Genetic Algorithm based Hinged-Blade Cross Axis Turbine Optimization Technique using Neural Network for Fitness Calculation  

Oleh:

Fernando, Arvin H. ; Vicerra, Ryan Rhay P. ; David, Kanny Krizzy A. ; Marfori III, Isidro Antonio V.

Jenis: Article from Proceeding
Dalam koleksi: The 14th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS), 3-6 December 2013 Cebu, Philippines, page 1-10.
Topik: Genetic Algorithm; Artificial Neural Network; Hinged-Blade Cross Axis Turbine; River Flow Simulation and Turbine Testing Tank Setup
Fulltext: 4015.pdf (315.46KB)

Isi artikel

In this research paper, we utilized genetic algorithm in order to optimize the power output of hinged-blade cross axis turbines. The following are its parameters; number of blades, length of blades, thickness of blade, angle of blade, and foil shape. The developed genetic algorithm optimization technique uses artificial neural network in order to calculate the fitness function of each possible combinations of the given parameters. The neural network training data are measured carefully in actual experiments in our newly designed (RS/HTTP) River-flow Simulator/ Hydro-kinetic Turbine Testing Platform. The RS/HTTP is composed of several actual test turbines, a fabricated large water tank and a powerful axial water pump simulating an actual river flow. Using Matlab programming the authors where able to train the neural network, utilize it in the genetic algorithm optimization technique and determine the optimized hinged-blade cross axis turbine design.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali