탄력적 수요 대응을 위한 SCM 체계(화장품 제조 L사 사례를 중심으로)

옥창훈 한국경영과학회 2022 한국경영과학회 학술대회논문집 Vol.2022 No.6

자동차 생산을 위한 통합창고 연구

옥창훈,김득수,공정수,서윤호,Ok, Chang-Hun,Kim, Duk-Su,Gong, Jung-Su,Seo, Yoon-Ho 한국시뮬레이션학회 2012 한국시뮬레이션학회 논문지 Vol.21 No.2

자동차 생산라인은 차체라인, 도장라인, 의장라인으로 구성된다. 이러한 생산라인들은 직렬로 배치되어 흐름생산을 거치기 때문에 전후 공정의 상태에 따라 라인에서는 starvation(물량 부족으로 인한 생산 불가능) 또는 blocking(용량 초과로 인한 생산 불가능)으로 인한 정지가 발생한다. 이에 starvation이나 blocking으로 오는 생산 손실을 막기 위해 WBS, PBS와 같은 창고를 개별적으로 보유하여 운영된다. 본 논문은 라인의 버퍼역할을 하는 각 창고들을 통합하여 운영할 수 있는 통합창고 시뮬레이션 모형을 제안한다. 적정 Stacker Crane 대수와 AGV 대수를 구하고, 이를 운영할 수 있는 운영방법론을 제안한다. 또한 개별창고와 통합창고 모형을 시뮬레이션을 이용하여 효율성 비교를 한다. Automobile manufacturing consists of body-line, painting-line, and assembly-line. These production lines are disposed in series and go through a flow process, so according to the status of pre & post processing, a suspension happens in a line by a starvation(impossibility of production by insufficient supply) or blocking(impossibility of production by exceed capacity). Therefore, to prevent a loss of production coming from a starvation or blocking, a storage such as WBS or PBS is independently owned and operated. The paper suggests the simulation model of integrated storage which can operate it by integrating each storage performing a role as a buffer of line. Specifically, the paper found the answers about reasonable number of Stacker Crane and AGV(Automatic Guided Vehicle) and suggested a methodology of operation which is available to operate them. Also, it compared an efficiency between a model of current storage and integrated storage through simulation. As a result, it turned out that the model suggested in the paper was more efficient on suspension of painting-line stop than a current storage.

탄력적 수요 대응을 위한 SCM 체계(화장품 제조 L사 사례를 중심으로)

옥창훈 대한산업공학회 2022 대한산업공학회 춘계학술대회논문집 Vol.2022 No.6

자동차 생산을 위한 통합창고 연구

옥창훈(Chang Hun Ok),김득수(Duk Su Kim),서윤호(Yoonho Seo),공정수(Jung Su Gong) (사)한국CDE학회 2012 한국 CAD/CAM 학회 학술발표회 논문집 Vol.2012 No.2

Automobile manufacturing consists of body-line, painting-line and assembly-line. And to prevent the production loss by starvation or blocking, all lines have buffers respectively. This paper focuses on the integrated storage design including WBS(White Body Storage), CRS(Color Rescheduling Storage), PBS(Painted Body Storage). This paper approaches three steps as follows: first, calculating the number of AS/RS and AGV. Second, proposing the dispatching rule to keep the production rate in an assembly-line. And then lastly, the proposed integrated storage model is compared with current storage model using simulation. And simulation result shown that the proposed model is more effective and flexible then current storage model to printing line stop.

정밀 정량 제어 기술을 적용한 가정용 페인트 배합기 개발

옥창훈(Chang-hoon Ok),황진순(Jin-soon Hwang),박성구(Sung-gu Park),정명진(Myung-Jin Chung) 대한기계학회 2020 대한기계학회 춘추학술대회 Vol.2020 No.12

