• The Journal of the Petrological Society of Korea
• /
• v.18 no.2
• /
• pp.115-135
• /
• 2009

We have studied general orientational characteristics of microcracks distributed in Tertiary crystalline tuff from the northeastern part of the Gyeongsang Basin. 108 sets of microcracks on horizontal surfaces of 6 rock samples from Heunghae-eup and Cheongha-myeon, Pohang-si areas were distinguished by image processing. Those microcrack sets show a distinct linear array in 38 images. Whole domain of the directional angle(${\theta}$)-frequency(N) chart for crystalline tuff can be divided into 20 domains in terms of the phases of the distribution of microcracks. From the related chart, microcrack sets show preferred orientation which are coincident with the direction of vertical common joints. Consequently, the potential for macroscopic vertical joints in a rock body can be inferred from the directional angle showing high frequency in each domain of the related chart. This joint pattern is nearly the same in Mesozoic granites from Seokmo-do, Gwanghwa-gun. From the rose diagram for orientations of microcrack in crystalline tuff, orientations of dominant sets of microcracks in terms of frequency orders reflect representative orientations of maximum principal stress acted on crystalline tuff. Meanwhile, orientations of microcracks in crystalline tuff were compared with those of open microcracks in Bulgugsa granites from the southwestern part of the Gyeongsang Basin, and vertical rift/grain planes from Mesozoic granite quarries in Korea. In regional distribution chart, the agreement of distribution pattern between above two types of microcrack sets and vertical planes suggests that microcrack systems developed in crystalline tuff probably occur regionally in Mesozoic granites in Korea.

• Proceedings of the Society of Korea Industrial and System Engineering Conference
• /
• 2002.05a
• /
• pp.359-364
• /
• 2002

In case of pn control chart often used in mass production system of plant industry and so on, we could evaluate it's performance by the approximation to normal distribution. It has many differences according to sample sizes and defective fraction, and have disadvantage that needs much samples to use the normal distribution approximation. Existent control charts can not detect the cause of process something wrong because it is taking the sampling intervals of fixed length about all times from the process. Therefore, to overcome this shortcoming we use VSI(variable sampling intervals) techniques in this paper. This technique takes a long sampling interval to have the next sampling point if the sample point is in stable state, and if the sample point is near control lines, it takes short sampling interval because the probability to escape control limit is high. To analyze performance of pn control charts that have existent fixed sampling intervals(FSI) and that use VSI technique, we compare ATS of two charts, and analyze the performance of each control chart by the sample sizes, process fraction defective and control limits that Ryan and Schwertman had proposed.

• Communications for Statistical Applications and Methods
• /
• v.23 no.6
• /
• pp.497-515
• /
• 2016

Modern processes often monitor more than one quality characteristic that are referred to as multivariate statistical process control (MSPC) procedures. The MSPC is the most rapidly developing sector of statistical process control and increases interest in the simultaneous inspection of several related quality characteristics. Most multivariate detection procedures based on a multi-normality assumptions are independent, but there are many processes that assume non-normality and correlation. Many multivariate control charts have a lack of related joint distribution. Copulas are tool to construct multivariate modelling and formalizing the dependence structure between random variables and applied in several fields. From copula literature review, there are a few copula to apply in MSPC that have multivariate control charts, and represent a successful tool to identify an out-of-control process. This paper presents various types of copulas modelling for the multivariate control chart. The performance measures of the control chart are the average run length (ARL) and the average number of observations to signal (ANOS). Furthermore, a Monte Carlo simulation is shown when the observations were from an exponential distribution.

• Proceedings of the Safety Management and Science Conference
• /
• 2000.11a
• /
• pp.217-234
• /
• 2000

Approximately normalized control charts, called Q charts, have been given Quesenberry(1991) for charting in process of short-run, job-shop, etc. We consider a Q chart with inspection error for job-shop floor under geometric distribution, which can be used for processes when a fraction nonconforming is very small. Our results would be applied for designing other control charts with inspection error.

