The world is now moving towards a shift from traditional energy sources to renewable energy, like, wind power. Wind turbine is being manufactured in larger sizes today to harvest more energy although this leads to several technical challenges. The focus of this thesis is on blade-related damages. The aeroelastic behaviour of the blades is investigated by developing reliable models in OpenFAST (wind turbine simulation tool). In this work, several timeseries data are generated through OpenFAST considering healthy and damaged cases, where the damage is artificially introduced by decreasing the structural stiffness of one blade at three critical locations along the blade span. The goal of the present study is to develop a Gaussian process regression model using evidence (marginal likelihood) function to identify the damaged measurements. This resulted in a successful detection of the anomalous group of samples using the developed anomaly detection algorithm under possible and impossible visual detection scenarios.Many thanks to my colleagues as well, Nastaran Dabiran, Brandon Robinson, and David Clarabut for their help during my masters.I want to thank my defense committee, Dr. Thomas Walker and Dr. Elena Dragomirescu for devoting their valuable time to read my thesis and for providing me with their insightful comments and feedback.Finally, I would like to thank my family for their continuous support, encouragement and belief in my abilities, my dad, my mom, my two sisters and my brother. My dad and mom were the biggest support, their sacrifices have enabled me to pursue my academic aspiration.Without my family's love and support, this achievement would not have been possible, and for that, I am always grateful.