• Proceedings of the KWS Conference
• /
• 2004.05a
• /
• pp.18-20
• /
• 2004

This study is to find the optimal work plan of robot welding in the subassembly process of shipbuilding and to verify the found solution through 3-D simulation. The optimal work plan was established by evenly distributing the work amount to each stage and finding the shortest work sequence. The shortest work sequence was found by using the genetic algorithm. The result was compared with the practically adopted case and verified through the 3-D simulation.

• International Journal of Industrial Entomology and Biomaterials
• /
• v.2 no.2
• /
• pp.91-105
• /
• 2001

Taxonomic and phylogenetic studies of firefly in Japan have been reviewed. Fourty-six lampyrid species and one rhagophthalmid are distributed in the Japanese Islands including the Ryukyus. Recently, molecular phylogenetic approaches have been employed in the systematic study of firefly using mitochondrial and luciferase genes. Based on the molecular phylogenetic trees, evolutionary process of flashing patterns related strictly to mating behavior was estimated. Furthermore, genetic diversity studies revealed geographic differentiation patterns within species, and conservation measures of firefly were proposed to protect genetic resources endemic to the localities.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.2 no.3
• /
• pp.58-67
• /
• 1992

This paper presents a method on applying Genetric Algorithms(GA), which is a well-know high performance optimizing algorithm, to construct the self-organizing fuzzy logic controller. Fuzzy logic controller considered in this paper utilized Sugeno's hybrid inference method. which has an advantage of simple defuzzification process in the inference engine. Genetic algorithm is used to find the iptimal parameters in the FLC. The proposed approach will be demonstrated using 2 d. o. f robot manipulator to verify its effectiveness.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.11 no.3
• /
• pp.135-145
• /
• 2011

Accurate process characterization and optimization are the first step for a successful advanced process control (APC), and they should be followed by continuous monitoring and control in order to run manufacturing processes most efficiently. In this paper, process characterization and recipe optimization methods with multiple outputs are presented in high density plasma-chemical vapor deposition (HDP-CVD) silicon dioxide deposition process. Five controllable process variables of Top $SiH_4$, Bottom $SiH_4$, $O_2$, Top RF Power, and Bottom RF Power, and two responses of interest, such as deposition rate and uniformity, are simultaneously considered employing both statistical response surface methodology (RSM) and neural networks (NNs) based genetic algorithm (GA). Statistically, two phases of experimental design was performed, and the established statistical models were optimized using performance index (PI). Artificial intelligently, NN process model with two outputs were established, and recipe synthesis was performed employing GA. Statistical RSM offers minimum numbers of experiment to build regression models and response surface models, but the analysis of the data need to satisfy underlying assumption and statistical data analysis capability. NN based-GA does not require any underlying assumption for data modeling; however, the selection of the input data for the model establishment is important for accurate model construction. Both statistical and artificial intelligent methods suggest competitive characterization and optimization results in HDP-CVD $SiO_2$ deposition process, and the NN based-GA method showed 26% uniformity improvement with 36% less $SiH_4$ gas usage yielding 20.8 ${\AA}/sec$ deposition rate.

• Industrial Engineering and Management Systems
• /
• v.11 no.3
• /
• pp.233-240
• /
• 2012

The implementation of business process management (BPM) systems in large number of business organizations transforms BPM system into such a level of maturity and tends to collect large repositories of business process (BP) models. This issue encourages BP flexibility that leads to a large number of process variants derived from the same model, but differing in structure, to be stored in the large repositories of BP models. Therefore, the repositories may include thousands of activities and related business objects with variation of requirements and quality of service. It is a common practice to customize processes from reference processes or templates in order to reduce the time and effort required to design and deploy processes on all levels. In order to address redundancy and underutilization problems, a generic process model, called as reference BP, is absolutely necessary to cover the best of process variants. This study aims to develop multiple-objective business process genetic algorithm (MOBPGA) to find a set of non-dominated (Pareto) solutions of business reference model to enhance conventional approach which considered only a single objective on creating BP reference model by using proximity score measurement. A mixed-integer linear program is constructed to evaluate performance of the proposed MOBPGA on small-scale problems by using standard measures for multiple-objective techniques. The results will show the viability of applying MOBPGA in terms of simultaneously maximizing proximity score measurement, minimizing total duration, and total costs of the selected reference model.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.442-445
• /
• 1997

