• Yash Dhayagude
• Aditya Pol
• Rutvik Gadade
• Sahil Bhagywant
• Yogita Shinkar

Wind turbines are a key player in harnessing clean, renewable energy. However, over time wind turbine blades can experience a variety of issues including cracks, erosion, or other forms of damage that affect operational efficiency, increase repair costs, and can even lead to failure of the wind turbine. Historically examining wind turbine blades for any of these issues has relied on manual inspection—in person or remotely—a process that can be slow, costly, and in some cases dangerous. In this project, we develop smarter methods for wind turbine blade fault detection based on modern technology. While other procedures also use modern technology, in practice we use safe non-destructive data collection techniques: signals, and thermal (heat) imaging, for example. Then we leverage signal processing and deep learning strategies with an emphasis on Convolutional Neural Networks (CNNs) to automate the detection and classification of any detected fault in the blades

Wind Turbine, Convolutional Neural Network, Pre-processing, Blade, Fault, Machine Learning, Deep Learning

" A Comprehensive Survey on Fault Detection in Wind Turbine Blades Using Machine Learning and NDT Tools", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 6, page no.c198-c204, June-2025, Available :http://www.jetir.org/papers/JETIR2506230.pdf

" A Comprehensive Survey on Fault Detection in Wind Turbine Blades Using Machine Learning and NDT Tools", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 6, page no. ppc198-c204, June-2025, Available at : http://www.jetir.org/papers/JETIR2506230.pdf