In recent years, energy prices have risen dramatically worldwide, including Turkey. In addition to these rises, the environmental harm caused by fossil fuels has increased interest in renewable energy sources. Wind, a renewable energy source, is one of the primary focuses of this attention. Different engineering services are used to design wind turbine systems that convert kinetic energy from the wind into electrical energy. Wind turbine systems have evolved fast in recent years because of the world's rapid technological innovation and interest in wind. The study of the health of such structures has become an essential topic as the number and importance of wind turbines have increased. This thesis examined the blade of the Wind-Er model produced by XGEN-Energy company. The covariance-driven stochastic subspace identification method (SSI-Cov) was programmed using python to determine the eigen frequencies and mode shapes of the turbine blade. The study consists of two main parts. In the first part, the blade model is parametrically designed using python, and its modal analysis is made using the CalculiX finite element program. After the modal analysis was completed, transient analysis was performed to decide on the appropriate experimental setup. The SSI-Cov method was tested with the output data from the study. In the second part, tests were carried out on the physical model of the blade. The numerical model and the physical model output data confirmed each other. Natural frequencies and the mode shape of first mode were calculated using SSI-Cov from the model's modal parameters, and the results were consistent.