Adaptive Wind Turbine Control via Surrogate Fatigue Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wind turbine control strategies are predetermined for a long period and do not account for actual site conditions during operation, leading to suboptimal balancing of turbine lifetime, operational expenditure, and annual energy production.
Innovation Solution
A method that involves using a surrogate model to estimate fatigue loading based on real-time sensor measurements, allowing for the modification of the control strategy to optimize turbine operation by adjusting power curve, thrust limits, and wind sector management, utilizing statistical data and machine learning algorithms trained with aero-elastic turbine load simulations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a predetermined control strategy is used for the turbine's lifetime, then the control strategy is simple to implement and plan, but it cannot account for actual site conditions during operation leading to suboptimal performance
Solution Approach 1:
The control strategy transitions from static predetermined values to dynamic adaptive values that are continuously updated based on real-time fatigue monitoring and actual site conditions. The control parameters (power curve, thrust limits, wind sector management) are modified dynamically throughout the turbine's operational lifetime.
Solution Approach 2:
A feedback mechanism is implemented where fatigue values are continuously measured by sensors, processed through a surrogate model, and used to update the control strategy. This closed-loop system allows the turbine to adapt to actual conditions while maintaining manageable complexity through automated decision-making algorithms.
2Measurement precision
If strain gauges are used to measure fatigue loading, then accurate direct measurement is achieved, but the cost becomes expensive
Solution Approach 1:
Instead of using expensive strain gauges for direct measurement, the patent creates a surrogate model that copies the fatigue measurement function using cheaper sensors. The surrogate model processes data from affordable sensors (accelerometers, anemometers, etc.) to generate fatigue estimates that replicate what strain gauges would measure, significantly reducing cost while maintaining adequate precision.
3Loss of information
If full sensor data is recorded and used for fatigue calculation, then complete operational information is captured, but computational efficiency decreases
Solution Approach 1:
The patent extracts only the essential features from full sensor data by deriving statistical parameters (mean, maximum, minimum, standard deviation, rainflow count statistics, load duration distribution) that capture the critical fatigue-relevant information. This extraction process removes redundant data while preserving the key characteristics needed for accurate fatigue estimation, significantly improving computational efficiency.
Data Source
Figure 1~2
Figure 3a~3b
Figure 4~5
AI summary
A method of operating a wind turbine. The wind turbine is operated over an operating period in accordance with a control strategy. A sensor signal is received over the operating period from a sensor measuring an operational parameter of the turbine. A model is used to obtain a modelled fatigue value based on the sensor signal. The modelled fatigue value provides an estimate of fatigue loading applied to a component of the turbine over the operating period. The control strategy is modified based on the modelled fatigue value.