Wind Turbine Individual Pitch Control for Blade Root Load Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The tuning of control laws for individual pitch control (IPC) methods in wind turbines remains a challenge, particularly in managing load variations at the blade root, which affects the structural dynamics and operational efficiency.
Innovation Solution
An IPC method utilizing a reinforcement learning (RL) process to train a neural network model that optimizes individual pitch control by minimizing load variations at the blade root, employing a cosine function-based control law adjusted by a trained model to adapt to current wind conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If individual pitch control (IPC) methods are applied to reduce load variations at the blade root, then the lifetime and structural integrity of the wind turbine is improved, but the complexity of control law tuning increases
Solution Approach 1:
The neural network model automatically adjusts the individual pitch control parameters based on real-time wind conditions and blade root load measurements, enabling the system to self-optimize without manual intervention. The model learns optimal control strategies through continuous operation and adapts to changing operational conditions autonomously.
Solution Approach 2:
The control system dynamically changes pitch angle parameters based on neural network predictions. The system monitors multiple parameters including wind speed, rotor speed, and blade root loads, then adjusts individual blade pitch angles in real-time to minimize load variations while maintaining optimal power generation.
2Adaptability or versatility
If a trained neural network model is used to select control laws based on wind conditions, then the adaptability to varying wind conditions is improved, but the device complexity increases
Solution Approach 1:
The patent replaces traditional mechanical control systems with an intelligent neural network-based control system. Instead of using complex mechanical sensors and actuators for each blade, the system uses a centralized neural network that processes wind condition data and generates control commands, simplifying the mechanical complexity while enhancing adaptability.
Solution Approach 2:
The neural network model serves multiple functions simultaneously: it predicts optimal pitch angles, adapts to different wind conditions, minimizes blade root loads, and maintains power generation efficiency. This multi-functional approach reduces the need for separate control systems for each function.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The individual pitch control method (100) comprises an online phase and an offline phase. The online phase comprises acquiring (130) a current value of a parameter corresponding to the wind speed, selecting (140) a current control law and generating (150) a control signal based on the current control law and a current azimuth angle of the blade. The offline phase (110) comprises obtaining a trained reinforcement learning model. Selecting a control law in the online phase consisting in running in inference the trained reinforcement learning model to estimate the current control law from the current value of at least one parameter corresponding to the wind speed.