• 한국기계가공학회지
• /
• 제7권3호
• /
• pp.3-11
• /
• 2008

Robust design pioneered by Dr. G. Taguchi has been applied to versatile engineering problems for improving quality. Since 1980s, the Taguchi method has been introduced to numerical optimization, complementing the deficiencies of deterministic optimization, which is often called the robust optimization. In this study, the robust optimization strategy is proposed by considering the robustness of objective and constraint functions. The statistics of responses in the functions are surrogated by kriging models. In addition, objective and/or constraint function is represented by the probability of success, thus facilitating robust optimization. The mathematical problem and the two-bar design problem are investigated to show the validity of the proposed method.

• 대한교통학회지
• /
• 제20권1호
• /
• pp.101-110
• /
• 2002

본 연구는 통행배분 모형과 네트워크 로딩의 일반적인 원리 및 그 관계를 규명하고. 시간을 고려한 네트워크 로딩방법 즉, 동적네트워크 로딩 방법을 소개한다. 우선 본 연구에서는, 동적 네트워크 로딩을 올바로 구현하기 위해 인과성 (causality), FIFO(First-In-First-Out), 교통량전파(flow propagation), 교통류보존(flow conservation) 등의 조건이 만족되어야 함을 제기한다. 그리고, 구체적인 동적 네트워크 로딩 방법을 알고리즘 형식으로 설명하였으며, 이후 링크 비용함수로써 결정적 대기행렬모형을 도입하여 가상 네트워크 속에서 동적 네트워크 로딩이 어떻게 이루어지는지를 수치적으로 보여준다.

• Water Engineering Research
• /
• 제4권3호
• /
• pp.111-126
• /
• 2003

Meteorological data are often needed to evaluate the long-term effects of proposed hydrologic changes. The evaluation is frequently undertaken using deterministic mathematical models that require daily weather data as input including precipitation amount, maximum and minimum temperature, relative humidity, solar radiation and wind speed. Stochastic generation of the required weather data offers alternative to the use of observed weather records. The precipitation is modeled by a Markov Chain-exponential model. The other variables are generated by multivariate model with means and standard deviations of the variables conditioned on the wet or dry status of the day as determined by the precipitation model. Ultimately, the objective of this paper is to compare Richardson's model and the improved weather generation model in their ability to provide daily weather data for the crop model to study potential impacts of climate change on the irrigation needs and crop yield. However this paper does not refer to the improved weather generation model and the crop model. The new weather generation model improved will be introduced in the Journal of KWRA.

• 품질경영학회지
• /
• 제40권1호
• /
• pp.49-59
• /
• 2012

In computer simulation models the output from the computer code is often deterministic, i.e., running the code twice with the same values for the input variables would give the same output. It is discussed why the response surface method with polynomial approximation for the true response function is a good approximation to the computer experiments model. A sequential strategy to find the proper reduced quadratic polynomial model is illustrated with a case study in the military war game computer simulation model.

• Industrial Engineering and Management Systems
• /
• 제16권1호
• /
• pp.44-51
• /
• 2017

In today's competitive environment, supply chain management is a major concern for a company. Two of the key issues in supply chain management are transportation and inventory management. To achieve significant savings, companies should integrate these two issues instead of treating them separately. In this paper we develop a framework for modeling stochastic programming in a supply chain that is subject to demand uncertainty. With reasonable assumptions, two stochastic programming models are presented, respectively, including a single-period and a multi-period situations. Our assumptions allow us to capture the stochastic nature of the problem and translate it into a deterministic model. And then, based on the genetic algorithm and stochastic simulation, a solution method is developed to solve the model. Finally, the computational results are provided to demonstrate the effectiveness of our model and algorithm.

• Management Science and Financial Engineering
• /
• 제16권3호
• /
• pp.21-47
• /
• 2010

Quantity discounts provide a practical foundation for supply chain inventory policies, improving the supplier's profit and reducing the buyer's inventory cost simultaneously. Traditional quantity-discount research, which deals with inventory coordination between a buyer and a supplier, is extended to a stationary stochastic environment. This research shows that the magnitude of the optimal discounts scheduled by the deterministic quantity discount models may not be large enough to cover the buyer's additional inventory stocking risks under uncertain conditions. As a result, the buyer's total inventory cost may often increase rather than decrease. In contrast, the proposed model allows the supplier to identify the discount level, which shares the buyer's amplified risk associated with temporary overstocking and ensures that both buyer and supplier benefit economically. The performance of the proposed model was tested in the continuous review environments via numerical experiments. The experimental results support the proposed method as a feasible alternative in coordinating inventory decisions under stochastic demand.

• 대한산업공학회지
• /
• 제9권2호
• /
• pp.37-46
• /
• 1983

The classical deterministic inventory model is investigated for the case of linear trend in demand and constant production rate. Three models are presented so as to minimize the total of set-up and inventory carrying costs over a finite time span. For each of the policies the methods are developed which can determine the optimal production quantities and times at which production should be started. Three policies are compared in point of costs and times for getting solutions and various case examples are also presented.

• Structural Engineering and Mechanics
• /
• 제32권1호
• /
• pp.1-20
• /
• 2009

The present contribution addresses uncertainty quantification and uncertainty propagation in structural mechanics using stochastic analysis. Presently available procedures to describe uncertainties in load and resistance within a suitable mathematical framework are shortly addressed. Monte Carlo methods are proposed for studying the variability in the structural properties and for their propagation to the response. The general applicability and versatility of Monte Carlo Simulation is demonstrated in the context with computational models that have been developed for deterministic structural analysis. After discussing Direct Monte Carlo Simulation for the assessment of the response variability, some recently developed advanced Monte Carlo methods applied for reliability assessment are described, such as Importance Sampling for linear uncertain structures subjected to Gaussian loading, Line Sampling in linear dynamics and Subset simulation. The numerical example demonstrates the applicability of Line Sampling to general linear uncertain FE systems under Gaussian distributed excitation.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2006년도 추계학술대회
• /
• pp.693-696
• /
• 2006

Global optimization is a method for finding more reliable models in various fields, such as financial engineering, pattern recognition, process optimization. In this study, we compare and analyze the performance of the state-of-the-art global optimization techniques, which include Genetic Algorithm (DE,SCGA), Simulated Annealing (ASA, DSSA, SAHPS), Tabu & Direct Search (DTS, DIRECT), Deterministic (MCS, SNOBIT), and Trust-Region algorithm. The test functions for the experiments are Benchmark problems in Hedar & Fukushima (2004), which are evaluated with respect to efficiency and accuracy. Through the experiment, we analyse the computational complexity of the methods and finally discuss the pros and cons of them.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 춘계학술대회 논문집
• /
• pp.817-821
• /
• 1997

Ever since the nonlinearity of machine tool dynamics was established, researchers attempted to make use of this fact to devise better monitoring, diagnostics and system, which were hitherto based on linear models. Theory of chaos, which explains many nonlinear phenomena comes handy for furthering the analysis using nonlinear model. In this study, measuring system will be constructed using multi-sensor (Tool Dynamometer, Acoustic Emission) in end millingprocess. Then, it will be verified that cutting force is low-dimensional deterministic chaos calculating Lyapunov exponents, Fractal dimension, Embedding dimension. Aen it will be investigated that the relations between characteristic parameter caculated form sensor signal and tool wear.