We present a hybrid self-tuning method of fuzzy inference systems with hyper elliptic Gaussian membership functions using genetic algorithm(GA) and back-propagation algorithm. The proposed self-tuning method has two phases : one is the coarse tuning process based on GA and the other is the fine tuning process based on back-propagation. But the parameters which is obtained by a GA are near optimal solutions. In order to solve the problem in GA applications, it uses a back-propagation algorithm, which is one of learning algorithms in neural networks, to finely tune the parameters obtained by a GA. We provide Box-Jenkins time series to evaluate the advantage and effectiveness of the proposed approach and compare with the conventional method.

• Journal of Microbiology and Biotechnology
• /
• v.2 no.1
• /
• pp.41-45
• /
• 1992

Shikonin production was examined in a bubble column bioreactor system with the hairy roots of Lithosphermum erythrorhizon. The volumetric productivity was higher than those obtained from other reactor configurations with free or immobilized cells of the same cell line. The productivities of the bubble column reactor, with and without a product absorption trap, were 7.4 and 4.5 mg of shikonin/l/d, respectively. This indicated the importance of the product removal in the design and operation of the shikonin production system with hairy root culture.

• Journal of the Korean Society for Precision Engineering
• /
• v.17 no.4
• /
• pp.173-180
• /
• 2000

In the process of grinding a long slender type workpiece, such as ballscrew, by the external cylindrical grinding machine, the cylindricity of the workpiece depends on the distance of rests, the stiffness of supports, the diameter and material of workpiece. Conventionally the process needs to be supported by one or more rests to prevent static deflection and vibration. In this paper, the optimal position of the rests was investigated in order to minimize the cylindricity due to the static deflection, by taking compliance of the workpiece and structure into account. In order to obtain the optimal position of rests, a new modeling that is considering the spring effect of all support elements was established. Since it is so complicated to obtain the optimal position analytically for various conditions due to discontinuity, a genetic algorithm u as utilized.

• Korean Management Science Review
• /
• v.17 no.2
• /
• pp.55-65
• /
• 2000

This paper addresses a problem of machining route selection in multi-stage process with machine group. This problem is considered the subcontracting and the production in-house such as regular and overtime work. the proposed model is formulated as a 0-1 integer programming constraining the avaliable time of each machine for planning period and total overtimes. The objective of the model is to minimize the sum of processing cost, overtime cost, and subcontracting cost. To solve this model, a genetic algorithm(GA) approach is developed. The effectiveness of the proposed GA approach is evaluated through comparisons with the optimal solution obtained from the branch and bound. In results, the same optimal solution is obtained from two methods at small size problem, and the consistent solution is provided by the GA approach at large size problem. The advantage of the GA approach is the flexibility into decision-making process because of providing multiple machining routes.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2873-2875
• /
• 2005

The optimal structure of the conventional Fuzzy Polynomial Neural Networks (FPNN)[3] depends on experience of designer. For the conventional Fuzzy Polynomial Neural Networks, input variable number, number of input variable, number of Membership Functions(MFs) and consequence structures are selected through the experience of a model designer iteratively. In this paper, we propose the new design methodology to find the optimal structure of Fuzzy Polymomial Neural Network by using Genetic Algorithms(GAs)[4, 5]. In the sequel, It is shown that the proposed Advanced Genetic Algorithms based Fuzzy Polynomial Neural Network(Advanced GAs-based FPNN) is more useful and effective than the existing models for nonlinear process. We used Medical Imaging System(MIS)[6] data to evaluate the performance of the proposed model.