☆ 3.8 Proceedings Paper

Imbalanced Multi-class Classification of Structural Damage in a Wind Turbine Foundation

EUROPEAN WORKSHOP ON STRUCTURAL HEALTH MONITORING (EWSHM 2022), VOL 3 (2023)

Structural Damage Classification in a Jacket-Type Wind-Turbine Foundation Using Principal Component Analysis and Extreme Gradient Boosting

Jersson X. Leon-Medina et al.

Summary: A data-driven pattern-recognition methodology for structural damage classification was developed and successfully applied to wind-turbine foundations in this study, with performance measures over 99.9% after validation through experimental tests.

SENSORS (2021)

添加到收藏夹

Article Chemistry, Analytical

Unsupervised Damage Detection for Offshore Jacket Wind Turbine Foundations Based on an Autoencoder Neural Network

Maria del Cisne Feijoo et al.

Summary: The article introduces a jacket-type foundation damage diagnosis strategy based on an autoencoder neural network model, which relies solely on healthy data and operates under different environmental conditions using vibration data. Experimental tests in laboratory settings have shown the effectiveness of this strategy.

SENSORS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Approximating XGBoost with an interpretable decision tree

Omer Sagi et al.

Summary: The increasing use of machine-learning models in critical domains has highlighted the importance of interpretable machine-learning models. Decision forests, especially Gradient Boosting Decision Trees (GBDT), are considered state-of-the-art in many classification challenges. This paper introduces a novel method for transforming any decision forest into an interpretable decision tree, providing transparency without compromising predictive performance like XGBoost.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Chemistry, Analytical