A comparative study between artificial neural network and linear regression for optimizing a hinged blade cross axis turbine

• Main Authors: Fernando, Arvin H., Marfori, Isidro Antonio V., Maglaya, Archie B.
• Format: text
• Published: Animo Repository 2016
• Subjects: Turbines—Blades; Turbines—Testing; Neural networks (Computer science); Mechanical Engineering
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/1919
• Institution: De La Salle University

In this paper a quantitative model was used to optimize the power output of a hinged blade cross axis turbine using different blade configuration. With the following parameters; number of blades, length of blades, thickness of blade, angle of blade, and foil shape. The data was collected on actual experiments using the newly design and built (RS/HTTP) River-flow simulator/ Hydrokinetic Turbine Testing Platform. The artificial Neural Network and Linear regression analysis are used to model the fitness function. In order to calculate the different blade combination resulting power output and find the optimize configuration. The result and data that was gathered between the two models was compared and analyzed. © 2015 IEEE.