English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Within commercial wind energy generation, the monitoring and predictivemaintenance of wind turbine blades in-situ is a crucial task, for which remotemonitoring via aerial survey from an Unmanned Aerial Vehicle (UAV) iscommonplace. Turbine blades are susceptible to both operational andweather-based damage over time, reducing the energy efficiency output ofturbines. In this study, we address automating the otherwise time-consumingtask of both blade detection and extraction, together with fault detectionwithin UAV-captured turbine blade inspection imagery. We propose BladeNet, anapplication-based, robust dual architecture to perform both unsupervisedturbine blade detection and extraction, followed by super-pixel generationusing the Simple Linear Iterative Clustering (SLIC) method to produce regionalclusters. These clusters are then processed by a suite of semi-superviseddetection methods. Our dual architecture detects surface faults of glass fibrecomposite material blades with high aptitude while requiring minimal priormanual image annotation. BladeNet produces an Average Precision (AP) of 0.995across our {\O}rsted blade inspection dataset for offshore wind turbines and0.223 across the Danish Technical University (DTU) NordTank turbine bladeinspection dataset. BladeNet also obtains an AUC of 0.639 for surface anomalydetection across the {\O}rsted blade inspection dataset.

Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery