• Korean Management Science Review
• /
• v.24 no.2
• /
• pp.73-80
• /
• 2007

Robust Design(RD) is a cost-effective methodology to determine the optimal settings of control factors that make a product performance insensitive to the influence of noise factors. To better facilitate the robust design optimization, a dual response surface approach, which models both the process mean and standard deviation as separate response surfaces, has been successfully accepted by researchers and practitioners. However, the construction of response surface approximations has been limited to problems with only a few variables, mainly due to an excessive number of experimental runs necessary to fit sufficiently accurate models. In this regard, an innovative response surface approach has been proposed to investigate robust design optimization problems with larger number of variables. Response surfaces for process mean and standard deviation are partitioned and estimated based on the multi-level approximation method, which may reduce the number of experimental runs necessary for fitting response surface models to a great extent. The applicability and usefulness of proposed approach have been demonstrated through an illustrative example.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.92-100
• /
• 2006

In many common control charting situations, the statistic to be charted can be viewed as the output of a linear filter applied to the sequence of process measurement data. In recent work that has generalized this concept, the charted statistic is the output of a general linear filter in impulse response form, and the filter is designed by selecting its impulse response coefficients in order to optimize its average run length performance. In this work, we restrict attention to the class of all second-order linear filters applied to the residuals of a time series model of the process data. We present an algorithm for optimizing the design of the second-order filter that is more computationally efficient and robust than the algorithm for optimizing the general linear filter. We demonstrate that the optimal second-order filter performs almost as well as the optimal general linear filter in many situations. Both methods share a number of interesting characteristics and are tuned to detect any distinct features of the process mean shift, as it manifests itself in the residuals.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.6
• /
• pp.109-116
• /
• 2017

In this study, the optimization of the overall dimensions of an automobile bumper was investigated through CAE and experiment using the Six Sigma method and design of experiment (DOE) method, respectively. Injection pressure, injection speed, injection time, cooling time, holding time, injection temperature, and holding pressure were selected as the vital parameters affecting the overall width of product through analysis of trivial many using CAE. The optimal values were determined using the DOE method, and we analyzed the improvement by applying the optimal conditions to the production process. As a result, the mean value of the overall width was close to the target value, with a deviation of 0.05mm, and the processability and I-MR control were remarkably improved. Finally, the dimension pass rate of the product improved by 20%.

• Journal of Korean Institute of Industrial Engineers
• /
• v.2 no.1
• /
• pp.93-100
• /
• 1976

Given a fixed production process and facility capacity, the ability to respond to market fluctuations in terms of changes in production, work force, and inventory is the major task of production management. The costs involved are primarily payroll (regular and overtime), inventory carrying, and hiring and firing. The magnitude of these costs is usually a significant portion of the operating costs of the firm and consequently a small percentage saving due to astute aggregate scheduling can mean substantial absolute saving. At least three demonstrably optimal techniques have been developed for solving this aggregate scheduling problem. These three optimal are apparently LDR, PPP, and SDR. By combining these three different approaches, another optimal solution was obtained by me. I call this CDR (Combined Decision Rule). This approach appears to be useful. This approach may be generalizable to aggregate scheduling involving a short term resources.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.7
• /
• pp.826-835
• /
• 1988

In this paper, we analyze the generation of an image pyramid as a 2-dimensional decimation-interpolation process, and suggest a performance index of FIR filter for decimation and interpolation filter. Until now, most deciamtion and interpolation filters are designed via the approximation of the impulse response of an ideal filter. In this paper, however, we propose a new performance index that minimizes the maximum frequency-weighted mean square error between the desired and the generated interpolated signal, and propose an optimal half-band filter based on the proposed performance index as an example. Some simulation results with real images show that the proposed optimal half-band filter yields a higher PSNR as well as the more preferable image quality, in comparison with other currently used filters with the same computational complexity.

