http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
송서일,이만웅 대한설비관리학회 1999 대한설비관리학회지 Vol.4 No.4
N/A The Cpsk index is introduced recently as a unified approach for process capability indices, and detects changes both in the centering and the dispersion of the process. It is as important as a development of new index that we calculate the confidence inte
宋瑞日,田在耕 동아대학교 공과대학 부설 한국자원개발연구소 1985 硏究報告 Vol.9 No.1
This thesis deals with the problem of determining a minimum cost sampling inspection plan for double destructive testing by attribute. Using Hald's Bayesian approach in a single nondestructive testing, procedures for finding the minimum cost double destructive sampling inspection plan by attribute are given. The linear cost model is constructed under the assumption that unit cost, destructive testing cost, and salvage cost are given. Assuming the uniform distribution as a prior distribution and being presentation theoretical approach, sampling inspection plan and a minimum cost is obtained. However, when the lot size is large, the global plan is very difficult to obtain even with the aids of an electronic computer. Therefore a method of finding suboptimal plan will be studied.
송서일,이보근 동아대학교 공과대학부설 생산기술연구소 1997 生産技術硏究所硏究論文集 Vol.2 No.2
The process incapability index intended to estimate the process capability by measuring process incapability provides more detailed information to evaluate the process capability by dividing information about the process mean and variance. But it is very difficult to evaluate the process capability accurately when the target value is not consistent with the center of specification, and the shape of distribution is changed. The proposed incapability index, in this paper, is specifically designed to help of control skewness-prone manufacturing processes typified by a hole-drilling and/or punching process. It is more sensitive to skewness and changes in the shape of distribution. Hence the proposed incapability index is very useful for monitoring mear-normal processes where loss of capability typically lead to asymmetry.
송서일,박현규 한국품질경영학회 2005 품질경영학회지 Vol.33 No.1
This paper develops a new VSI X ̄-CRL synthetic control chart that considers convenience of use in the field, and perception of change of process applying VSI techniques to synthetic control chart, simultaneously. We found the optimal sampling interval and various control limit factor of the suggested chart using markov chain. Comparison and analysis is carried out between synthetic VSI X ̄-CRL chart and other chart in the statistical aspect; X ̄ control chart, VSI X ̄ chart, another synthetic chart. In case that the process follows normal distribution, the proposed VSI X ̄ -CRL synthetic control chart in detecting process mean shift showed the best performance in aspect of statistical performance, regardless of control limit L of CRL/S control chart.
송서일,정혜진 한국품질경영학회 2002 품질경영학회지 Vol.30 No.4
Traditional SPC techniques are looking out variation of process by fixed sampling interval and fixed sample size about every hour, the process of in-control or out-of-control couldn't be detected actually when the sample points are plotted near control limits, and it takes no notice of expense concerned with such sample points. In this paper, to overcome that, consider VSI(variable sampling interval) EWMA control charts which VSI method is applied. The VSI control charts use a short sampling internal if previous sample points are plotted near control limits, then the process has high probability of out-of-control. But it uses a long sampling interval if they are plotted near centerline of the control chart, since process has high possibility of in-control. And then a comparison and analysis between FSI(fixed sampling interval) and VSI EWMA in the statistical aspect and economic aspect is studied. Finally, we show that VSI EWMA control chart is more efficient than FSI EWMA control chart in the both aspects.
송서일,박현규,정혜진 한국품질경영학회 2004 품질경영학회지 Vol.32 No.1
This paper present an economic statistical design which have statistically constraints for the optimal design of an EWMA control charts with variable sampling interval. Cost function use that proposed by Lorenzen and Vance, and the optimal design parameters include the sample size, control limit width, sampling interval, EWMA weight value. Comparisons between VSI EWMA control charts optimal economic design and optimal economic statistical designs show the following fact. Although have demerits which are more costly than economic design, have merits which to detect shifts more efficiently and to improve statistical performance.
宋瑞日 동아대학교 공과대학 부설 한국자원개발연구소 1982 硏究報告 Vol.6 No.1
This paper considers the theoretical difference from Ishikawa's method in the case of estimating expected values of unbiased variance for each factor, when analysis of variance is adopted to interpret the data by the replicated tow-way layout (A: parameter, B: random) which type of factors is the mixed model in the experimental design.