Abdurrahman Hacioglu

Path planning for autonomous UAV via vibrational genetic algorithm

Purpose – It is aimed to provide an efficient algorithm for path planning in guidance of autonomous unmanned aerial vehicle (UAV) through 3D terrain environments.Design/methodology/approach – As a stochastic search method, vibrational genetic algorithm (VGA) is improved and used to accelerate the algorithm for path planning.Findings – Using VGA, an efficient path planning algorithm for autonomous UAV was obtained under low population rate and short generation cycle conditions.Originality/value – 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.

Inverse airfoil design by using an accelerated genetic algorithm via distribution strategies

In this study, the distribution strategies (DS) in evolutionary computations and their application to the inverse airfoil design problems have been introduced. Distribution strategies are based on the decomposition of the genetic operations for both upper and lower surfaces of the airfoil. We developed new strategies and combined these with a real coded genetic algorithm to obtain a faster and more robust method. We applied this new powerful method to the inverse airfoil design problems for inviscid, incompressible, and transonic flow conditions. The performance of this new method is compared with ones that were offered by classical or more commonly used genetic algorithms seen in the literature. That the number of computational fluid dynamics calculations decreased considerably, as much as 75%, shows the effectiveness of our new method.

Vibrational Genetic Algorithm (Vga) for Solving Continuous Covering Location Problems

This paper deals with a continuous space problem in which demand centers are independently served from a given number of independent, uncapacitated supply centers. Installation costs are assumed not to depend on either the actual location or actual throughput of the supply centers. Transportation costs are considered to be proportional to the square Euclidean distance travelled and a mini-sum criteria is adopted. In order to solve this location problem, a new heuristic method, called Vibrational Genetic Algorithm (VGA), is applied. VGA assures efficient diversity in the population and consequently provides faster solution. We used VGA using vibrational mutation and for the mutational manner, a wave with random amplitude is introduced into population periodically, beginning with 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. Since the problem is recognized as identical to certain cluster analysis and vector quantization problems, we also applied Kohonen maps which are Artificial Neural Networks (ANN) capable of extracting the main features of the input data through a self-organizing process based on local adaptation rules. The numerical results and comparison will be presented.

Vibrational genetic algorithm (VGA) and dynamic mesh in the optimization of 3D wing geometries

The objective of this study is to combine dynamic mesh technique and heuristic algorithms [Vibrational Genetic Algorithm (VGA)] to improve aerodynamic design of a wing, in order to see the effect of thickness ratio constraint when it is taken into the design parameters, additionally to reduce the drag values as much as possible while holding the lift value fixed. To solve the flow field around the 3D models obtained during the optimization stages, the mesh required is generated by dynamic mesh technique. The code developed for this aim is robust and faster than the codes, which only produce mesh by classical techniques. Because the operating time of the code is very long, on account of our low capacity computer resources, parallel processing has been used. Obviously, the strategy applied here can be used for any slowly deforming complex geometries, as long as an effective combination of the genetic algorithm and dynamic mesh be succeeded. From the results, it is observed that the optimization process is working as expected. The inviscid drag was reduced by about 25%.

A novel usage of neural network in optimization and implementation to the internal flow systems

Purpose – To propose a robust and more effective algorithm for aerodynamic design optimization problem by using neural network.Design/methodology/approach – 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.Findings – 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.Originality/value – It is the first time that the neural network is used for the candidate solution in the GA.

The effect of radius of joint location on workspace analysis of the 6-6 Stewart Platform Mechanism

In recent years, Stewart Platform Mechanism has been utilized extensively in applications which are vibration control and aligning optics of astronomical telescopes, satellite dish positioning, flight simulators, and so on requiring high precision, loading capacity, accuracy, rigidity and high velocity. However, the limited workspace, complex kinematic / kinetic solutions and singularities inside the workspace are the most important problems encountered with regard to this type of mechanisms. There are some parameters which affect significantly the workspace of Stewart Platform Mechanism. Some of these parameters are leg lengths, joint location angles and radius of joint location. Within this study, the effect of the radius of joint location of both moving platform and fixed platform on the workspace is investigated by calculating workspaces and comparing results for different radii of joint locations utilizing inverse kinematics technique.

A novel geometrical approach to determining the workspace of 6-3 Stewart Platform Mechanism

This paper presents a novel methodology for the workspace analysis of 6-3 Stewart Platform Mechanism covering all possible leg configurations which need the forward kinematics consideration. The proposed methodology uses a geometrical algorithm to evaluate the position of the movable platform. In this algorithm, the entire achievable positions of the first vertex of the movable platform are defined by considering the constraints of the connected leg lengths and joint angles. The second vertex is determined geometrically by utilizing the linked legs length, and an inverse kinematics approximation gives possible locations for the third vertex. Although it includes the forward kinematics point of view, the suggested method does not require the use of highly nonlinear algebraic equations with multiple solutions and time-consuming iterations which entail good initial values.