• Journal of Korean Society for Quality Management
• /
• v.41 no.1
• /
• pp.109-118
• /
• 2013

Purpose: Given the several proper models for given mixture components-process variables experimental data, we propose a strategy to find the optimal condition in which the performance of the responses is well-behaved under those models. Methods: Given the mixture experimental data with process variables, first we choose the reasonable starting models among the class of admissible product models based on the model selection criteria and then, search for the candidate models that are the subset models of the starting model by the sequential variable selection method or all possible regressions procedure. Good candidate models are screened by the evaluation of model selection criteria and checking the residual plots for the validity of the model assumption. Results: We propose a strategy to find the optimal condition in which the performance of the responses is well-behaved under those good candidate models by adopting the optimization methods developed in multiple responses surface methodology. Conclusion: A strategy is proposed to find the optimal condition in which the performance of the responses is well-behaved under those proper combined models. This strategy to find the optimal condition is illustrated with the example in this paper.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.854-860
• /
• 2020

Deep neural networks have shown remarkable performance in various areas, including image classification and speech recognition. The variety of data generated by augmentation plays an important role in improving the performance of the neural network. The transformation of data in the augmentation process makes it possible for neural networks to be learned more generally through more diverse forms. In the traditional field of image process, not only new augmentation methods have been proposed for improving the performance, but also exploring methods for an optimal augmentation policy that can be changed according to the dataset and structure of networks. Inspired by the prior work, this paper aims to explore to search for an optimal augmentation policy in the field of sound data. We carried out many experiments randomly combining various augmentation methods such as adding noise, pitch shift, or time stretch to empirically search which combination is most effective. As a result, by applying the optimal data augmentation policy we achieve the improved classification accuracy on the environmental sound classification dataset (ESC-50).

• Korean System Dynamics Review
• /
• v.13 no.2
• /
• pp.47-71
• /
• 2012

The purpose of this research is the examination of validity of data as well as simulation model, i.e. to simulate the real data in the SD model with the least error using the adjustments for the faithful reflection of real data to the simulation. In general, SD programs (e.g. VENSIM) utilize the Euler or Runge-Kutta method as an algorithm. It is possible to reflect the trend of real data via these two estimation methods however can cause the validity problem in case of the simulation requiring the accuracy as they have endogenous errors. In this article, the future population estimated by the Korea National Statistical Office (KNSO) to 2050 is simulated by the aging chain model, dividing the population into three cohorts, 0-14, 15-64, 65 and over cohorts by age and offering the adjustments to them. Adjustments are calculated by optimization with three different methods, optimization in EXCEL, manual optimization with iterative calculation, and optimization in VENSIM DSS, the results are compared, and at last the optimal adjustment set with the least error are found among them. The simulation results with the pre-determined optimal adjustment set are validated by methods proposed by Barlas (1996) and other alternative methods. It is concluded that the result of simulation model in this research has no significant difference from the real data and reflects the real trend faithfully.

• Management Science and Financial Engineering
• /
• v.13 no.1
• /
• pp.1-24
• /
• 2007

I propose new combined randomized methods for global optimization problems. These methods are based on the Nested Partitions(NP) method, a useful method for simulation optimization which guarantees global optimal solution but has several shortcomings. To overcome these shortcomings I hired various statistical selection methods and combined with NP method. I first explain the NP method and statistical selection method. And after that I present a detail description of proposed new combined methods and show the results of an application. As well as, I show how these combined methods can be considered in case of computing budget limit problem.

• Structural Engineering and Mechanics
• /
• v.32 no.3
• /
• pp.371-382
• /
• 2009

Response of harbor structure to environmental loads such as wave load, impact load, ship's contacting load, is a fundamental factor in designing of the structure's optimal configuration. In this paper, typical environmental loads against coastal structures are investigated for designing of the optimal harbor structure. Loads to be considered here are wave load, impact load and contacting load due to ship mooring. Statistical analysis for several harbor structure types under the corresponding loads is carried out, followed by investigation of effect of individual environmental load. Based on these, the optimal configuration for the harbor structure is obtained after considerable engineering process. Estimation of contacting load of the ship is suggested using effective energy concepts for the load, and analysis of structural behavior is done for the optimal designing of the structure in the particular load. A guideline for the design process of the harbor structure is established, and safety of the structure is examined by proposed scheme. For verification of the analytical approach, various steel-piled coastal structures and caissons are chosen and relevant structural analyses are carried out using the Finite Element Methods combined with MIDAS/GTS and ANSYS code. It is found using the Morison equation that impact load cannot be a major load in the typical harbor structure compared with the original wave load, and that configuration shape of the structure may play an important role in consideration of the response criteria.

