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

Barker, J.W.; Bhowmik, N.; Breckon, T.P.

Abstract

Within commercial wind energy generation, the monitoring and predictive maintenance of wind turbine blades in-situ is a crucial task, for which remote monitoring via aerial survey from an Unmanned Aerial Vehicle (UAV) is commonplace. Turbine blades are susceptible to both operational and weather-based damage over time, reducing the energy efficiency output of turbines. Here, we address automating the otherwise timeconsuming task of both blade detection and extraction, together with fault detection within UAV-captured turbine blade inspection imagery. In this work, we propose BladeNet, an application-based, robust dual architecture to perform both unsupervised turbine blade detection and extraction, followed by super-pixel generation using the Simple Linear Iterative Clustering (SLIC) method to produce regional clusters. These clusters are then processed by a suite of semi-supervised detection methods. Our dual architecture detects surface faults of glass fibre composite material blades with high aptitude while requiring minimal prior manual image annotation. BladeNet produces an Average Precision (AP) of 0.995 across our Ørsted blade inspection dataset for offshore wind turbines and 0.223 across the Danish Technical University (DTU) NordTank turbine blade inspection dataset. BladeNet also obtains an AUC of 0.639 for surface anomaly detection across the Ørsted blade inspection dataset.

Citation

Barker, J., Bhowmik, N., & Breckon, T. (2022, February). Semi-Supervised Surface Anomaly Detection of Composite Wind Turbine Blades From Drone Imagery. Presented at Computer Vision Theory and Applications 2022

• Presentation Conference Type: Conference Paper (published)
• Conference Name: Computer Vision Theory and Applications 2022
• Acceptance Date: Nov 16, 2021
• Online Publication Date: Feb 6, 2022
• Deposit Date: Dec 1, 2021
• Publicly Available Date: Dec 9, 2021
• Publisher: Institute of Electrical and Electronics Engineers
• Public URL: https://durham-repository.worktribe.com/output/1137895
• Publisher URL: https://visapp.scitevents.org/CallForPapers.aspx?y=2022#A5