• 한국산업융합학회 논문집
• /
• 제26권6_1호
• /
• pp.977-983
• /
• 2023

The tank uses a twin turbo diesel engine equipped with two turbocharger systems for high output. The main component of the turbocharger system is the turbine housing through which the exhaust flows. Turbine housing is manufactured through a sand casting process, taking into account the shape and material characteristics according to the environmental conditions in which it is used. Currently, turbine housing is imported, and local production is necessary. In this study, basic research was conducted to localize the turbine housing of a tank diesel turbo engine. Reverse engineering and finite element analysis of the imported turbine housing were performed. The prototype of the turbine housing was printed using FDM and PBF 3D printers. The prototype of the turbine housing printed with an FDM 3D printer has an overall appearance similar to 3D modeling, but the printed surface of the whorl part is rough. The prototype printed with the PBF 3D printer is completely identical to the 3D modeling, including the whorl part.

• Elastomers and Composites
• /
• 제58권1호
• /
• pp.44-56
• /
• 2023

Additive manufacturing (AM) or three-dimensional (3D) printing of metals has been drawing significant attention due to its reliability, usefulness, and low cost with rapid prototyping. Among the various AM technologies, fused deposition modeling (FDM) or fused filament fabrication is receiving much interest because of its simple manufacturing processing, low material waste, and cost-effective equipment. FDM technology uses metal-filled polymer filaments for 3D printing, followed by debinding and sintering to fabricate complex metal parts. An efficient binder is essential for producing polymer filaments and the thermal post-processing of printed objects. This study involved an in-depth investigation of and a fabrication route for a novel multi-component binder system with steel alloy powder (45 vol.%) ranging from filament fabrication and 3D printing to debinding and sintering. The binder system consisted of polyvinyl pyrrolidone (PVP) as a binder and thermoplastic polyurethane (TPU) and polylactic acid (PLA) as a carrier. The PVP binder held the metal components tightly by maintaining their stoichiometry, and the TPU and PLA in the ratio of 9:1 provided flexibility, stiffness, and strength to the filament for 3D printing. The efficacy of the binder system was examined by fabricating 3D-printed cubic structures. The results revealed that the thermal debinding and sintering processes effectively removed the binder/carrier from the cubic structures, resulting in isotropic shrinkage of approximately 15.8% in all directions. The scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDX) patterns displayed the microstructure behavior, phase transition, and elemental composition of the 3D cubic structure.

• 한국멀티미디어학회논문지
• /
• 제22권2호
• /
• pp.250-259
• /
• 2019

Big data processing technology and artificial intelligence (AI) are increasingly attracting attention. Natural language processing is an important research area of artificial intelligence. In this paper, we use Korean news articles to extract topic distributions in documents and word distribution vectors in topics through LDA-based Topic Modeling. Then, we use Word2vec to vector words, and generate a weight matrix to derive the relevance SCORE considering the semantic relationship between the words. We propose a way to recommend documents in order of high score.

• 한국정밀공학회지
• /
• 제14권4호
• /
• pp.110-118
• /
• 1997

Multi-layer neural networks with error back-propagation algorithm have a great potential for identifying nonlinear systems with unknown characteristics. However, because they have a demerit that the speed of convergence is too slow, various methods for improving the training characteristics of backpropagition networks have been proposed. In this paper, a fuzzy division method is proposed to improve the convergence speed, which can find out an effective fuzzy division by the tuning of membership function and independently train each neural network after dividing the network model into several parts. In the simulations, the proposed method showed that the optimal fuzzy partitions could be found from the arbitray initial ones and that the convergence speed was faster than the traditional method without the fuzzy division.

• 공학교육연구
• /
• 제15권6호
• /
• pp.92-97
• /
• 2012

This paper deals with the model of natural sciences and engineering's convergence education. Recently, convergence education's necessary is needed since the most of new products are designed and produced based on the convergence technology. But our country's education system is keeping existing education process. This make industrial world undurable to employ the current graduated students. Also in view of educational world, they have no proper convergence education model for their students. In this paper, to solve the non-existing convergence education model, we derive the a few convergence education model and list up their model each. This result will be helpful for the introducer of the convergence education system.

• 한국지능시스템학회논문지
• /
• 제10권5호
• /
• pp.432-441
• /
• 2000

본 논문은 기존의 수학적인 모델링으로는 만족스러운 결과를 얻기 어려운 복잡하고 불확실한 비선형 시스템에 대한 퍼지 모델링 기법을 다룬다. 유전 알고리듬은 어느 정도 최적해를 전역적으로 찾을 수 있기 때문에 퍼지 모델링시에 파라미커와 구조를 동정하기 위하여 사용되었다. 하지만, 유전 알고리듬은 개체군이 유전적 다양성을 잃었을 경우 조기 수렴한다는 문제점이 있으며 바이러스-진화 유전 알고리듬은 이러한 지역수렴에 대한 방아닝 될 수 있다. 따라서, 본 논문에서는 바이러스 이론이 적용된 VEGA를 퍼지 모델링 할 때 이용할 수 있는 방법을 제안한다. 이 방법에서는 지역정보가 개체군 내에서 교환됨으로써 유전적 다양성을 유지하게 된다. 마지막으로, 본 논문에서 제안한 방법의 우수성과 일반성을 평가하기 위해 몇 가지의 수치적 예제를 제공한다.

