• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.12
• /
• pp.1165-1172
• /
• 2007

The spacer grid set is a part of a nuclear fuel assembly. The set has a spring and the spring supports the fuel rods safely. Although material nonlinearity is involved in the deformation of the spring, nonlinearity has not been considered in design of the spring. Recently a nonlinear response structural optimization method has been developed using equivalent loads. It is called nonlinear response optimization equivalent loads (NROEL). In NROEL, the external loads are transformed to the equivalent loads (EL) for linear static analysis and linear response optimization is carried out based on the EL in a cyclic manner until the convergence criteria are satisfied. EL is the load set which generates the same response field of linear analysis as that of nonlinear analysis. Shape optimization of the spring is carried out based on EL. The objective function is defined by minimizing the maximum stress in the spring while mass is limited and the support force of the spring is larger than a certain value. The results are verified by nonlinear response analysis. ABAQUS is used for nonlinear response analysis and GENESIS is employed for linear response optimization.

• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.4
• /
• pp.259-275
• /
• 2021

This study explored the usefulness and implications of the Bayesian hyperparameter optimization in developing species distribution models (SDMs). A variety of machine learning (ML) algorithms, namely, support vector machine (SVM), random forest (RF), boosted regression tree (BRT), XGBoost (XGB), and Multilayer perceptron (MLP) were used for predicting the occurrence of four benthic macroinvertebrate species. The Bayesian optimization method successfully tuned model hyperparameters, with all ML models resulting an area under the curve (AUC) > 0.7. Also, hyperparameter search ranges that generally clustered around the optimal values suggest the efficiency of the Bayesian optimization in finding optimal sets of hyperparameters. Tree based ensemble algorithms (BRT, RF, and XGB) tended to show higher performances than SVM and MLP. Important hyperparameters and optimal values differed by species and ML model, indicating the necessity of hyperparameter tuning for improving individual model performances. The optimization results demonstrate that for all macroinvertebrate species SVM and RF required fewer numbers of trials until obtaining optimal hyperparameter sets, leading to reduced computational cost compared to other ML algorithms. The results of this study suggest that the Bayesian optimization is an efficient method for hyperparameter optimization of machine learning algorithms.

• The KIPS Transactions:PartA
• /
• v.10A no.5
• /
• pp.519-528
• /
• 2003

Container terminals need decisions in the course of daily-24 hour and 365 day - operations, and all these decisions are inter-related. The ultimate goal of Decision Support System is to minimize ship loading/unloading time, resources used to handle the workload, and congestion on the roads inside the terminal. It is also to make the best possible use of the storage space available. Therefore, the necessity of decision support tools are emphasized to enhance the operational efficiency of container shipping terminals more, because of limits and complexity of these decisions. So, in thia paper, we draw evaluation items for Decision Support Systems and suggest optimization strategy of evaluation items which have the greatest influence on Decision Support system, that is, yard stacking allocation, RTGC deployment among blocks, and YT allocation to QCs. We also estimate the efficiency of Decision Support System design by simulation using G2 language, comparing ship loading/unloading time.

• Korean Chemical Engineering Research
• /
• v.48 no.6
• /
• pp.717-724
• /
• 2010

The flash point is one of the most important physical properties used to determine the potential for fire and explosion hazards of flammable liquids. Despite the needs of the experimental flash point data for the design and construction of chemical plants, there is often a significant gap between the demands for the data and their availability. This study have built and compared two models of partial least squares(PLS) and support vector machine(SVM) to predict the experimental flash points of 893 organic compounds out of DIPPR 801. As the independent variables of the models, 65 functional groups were chosen based on the group contribution method that was oriented from the assumption that each fragment of a molecule contributes a certain amount to the value of its physical property, and the logarithm of molecular weight was added. The prediction errors calculated from cross-validation were employed to determine the optimal parameters of two models. And, an optimization technique should be used to get three parameters of SVM model. This work adopted particle swarm optimization that is one of heuristic optimization methods. As the selection of training data can affect the prediction performance, 100 data sets of randomly selected data were generated and tested. The PLS and SVM results of the average absolute errors for the whole data range from 13.86 K to 14.55 K and 7.44 K to 10.26 K, respectively, indicating that the predictive ability of the SVM is much superior than PLS.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.4
• /
• pp.450-456
• /
• 2014

Humanoid robot is the most suitable robot platform for effective human and robot interaction. However, the robot's complicated body structure containing more than twenty joint actuators makes it difficult to generate stable and elaborate postures using the conventional inverse kinematic method. This paper proposes an alternative approach to generate difficult postures of touching an object placed in front of the foot by the left or right hand with its torso bent forward in single support phase using the fast computational optimization method, particle swarm optimization. The simulated postures are also applied to a commercial humanoid robot platform, which validates the feasibility of the proposed approach.

