scholarly journals Data Fusion Based on an Iterative Learning Algorithm for Fault Detection in Wind Turbine Pitch Control Systems

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8437
Author(s):  
Leonardo Acho ◽  
Gisela Pujol-Vázquez
Keyword(s):  
Data Fusion ◽  
Wind Turbine ◽  
Control Systems ◽  
Iterative Learning Control ◽  
Numerical Experiments ◽  
Learning Algorithm ◽  
Iterative Learning ◽  
Sensor Data ◽  
Pitch Control ◽  
Actuator Failures

In this article, we propose a recent iterative learning algorithm for sensor data fusion to detect pitch actuator failures in wind turbines. The development of this proposed approach is based on iterative learning control and Lyapunov’s theories. Numerical experiments were carried out to support our main contribution. These experiments consist of using a well-known wind turbine hydraulic pitch actuator model with some common faults, such as high oil content in the air, hydraulic leaks, and pump wear.

Eliminating Structural Error in Real-Time Adjustable Four-Bar Path Generators Using Iterative Learning Control

2004 ◽  
Author(s):  
Hong-Jen Chen ◽  
Richard W. Longman ◽  
Meng-Sang Chew
Keyword(s):  
Control Systems ◽  
Real Time ◽  
Iterative Learning Control ◽  
Learning Control ◽  
Iterative Learning ◽  
Path Generation ◽  
Structural Error ◽  
Four Bar Linkage

Fundamental concepts of Iterative Learning Control (ILC) are applied to path generating problems in mechanisms. As an illustration to such class of problems, an adjustable four-bar linkage is used. The coupler point of a four-bar traces a coupler curve that will in general deviate from the desired coupler path. Except at the precision points, the coupler curve will exhibit some structural error, which is the deviation from the specified curve. The structural error will repeat itself every cycle at exactly the same points over the range of interest. Since ILC is a methodology that was developed to handle similar repetitive errors in control systems, it is believed that it will be well served to apply it to this class of problems. Results show that ILC can be simple to implement, and it is found to be very well suited for such path generation problems.

Iterative Learning Control for a Class of Modeling Undesirable Single Degree of Freedom System

2014 ◽  
Vol 538 ◽  
pp. 379-382
Author(s):  
Wei Zhou ◽  
Bao Bin Liu
Keyword(s):  
Iterative Learning Control ◽  
Learning Algorithm ◽  
Learning Control ◽  
Iterative Learning ◽  
Degree Of Freedom ◽  
Control Input ◽  
Convergence Properties ◽  
Single Degree Of Freedom ◽  
Single Degree ◽  
Simulation Results

A class of modeling undesirable single degree of freedom system is studied by using iterative learning control. The proposed iterative learning algorithm constantly updates the control input according to output error until the desired output occurred. So the system with designed controller can achieve perfect accuracy. We have proved convergence properties in iteration domain and simulation results demonstrate the effectiveness of the presented method.

Sign in / Sign up

Export Citation Format

Share Document