• Journal of the Korea Management Engineers Society
• /
• v.23 no.4
• /
• pp.73-86
• /
• 2018

Most electric products produced during the manufacturing process are produced after design and mass production under a given control standard. In particular, the development phase should present the criteria for the production process by setting appropriate limits based on the performance being targeted. Even if the standard of performance is set considering the performance of the process, measuring the performance of the product after actual production results will cause nonconformities with the expected results. Among the performance of electrical products, Energy standards represented by energy consumption efficiency continue to be of importance, and are mandatory standards that correspond to national standards in most countries. Therefore, statistical quality control of these standards shall basically have a large number of test equipment for each product, ensure sufficient test time and continuous sampling of product samples. In the end, companies that produce and sell electric appliances are striving to control mass production at a great cost, but this is not acceptable. This study presents basic characteristics of the energy efficiency of electrical products and proposes and conducts a case study on statistical production control methods for performance variation across products under the standards about domestic and international regulations.

• Journal of the Korean Statistical Society
• /
• v.36 no.2
• /
• pp.229-235
• /
• 2007

We consider a ruin model whose surplus process is formed by a compound Poisson process. If the level of surplus reaches V > 0, it is assumed that a certain amount of surplus is invested. In this paper, we apply the optional sampling theorem to the surplus process and obtain the expectation of period T, time from origin to the point where the level of surplus reaches either 0 or V. We also derive the total and average amount of surplus during T by establishing a backward differential equation.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.523-530
• /
• 2016

Most classical control charts assume that processes are serially independent, and autocorrelation among variables makes them unreliable. To address this issue, a variety of statistical approaches has been employed to estimate the serial structure of the process. In this paper, we propose a multioutput least squares support vector regression and apply it to construct a residual multivariate cumulative sum control chart for detecting changes in the process mean vector. Numerical studies demonstrate that the proposed multioutput least squares support vector regression based control chart provides more satisfying results in detecting small shifts in the process mean vector.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2007.04a
• /
• pp.302-309
• /
• 2007

To conduct statistical process control needs the assumption that the process data are independent. However, most of chemical processes, like a semi-conduct processes do not satisfy the assumption because of autocorrelation. It causes abnormal out of control signal in the process control and misleading process capability. In this study, we introduce that Shore's method to solve the problem and to find the optimal subgroup size to estimate variance for AR(l) model. Especially, we focus on finding an actual subgroup size for small samples using simulation. It may be very useful for statistical process control to analyze process capability and to make a Shewhart chart properly.

• Journal of Welding and Joining
• /
• v.32 no.3
• /
• pp.1-10
• /
• 2014

The efficient application of any welding process depends on the understanding of associated process parameters influence on the weld quality. The weld quality includes the weld bead dimensions, temperature distribution, metallurgical phases and the mechanical properties. A detailed review on the experimental and numerical approaches to understand the parametric influence of a single wire submerged arc welding (SAW) and multi-wire SAW processes on the final weld quality is reported in two parts. The first part deals with the experimental approaches which explain the parametric influence on the weld bead dimensions, metallurgical phases and the mechanical properties of the SAW weldment. Furthermore, the studies related to statistical modeling of the present welding process are also discussed. The second part deals with the numerical approaches which focus on the conduction based, and heat transfer and fluid flow analysis based studies in the present welding process. The present paper is the first part.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.22 no.52
• /
• pp.347-354
• /
• 1999

Statistical Process Control(SPC) which uses control charts is widely used to inspect and improve manufacturing process as a effective method. A parametric method is the most common in statistical process control. Shewhart chart was made under the assumption that measurements are independent and normal distribution. In practice, this assumption is often excluded, for example, in case of (equation omitted) chart, when the subgroup sample is small or correlation, it happens that measured data have bias or rejection of the normality test. A bootstrap method can be used in such a situation, which is calculated by resampling procedure without pre-distribution assumption. In this study, applying bootstrap percentile method to (equation omitted) chart, it is compared and evaluated standard process control limit with bootstrap percentile control limit. Also, under the normal and non-normal distributions, where parameter is 0.5, using computer simulation, it is compared standard parametric with bootstrap method which is used to decide process control limits in process quality.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.1
• /
• pp.106-114
• /
• 2019

Recently, the manufacturing process system in the industrial field has become more and more complex and has been influenced by many and various factors. Moreover, these factors have the dependent correlation rather than independent of each other. Therefore, the statistical analysis has been extended from the univariate method to the multivariate method. The process capability indices have been widely used as statistical tools to assess the manufacturing process performance. Especially, the multivariate process indices need to be enhanced with more useful information and extensive application in the recent industrial fields. The various multivariate process capability indices have been studying by many researchers in recent years. Hence, the purpose of the study is to compare the useful and various multivariate process capability indices through the simulation. Among them, we compare the useful models of several multivariate process capability indices such as $MC_{pm}$, $MC^+_{pm}$ and $MC_{pl}$. These multivariate process capability indices are incorporates both the process variation and the process deviation from target or consider the expected loss caused by the process deviation from target. Through the computational examples, we compare these process capability indices and discuss their usefulness and effectiveness.

• The Korean Journal of Applied Statistics
• /
• v.21 no.2
• /
• pp.247-264
• /
• 2008

This paper considers the integrated process control procedure for detecting special causes in an ARIMA(0,1,1) process that is being adjusted automatically after each observation using a minimum mean squared error adjustment policy. It is assumed that a special cause can change the process mean and the process variance. We derive expressions for the process deviation from target for a variety of different process parameter changes, and introduce a control chart, based on the generalized likelihood ratio, for detecting special causes. We also propose the integrated process control scheme bases on the future loss. The future loss denotes the cost that will be incurred in a process remaining interval from a true out-of-control signal.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.1
• /
• pp.47-57
• /
• 2010

There have been many problems to apply SPC(Statistical Process Control) which is a traditional process control technology to the process of multi-product, small-sized production because a machine in the process manufactures small numbers, but various kinds of products. Therefore, we need the new process control system that can flexibly control the process by setting up the SPEC rules and the KNOWHOW rules. The SPEC rule contains the combination of diverse conditions to specify the characteristics of various products. The KNOWHOW rule is based on engineers' know-how. The study suggests the Rule-base Process Control that can be optimized to the multi-product, small-sized production. It was validated in the process of semiconductor production.

• Journal of the Korean Statistical Society
• /
• v.30 no.2
• /
• pp.265-280
• /
• 2001

Estimation of the edge of a distribution has many important applications. It is related to classification, cluster analysis, neural network, and statistical image recovering. The problem also arises in measuring production efficiency in economic systems. Three most promising nonparametric estimators in the existing literature are introduced. Their statistical properties are provided, some of which are new. Themes of future study are also discussed.