직관 퍼지 와이블 분포에서 알파 컷 셋을 이용한 시스템 신뢰성 분석

최성운 ( Choi¸ Sungwoon ) 한국경영공학회 2021 한국경영공학회지 Vol.26 No.3

Purpose This study is to analyze system reliability using fuzzy Weibull lifetime distribution in which scale parameters are assumed to be Intuitionistic Fuzzy Set (IFS) with α-cut set due to uncertainties and inaccuracy of data. Methods The IFS is utilized to present the information of membership function and non-membership function with the three intervals that include belief, disbelief and unbelief functions. The paper discusses the intuitionistic fuzzy Weibull system reliability models to assess the membership function and non-membership function by considering the different types of component intuitionistic fuzzy scale parameter. Due to the existence of different types of uncertainties, the three types of component TIFS (Triangular IFS) and TrIFS (Trapezoidal IFS) with α-cut set were presented for computing intuitionistic fuzzy system reliability in both series structure and parallel structure. Results The validity of proposed model is demonstrated by analyzing intuitionistic fuzzy Weibull system reliabilities with α-cut set using different types of intuitionistic fuzzy scale parameter. A numerical example is indicated to discuss the usefulness and practicality of the proposed model. Conclusions When conducting a group decision making for evaluating the intuitionistic fuzzy Weibull system reliability, α-cut set models proposed in this paper can be used to reflect various experts’ judgments on agreement, disagreement and undecidedness when evaluating system reliability.

퍼지 베이지안 네트워크와 증거 이론을 이용한 FTA-FMEA 통합시스템에 의한 오류진단

최성운 ( Choi¸ Sungwoon ) 한국경영공학회 2020 한국경영공학회지 Vol.25 No.4

Purpose This study presents a combined model of Fault Tree Analysis (FTA) and Failure Mode and Effects Analysis (FMEA) using evidence theory and Fuzzy Bayesian Network (FBN) under uncertain circumstances which are caused by the presence of incompleteness, randomness and ambiguity of failure modes. Methods In order to identify the critical failure modes according to the multi-level FTA-FMEA, the Trapezoidal Distribution-Type Basic Belief Assignment (TrDTBBA) is used to consider the viewpoints of experts and to resolve the conflicts of evidence The proposed FTA-FMEA-FBN model derives fuzzy posterior probabilities to implement fault diagnosis approach which is more suitable than fuzzy prior probabilities when conducting qualitative reasoning of vague probability. Results A novel method for identifying the critical failure modes according to the level of hierarchical Bill of Material (BOM) is based on the proposed FTA-FMEA-FBN integrated model that illustrates chassis system consisting of 6 components, 4 modules and 6 parts. Conclusion This suggested FTA-FMEA-FBN model is convenient for a risk evaluation in the following uncertain circumstances: 1) The information of failure modes are incomplete, 2) The numbers of failure modes comprised of three levels are too abundant, 3) The probabilities of failure modes have a lack of quantification data. The fusion strategy of those three risk techniques implements computational efficiency and provides a synergistic effect to accurately identify the critical failure modes under uncertain circumstances.

해석학적 차원에서의 디자인의 형식적 함축성에 대한 고찰 : Wilhelm Dilthey의 해석학을 중심으로

최성운(Choi Sungwoon),최성운(Choi Sungwoon) 한국디지털디자인학회 2011 디지털디자인학연구 Vol.11 No.3

디자인은 시대와 경향에 따라 각기 다른 함축된 내용을 포함하게 되며 시대정신에 의한 내용과 같은 무형적 가치가 적용됨으로서 디자인마다 고유한 특성을 지니게 된다. 이는 곧 제품언어로 이해될 수 있는 함축성이 포함된 내용이 은유와 개별적 특징을 지니고 있음을 의미한다. 오늘날 디자인 개발에 있어 다양한 변수가 작용하고 있으며 디자인 환경에 대한 예측 자체가 어려운 상황이다. 게다가 소비자들의 기호 또한 다양해지고 있으며 디자인은 시장과 소비자의 요구에 의해 수동적 입장을 취하게 된다. 결과적으로 디자인 개발에 대한 확실성을 더 이상 보장할 수 없게 되었음을 의미하며 이 문제를 해결하기 위해 시스템적이며 과학적 차원에서의 디자인 개발이 요구되고 있는 것이다. 디자인은 소비자들로 하여금 유형적(有形的) 기반 또는 합의(合議) 과정에서 실제적이며 공통적으로 인식하게 하는 것들을 포함하고 있다. 이에 따라 디자인 또한 해석학적 대상으로 볼 수 있으며 그 내용을 시스템적으로 이해하게 된다면 디자인 개발에 있어 명료성을 획득하게 된다. 해석학적 접근방법은 디자인의 함축적 내용을 검증하는 시스템이자 시장에서의 최적화 상태의 디자인을 위한 처방적 시스템이라고 할 수 있다. 본 논문에서는 디자인 전략적 차원에서 함축성을 이해하기 위해 해석학적 접근을 시도하였으며 함축성에 대한 내용을 분석하고 리스트화 할 수 있는 검증내지는 평가시스템에 대하여 연구하고자 하였다. Design always includes individually different implicative contents according to the tendency by the times and it comes to take on design characteristics through the application of intangible value such as the contents reflecting the spirit of the times. This means the implicative contents which can be understood as a product language have a metaphoric and individual characteristic. Today a variety of variables are operating in design development and so it's in a situation where designers feel it difficult even to forecast design environment. Moreover consumers' taste is becoming more diverse and subsequently design comes to take up a passive position by the demand of the market and consumers. Consequently it means that it's impossible to guarantee the certainty of design development any more and that's why there needs to be design development at a systematic and scientific level in order to solve this problem. Design includes the things that make consumers perceive practically and in common on a tangible foundation or in the process of agreement. Accordingly design can be seen as an analytic subject so it's possible to acquire clarity in design development once the contents could be accurately understood. Thus this research thinks that the analytic approach is a system that can verify the connotative contents of design and also a prescriptive system for the design in a state of optimization in the market. This thesis made an attempt at an analytic approach with the aim of understanding the implications at a design strategy level and tried to suggest the verification & evaluation system that can analyze and list up the contents of implications.

