Publication Date


Document Type


Committee Members

Harok Bae, Ph.D. (Advisor); Hong Huang, Ph.D. (Committee Member); James Menart, Ph.D. (Committee Member)

Degree Name

Master of Science in Renewable and Clean Energy Engineering (MSRCE)


As we expand and innovate for better and safer living, there will always be a need for new energy sources. By replacing fossil fuels, renewable energy is becoming a viable option for primary power generation. That is why researchers are turning their attention to renewable energy sources and ways of making the most of them. WIND ENERGY is a promising renewable and clean energy source harvested from the wind which is plentiful on the planet. We already have the technology to harvest it, but the efficiency and power output are not optimal. In this thesis, to enhance the energy harvesting performance of a wind turbine, the goal is to regulate frequency and power output fluctuations caused due to varying wind speeds. This thesis builds a physics-based simulation model of the wind turbine system with a flywheel to perform design studies. The flywheel, an inertia energy storage device, is implemented in the wind turbine to regulate the fluctuations. An illustration of the power outcomes of the wind turbine models with and without a flywheel is presented. Parameter studies are performed to understand how variables (weight, blade length, wind speed, and distance of weight from the center of the hub) influence the power outcomes. An artificial neural network model is trained using a multi-layer feedforward backpropagation network by applying the Levenberg-Marquardt algorithm. Simulation data is acquired from a physics-based iii wind turbine model formulated and built using MATLAB/SIMULINK to enable power output prediction and comprehensive design studies. The parametric studies found that the proposed wind turbine with the flywheel could regulate inconsistencies in the power output. The predictive neural network model was trained with the simulation data to enable a cost-effective design study. It is demonstrated how the neural network model can help develop a wind turbine with a flywheel system that produces desired power output by optimizing the selected design variables for any location or representation of the wind turbine.

Page Count


Department or Program

Department of Mechanical and Materials Engineering

Year Degree Awarded


Creative Commons License

Creative Commons Attribution-Noncommercial-Share Alike 3.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 License.