• IE interfaces
• /
• v.16 no.spc
• /
• pp.39-44
• /
• 2003

As one of many design variables, the role of dimension tolerances is to restrict the amount of size variation in a manufactured feature while ensuring functionality. In this study, a nonlinear integer model has been modeled to allocate the optimal tolerance to each individual feature at a minimum manufacturing cost. While a normal distribution determines statistically worst tolerances with its symmetrical property in many previous tolerance allocation studies, a asymmetrical distribution is more realistic because its mean is not always coincident with a process center. A nonlinear integer model is modeled to allocate the optimal tolerance to a feature based on a beta distribution at a minimum total cost. The total cost as a function of tolerances is defined by machining cost and quality loss. After the convexity of manufacturing cost is checked by the Hessian matrix, the model is solved by the Complex Method. Finally, a numerical example is presented demonstrating successful model implementation for a nonlinear design case.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.21 no.45
• /
• pp.237-246
• /
• 1998

In most statistical process control(SPC), control charts are used in which samples are taken and a suitable statistic is determined and plotted. In these control charts, control limits, ${\mu}{\pm}textsc{k{\sigma}}$, from which a decision is made are mostly ${\mu}{\pm}3{\sigma}$ and current literature in control charts are mainly concerned with detecting a shift in the mean. Therefore, when $\sigma$ is increased considerably after a long time, using control limits set at the first time causes a great deal of economic loss. In this paper the solutions to determine new control limits which maximizes the profit per unit produced and reduce $\sigma$ to economically optimal level for a certain cost when $\sigma$ is increased due to process deterioration are proposed. By applying new control limits, $\alpha$ error decreases considerably compared to apply initial control limits when $\sigma$ is increased due to process deterioration. Therefore, false alarm investigation cost drops down to the level of initial a error. And also this solution provides useful information regarding replacement of a process when the process is reviewed regularly.

• Proceedings of the KIEE Conference
• /
• 2005.10b
• /
• pp.149-151
• /
• 2005

In this paper, we propose the Optimal Polynomial Neural Networks(PNN) for nonlinear process. The PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and can be generated. The each node of PNN structure uses several types of high-order polynomial such as linear, quadratic and modified quadratic, and is connected as various kinds of multi-variable inputs. The conventional PNN depends on experience of a designer that select No. of input variable, input variable and polynomial type. Therefore it is very difficult a organizing of optimized network. The proposed algorithm identified and selected No. of input variable, input variable and polynomial type by using Genetic Algorithms(GAs). In the sequel the proposed model shows not only superior results to the existing models, but also pliability in organizing of optimal network. Medical Imaging System(MIS) data is simulated in order to confirm the efficiency and feasibility of the proposed approach in this paper.

• Journal of Korean Society for Quality Management
• /
• v.43 no.4
• /
• pp.471-488
• /
• 2015

Purpose: Double sampling $T^2$ chart is a useful tool for detecting a relatively small shift in process mean when the process is controlled by multiple variables. This paper finds the optimal design of the double sampling $T^2$ chart in both economical and statistical sense under Weibull failure model. Methods: The expected cost function is mathematically derived using recursive equation approach. The optimal designs are found using a genetic algorithm for numerical examples and compared to those of single sampling $T^2$ chart. Sensitivity analysis is performed to see the parameter effects. Results: The proposed design outperforms the optimal design of the single sampling $T^2$ chart in terms of the expected cost per unit time and Type-I error rate for all the numerical examples considered. Conclusion: Double sampling $T^2$ chart can be designed to satisfy both economic and statistical requirements under Weibull failure model and the resulting design is better than the single sampling counterpart.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.16 no.6
• /
• pp.117-124
• /
• 2017

In this study, we investigated the optimization of process conditions by using the Six Sigma process, design of experiment (DOE) method and response surface method (RSM) to resolve dimensional deviation and appearance problems arising from the shortened process time of the mobile phone rear cover. The analysis of the trivial many was performed by 2-sample T-test and cooling time, and mold temperature and packing pressure were selected as the vital fews affecting the overall width of the product. The optimal conditions of the process were then studied using the DOE and the RSM. We analyzed the improvement effects by applying the selected optimal conditions to the production process and the results showed that the difference between the mean value and target value of the overall width stood at 0.01 mm, an improvement of 88.89% compared to current process that fell within the range of standard dimension. The short-term process capability stood at $4.77{\sigma}$, which implied an excellent technology level despite a decrease by $0.22{\sigma}$ compared to the current process. The difference in process capability decreased by $2.44{\sigma}$ to $0.41{\sigma}$, showing a significant improvement in management capability. Ultimately, the process time of the product was shortened from 18.3 seconds in the current process to 13.65 seconds, resulting in a 34.07% improvement in production yield.