TRIZ for Total Quality Management : Overview

Sungwoon Choi 대한안전경영과학회 2004 대한안전경영과학회 학술대회논문집 Vol.2004 No.11

This paper presents 40 inventive principles with applications in total quality management. We also propose how to integrate TRIZ tools into global problem-solving steps.

Large-scale machine learning of media outlets for understanding public reactions to nation-wide viral infection outbreaks

Choi, Sungwoon,Lee, Jangho,Kang, Min-Gyu,Min, Hyeyoung,Chang, Yoon-Seok,Yoon, Sungroh Elsevier 2017 Methods Vol.129 No.-

<P>From May to July 2015, there was a nation-wide outbreak of Middle East respiratory syndrome (MERS) in Korea. MERS is caused by MERS-CoV, an enveloped, positive-sense, single-stranded RNA virus belonging to the family Coronaviridae. Despite expert opinions that the danger of MERS might be exaggerated, there was an overreaction by the public according to the Korean mass media, which led to a noticeable reduction in social and economic activities during the outbreak. To explain this phenomenon, we presumed that machine learning-based analysis of media outlets would be helpful and collected a number of Korean mass media articles and short-text comments produced during the 10-week outbreak. To process and analyze the collected data (over 86 million words in total) effectively, we created a methodology composed of machine-learning and information-theoretic approaches. Our proposal included techniques for extracting emotions from emoticons and Internet slang, which allowed us to significantly (approximately 73%) increase the number of emotion-bearing texts needed for robust sentiment analysis of social media. As a result, we discovered a plausible explanation for the public overreaction to MERS in terms of the interplay between the disease, mass media, and public emotions. (C) 2017 Elsevier Inc. All rights reserved.</P>

Relative Performance of Group CUSUM Charts

SUNGWOON CHOI,SANGHOON LEE 대한산업공학회 1996 대한산업공학회 춘계학술대회논문집 Vol.1996 No.4

Design of a General Multivariate EWMA Control Chart

Sungwoon Choi,Sanghoon Lee 대한산업공학회 1999 대한산업공학회 추계학술대회논문집 Vol.1999 No.10

TRIZ for Total Quality Management : Overview

Sungwoon Choi 대한안전경영과학회 2004 대한안전경영과학회 학술대회논문집 Vol.2004 No.1

Relative Performance of Group CUSUM Charts

CHOI, SUNGWOON,LEE, SANGHOON 한국경영과학회 1996 한국경영과학회 학술대회논문집 Vol.- No.1

Performance of the group cumulative sum(CUSUM) control scheme using multiple univariate CUSUM charts is more sensitive to the change of quality control(QC) characteristics than the control chart schemes based on the Hotelling statistic. We examine three group charts for multivariate normal data sets simulated with various correlation structures and shift directions in the mean vector. These group schemes apply the original measurement vectors, the scaled residual vectors from the regression of each variable on all others and the principal component vectors respectively to calculating the CUSUM statistics. They are also compared to the multivariate QC charts based on the Hotelling statistic by estimating average run lengths, coefficients of variation of run length and ranks in signaling order. On the basis of simulation results, we suggest a control chart scheme appropriate for specific quality control environment.

Comparisons of Multivariate Quality Control Charts by Use of Various Correlation Structures

Choi, Sungwoon,Lee, Sanghoon 한국경영과학회 1995 韓國經營科學會誌 Vol.20 No.3

Several quality control schemes have been extensively compared using multivariate normal datasets simulated with various correlation structures. They include multiple univariate CUSUM charts, multivariate EWMA charts, multivariate CUSUM charts and Shewhart T^2 chart. This paper considers a mew approach of the multivariate EWMA chart, in which the smoothing matrix has full elements instead of only diagonal elements. Performance of the schemes is measured by average run length(ARL), coefficient of variation of run length(CVRL) and rank in order of signaling of off-target shifts in the process mean vector. The schemes are also compared by noncentrality parameter. The multiple univariate CUSUM charts are generally affected by the correlation structure. The multivariate EWMA charts provide better ARL performance. Especially, the new EWMA chart shows remarkable results in small shifts.