• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.3
• /
• pp.1063-1069
• /
• 2011

Today, tire performance becomes better as vehicle performance increases. Driviability, endurance, comfortability, noise, and antiwear performance is influenced by tire contour. Tire design method is developed by high-tech engineering technology. Among theses studies, tire performance improvement through tire contour optimization is performed by many vehicle investigator. Therefore, in the present study, an optimum contour design system satisfying the tire performance requirements is constructed by regression analysis and genetic algorithm by using design of experiments.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.27 no.2
• /
• pp.189-194
• /
• 2017

An compressor that is combined with the rotor and pneumatic technology has been researching for the performance of pressure. However, the control of operations, an accurate diagnosis and the maintenance of compressor system are limited though the simple structure of compressor and compression are advantaged to reduce the energy. In this paper, the characteristic of the compressor operating under the normal or abnormal condition is realized. and the efficient diagnosis method is proposed through feature based analysis. Also, by using the GA (genetic algorithm) and SVM (support vector machine) of machine learning, the performance of feature analysis is conducted. Different misalignment mode of learning data for compressor is evaluated using the fault simulator. Therefore, feature based analysis is conducted considering misalignment mode of the compressor and the possibility of a diagnosis of misalignment is evaluated.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.3
• /
• pp.191-199
• /
• 2001

This paper presents a new genetic algorithm for job-shop scheduling problems. When we design a genetic algorithm for difficult ordering problems such as job-shop scheduling problems, it is important to design encoding/crossover that is excellent in characteristic preservation and to maintain a diversity of population. We used Job-based order crossover(JOX). Since the schedules generated by JOX are not always active-schedule, we proposed a method to transform them into active schedulesby using the GT method with c)laracteristic preservation. We introduce strategies for maintaining a diversity of the population by eliminating same individuals in the population. Furthermore, we are not used mutation. Experiments have been done on two examples: Fisher s and Thompson s $lO\timeslO and 20\times5$ benchmark problem.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.38 no.5
• /
• pp.427-436
• /
• 2010

This paper deals with a task assignment problem of multiple UAVs performing multiple tasks on multiple targets. The task assignment problem of multiple UAVs is a kind of combinatorial optimization problems such as traveling salesman problem or vehicle routing problem, and it has NP-hard computational complexity. Therefore, computation time increases as the size of considered problem increases. To solve the problem efficiently, approximation methods or heuristic methods are widely used. In this study, the problem is formulated as a mixed integer linear program, and is solved by a mixed integer linear programming and a genetic algorithm, respectively. Numerical simulations for the environment of the multiple targets, multiple tasks, and obstacles were performed to analyze the optimality and efficiency of each method.

• Proceedings of the KSME Conference
• /
• 2001.06e
• /
• pp.548-554
• /
• 2001

A GA(Genetic Algorithm) based 3D-PTV technique has been developed. The measurement system consists of three CCD cameras, Ar-ion laser, an image grabber and a host computer. The fundamental of the developed technique was based on that one-to-one correspondence is found between two tracer particles selected at two different image frames taking advantage of combinatorial optimization of the genetic algorithm. The fitness function controlling reproductive success in the genetic algorithm was expressed by a kind of continuum theory on the sparsely distributed particles in space. In order to verify the capability of the constructed measurement system, a performance test was made using the LES data set of an impinging jet. The developed 3D-PTV system was applied to the measurement of flow characteristics of the wake of a circular cylinder.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.54 no.5
• /
• pp.234-241
• /
• 2005

The performance of passive conductor loop (hereinafter 'loop') method which is used to mitigate the magnetic field around overhead power transmission line is dependent on its configuration and installed location, which are affected by installation conditions of the loops such as objective areas and levels of magnetic field mitigation. Thus, because the design problem of loops is difficult and cumbersome by variety of their configuration and complexity of magnetic coupling mechanism, it is need to be formulated as a computer-based optimum problem to determine the most effective and reasonable loop model satisfying the installation conditions. In this paper, the optimum locations of the multi-wired multiple loops including series reactance compensations are searched by using the genetic algorithm (GA) to mitigate effectively the magnetic fields of relatively near points or far points from transmission line at Am height, and the magnetic fields mitigation characteristics of each loop are analyzed in the view of magnitude, direction and phase of cancellation fields by polarized vector concept to identify their adequacy and rationality for the installation objectives.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.1
• /
• pp.98-103
• /
• 2000

