Wind Turbine Yaw Irregularity Detection via Virtual Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting irregular yaw activity in wind turbines are inefficient, often requiring access to MET tower readings and accurate nacelle orientation, and involve costly and time-consuming processes, including the use of specialized equipment and post-assembly sensor installations.
Innovation Solution
A data analytics platform identifies clusters of peer wind turbines based on shared meteorological conditions and derives yaw activity measures from available data to compare individual turbine yaw activity, identifying outliers through time-series analysis and differential calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If specialized equipment like LIDAR is used to detect irregular yaw activity, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent creates a virtual model (digital twin) of the wind turbine's yaw system that replicates its behavior using readily available sensor data. Instead of using complex physical measurement equipment like LIDAR, the system copies the yaw activity patterns through software simulation and compares them against expected patterns to detect irregularities, achieving accurate detection without specialized hardware
Solution Approach 2:
The patent replaces complex mechanical measurement systems (LIDAR, specialized sensors) with a computational approach using standard sensors and data analytics. The system substitutes physical measurement complexity with algorithmic complexity, using time-series analysis and pattern recognition to detect yaw irregularities that would otherwise require expensive specialized equipment
2Measurement precision
If post-assembly sensor installation is performed to detect irregular yaw activity, then measurement precision is improved, but loss of time and ease of manufacture deteriorate
Solution Approach 1:
The patent performs preliminary configuration during the software deployment phase rather than requiring post-assembly sensor installation. The detection system is pre-configured to work with standard sensors already present on the wind turbine, and the virtual model is established beforehand, allowing immediate detection capabilities without additional installation time
Solution Approach 2:
The patent creates a universal detection system that works with standard sensors already installed on wind turbines for other purposes. The same sensors used for general monitoring can feed data into the yaw activity detection algorithm, eliminating the need for specialized sensor installations and reducing deployment time while maintaining measurement precision
3Measurement precision
If MET tower readings and accurate nacelle orientation data are required for detection, then measurement precision is improved, but ease of operation and device complexity worsen
Solution Approach 1:
The patent introduces a virtual model as an intermediary that bridges the gap between available sensor data and accurate yaw activity measurement. The virtual model processes and integrates data from standard sensors, effectively mediating to produce precise measurements without requiring direct access to MET tower readings or specialized orientation sensors
Solution Approach 2:
The patent substitutes the need for complex data integration from multiple specialized sources (MET tower, precise orientation sensors) with a computational model that derives accurate yaw activity information from readily available standard sensor data, replacing mechanical measurement complexity with algorithmic processing
4Measurement precision
If manual positioning of specialized equipment is performed, then measurement precision is improved, but loss of time and productivity deteriorate
Solution Approach 1:
The patent implements a self-service detection system that automatically monitors yaw activity without requiring manual intervention for equipment positioning or data collection. The virtual model continuously processes sensor data and autonomously identifies irregularities, eliminating the need for manual operations while maintaining high measurement precision and improving overall productivity
Data Source
AI summary
A computing system is configured to detect irregular yawing at wind turbines. To this end, the computing system (i) for each respective turbine of an identified cluster of wind turbines: (a) obtains yaw-activity data indicative of the respective turbine's yaw activity during a window of time, and (b) based on obtained yaw-activity data, derives a yaw-activity-measure dataset having measures of the respective turbine's yaw activity during time intervals within the window of time, (ii) based on the respective yaw-activity-measure datasets for the turbines in the cluster, derives a cluster-level yaw-activity-measure dataset, (iii) evaluates the respective yaw-activity-measure dataset for one or more turbines in the cluster as compared to the cluster-level yaw-activity-measure dataset, (iv) based on the evaluation, identifies at least one turbine of the cluster that exhibited irregular yaw activity, and (v) transmits, to an output device, a notification of the irregular yaw activity at the at least one turbine.