• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2001.11a
• /
• pp.166-171
• /
• 2001

In order to improve the efficiency of the design process and the quality of the resulting design for the application-based exclusive rolling element bearings, this study propose design methodologies by using a genetic-based combinatorial optimization. By the presence of discrete variables such as the number of rolling element (standard component) and by the engineering point of views, the design problem of the rolling element bearing can be characterized by the combinatorial optimization problem as a fully discrete optimization. A genetic algorithm is used to efficiently find a set of the optimum discrete design values from the pre-defined variable sets. To effectively deal with the design constraints and the multi-objective problem, a ranking penalty method is suggested for constructing a fitness function in the genetic-based combinatorial optimization. To evaluate the proposed design method, a robust performance analyzer of ball bearing based on quasi-static analysis is developed and the computer program is applied to some design problems, 1) maximize fatigue life, 2) maximize stiffness, 3) maximize fatigue life and stiffness, of a angular contact ball bearing. Optimum design results are demonstrate the effectiveness of the design method suggested in this study. It believed that the proposed methodologies can be effectively applied to other multi-objective discrete optimization problems.

• Proceeding of EDISON Challenge
• /
• 2015.03a
• /
• pp.518-520
• /
• 2015

Automotive aerodynamic drag coefficient is important variable for vehicle's driving performance and fuel economy. In this research, we applied genetic algorithm to determine the geometrical figure which can optimize Carr's automotive aerodynamic underbody coefficient. And it's verified by previous research.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.52.2-52
• /
• 2001

We propose a new optimization method to improve the productivity of dispenser machines in PCB assembly lines. The optimization problem for multi-nozzle dispensers is formulated as a variant TSP. A genetic algorithm is applied to the problem to get a near-optimal solution. Chromosome and some operator are newly defined to implement the genetic algorithm for multi-nozzle dispensers. Simulation results are then presented to verify the usefulness of the method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.6
• /
• pp.767-772
• /
• 2018

Recently, some meta-heuristic algorithms, such as GA(Genetic Algorithm) and GP(Genetic Programming), have been used to optimize CNN(Convolutional Neural Network). The CNN, which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, the recent attempts to automatically construct CNN architectures are investigated and analyzed. First, two GA based methods are summarized. One is the optimization of CNN structures with the number and size of filters, connection between consecutive layers, and activation functions of each layer. The other is an new encoding method to represent complex convolutional layers in a fixed-length binary string, Second, CGP(Cartesian Genetic Programming) based method is surveyed for CNN structure optimization with highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.31 no.1
• /
• pp.34-38
• /
• 1994

본 연구에서는 Genetic Algorithm을 사용하여 상기의 문제를 해결하고자 한다. 특히 다목적 함수 최적화에는 한 번의 최적화 계산으로 Pareto최적해 집합이 동시에 구해지는 새로운 방법인 MOGA(Multicriteria Optimization by Genetic Algorithm)을 개발하였다. 먼저 Genetic Alorithm의 기본 특성에 대해 살펴보고, 다양한 종류의 문제를 통해 Genetic Algorithm의 유용 성을 검토하였다.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.2
• /
• pp.145-152
• /
• 2004

This paper proposes a representation for the embodiment design of mechanical structures and a genetic algorithm suited for the representation. In order to represent early stages and latter stages of the embodiment design, the designs are modeled as simultaneous multi-objective optimization problems of parametric designs for parts and of layout generation for structures. The study, thus, involves genotypes that are adequate to represent phenotypes of the models for the genetic algorithm to solve the given problems. We demonstrate the implementation of the genetic algorithm with the result applied to the gear equipment design.

• Journal of the Korean Society for Precision Engineering
• /
• v.21 no.9
• /
• pp.48-55
• /
• 2004

This study presents a genetic algorithm-based method fur optimizing control parameters in the pressure control of electro-hydraulic pump with variable displacement. Genetic algorithms are general-purpose optimization methods based on natural evolution and genetics and search the optimal control parameters maximizing a measure that evaluates the performance of a system. Four control gains of the PI-PD cascade controller for an electro-hydraulic pressure control system are optimized using a genetic algorithm in the experiment. Optimized gains are confirmed by inspecting the fitness distribution which represents system performance in gain spaces. It is shown that genetic algorithm is an efficient scheme in optimizing control parameters of the pressure control of electro-hydraulic pump with variable displacement.

• Journal of Environmental Impact Assessment
• /
• v.18 no.2
• /
• pp.99-109
• /
• 2009

In general, manual calibration is commonly used for the stream water quality modelling. Because the manual calibration depends upon the subjectivity and experience of the researcher, it has a problem with the objectivity of the modelling. Thus, the interest about the automatic calibration by the optimization technique is deeply increased. In this study, Influence coefficient algorithm and Genetic algorithm are introduced to develop an automatic calibration model for the QUAL2K that are the latest version of the QUAL2E. Genetic algorithm, used in this study, is very simple and easy to understand but also applicable to any complicated mathematical problem, and it can find out the global optimum solution effectively. The developed automatic calibration model is applied to the Gangneung Namdaecheon. The calibration results about the 11 water quality variables show the good correspondence between the calculated and observed water quality values.

• Steel and Composite Structures
• /
• v.4 no.6
• /
• pp.453-469
• /
• 2004

In this article, a genetic algorithm based optimum design method is presented for non-linear steel frames with semi-rigid connections. The design algorithm obtains the minimum weight frame by selecting suitable sections from a standard set of steel sections such as European wide flange beams (i.e., HE sections). A genetic algorithm is employed as optimization method which utilizes reproduction, crossover and mutation operators. Displacement and stress constraints of Turkish Building Code for Steel Structures (TS 648, 1980) are imposed on the frame. The algorithm requires a large number of non-linear analyses of frames. The analyses cover both the non-linear behaviour of beam-to-column connection and $P-{\Delta}$ effects of beam-column members. The Frye and Morris polynomial model is used for modelling of semi-rigid connections. Two design examples with various type of connections are presented to demonstrate the application of the algorithm. The semi-rigid connection modelling results in more economical solutions than rigid connection modelling, but it increases frame drift.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2002.04a
• /
• pp.621-624
• /
• 2002

The purpose of this paper is a study on getting proper gain set of PID controller which satisfies multi-performance specifications of the control system. The multi-objective optimization method is introduced to evaluate specifications, and the genetic algorithm is used as an optimal problem solver. To enhance the performance of genetic algorithm itself, adaptive technique is included. According to the proposed method in this paper, finding suitable gain set can be more easily accomplishable than manual gain seeking and tuning.