• Journal of Welding and Joining
• /
• 제18권5호
• /
• pp.63-69
• /
• 2000

A genetic algorithm was applied to an arc welding process to determine near optimal settings of welding process parameters which produce good weld quality. This method searches for optimal settings of welding parameters through systematic experiments without a model between input and output variables. It has an advantage of being able to find optimal conditions with a fewer number of experiments than conventional full factorial design. A genetic algorithm was applied to optimization of weld bead geometry. In the optimization problem, the input variables was wire feed rate, welding voltage, and welding speed and the output variables were bead height, bead width, and penetration. The number of level for each input variable is 16, 16, and 8, respectively. Therefore, according to the conventional full factorial design, in order to find the optimal welding conditions, 2048 experiments must be performed. The genetic algorithm, however, found the near optimal welding conditions from less than 40 experiments.

• 대한기계학회논문집B
• /
• 제28권3호
• /
• pp.296-303
• /
• 2004

The heat and flow characteristics in a single-phase parallel-flow heat exchanger was examined numerically to obtain its optimal shape. A response surface method was introduced to approximately predict its performance with respect to the design parameters over the design domain. The inflow/outflow angle of the working fluid, the location of inlet/outlet, the protruding height of flat tube and the height of header were chosen as a design parameter The evaluation of the relative importance of the design parameters was performed based on a sensitivity analysis. An efficiency index was used as an evaluation characteristics value to simultaneously consider both the heat transfer and the pressure drop. The efficiency index of the optimum model, compared to that of the base model, was increased by 9.3%.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 B
• /
• pp.1002-1004
• /
• 1999

The aim of this paper is to suggest a design method of the optimal multivariable $H_{\infty}$ control system using genetic algorithm(GA). This $H_{\infty}$ control system is designed by applying GA to the optimal determination of weighting functions and design parameter ${\gamma}$ that are given by Glover-Doyle algorithm which can design $H_{\infty}$ controller in the state space. The effectiveness of this $H_{\infty}$ control system is verified by nonlinear simulation.

• 산업경영시스템학회지
• /
• 제24권63호
• /
• pp.1-12
• /
• 2001

When designing the parameter on the multiple quality characteristics, there has been a study for optimization of problems, but there has been few former study on the possible conflicting phenomena in consideration of the correlations among the characteristics. To solve the issue on the optimal design for multiple quality characteristics, this study propose the expected loss function with cross-product terms among the characteristics and derived range of the coefficients of the terms. The model will be used to determine the global optimal design parameters where there exists the conflict among the characteristics, which shows difference in optimal design parameters for the individual characteristics. Also, when an adjustment factor exists for each m performance characteristics, this research propose a method by minimizing the expected loss after adjustment.

• 소성∙가공
• /
• 제7권6호
• /
• pp.562-569
• /
• 1998

The limit drawing ratio (LDR) is a major process parameter in the process design of deep drawing. If the actual drawing ratio is greater than the LDR for a particular stage then an intermediate stage has to b added the process sequence to avoid failure during the drawing operation and the optimal process design considering for the first-drawing and redrawing by using finite element method combined with ductile fracture criterion. From the results of finrte element analysis the optimal value of drawing ratio is obtained which contributes to the more uniform distribution of thickess and the smaller values of the ductile fracture infinal cup.

• Journal of information and communication convergence engineering
• /
• 제5권2호
• /
• pp.164-170
• /
• 2007

In this paper, the new method alternating with the method for forming the symmetrical distribution of power and local dispersion in high bit-rate WDM system with optical phase conjugator (OPC) is proposed. The proposed method is carried by finding out the optimal values of OPC position offset and fiber dispersion offset. It is assumed to be that NRZ-formatted 24-channels of 40 Gbps are simultaneously propagated in WDM system with non zero - dispersion shifted fiber (NZ-DSF) of 1,000 km. It is confirmed that the compensation extents of overall WDM channels are more improved by applying the induced optimal values into WDM system than those in WDM system with the conventional mid-span spectral inversion (MSSI) technique, and the searching procedure of the optimal values makes little difference of performance if the optimal value of one parameter related with another parameter. And, it is confirmed that the flexible design of WDM system with OPC is possible by effectiviely using by these optimal values. Thus, it is expected that the proposed method alternate with the forming method of the symmetrical distributions of power and local dispersion.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권6호
• /
• pp.683-691
• /
• 1999

In this paper, it is suggested that the selection method of optimal parameter of power system stabilizer(PSS) with robustness in low frequency oscillation for power system using Real Variable Elitism Genetc Algorithm(RVEGA). The optimal parameters were selected in the case of power system stabilizer with one lead compensator, and two lead compensator. Also, the frequency responses characteristic of PSS, the system eigenvalues criterion and the dynamic characteristic were considered in the normal load and the heavy load, which proved usefulness of RVEGA compare with Yu's compensator design theory.

• Structural Engineering and Mechanics
• /
• 제9권3호
• /
• pp.227-240
• /
• 2000

The study of the optimal damping ratio of a tuned liquid-column damper (or TLCD) attached to a single-degree-of-freedom system is presented. The tuned liquid-column damper is composed of two vertical columns connected by a horizontal section in the bottom and partially filled with water. The ratio of the length of the horizontal section to the effective wetted length of a TLCD considered as another important parameter is also presented for investigation. A simple pendulum-like model test is conducted to simulate a long-period motion in order to prove the effectiveness of TLCD for vibrational control. Comparisons of the experimental and analytic results of the TLCD, TLD (tuned-liquid damper), and TMD (tuned-mass damper) are included for discussion.

• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.132-139
• /
• 2019

We address the problem about forecasting the direction of stock price movement in the Korea market. Recently, the deep neural network is popularly applied in this area of research. In deep neural network systems, proper parameter initialization reduces training time and improves the performance of the model. Therefore, in our study, we propose a novel parameter initialization technique and apply this technique for the stock price movement prediction model. Specifically, we design a framework which consists of two models: a base model and a main prediction model. The base model constructed with LSTM is trained by using the large data which is generated by a large amount of the stock data to achieve optimal parameters. The main prediction model with the same architecture as the base model uses the optimal parameter initialization. Thus, the main prediction model is trained by only using the data of the given stock. Moreover, the stock price movements can be affected by other related information in the stock market. For this reason, we conducted our research with two types of inputs. The first type is the stock features, and the second type is a combination of the stock features and the Korea Composite Stock Price Index (KOSPI) features. Empirical results conducted on the top five stocks in the KOSPI list in terms of market capitalization indicate that our approaches achieve better predictive accuracy and F1-score comparing to other baseline models.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.1117-1120
• /
• 1999

In this paper, we design the H$\infty$ optimal controller satisfying robust stability and performance in spite of the plant uncertainty for an electro-mechanical actuator system and analyze the controller in frequency domain. H$\infty$ optimal controller K was designed using iteration algorithm suggested by DOYLE. Using the controller in an electro-mechanical actuator system, the joint with very small coupling rigidity coefficient was used to vary the control parameter. The plant unstructured uncertainty was assumed to be a multiplicative type.