• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 학술대회 논문집 정보 및 제어부문
• /
• pp.174-176
• /
• 2005

This treatise studies composing process that renew information mastered by interactive experience between environment and system via network among individuals. In the previous study map information regarding free space is learned by using of reinforced learning algorithm, which enable each individual to construct optimal action policy. Based on those action policy each individuals can obtain optimal path. Moreover decision process to distinguish best optimal path by comparing those in the network composed of each individuals is added. Also information about the finally chosen path is being updated. A self renewing method of each system information by sharing the each individual data via network is proposed Data enrichment by shilling the information of many maps not in the single map is tried Numerical simulation is conducted to confirm the propose concept. In order to prove its suitability experiment using micro-mouse by integrating and comparing the information between individuals is carried out in various types of map to reveal successful result.

• 한국정밀공학회지
• /
• 제13권2호
• /
• pp.168-175
• /
• 1996

The measured vibration on a machine or a structure is shaped by the excitation waveform and the path transfer function. Mechanism diagnostics tends to focus on retrieving source features by minimizing the effects of the structiral path, while in structural diagnostics we are more interested in minimizing source effects and retrieving path parameters. In structural diagnostics, therefore, there are experimental issues of gathering date that are independent source effects and finding a transfer function signature that reveals structural defects. This paper describes how the transfer function can be obtained more accurately by experiment using the compatibility relationship which is newly discovered.

• 한국경영과학회지
• /
• 제27권2호
• /
• pp.33-49
• /
• 2002

CBM (Condition-Based Maintenance) has increasingly drawn attention in industry because of its many benefits. CBM Problem Is characterized as a state-dependent scheduling model that demands simultaneous maintenance actions, each for an attribute that influences on machine condition. This problem is very hard to solve within conventional Markov decision process framework. In this paper, we present an intelligent machine maintenance scheduler, for which a new incremental decision tree learning method as evolutionary system identification model and shortest path problem as schedule generation model are developed. Although our approach does not guarantee an optimal scheduling policy in mathematical viewpoint, we verified through simulation based experiment that the intelligent scheduler is capable of providing good scheduling policy that can be used in practice.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.2027-2030
• /
• 2002

SFFS(Solid Freeform Fabrication System) is commercializing to rapid prototyping concept in world- wide some corporations including the U.S.A, have much technological problems yet and need new mode for agile solid freeform fabrication as well as prototyping. In this paper, we design an algorithm that the cutting path of laser beam, on the SFFS, is controlled with constant speed. The designed algorithm fer constant-speed path control is implemented and experimented in the CAFL$\^$VM/ (Computer Aided Fabrication of Lamination for Various Material) system, the new SffS which is developed in this paper. Finally, the ceramic, new material developed in this paper, cut and fabricated. The dimensional accuracy and mechanical stability of the 3D object is confirmed through the experiment, also.

• 한국정밀공학회지
• /
• 제17권10호
• /
• pp.56-62
• /
• 2000

A fast and precise technique to make 3-dimensional object which is called direct metal shaping process is processed. It is very useful technique in design and inspection. Using this developed system, a solid object is made. In experiment, test parts are built by varying three factors, laser power, scan path, scan speed. This process used device, which is different from the widely used in rapid prototyping in that powder feeding device is used. Spraying powder directly at the focused laser beam and then three dimensional object is made by the deposit of melted metal powder. The optimum scanning path is found to be zigzag path, which had little thermal affection on base metal. As a result of these experiments, it was found that optimum scanning speed is 15mm/sec laser power is 50W. This constructed 3-dimensional object could be used in mold manufacturing directly.

• 디자인학연구
• /
• 제18권4호
• /
• pp.139-146
• /
• 2005

지금까지의 애니메이션 작업은 애니메이터의 객관적 감성과 경험에 의해 이루어져 왔다. 소프트웨어 디자인에 있었어도 지성적인 데이터들을 바탕으로 제작되어져 왔다. 이는 객관화하기 용이한 자료로서 데이터화하기가 쉬웠기 때문 일 것으로 보인다. 이와는 반대로 인간의 감성은 객관화하고 디지털화하기 어려운 요소들이 많이 존재한다. 본 연구는 디지털화하기 어려운 인간의 감성적 데이터를 객관화하고 이를 정량적 데이터로 활용할 수 있는 방법에 대한 부분으로 나는(flying) 궤적(path)을 연구 대상으로 하였다. 실험에 있어 인간이 나는 제적에 대해 어떻게 표현하는지에 대한 감성어를 수집하였다. 수집한 감성어를 통해 감성 평가어를 추출하고 추출한 감성 평가어에서 느껴지는 나는 궤적에 대한 스케치 이미지를 수집하였다. 수집한 스케치 이미지를 기초로 본 연구의 핵심이 되는 실험 동영상 샘플을 제작하였다. 다음으로 나는 궤적을 나타내는 감성어에 대한 물리적 요소와 동영상 샘플과의 상관관계를 분석하기 위해 수량화이론III류와 수량화이론I류를 각각 이용하였다. 그 결과 감성어와 동영상 샘플과의 구조를 파악 할 수 있었고, 나는 궤적에 대한 감성반응의 물리적 자극요소 또한 분석 할 수 있었다. 나는 궤적은 오브젝트(object)가 지나간 경로(path)에 해당한다. 이러한 경로(궤적)를 보고 감성자극 요소들이 복합적으로 작용하여 독특한 감성어로 표현되어 지는 것으로 보인다. 여기엔 감성을 자극하는 요소들이 존재하는데, 그 요소로는 속도, 회전, 규칙 그리고 호의 길이가 그 물리적 요소인 것으로 파악되었다. 본 연구를 통해 나는 궤적의 애니메이션을 표현하는데 있어 애니메이터들의 주관적인 감성 표현들을 객관화, 정량화 시키고자 하였으며, 본 연구의 데이터는 감성 애니메이션 시스템 설계에 있어 기본 데이터로 적용되는 것을 목표로 하고 있다.

