• International Journal of Reliability and Applications
• /
• v.6 no.1
• /
• pp.31-39
• /
• 2005

An economic life test sampling plan for products with exponential lifetime distribution is developed. To reduce test time, a test plan with curtailed Type II censoring is considered. A cost model is constructed which involves three cost components; test cost, accept cost, and reject cost. Determination of optimal plan minimizing the expected average cost per lot is discussed with a constraint related to consumer's risk. Some numerical examples are provided.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.23 no.59
• /
• pp.97-103
• /
• 2000

This study considers the design of life test sampling inspection plans by attributes for failure rate level qualification at selected confidence level. The lifetime distribution of products is assumed to be exponential. MIL-STD-690C and KS C 6032 standards provide this procedures. But these procedures have some questions to apply in the field. The cost of test and confidence level($1-{\beta}$ risk) are the problem between supplier and user. So, we suggest that the optimal life test sampling inspection plans using expected cost model considering product cost, capability, environmental test cost, etc.

• Journal of the Korean Statistical Society
• /
• v.6 no.1
• /
• pp.3-20
• /
• 1977

In many applications one is concerned with repeated Bernoulli trials whose parameter (success probability) is usually unknown and has to be estimated from a sample. The probability distribution and statistical inference on the repeated independent Bernoulli trials have been studied extensively for the cases of fixed sample size sampling plan, and inverse binomial sampling plan in which observations are cotinued until a pressigned number of successes are obtained. See, for example, Haldane, Girschick et al., DeGroot and Johnson and Kotz.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.5 no.2
• /
• pp.212-225
• /
• 1995

This study was performed in a diatomite factory located at Pohang City, Kyeongsangbuk-Do. The major objectives were to evaluate sampling and analytical methods of diatomaceous earth dust. Concentrations of total and respirable diatomaceous earth dust were measured. Size distribution of dust was analyzed by a personal cascade impactor and the particle size analyzer which is an application of multiple diffraction method. Also crystalline silica in respirable and total dust samples was analyzed quantitatively by X-ray diffraction and Fourie Transform Infrared Spectroscopy(FTIR). The results were as follows: The airborne total and respirable dust concentrations, particle size distribution, and cristalline silica(quartz) concentrations showed approximately a log-normal distribution. The means of totaldust concentrations at flour maufacturing, fire brick grinding and packaging processes exceeded the Korean and American Conference of Governmental Industrial Hygienists standards, $10mg/m^3$. The size distribution of diatomaceous earth dust was log-normal and identified as the rspirable particle mass and thoracic particle mass. The crystalline silica in respirable and total dust samples was identified to quartz and contained about 10 % in those samples. Finally, it is necessary to study the applicability of multiple diffraction for particle size distribution to compare the ACGIH's size selective sampling with other materials containing crystalline silica. Also, advanced quantitative study to X-ray diffraction and FTIR methods shoud be carried out 10 verify general and specific characteristics for respirable crystalline silica.

• Journal of Korean Society for Atmospheric Environment
• /
• v.14 no.2
• /
• pp.117-132
• /
• 1998

The main purposes of this study are to investigate the distributional characteristics of polycyclic aromatic hydrocarbons (PAH) in the vapor and particulate phases in the ambient atmosphere, and to evaluate the effect of ambient temperature on the vapor-particle partitioning during the sampling period. A total of 64 samples were collected during a period of 1995 to 1996, using a medium-volume sampler with XAD-2 adsorbents and quartz fiber filters. Analyses of PAH were carried out using HPLC with UV and Fluorescence detections. In this study, a significant seasonal variation in the distributions was observed, reflecting the effect of ambient temperature on the vapor-particle partitioning of PAH. The relationship between the vapor-particle distributions of the 3 to 5 rings PAH and ambient temperature is considered to be well described using the Langmuir adsorption concept. The estimated empirical constants for each PAH in the relationship, particularly for the more volatile compounds, were also comparable with results from other studies. However, it is still difficult to accurately estimate the initial vapor-particle distribution of PAH in the ambient air, since it is not known to what extent the trapped vapours originated from the particles laden in the filter by being volatilized or from the air samples initially present in the vapour phase. The distribution factors for volatile PAH with 3 to 4 rings appeared to be comparable with those in the literature. It should be noted, however, that these distribution factors give information only about the distribution of PAH between the two phases under a specific sampling condition, and hence may provide only semi -quantitative information on the vapor-particle distributions in the atmosphere.

