovation Solution
A monitoring system that accumulates and analyzes azimuth variation characteristics data to identify clusters associated with wear or damage, using machine learning and artificial intelligence techniques to predict upcoming damage and initiate maintenance before significant issues arise, allowing for proactive repairs and reducing the risk of main drivetrain damage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional monitoring systems are used to detect azimuth drivetrain wear, then the system structure remains simple, but the detection precision and timeliness are insufficient
Solution Approach 1:
The patent replaces traditional mechanical monitoring systems with a data-driven machine learning system. The system collects azimuth variation data from existing sensors and uses clustering algorithms to detect wear patterns, substituting complex mechanical detection mechanisms with computational analysis of operational data.
Solution Approach 2:
The patent introduces azimuth variation characteristics as an intermediary parameter to detect drivetrain wear. Instead of directly monitoring wear or excessive forces, the system measures azimuth variations around the set point, which serve as an indirect indicator of drivetrain health and wear conditions.
2Reliability
If proactive maintenance is implemented using machine learning predictions, then the reliability of the main drivetrain is improved, but the complexity of the monitoring system increases
Solution Approach 1:
The patent implements preliminary action by using machine learning models to predict future drivetrain damage before it occurs. The system analyzes historical azimuth variation data to identify patterns indicating wear, enabling maintenance teams to perform repairs proactively before excessive forces damage the main drivetrain components.
Solution Approach 2:
The patent establishes a feedback loop where azimuth variation measurements are continuously collected, analyzed by machine learning algorithms, and used to update maintenance decisions. The system learns from accumulated data to improve its predictions of drivetrain wear and damage risks over time.
Data Source
AI summary
Systems and methods to monitor a wind turbine azimuth drivetrain. Azimuth variation characteristics data are accumulated from wind turbines over a period of time. Clusters of values within the azimuth variation characteristics data are identified and a respective condition of the main drivetrain is associated with different clusters of values. After the associating, a measured set of azimuth variation characteristics data is received. A cluster corresponds to values in the measured set of azimuth variation characteristics data is determined and a condition associated with that cluster is determined to be a condition associated with the subject main drivetrain. That condition is then reported.