Wind Turbine Rotor Speed Control for Fast MPPT Tracking

Solution Overview

Problem

Existing wind turbine control systems face challenges in efficiently tracking maximum power at varying wind speeds due to the intermittence of wind speed, leading to suboptimal power generation and increased costs with existing MPPT control methods.

Innovation Solution

A neural network-based control system for wind turbines that considers wind speed, blade pitch angle, tip speed ratio, and other parameters to determine the optimum rotor speed and maximum power output, using machine learning algorithms to adjust operations in real-time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If conventional MPPT control methods (P&O, TSR, PSF) are used, then the control system is simple and cost-effective, but the response speed is slow and power tracking efficiency is reduced due to wind speed intermittence

Engineering Contradiction:

Improvecontrol system complexityVSAvoidresponse speed

Core Design Contradiction:

Device complexityVSSpeed

Solution Approach 1:

The neural network model is trained offline with pre-collected wind turbine data to learn the complex non-linear relationships between wind speed, rotor speed, and power output. This preliminary training phase enables the controller to rapidly predict optimal rotor speeds and maximum power points during online operation without requiring complex real-time calculations, thus achieving fast response while keeping the online control system relatively simple

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Traditional MPPT methods rely on mechanical feedback loops and iterative adjustment mechanisms that are inherently slow. The patent replaces these mechanical control approaches with an intelligent neural network-based system that uses pattern recognition and prediction algorithms to directly determine optimal operating points, eliminating the need for slow iterative search processes and achieving millisecond-level response speed

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Speed

If neural network-based control is implemented, then response speed and power tracking accuracy are improved, but device complexity and computational requirements increase

Engineering Contradiction:

Improveresponse speedVSAvoidcontrol system complexity

Core Design Contradiction:

SpeedVSDevice complexity

Solution Approach 1:

The neural network model is trained offline with pre-collected wind turbine data to learn the complex non-linear relationships between wind speed, rotor speed, and power output. This preliminary training phase enables the controller to rapidly predict optimal rotor speeds and maximum power points during online operation without requiring complex real-time calculations, thus achieving fast response while keeping the online control system relatively simple

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses a simplified neural network architecture that copies only the essential patterns and relationships from the complex non-linear wind turbine system. By training the network offline with comprehensive data, the model learns to replicate the system's optimal behavior without needing to implement the full physical complexity, thereby achieving high-performance control with reduced computational burden during operation

Inventive Principle:

Principle #26Copying

3Ease of manufacture

If traditional MPPT methods are used, then implementation is straightforward, but power generation efficiency is reduced due to slow response to wind speed changes

Engineering Contradiction:

Improveimplementation easeVSAvoidpower generation efficiency

Core Design Contradiction:

Ease of manufactureVSProductivity

Solution Approach 1:

The neural network model is trained offline with pre-collected wind turbine data to learn the complex non-linear relationships between wind speed, rotor speed, and power output. This preliminary training phase enables the controller to rapidly predict optimal rotor speeds and maximum power points during online operation without requiring complex real-time calculations, thus achieving fast response while keeping the online control system relatively simple

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

Traditional MPPT methods rely on mechanical feedback loops and iterative adjustment mechanisms that are inherently slow. The patent replaces these mechanical control approaches with an intelligent neural network-based system that uses pattern recognition and prediction algorithms to directly determine optimal operating points, eliminating the need for slow iterative search processes and achieving millisecond-level response speed

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11585322B1Wind turbine control apparatus and method therefor

Publication Date: 2023.02.21 KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS

AI summary

A wind turbine control apparatus, method and non-transitory computer-readable medium are disclosed. The wind turbine control apparatus comprises a generator connected to a wind turbine with a drive train. The drive train comprises a rotor, a low speed shaft, a gear box, a high speed shaft, and a controller module. The controller module is configured to obtain a maximum power within a large range of varying wind velocities by operating the rotor at a neural network determined optimal angular speed for the current wind velocity.