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

Wind turbines are subjected to continuous rotational stresses and unusualexternal forces such as storms, lightning, strikes by flying objects, etc.,which may cause defects in turbine blades. Hence, it requires a periodicalinspection to ensure proper functionality and avoid catastrophic failure. Thetask of inspection is challenging due to the remote location and inconvenientreachability by human inspection. Researchers used images with cropped defectsfrom the wind turbine in the literature. They neglected possible backgroundbiases, which may hinder real-time and autonomous defect detection using aerialvehicles such as drones or others. To overcome such challenges, in this paper,we experiment with defect detection accuracy by having the defects with thebackground using a two-step deep-learning methodology. In the first step, wedevelop virtual models of wind turbines to synthesize the near-reality imagesfor four types of common defects - cracks, leading edge erosion, bending, andlight striking damage. The Unity perception package is used to generate windturbine blade defects images with variations in background, randomness, cameraangle, and light effects. In the second step, a customized U-Net architectureis trained to classify and segment the defect in turbine blades. The outcomesof U-Net architecture have been thoroughly tested and compared with 5-foldvalidation datasets. The proposed methodology provides reasonable defectdetection accuracy, making it suitable for autonomous and remote inspectionthrough aerial vehicles.

A Novel Approach for Defect Detection of Wind Turbine Blade Using Virtual Reality and Deep Learning