Fatigue Damage Monitoring of Wind Turbine Blades by Using the Kalman Filter

Namura, Nobuo; Muto, K.; Ueki, Yosuke; Ueta, Ryo; Takeda, Norio

doi:10.2514/1.j060254

Cited by 5 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The paper showed successful detection of early failures of gearboxes in wind turbines, and failure of generator bearings in direct drive wind turbines. Kalman filters and state estimators were used in several contributions to predict the load history of mechanical components based on structural health monitoring (SHM) systems [5,6]. These state estimators can be based on simplified physics-based models or data-driven models.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Damage Equivalent Loads of Drivetrain of Wind Turbines using Machine Learning

Kamel

Hauptmann²,

Bottasso

2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In the recent years machine learning techniques have attracted the attention of wind energy community to make use of the large amount of available data produced from the running wind turbines. These modern wind turbines are typically equipped with measurement systems and sensors that can provide a wealth of information about the operating conditions of the machine. Nevertheless, not all the acquired raw data can be used effectively to enhance the operation of a turbine. This work addresses the question of estimating the damage equivalent loads (DEL) of different components of a drivetrain. The estimation is based on low frequency sampled typically available SCADA measurements. Typical SCADA measurements that are used as input for the estimation model are generator rotational speed, low speed shaft torque and generator torque as well as, wind speed and direction. Several machine learning methods as random forests (RF), support vector machines (SVM), linear regression (LR), decision trees and neural networks (NN) were developed, exhibiting different behavior for each approach. The qualitative and quantitative performance of each algorithm are evaluated and compared against each other. Furthermore, analysis of importance of the input features is presented.

show abstract

Section: Introductionmentioning

confidence: 99%