• Particle and aerosol research
• /
• v.7 no.4
• /
• pp.139-149
• /
• 2011

It is very important to measure atmospheric particles and evaluate the characteristics of them since aerosol can influence atmospheric environment, climate, and health. Satellite, aircraft, radio sonde are usually used to measure the vertical distribution of particle properties, temperature, humidity, and pressure. Although the method of using an aircraft is favorable to collect the horizontal distribution of the particles, but unadaptable to measure the vertical distribution of the particles. However, all-in-one balloon particle sampler system can collect particles depending on each altitude controling the balloon by winch. In this research, we performed the air sampling on the TEM grids using house made light weight impactor at the altitude of 300m and 900m. The collected particles were analyzed using TEM/EDS.

• Journal of Korean Society for Atmospheric Environment
• /
• v.1 no.1
• /
• pp.93-98
• /
• 1985

Mass size distribution of atmospheric particulates were measured using an Andersen using an Andersen sampler in urban air. The atmospheric particulates were fractionated in eight stages of an Andersen sampler operating at 28.4$\ell/min$ and collected on polyester sheets. A quartz filter was placed behind the last stage collect permeated partculates. The size distribution of atmospheric particulates were divided around 1-2 $\mu$m into two groups, coarse and fine particulates regardless of sampling times. The variation of course particulates concentration was higher than fine particulates among sampling times. Different meterorological conditions and natural phenomena brought high variation of course particulates' concentration. The rain caused removal of coarse particulates seriously and the yellow and may take part in a increase of the course particulates in spring. The average concentration of atmospheric particulates to be collected by Andersen sampler was 170.8 $\mug/m^3$ during 3 times of sampling. Among them the average concentration of atmospheric particulates which could penetrated under a bronchi and alveoli were 70.4$\mug/m^3$ and 36.6$\mug/m^3$ respectively.

• Communications for Statistical Applications and Methods
• /
• v.19 no.3
• /
• pp.315-331
• /
• 2012

In this research, we estimated the number of hits per song and its sampling error from 11 (areas including Gangnam) based on log data compiling the number of hits collected from offline karaoke players in March 2011. Then, we calculated the monetary equivalent of the sampling error under the current system that distribute royalties from the karaoke players to copyright holders(song writers and arrangers) according to the estimated hits. Because of the small sample size, the estimated number of hits had a very large sampling error. This research proposes a more reasonable sample design to estimate the usage of copyrighted music works for a fair distribution of royalties by reducing sampling error.

• Journal of the Korean Society of Safety
• /
• v.30 no.5
• /
• pp.131-137
• /
• 2015

For the evaluation of safety margin of a nuclear power plant using a conservative methodology, the influence of applied assumptions such as initial conditions and boundary conditions needs to be assessed deliberately. Usually, a combination of the most conservative initial conditions is determined, and the safety margin for the transient is evaluated through the analysis for this conservative conditions. In existing conservative methodologies, a most-conservative condition is searched through the analyses for the maximum, minimum, and nominal values of the major parameters. In the present study, we investigates a new approach which can be applied to choose a most-conservative initial condition effectively when a best-estimate computer code and a conservative evaluation methodology are utilized for the evaluation of safety margin of transients. By constituting the band of various initial conditions using the random sampling of input parameters, the sensitivity study for various parameters are performed systematically. A method of sampling the value of control or operation parameters for a certain range is adopted by use of MOSAIQUE program, which enables to minimize the efforts for achieving the steady-state for various different conditions. A representative control parameter is identified, which governs the reactor coolant flow rate, pressurizer pressure, pressurizer level, and steam generator level, respectively. It is shown that an appropriate distribution of input parameter is obtained by adjusting the range and distribution of the control parameter.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.1
• /
• pp.104-112
• /
• 2008

This paper presents the computer program for station reliability assessment. The developed program is based on Monte-Carlo simulation using system state transition sampling, which has the merit of rapid assessment compared to state duration sampling. One of the contributions of this paper is introduction of exclusiveness among events, which makes non-exponential probabilistic distribution be utilized in modeling repair time. The developed program is applied to well-blown sample system, and its assessment results are listed in this paper to show the reliability of the program.