• Industrial Engineering and Management Systems
• /
• v.16 no.1
• /
• pp.1-21
• /
• 2017

This paper discusses a reverse supply chain (RSC) which consists of the process flows from procurement of used products collected from a market, through remanufacturing products from the used products, to sales of the products in a market. In general, it is conceivable for the RSC to face the uncertainty in quality of used products collected from a market. Inspection is one of efficient methods to deal with the problem regarding quality of used products. However, there is a trade-off between inspection cost and inspection accuracy. This paper focuses on the following five types of inspection: (1) 100% inspection, (2) sampling inspection, (3) sampling inspection with screening of rejected lots, (4) sampling inspection with screening of acceptable lots, and (5) no inspection, and determines the optimal operation consisting of the optimal number of procured used products and the optimal inspection policy. Numerical analysis clarifies not only how changes of conditions of the RSC affect the manufacturer's optimal operation but also features of each inspection type. In addition, from the results of numerical analysis, this paper shows the usability to add the proposed inspection in this paper, the sampling inspection with screening of acceptable lots, to choices of inspection type.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.5
• /
• pp.589-597
• /
• 2011

In this paper, optimal tuning of a cross-coupled controller linked with the feedforward controller and the disturbance observer is studied to improve contouring and tracking accuracy as well as robustness against disturbance. Previously developed integrated design and optimal tuning methods are applied for developing the robust tuning method. Strict mathematical modeling of the multivariable system is formulated as a state-space equation. Identification processes of the servomechanism are conducted for mechanical servo models. An optimal tuning problem to minimize both the contour error and settling time is formulated as a nonlinear constrained optimization problem including the relevant controller parameters of the servo control system. Constraints such as relative stability, robust stability and overshoot, etc. are considered for the optimization. To verify the effectiveness of the proposed optimal tuning procedure, linear and circular motion experiments are performed on the xy-table. Experimental results confirm the control performance and robustness despite the variation of parameters of the mechanical subsystems.

• International Journal of Highway Engineering
• /
• v.19 no.3
• /
• pp.65-70
• /
• 2017

PURPOSES : Pavement Management System contains the data that describe the condition of the road. Under limited budget, the data can be utilized for efficient plans. The objective of this research is to develop a mixed integer program model that maximizes remaining durable years (or Lane-Kilometer-Years) in road maintenance planning. METHODS : An optimization model based on a mixed integer program is developed. The model selects a cluster of sectors that are adjacent to each other according to the road condition. The model also considers constraints required by the Seoul Metropolitan Facilities Management Corporation. They select two lanes at most not to block the traffic and limit the number of sectors for one-time construction to finish the work in given time. We incorporate variable cost constraints. As the model selects more sectors, the unit cost of the construction becomes smaller. The optimal choice of the number of sectors is implemented using piecewise linear constraints. RESULTS : Data (SPI) collected from Pavement Management System managed by Seoul Metropolitan City are fed into the model. Based on the data and the model, the optimal maintenance plans are established. Some of the optimal plans cannot be generated directly in existing heuristic approach or by human intuition. CONCLUSIONS:The mathematical model using actual data generates the optimal maintenance plans.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.6
• /
• pp.979-986
• /
• 2016

At present, electric power industry around the world are being gradually changed to a new paradigm, such as electrical energy storage system, the wireless power transmission. Demand for ESS, the core technology of the new paradigm, has been growing worldwide. However, it is essential to estimate the optimal capacity of ESS facilities for frequency regulation because the benefit would be saturated in accordance with the investment moment and the increase of total invested capacity of ESS facilities. Hence, in this paper, the annual optimal mathematical investment model is proposed to estimate the optimal capacity and to establish investment plan of ESS facility for frequency regulation. The optimal mathematical investment model is newly established for each season, because the construction period is short and the operation effect for the load by seasons is different unlike previous the mathematical investment model. Additionally, the marginal operating cost is found by new mathematical operation model considering no-load cost and start-up cost as step functions improving the previous mathematical operation model. ESS optimal capacity is established by use value in use iterative methods. In this case, ESS facilities cost is used in terms of the value of the beginning of the year.

• KIEAE Journal
• /
• v.14 no.3
• /
• pp.97-103
• /
• 2014

This study aimed at developing integrated logic for controlling heating device and openings of the double skin facade buildings. Two major logics were developed-rule-based control logic and artificial neural network based control logic. The rule based logic represented the widely applied conventional method while the artificial neural network based logic meant the optimal method. Applying the optimal method, the predictive and adaptive controls were feasible for supplying the advanced thermal indoor environment. Comparative performance tests were conducted using the numerical computer simulation tools such as MATLAB (Matrix Laboratory) and TRNSYS (Transient Systems Simulation). Analysis on the test results in the test module revealed that the artificial neural network-based control logics provided more comfortable and stable temperature conditions based on the optimal control of the heating device and opening conditions of the double skin facades. However, the amount of heat supply to the indoor space by the optimal method was increased for the better thermal conditioning. The number of on/off moments of the heating device, on the other hand, was significantly reduced. Therefore, the optimal logic is expected to beneficial to create more comfortable thermal environment and to potentially prevent system degradation.