Wind energy, as a major contributor to the renewable energy sector, is receiving increasing attention to meet the growing demand for low-carbon electricity. The performance of a wind turbine can be significantly affected by various types of damage in its components, particularly the rotor blades. If left undetected, damage can develop rapidly under harsh operating conditions, potentially leading to severe failure, reduced power output, and considerable economic losses. However, the anisotropic properties and curved geometry of composite wind turbine blades make conventional time-domain methods less effective for reliable damage identification and localisation. To address this challenge, a methodology is developed that integrates deep learning with ultrasonic guided wave data analysis to enable accurate detection and classification of blade damage. An extensive numerical investigation is conducted, considering a range of damage locations and sizes across the blades. The samples are excited using a five-cycle Hanning-modulated sinusoidal pulse, and the structural responses at selected sensing positions are captured and converted into time-frequency representations to reveal more damage-sensitive features. The image-like data are then analysed using a custom-designed deep learning model to categorise and localise different damage cases. The results demonstrate a high level of accuracy in detecting both the location and severity of damage, indicating the strong potential of this approach for large-scale application in smart structural health monitoring of wind turbines.
Farbod Dadashbaki, S. Sikdar, D. D. Mandal et al.· e-Journal of Nondestructive...· 0 citations
Wind turbines (WT) need to perform well to meet the ever-growing demand of green energy. However, the performance of a wind turbine can be jeopardized due to occurrence of damage within its components. Acoustic emission (AE) is highly sensitive to occurrence of damage and can be used for damage identification. However, the localization of an AE source is challenging using a time domain method for structures that involve material anisotropy and complex geometry (e.g., curved surfaces and variable thickness). With this view, this work presents an unsupervised framework that operates on narrow frequency bands (NFBs) for artificial AE source determination in composite wind turbine blades. Unlike the conventional time-domain methods that require a network of sensors and the time of arrival information, the new method requires only one sensor and the information contained in the reduced frequency bands within each AE signal to discern its source. The unsupervised framework is found to be highly efficient in finding pattern in the multi-dimensional frequency domain dataset extracted from AE signals and can easily cluster the AE signals as per their zone of occurrence in a WT blade. This method can be easily implemented in real and complex structures as it requires only one sensor. Due to the very high degree of accuracy, the method can be applied to real complex systems and structures where time domain methods are not feasible. The method can also be included in a digital twin model for accurate prediction of an AE source.
D. D. Mandal, S. Sikdar, Rakesh Mishra· e-Journal of Nondestructive...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