• Proceedings of the Safety Management and Science Conference
• /
• 2010.11a
• /
• pp.35-39
• /
• 2010

The research classifies three types of asymptotic tail distributions such as long(heavy, thick) tailed distribution, medium tailed distribution and short(light, thin) tailed distribution. The extreme value distributions(EVD) classified in this paper can be used in SPC(Statistical Process Control) control chart and reliability engineering.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1353-1366
• /
• 2015

These days Shewhart control chart for evaluating stability of the process is widely used in various field. But it must follow strict assumption of distribution. In real-life problems, this assumption is often violated when many quality characteristics follow non-normal distribution. Moreover, it is more serious in multivariate quality characteristics. To overcome this problem, many researchers have studied the non-parametric control charts. Recently, SVDD (Support Vector Data Description) control chart based on RBF (Radial Basis Function) Kernel, which is called K-chart, determines description of data region on in-control process and is used in various field. But it is important to select kernel parameter or etc. in order to apply the K-chart and they must be predetermined. For this, many researchers use grid search for optimizing parameters. But it has some problems such as selecting search range, calculating cost and time, etc. In this paper, we research the efficiency of selecting parameter regions as data structure vary via simulation study and propose a new method for determining parameters so that it can be easily used and discuss a robust choice of parameters for various data structures. In addition, we apply it on the real example and evaluate its performance.

• Journal of Internet Computing and Services
• /
• v.17 no.5
• /
• pp.121-129
• /
• 2016

Company A, an embedded system manufacturer, has been managing multiple development projects. Executives need to understand the risk level of every project and prioritize resource distribution. Traditional project monitoring tools or excel sheets are too complex for calculating the risk factors across a functional organization. Two new charts, "Spear-head Chart" and "Float Chart" were designed to assist high level decision making processes. Two charts were used for weekly executive meetings in order to monitor project progress and rectify project direction. One page graphical monitoring tools in Company A are good enough for high management decision making. Authors explain the characteristics of two charts and propose its practical implementation in real working environment. Spear-head chart was also implemented as a system.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.43
• /
• pp.205-209
• /
• 1997

One objective of the u control chart is to detect changes of mean nonconformities per unit occurred owing to various causes. This paper shows the detection probability using the Poisson distribution for various parameters, that is, subsample size n, mean nonconformities per unit $u_o$, and $u_o's$ change ratio k. We find that (1) as $u_o$ increases the smaller n is required for the same detection probability and the same change ratio; (2) as k gets away from 1 the smaller n is required; (3) the bigger n is required for the bigger detection probability. Several tables are given from our findings and are hoped to be used as guidelines for u chart users.

• Food Science and Biotechnology
• /
• v.18 no.3
• /
• pp.745-748
• /
• 2009

Sensory quality variations of jajang sauce were monitored by the $\bar{X}-chart$ and capability analysis based on specifications of each sensory attributes. For sensory quality control (QC) of the sauce which has a strong sweetness and sourness, the ratio of sourness/sweetness was examined as a necessary QC factor to maintain the balance of sweetness and sourness. For the sensory QC factors, all the sensory data were divided into individual sensory score of reference which was a pack of sauce manufactured a week ago. The ratio form of sensory data was useful for decreasing individual variations and for increasing normality of data measured by category scale. The overall proportion of out-spec products under normal manufacturing conditions was obtained by capability analysis of sensory data with normal distribution. Out-spec samples were monitored by the $\bar{X}-chart$ of each sensory attributes.

• Proceedings of the Safety Management and Science Conference
• /
• 1999.11a
• /
• pp.247-257
• /
• 1999

There are several models for process quality assurance by quality system(ISO 9000), process capability analysis, acceptance control chart and so on. When a high level process capability has been achieved, it takes a long time to monitor the process shift, so it is sometimes necessary to develop a quicker monitoring system. To achieve a quicker quality assurance model for high-reliability process, this paper presents a model for process quality assurance when the fraction nonconforming is very small. We design an acceptance control chart based on variable quality characteristic and time-censored accelerated testing. The distribution of the characteristics is assumed to be normal of lognormal with a location parameter of the distribution that is a linear function of a stress. The design parameters are sample size, control limits and sample proportions allocated to low stress. These parameters are obtained under minimization of the relative variance of the MLE of location parameter subject to APL and RPL constraints.