머신러닝 기반 인공지능 특허 품질 예측

김성현,옥창훈,김영민 기술경영경제학회 2023 Journal of Technology Innovation Vol.31 No.4

인공지능은 4차 산업혁명의 프레임이 소개된 이후 점차 보편적인 기술로 자리를 잡아가고 있으며, 인공지능 관련 특허 출원도 크게 증가하고 있다. 최근에는 특허 생태계가 출원 건수 위주의 양적 경쟁에서 고품질의 특허 확보라는 질적 경쟁으로 패러다임이 변화되면서, 저품질 특허로 인한 비용 손실에 관심이 높아지고 있다. 이러한 배경으로 본 연구에서는 머신러닝과 Doc2Vec 알고리즘을 활용하여 특허 품질을 예측하는 방법을 제안하고자 한다. 본 연구를 위해 WIPO에서 정의한 CPC 코드를 활용하여 미국 특허청(USPTO)에 등록된 인공지능 관련 특허 데이터를 추출하였고, 이를 통해 정형 데이터 기반 19개 변수, 비정형 데이터 기반 7개 변수를 개발하였다. 특히, 새롭게 제안하는 Doc2Vec 알고리즘을 이용한 제목과 초록 텍스트 유사도 변수는 고품질 특허를 예측하는데 영향을 미칠 것으로 판단된다. 이에 유사도 변수의 효과를 확인하기 위해 유사도 변수를 포함한 앙상블 기반 머신러닝 모델과 포함하지 않은 모델을 개발하여 비교하였다. 실험 결과, 유사도 변수를 포함한 모델이 AUC 0.013, f1-score 0.025가 높게 나타나 더 우수한 성능을 보였다. 이는 유사도 변수가 고품질 특허 예측에 기여한다는 것을 시사한다. 또한, SHAP을 이용하여 블랙박스 형태의 머신러닝 변수 영향도를 설명하였다. 본 연구를 통해 핵심 기술 분야인 인공지능과 같은 영역에서 특허의 품질을 예측하고, 고품질 특허 개발을 장려함으로써 사회적 가치를 실현하는 데 기여할 수 있을 것으로 기대한다. Artificial intelligence has gradually become a ubiquitous technology since the introduction of the framework of the Fourth Industrial Revolution, and the number of patent applications related to artificial intelligence has also significantly increased. Recently, the paradigm of the patent ecosystem has shifted from a quantitative competition based on the number of applications to a qualitative competition focused on securing high-quality patents, due to the growing concern about the costs incurred by low-quality patents. Against this background, this study proposes a method for predicting patent quality using machine learning and the Doc2Vec algorithm. For this research, we utilized CPC codes defined by WIPO to extract patent data related to artificial intelligence from the United States Patent and Trademark Office (USPTO). Through this process, we developed 19 variables based on structured data and 7 variables based on unstructured data. Particularly, we introduced a novel approach using the Doc2Vec algorithm to calculate similarity variables for the title and abstract texts, which are expected to influence the prediction of high-quality patents. To assess the impact of these similarity variables, we developed and compared an ensemble-based machine learning model that includes the similarity variables with a model that does not. The experimental results showed that the model incorporating the similarity variables exhibited superior performance with an AUC of 0.013 and an f1-score of 0.025, indicating their contribution to predicting high-quality patents. Additionally, we explained the variable importance of the black-box machine learning model using SHAP. Through this study, we expect to contribute to the realization of social value by predicting the quality of patents and promoting the development of high-quality patents in the field of key technologies such as artificial intelligence. Key Words:Patent quality prediction, Machine learning, AI, Doc2Vec, Similarity

Flow Shop 배치설계를 위한 휴리스틱 알고리즘

남기호,서민석,옥창훈,서윤호 대한산업공학회 2011 대한산업공학회 춘계학술대회논문집 Vol.2011 No.5

To date, facility layout problems were solved and applied for job shops. Since flow shops have a smaller solution space in layout problem than job shop, an efficient heuristic algorithm for facility layout problems for flow shops need to be developed. In this paper, a heuristic algorithm for the rectangular bay layout in a flow shop situation is presented. The proposed algorithm is developed by using slicing tree representation and applied to various flow shop layout problems.

Flow Shop 배치설계를 위한 휴리스틱 알고리즘

남기호,서민석,옥창훈,서윤호 한국경영과학회 2011 한국경영과학회 학술대회논문집 Vol.2011 No.5

To date, facility layout problems were solved and applied for job shops. Since flow shops have a smaller solution space in layout problem than job shop, an efficient heuristic algorithm for facility layout problems for flow shops need to be developed. In this paper, a heuristic algorithm for the rectangular bay layout in a flow shop situation is presented. The proposed algorithm is developed by using slicing tree representation and applied to various flow shop layout problems.

Supply Chain에서 인공지능의 활용에 관한 연구 :머신러닝 기반의 분류 기법 활용

고강욱 ( Ko¸ Kang Wook ),옥창훈 ( Ok¸ Chang Hoon ),김영민 ( Kim¸ Young Min ) 한국경영공학회 2023 한국경영공학회지 Vol.28 No.3

Purpose The study aims to identify trends, assess research status by country and SCOR standard processes, and provide machine learning-based classification methods in the research area. Methods Qualitative analysis is conducted on a total 493 literature data. And nine machine learning models to classify the SCM process are performed Results Artificial intelligence in Supply Chain research has been consistent since 1998, with a noteworthy concentration from 2017 to 2023. High-performing models (XGBoost, LightGBM, CatBoost) achieve F1 values exceeding 70% and AUC values over 80%, effectively classifying literature data into SCOR's 6 processes. Conclusion In Supply Chain research, focus is on 'Enable' for decision support and 'Plan' for predictive optimization,. This addresses global AI-driven efficiency demands for strengthening domestic supply chains. Korea's 1% contribution requires policy-driven activation. Employing ML-based classification enhances future analysis, allowing ongoing research and easy referencing for national and corporate endeavors.

Flow Shop 배치설계를 위한 휴리스틱 알고리즘

남기호(Kee-ho Nam),옥창훈(Chang-Hun Ok),서윤호(Yoonho Seo) 한국산업경영시스템학회 2011 한국산업경영시스템학회지 Vol.34 No.4

To date, facility layout problems has been solved and applied for job shop situations. Since flow shop has more restrictions, the solution space is much smaller than job shop. An efficient heuristic algorithm for facility layout problems for flow shop layouts is needed to be developed. In this thesis, a heuristic algorithm for rectangular bay layouts in a flow shop situation is presented. The proposed algorithm is developed by using slicing tree representation and applied to various flow shop layout problems. The effectiveness of the proposed algorithm in terms of exploration rate and objective function value are shown by comparing our results to simulated annealing.