Search results

We introduce the Vibration concept for real coded Genetic Algorithm and its implementation to inverse airfoil design, which decreases the number of CFD calculations. This concept assures efficient diversity in the population and consequently gives faster solution. We used the Vibration concept as vibrational mutation and vibrational crossover. For the mutational manner, a sinusoidal wave with random amplitude is introduced into population periodically from the beginning of the initial step of the genetic process. This operation spreads out the population over the design space and increases exploration performance of the genetic process. This makes passing over local optimums for genetic algorithm easy. In order to apply this new concept at the crossover stages, Double Directional Alpha (DDA) approximation in BLX‐α as a new crossover technique which was already presented in our earlier study is used. In the developed technique, the value of α oscillates systematically during the genetic process. Implementation of the Vibration concept to the inverse airfoil design makes the convergence faster.

It is aimed to provide an efficient algorithm for path planning in guidance of autonomous unmanned aerial vehicle (UAV) through 3D terrain environments.

As a stochastic search method, vibrational genetic algorithm (VGA) is improved and used to accelerate the algorithm for path planning.

Using VGA, an efficient path planning algorithm for autonomous UAV was obtained under low population rate and short generation cycle conditions.

VGA decreased the required time for optimal path solution beside its simplicity. Low population rate and short generation cycle are the main benefits of VGA.

To propose a robust and more effective algorithm for aerodynamic design optimization problem by using neural network.

Neural network and genetic algorithm (GA) are hybridized in a new way, and quasi one‐dimensional Euler equations are solved for internal flow in the nozzle.

The results indicate that the nozzle design can be performed successfully and quickly by using the implemented algorithm. It is observed that using the method decreased CFD solver calls about 21 and 46 per cent for transonic and supersonic flow, respectively.

It is the first time that the neural network is used for the candidate solution in the GA.