Wind turbine blade structural state evaluation by hybrid object detector relying on deep learning models
- PDF / 2,768,571 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 108 Downloads / 159 Views
ORIGINAL RESEARCH
Wind turbine blade structural state evaluation by hybrid object detector relying on deep learning models Dipu Sarkar1 · Sravan Kumar Gunturi2 Received: 20 February 2020 / Accepted: 30 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Surveillance drones are remarkable devices for monitoring, as they have strong spatial and remote sensing capabilities. The prompt detection of peripheral damage to the blades of wind turbines is necessary to reduce downtime and prevent the potential failure of wind farms. Computer vision breakthroughs with deep learning have developed and been refined over time, mainly using convolution neural networks. From this perspective, we suggest a deep learning model for monitoring and diagnosing the blade health of wind turbines based on images captured by surveillance drones. The main limitations of standard monitoring devices are their poor detection accuracy and lack of real-time performance, making it complex to obtain the attributes of blades from aerial images. Based on the foregoing, this study introduces a method for increasing detection accuracy when carrying out operations in real time using You Only Look at Once version 3 (YOLOv3). We train and evaluate three deep learning models on the wind turbine image dataset. We find that many aerial images are unclear because of blurred motion. As avoiding such low-resolution images for training can affect accuracy, we use a super-resolution convolution neural network to reconstruct a blurred picture as a high-resolution one. The computational results demonstrate that YOLOv3 outperforms traditional models in terms of both accuracy and handling time. Keywords Wind turbine · Surveillance drones · Renewable energy · YOLOv3
1 Introduction Wind energy has become a preferred method of generating renewable energy, since 1 MW of wind energy compensates for roughly 2600 tons of annual CO2 emission (AlKhudairi and Ghasemnejad 2015). A Wind Turbine (WT) comprises rotatory blades, core, gear unit, generator unit, tower, and base structures. Sufficient wind forces the WT blades to spin, and then the generator produces electricity from that motion. Blades are now commonly made of glass fiber-hardened composites, which offer enhanced resilience, increased resistance to corrosion, and lower weight, as well as enabling larger dimensions for greater harvesting of wind * Dipu Sarkar [email protected] 1
Department of Electrical and Electronics Engineering, National Institute of Technology Nagaland, Dimapur 797103, India
Department of Electronics and Instrumentation Engineering, National Institute of Technology Nagaland, Dimapur 797103, India
2
energy (Light-Marquez et al. 2011). WT blades are subject to various hazards over their 20-year lifecycle, including fatigue-induced deterioration from shifting loads, heavy wind, rain, thunderstorms, and bird strikes (Mandell et al. 2008). Since blades account for 15–20% of overall system cost, their damage may result in significant capital loss,
Data Loading...
