Wind Turbine Performance Index for Underperforming Farm Units
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current wind turbine performance monitoring technologies, such as power curves and machine learning methods, require extensive data collection and are inefficient for optimizing energy extraction in multi-turbine sites due to inter-turbine aerodynamics and remote operation challenges.
Innovation Solution
A method for identifying underperforming wind turbines in a wind farm using a performance analyzer processor that calculates a performance index based on state and control information, excluding wind speed, to optimize control data and improve energy extraction efficiency without requiring prior construction of performance curves.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If power curve methodology is used to monitor wind turbine performance, then extracted energy can be predicted at any wind speed, but extensive data collection over a sufficiently long period is required which delays meaningful results
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing performance metrics for each turbine in the farm during system initialization or using manufacturer data. This allows immediate performance comparison without requiring each turbine to accumulate its own historical data, thus eliminating the time delay while maintaining prediction accuracy
Solution Approach 2:
The patent uses copying by replicating the performance characteristics of a reference turbine (or multiple reference turbines) to estimate the performance of other turbines. Instead of requiring each turbine to build its own power curve from scratch, the system copies performance data from comparable turbines, significantly reducing the data collection period while maintaining measurement precision
2Adaptability or versatility
If multi-variable machine learning models are constructed to predict turbine extracted energy, then performance can be modeled with multiple inputs including shear, wind speed, and turbulence, but more data is required and implementation becomes more difficult
Solution Approach 1:
The patent segments the complex multi-variable performance modeling problem into simpler components by comparing turbines based on key operational parameters (wind speed, turbulence, shear) and grouping them into performance categories. This segmentation allows the system to handle multiple variables without requiring a single complex model, reducing implementation difficulty while maintaining adaptability
Solution Approach 2:
The patent applies parameter changes by dynamically adjusting the weighting and selection of input variables (wind speed, turbulence intensity, shear exponent) based on current operating conditions and turbine-specific characteristics. This allows the system to adapt to multiple variables without fixing a complex model structure, making implementation more straightforward while maintaining versatility
3Measurement precision
If traditional performance monitoring is used in multi-turbine sites, then individual turbine performance can be assessed, but inter-turbine aerodynamics and remote operation challenges reduce optimization efficiency
Solution Approach 1:
The patent merges individual turbine performance assessments with farm-level optimization by comparing each turbine's performance against others in the farm while accounting for inter-turbine aerodynamics. This combined approach maintains precise individual assessment while improving overall productivity by identifying and addressing aerodynamic interactions between turbines that affect energy extraction
Data Source
AI summary
A method for identifying underperforming agents in a multi-agent cooperative system includes receiving information relating to the performance of each agent in the multi-agent system, calculating an estimated extracted resource value of each agent based on the received information, comparing the estimated extracted resource value of each agent to a threshold value, calculating a performance index based on the comparison and identifying an agent as an under-performing agent based on the performance index. A system for identifying under-performing agents in a plurality of agents in a multi-agent cooperative system includes a performance analyzing processor, a communications port for receiving state information for each agent and control information for each agent, a classifier for identifying a subset of agents in the plurality of agents that are performance comparable and an optimizer configured to identify an under-performing agent of performance comparable agents and generate updated control information for the identified under-performing agent.