This paper suggests a method to recognize the various defect patterns of a cold mill strip using a binary decision tree automatically constructed by a genetic algorithm(GA). In classifying complex patterns with high similarity like the defect patterns of a cold mill stirp, the selection of an optimal feature set and an appropriate recognizer is important to achieve high recognition rate. In this paper a GA is used to select a subset of the suitable features at each node in the binary decision tree. The feature subset with maximum fitness is chosen and the patterns are classified into two classes using a linear decision function. This process is repeated at each node until all the patterns are classified into individual classes. In this way, the classifier using the binary decision tree is constructed automatically. After constructing the binary decision tree, the final recognizer is accomplished by having neural network learning sits of standard patterns at each node. In this paper, the classifier using the binary decision tree is applied to the recognition of defect patterns of a cold mill strip, and the experimental results are given to demonstrate the usefulness of the proposed scheme.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.17 no.12
• /
• pp.1161-1168
• /
• 2005

A Multi-Sectional 3D-PTV algorithm was developed to reduce the calculation time of the conventional GA-3D-PTV. The hardware system of the constructed 3D-PTV system consists of two high-speed cameras ($1,024\times1,018$ pixels, 60 fps), a metal halogen lamp (400W) and a host computer. The sphere(D=30mm) is suspended in a circulating water channel $(300mm\times300mm\times1,200m)$ and Reynolds number is 1,130. About 5,000 instantaneous three-dimensional velocity vectors have been obtained by the constructed 3D-PTV system. Turbulent properties such as turbulent intensity, Reynolds stress and turbulent kinetic energy were obtained. An eigenvalue analysis was carried out using the obtained instantaneous 3D velocity vectors to get the topological relations of the asymptotically stable critical point. Two structured shells, inner shell and outer shell, were found in the sphere wake and their motions were clarified by the measured data.

• Journal of Welding and Joining
• /
• v.27 no.4
• /
• pp.54-59
• /
• 2009

In the process to manufacture for metallic structures, control of welding deformation is one of an important problems connected with reliability of the manufactured structures so that welding deformation should be measured and controlled with quickly and actively. Also, welding parameters which have as lot of effects on welding deformation such as arc voltage, welding current and welding speed can also be controlled. The objectives for this study were to develop a simple 2-D FEM to calculate not only the transient thermal histories but also the sizes of fusion and heat-affected zone (HAZ) in multi pass arc welds including the butt and fillet weld type with dissimilar thickness, and to concentrate on a developed model for the finding the parameters of Godak's moving heat source model based on a GA. The developed model includes a GA program using MATLB and GA toolbox, and a batch mode thermal model using ANSYS software. Not only the thermal model was verified by comparison with Goldak's work but also the developed model was validated with molten zone section experimental data.

• Journal of the Korean Chemical Society
• /
• v.53 no.6
• /
• pp.653-662
• /
• 2009

Developing effective tools for predicting absorption, distribution, metabolism, excretion properties and toxicity (ADME/T) of new chemical entities in the early stage of drug design is one of the most important tasks in drug discovery and development today. As one of these attempts, support vector machines (SVM) has recently been exploited for the prediction of ADME/T related properties. However, two problems in SVM modeling, i.e. feature selection and parameters setting, are still far from solved. The two problems have been shown to be crucial to the efficiency and accuracy of SVM classification. In particular, the feature selection and optimal SVM parameters setting influence each other, which indicates that they should be dealt with simultaneously. In this account, we present an integrated practical solution, in which genetic-based algorithm (GA) is used for feature selection and grid search (GS) method for parameters optimization. hERG ion-channel inhibitor classification models of ADME/T related properties has been built for assessing and testing the proposed GA-GS-SVM. We generated 6 different models that are 3 different single models and 3 different ensemble models using training set - 1891 compounds and validated with external test set - 175 compounds. We compared single model with ensemble model to solve data imbalance problems. It was able to improve accuracy of prediction to use ensemble model.