• Proceedings of the KSME Conference
• /
• 2007.05a
• /
• pp.694-699
• /
• 2007

The spacer grid set is a part of a nuclear fuel assembly. The set has a spring and the spring supports the fuel rods safely. Although material nonlinearity is involved in the deformation of the spring,nonlinearity has not been considered in design of the spring. Recently a nonlinear response structural optimization method has been developed using equivalent loads. It is called nonlinear response optimization equivalent loads (NROEL). In NROEL, the external loads are teansformed to the equivalent loads (EL) for linear static analysis and linear response optimization is carried out based on the EL in a cyclic manner until the convergence criteria are satisfied. EL is the load set which generates the same response no EL. The objective function is defined by minimizing the maximum stress in the spring while is limited and the support force of the spring is larger than a certain value. The results are verified by nonlinear. ABAQUS is used for nonlinear response analysis and GENESIS is employed for linear response optimization.

• Journal of Mechanical Science and Technology
• /
• v.20 no.3
• /
• pp.366-375
• /
• 2006

In this paper, it is intended to introduce a method to solve multi-objective optimization problems and to evaluate its performance. In order to verify the performance of this method it is applied for a vertical roller mill for Portland cement. A design process is defined with the compromise decision support problem concept and a design process consists of two steps: the design of experiments and mathematical programming. In this process, a designer decides an object that the objective function is going to pursuit and a non-linear optimization is performed composing objective constraints with practical constraints. In this method, response surfaces are used to model objectives (stress, deflection and weight) and the optimization is performed for each of the objectives while handling the remaining ones as constraints. The response surfaces are constructed using orthogonal polynomials, and orthogonal array as design of experiment, with analysis of variance for variable selection. In addition, it establishes the relative influence of the design variables in the objectives variability. The constrained optimization problems are solved using sequential quadratic programming. From the results, it is found that the method in this paper is a very effective and powerful for the multi-objective optimization of various practical design problems. It provides, moreover, a reference of design to judge the amount of excess or shortage from the final object.

• Journal of Communications and Networks
• /
• v.14 no.1
• /
• pp.91-103
• /
• 2012

Network mobility (NEMO) based on mobile IP version 6 has been proposed for networks that move as a whole. Route optimization is one of the most important topics in the field of NEMO. The current NEMO basic support protocol defines only the basic working mode for NEMO, and the route optimization problem is not mentioned. Some optimization schemes have been proposed in recent years, but they have limitations. A new NEMO route optimization scheme-involving a combination of the optimized route cache protocol (ORC) and reverse routing header (RRH) and the use of a quota mechanism for optimized sessions (OwR)-is proposed. This scheme focuses on balanced performance in different aspects. It combines the ORC and RRH schemes, and some improvements are made in the session selection mechanism to avoid blindness during route optimization. Simulation results for OwR show great similarity with those for ORC and RRH. Generally speaking, the OwR's performance is at least as good as that of the RRH, and besides, the OwR scheme is capable of setting up optimal routing for a certain number of sessions, so the performance can be improved and the cost of optimal routing in nested NEMO can be decreased.

• Knowledge Management Research
• /
• v.19 no.2
• /
• pp.151-162
• /
• 2018

Response surface methodology (RSM) is one of popular tools to support a systematic improvement of quality of design in the product and process development stages. It consists of statistical modeling and optimization tools. RSM can be viewed as a knowledge management tool in that it systemizes knowledge about a manufacturing process through a big data analysis on products and processes. The conventional RSM aims to optimize the mean of a response, whereas dual-response surface optimization (DRSO), a special case of RSM, considers not only the mean of a response but also its variability or standard deviation for optimization. Recently, a posterior preference articulation approach receives attention in the DRSO literature. The posterior approach first seeks all (or most) of the nondominated solutions with no articulation of a decision maker (DM)'s preference. The DM then selects the best one from the set of nondominated solutions a posteriori. This method has a strength that the DM can understand the trade-off between the mean and standard deviation well by looking around the nondominated solutions. A posterior method has been proposed for DRSO. It employs an interval selection strategy for the selection step. This strategy has a limitation increasing inefficiency and complexity due to too many iterations when handling a great number (e.g., thousands ~ tens of thousands) of nondominated solutions. In this paper, a TOPSIS-based method is proposed to support a simple and efficient selection of the most preferred solution. The proposed method is illustrated through a typical DRSO problem and compared with the existing posterior method.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.21 no.2
• /
• pp.39-51
• /
• 2018

Long-term unexecuted urban parks will be released from urban planning facilities after 2020, this may result in development of those parks. However, little research have been focused on how to develop those parks considering conservation, development, spatial pattern, and so on. Therefore, in this study, we suggested an optimization planning model that minimizes the fragmentation while maximizing the conservation and development profit using ACO (Ant Colony Optimization). Our study area is Suwon Yeongheung Park, which is long-term unexecuted urban parks and have actual plan for private development in 2019. Using our optimization planning model, we obtained four alternatives(A, B, C, D), all of which showed continuous land use patterns and satisfied the objectives related to conservation and development. Each alternative are optimized based on different weight combinations of conservation, development, and fragmentation, and we can also generated other alternatives immediately by adjusting the weights. This is possible because the planning process in our model is very fast and quantitative. Therefore, we expected our optimization planning model can support "spatial decision making" of various issue and sites.