• 한국시뮬레이션학회논문지
• /
• 제22권2호
• /
• pp.53-62
• /
• 2013

클라우드 환경은 분산컴퓨팅 분야의 한가지로서, 물리 노드와 가상 노드로 구성이 되어 있다. 분산화 된 클라우드 환경에서의 최적 경로 탐색은 각 노드들이 최적 경로 탐색을 수행하는 것이다. 실시간으로 급변하는 탐색 환경은 빠른 데이터 전송을 통한 각 노드들의 동기화를 요구한다. 따라서 QoS의 보장과 최적 경로 탐색을 위해서 양자화 기법이 필요하다. 양자화 기법을 통해 중앙 서버는 각 노드로 실시간 탐색 환경 데이터를 빠르게 전송가능하며 각 노드들은 원활하게 최적 경로 탐색을 수행할 수 있다. 본 논문에서는 중앙 서버에서 각 노드들의 최적 경로 탐색 문제를 해결하기 위해 데이터의 전송량을 줄일 수 있는 양자화를 적용한다. 최적 경로 생성 시스템에 양자화 데이터 전송을 적용하는 실험을 하기 위해 클라우드 환경의 시뮬레이션을 구성하였다. 양자화 기법의 적용을 통해 클라우드 환경에서 전송 되는 총 데이터를 줄이면서 성능을 높일 수 있으며, 최적 경로 탐색을 위한 어플리케이션의 QoS를 보장할 수 있다.

• 한국정밀공학회지
• /
• 제17권4호
• /
• pp.114-120
• /
• 2000

Burr is an unavoidable and undesirable by-product of most metal cutting or shearing operations. This burr must be removed to improve the fit of machined parts and safety of workers, to improve the effectiveness of finishing operations. Despite the full or partial automation of FMC or FMS, deburring operations to obtain workpiece with fine surface quality are difficult to be automated since the occurrence and condition of burr are not constant. This study focused on developing a software for deburring automation, which includes automatic recognition of parts, generation of deburring tool path and NC code, by analyzing the IGES format file which contains information of part geometry. The successful performance of developed software was demonstrated by computer simulation and deburring experiment using miniature end brush. And, this research can provide a basis for further advanced studies for automated deburring applications.

• 한국IT서비스학회지
• /
• 제21권2호
• /
• pp.85-95
• /
• 2022

This study analyzed the translation error factors of machine translation services such as Naver Papago and Google Translate through Self-Attention path visualization. Self-Attention is a key method of the Transformer and BERT NLP models and recently widely used in machine translation. We propose a method to explain translation error factors of machine translation algorithms by comparison the Self-Attention paths between ST(source text) and ST'(transformed ST) of which meaning is not changed, but the translation output is more accurate. Through this method, it is possible to gain explainability to analyze a machine translation algorithm's inside process, which is invisible like a black box. In our experiment, it was possible to explore the factors that caused translation errors by analyzing the difference in key word's attention path. The study used the XLM-RoBERTa multilingual NLP model provided by exBERT for Self-Attention visualization, and it was applied to two examples of Korean-Chinese and Korean-English translations.

• 한국산업융합학회 논문집
• /
• 제25권4_1호
• /
• pp.521-531
• /
• 2022

This study proposed a new approach to intelligent control of a mobile robot system by back properpagation based on multi-layer neural network. A experiment result is given in which some artificial assumptions about the linear and the angluar velocities of mobile robots from recent literature are dropped. In this study, we proposed a new thinique to impliment the real time conrol of he position and velocity of mobile robots. With the proposed control techinique, mobile robots can now globally follow any path such as a straight line, a circle and the path approaching th toe origin using proposed controller. Computer simulations are presented, which confirm the effectiveness of the proposed control algorithm. Moreover, practical experimental results concerning the real time control are reported with several real line constraints for mobile robots with two wheel driving.