Condition monitoring of wind turbine blades via learning-based methods

TL;DR

This paper introduces a learning-based fault detection method for wind turbine blades using PCA and Autoencoders, validated with real turbine data to improve condition monitoring accuracy.

Contribution

It presents a novel data-driven approach combining PCA and Autoencoders for effective fault detection in wind turbine blades.

Findings

Successful detection of blade faults using real turbine data

Effective use of residual analysis with thresholds and likelihood ratio tests

Demonstrated robustness of the method in real-world conditions

Abstract

This paper addresses the topic of condition monitoring of wind turbine blades and presents a learning-based approach to fault detection. The proposed scheme utilises Principal Components Analysis and Autoencoders to derive data-driven models from root-bending moment and other measurements. The models are trained with real data obtained from a fault-free wind turbine, and then validated on data corresponding to unknown health condition. Online test statistics, employing static thresholds and Generalized Likelihood Ratio tests, are used on residual signals generated by discrepancies between the actual and reconstructed measurements to detect deviations from nominal operation. The efficacy and effectiveness of the proposed methods are demonstrated using real-life data collected from wind turbines experiencing blade faults.