http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
균형배열에 의해 설계되는 2-수준 Resolution-V 실험법의 직교성 평가측도
김상익,Kim, Sang-Ik 한국통계학회 2008 Communications for statistical applications and me Vol.15 No.2
실험계획의 요인배치법에서 부분실험을 설계할 때, 직교배열을 이용한 실험설계방법이 널리 사용된다. 그러나 부분실험의 해상도(resolution)가 큰 경우, 직교배열을 일반화한 균형배열이 효과적으로 사용될 수 있다. 특히 2-수준 요인실험법에서는 강도(strength)가 4인 균형배 열은 resolution-V인 부분실험법과 동일하다는 것이 알려져 있다. 본 연구에서는 강도(strength)가 4인 균형배열의 직교성을 평가하는 측도를 제시하고자 한다. 그리고 본 연구에서 제시된 평가측도를 응용하여 실험횟수가 가장 적고 직교성에 가까운 최소 균형 resolution-V 부분실험법의 설계방법을 제시하고자 한다. Balanced arrays which are generalized orthogonal arrays, introduced by Chakravarti (1956) can be used to construct the fractional factorial designs. Especially for 2-level factorials, balanced arrays with strength 4 are identical to the resolution-V fractional designs. In this paper criteria for evaluation the degree of the orthogonality of balanced arrays of 2-levels with strength 4 are developed and some application methods of the suggested criteria are discussed. As a result, in this paper, we introduce the constructing methods of near orthogonal saturated balanced resolution-V fractional 2-level factorial designs.
염소계 화합물(TCE, PCE)로 오염된 토양 및 지하수 처리를 위한 실용적 고도산화처리시스템 개발 (II)
김상익,손석규,공성호,Kim, Sang-Yeek,Sohn, Seok-Gyu,Kong, Sung-Ho 한국지하수토양환경학회 2010 지하수토양환경 Vol.15 No.2
Advanced oxidation processes (AOPs) have advantages to reduce the processing time and mineralize contaminants dissolved in groundwater. Recently, remediation techniques for organic contamination in groundwater have been studied, and technology using $UV/H_2O_2$ is generally accepted as one of the most powerful and reliable alternative for the remediation of groundwater contamination. In this study, $UV/H_2O_2$ technology, which generates hydroxyl radical ($\cdot$ OH) as known for strong non-selective oxidant, was used to degrade chlorinated solvents (TCE and PCE), and it was expanded to apply continuous stirred tank reactor (CSTR) system (i.e. combinations of three CSTR). The tested parameters for CSTR system were retention time and groundwater/$H_2O_2$ injection volume ratio. To find optimum parameters for CSTR system, various retention time (6 min ~ 90 min) and groundwater/$H_2O_2$ injection volume ratio (5/1 ~ 119/1) were tested. Other conditions for CSTR were adapted from the batch test results, which concentration of $H_2O_2$ and UV dose were 29.4 mM (0.1%) and 4.3 kWh/L, respectively. Based on the experimental results, the optimum parameters for CSTR system were 20 min for retention time and 119/1 for groundwater/$H_2O_2$ injection volume ratio. Applying these optimum conditions, chlorinated solvents (TCE and PCE) were removed at 99.9% and 99.6%. Moreover, the effluent concentrations of TCE and PCE are 0.036 mg/L and 0.087 mg/L, respectively, which are satisfied the regulatory level (TCE 0.3 mg/L, PCE 0.1 mg/L). Consequently, the CSTR system using $UV/H_2O_2$ technology can achieve high removal efficiency in the event of treatment of groundwater contaminated by chlorinated solvents (TCE and PCE).
축차적 반응표면 분석을 통한 M&S 메타모형 구축에 관한 사례 연구
김상익 ( Sang Ik Kim ),김용대 ( Yong Dai Kim ),임용빈 ( Yong Bin Lim ),최기헌 ( Ki Heon Choi ),김정은 ( Jeong Eun Kim ) 한국품질경영학회 2012 품질경영학회지 Vol.40 No.1
In computer simulation models the output from the computer code is often deterministic, i.e., running the code twice with the same values for the input variables would give the same output. It is discussed why the response surface method with polynomial approximation for the true response function is a good approximation to the computer experiments model. A sequential strategy to find the proper reduced quadratic polynomial model is illustrated with a case study in the military war game computer simulation model.
유사직교 분해가능 V2t 포화부분요인계획법의 베이지안 분석방법
김상익(Sang Ik Kim),박창문(Chang Moon Park) 건국대학교 경제경영연구소 1996 商經硏究 Vol.21 No.1
In this paper, we investigate a Bayesian method introduced by Box and Meyer(1986) in analyzing near orthogonal resolution Ⅴ saturated 2t fractional factorial designs. Such designs, constructed by Kim(1992) are characterized by a minimum number of treatment combinations and near orthogonality property of the estimates. As a result, we can see that the pre-estimation procedure of parameters in the Bayesian model is necessary, and in this paper some effective analyzing methods with pre-estimation procedure of the parameters are discussed.
품질경영학회 50주년 특별호: 실험계획법 분야 연구 리뷰
김상익 ( Sang Ik Kim ),이상복 ( Sang Bok Lee ),임용빈 ( Yong Bin Lim ),장대흥 ( Dae Heung Jang ) 한국품질경영학회 2016 품질경영학회지 Vol.44 No.2
Purpose: This article focuses on the reviewing the papers published in the Journal of the Korean Society for Quality Control (JKSQC) and the Journal of the Korean Society for Quality Management (JKSQM) since 1965, in the area of design of experiments. In this paper, moreover, some other contents of another statistical quality control areas is included. Methods: The reviewed articles are classified into the three main categories: theory and application of experimental designs, response surface methodology and mixture experiments, and roust designs. Some omitted papers in the other areas of reviewing works are also included in this paper, and the contents and relationships of the published articles are examined and summarized in each sub-field. Results: We summarize the reviewed papers in the chronological road-maps for each sub-field, and outline the relations of the connected papers. We provide comments on the contents and the contributions of the reviewed papers. The future direction of the research in the theory and application areas of experimental designs can be provided by the contents of this research. Conclusion: The diverse topics on the improving the quality in the various industry fields are studied and published on the theory, methodology and the empirical application in the fields of designs of experiments. We can see that the Korean Society for Quality Management (KSQM) has tremendously contributed on the improvement of quality in the manufacturing and service industries by publishing the reviewed articles in this paper.