• 디지털융복합연구
• /
• 제13권1호
• /
• pp.243-248
• /
• 2015

인식 모델을 구성할 때 정의되지 않은 모델, 인식 모델 구성 후에 추가되어진 모델, 모델이 부족하여 하나의 모델 클러스터링으로 모델링하여 생성된 인식 모델들은 인식률 저하의 원인이 된다. 이러한 원인을 개선하기 위하여 Bayesian 기법의 모수 추정을 이용한 결정트리 상태 공유 모델링 방법을 제안하였다. 제안 방법은 Bayesian 기법의 파라미터 추정을 통하여 탐색된 결과로부터 결정트리 기반 상태 공유 모델링의 최대 확률 기법에 따라 인식모델을 결정한다. 본 논문에서 제안하여 시뮬레이션 데이터를 이용한 실험 결과에서 제안한 군집화 방식을 비교하여 1.29%의 음성인식 오류감소율을 보였으며, 기존 군집화 방식에 비해 개선된 성능을 보였다.

• 한국융합학회논문지
• /
• 제10권7호
• /
• pp.175-182
• /
• 2019

본 연구는 기계학습 기법 중 토픽 모델링을 활용하여 건설현장에서 발생하는 추락재해에 대한 토픽을 분류하고 각 토픽에 따른 재해요인을 분석하였다. 잠재 디리클레 할당 기반의 토픽 모델링을 적용하기 위해 텍스트 데이터의 전처리를 하였고 Perplexity 점수로 평가하여 모형의 신뢰성을 높였다. 각 토픽에서 공통으로 도출된 추락재해의 대부분은 소규모 사업장에 속한 일용직 작업자들에게 발생하였다. 추락재해의 대부분의 원인은 안전장비 미착용, 현장 정리 정돈 미흡, 안전장비의 성능 및 착용 상태로 인해 제대로 작동하지 않은 것으로 판단되었다. 추락재해를 예방하고 절감하기 위해서는 소규모 사업장에 맞는 안전교육과 작업장의 정리 정돈과 개인 안전장비의 적절한 착용 상태 및 성능을 확인하는 것이 중요한 것으로 도출되었다.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권2호
• /
• pp.31-42
• /
• 2019

As smartphone H/W performance and mobile communication service have been enhanced, large-capacity 3D modeling files are available in smartphones. Common formats of 3D modeling files include STL (STereoLithography), OBJ (Wavefront file format specification), FBX (Filmbox), and glTF (open GL Transmission Format). Each format has different characteristics depending on the configuration and functions, and formats that are supported are varied depending on the applications. Large-size files are commonly used. The 4th generation mobile communication network secures loading of 3D modeling files and transmission of large-size geometric files in order to provide augmented reality services via smartphones. This paper explains the concepts and characteristics of major 3D file formats such as OBJ, FBX, and glTF. In addition, it compares their performance in a wired web with that in the 4th generation mobile communication network. The loading time and packet transmission in each 3D format are also measured by means of different mobile web browsers (Google Chrome and MS Edge). The experiment result shows that glTF demonstrated the most efficient performance while the loading time of OBJ was relatively excessive. Findings of this study can be utilized in selecting specific 3D file formats for rendering time reduction depending on the mobile web environments.

• 한국산업융합학회 논문집
• /
• 제27권2_2호
• /
• pp.343-356
• /
• 2024

Super app is an application that provides a variety of services in a unified interface within a single platform. With the acceleration of digital transformation, super apps are becoming more prevalent. This study aims to suggest service enhancement measures by analyzing the user review data before and after the transition to a super app. To this end, user review data from a payment-based super app(Shinhan Play) were collected and studied via topic modeling. Moreover, a matrix for assessing the importance and usefulness of topics is introduced, which relies on the eigenvector centrality of the inter-topic network obtained through topic modeling and the number of review recommendations. This allowed us to identify and categorize topics with high utility and impact. Prior to the transition, the factors contributing to user satisfaction included 'payment service,' 'additional service,' and 'improvement.' Following the transition, user satisfaction was associated with 'payment service' and 'integrated UX.' Conversely, dissatisfaction factors before the transition encompassed issues related to 'signup/installation,' 'payment error/response,' 'security authentication,' and 'security error.' Following the transition, user dissatisfaction arose from concerns regarding 'update/error response' and 'UX/UI.' The research results are expected to be used as a basis for establishing strategies to strengthen service competitiveness by making super app services more user-oriented.