• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.102.1-102
• /
• 2002

In this paper, we propose Self-organizing neurofuzzy networks(SONFN) and discuss their comprehensive design methodology. The proposed SONFN is generated from the mutually combined structure of both neurofuzzy networks (NFN) and polynomial neural networks(PNN) for model identification of complex and nonlinear systems. NFN contributes to the formation of the premise part of the SONFN. The consequence part of the SONFN is designed using PNN. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. We discuss two kinds of SONFN architectures and propose a comprehensive learning algorithm. It is shown that this network...

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1181-1186
• /
• 1993

In the paper, a new design method of rule-based fuzzy modeling is proposed for model identification of nonlinear systems. The structure indentification is carried out, utilizing fuzzy c-means clustering. Fuzzy-neural networks composed back-propagation algorithm and linear fuzzy inference method, are used to identify parameters of the premise and consequence parts. To obtain optimal linguistic fuzzy implication rules, the learning rates and momentum coefficients are tuned automatically using a modified complex method.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1293-1302
• /
• 1999

In this paper, an on-line process scheme is presented for implementation of a intelligent on-line modeling of nonlinear complex system. The proposed on-line process scheme is composed of FNN-based model algorithm and PLC-based simulator, Here, an adaptive fuzzy-neural networks and HCM(Hard C-Means) clustering method are used as an intelligent identification algorithm for on-line modeling. The adaptive fuzzy-neural networks consists of two distinct modifiable sturctures such as the premise and the consequence part. The parameters of two structures are adapted by a combined hybrid learning algorithm of gradient decent method and least square method. Also we design an interface S/W between PLC(Proguammable Logic Controller) and main PC computer, and construct a monitoring and control simulator for real process system. Accordingly the on-line identification algorithm and interface S/W are used to obtain the on-line FNN model structure and to accomplish the on-line modeling. And using some I/O data gathered partly in the field(plant), computer simulation is carried out to evaluate the performance of FNN model structure generated by the on-line identification algorithm. This simulation results show that the proposed technique can produce the optimal fuzzy model with higher accuracy and feasibility than other works achieved previously.

• 한국습지학회지
• /
• 제10권3호
• /
• pp.99-109
• /
• 2008

본 연구는 I편에서 개발된 일체형 블록시스템의 수리모형실험 결과를 검증하고 호안블록의 효과를 해석하기 위하여 수치해석을 통한 수리모형 실험을 수리특성을 모의하고자 하였다. 하도내 적용된 일체형 호안블록의 수치해석을 위하여 1차원 HEC-RAS 모형과 2차원 흐름 모의를 위하여 RMA-2 모형을 적용하여 식생전후의 수리현상을 수리모형 실험결과와 비교하여 홍수 시 유속 저감효과의 분석 및 대안으로 제시하는데 그 목적이 있다. 분석결과 2차원 수치해석 모형이 1차원 수치해석보다는 수위 유속 모두 수리모형실험결과와 근접한 결과를 나타내어 수치해석을 통한 자료구축 시 좀 더 신뢰성 있는 자료를 구축할 수 있는 것으로 판단되었다. 유속은 최저 0.21m/sec에서 최대 1.89m/sec의 저감효과를 나타내었으며, 이는 100m 당 4.89sec에서 7.33sec의 지체시간을 가져오는 것으로 분석되었다.

• 한국자동차공학회논문집
• /
• 제6권2호
• /
• pp.220-227
• /
• 1998

In substitution of beam-nonlinear spring model for real-car, it may have errors due to complicated characteristics of joint and overestimation of joints stiffness. In this research, a method for the joint modeling was suggested by nonlinear static and dynamic analyses of beam and shell joint models and verified by the application of accomplished joint modeling method to simplified full car model. In consequence, modified simplified full car model was improved in local acceleration and rigid wall force. Finally, the frontal crash analyses with the dummy were established and the accelerations of accelerations of head, chest and pelvis had good agreements with those of shell model.

• 한국지하수토양환경학회:학술대회논문집
• /
• 한국지하수토양환경학회 2004년도 총회 및 춘계학술발표회
• /
• pp.19-22
• /
• 2004

Two-dimensional modeling studies using TOUGHREACT were conducted to investigate the coupling between flow and transport developed as a consequence of differences in density, dissolution/ precipitation, and medium heterogeneity. The model includes equilibrium reactions for aqueous species, kinetic reactions between tile solid phases and aqueous constituents, and full coupling of porosity and permeability changes resulting from precipitation and dissolution reactions in porous media. Generally, the evolutions in the concentrations of the aqueous phase are intimately related to the reaction-front dynamics. Plugging of the medium contributed to significant transients in patterns of flow and mass transport.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2008년도 공동추계학술대회
• /
• pp.251-253
• /
• 2008

Erosion and landslide cause serious damage to forest areas. As a consequence, partial or complete destruction of vegetation occurs, which leads to many cascading problems. In this study, an attempt has been made to identify the forest areas, which are under different risk categories of erosion and landslide, in part of Eastern Ghats of Tamil Nadu. Relevantthematic maps were generated from satellite data, topographical maps, primary and secondary data and weights to each map were assigned appropriately. Weighted overlay analysis was carried out to identify the erosionprone forest areas. The result of erosion and landslide prone model reveals that 4712 ha(17%) of forest area is under high risk category and 15879 ha(58.65%) isunder medium risk category. The results of spatial modeling would be very much useful to the forest officials and conservationist to plan for effective conservation.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2003년도 추계학술대회
• /
• pp.207-214
• /
• 2003

3D Modeling Solution can reduce projecting error and also make possible to design visually, so that it can minimize human resources. On the other hand, it has defects of operating difficulties caused by too much complex function, thus it consequently prevent user from prompt handling. According to this paper, the developed party S/W will help that user can construct the parts easily, can let everybody use 3D modeling solution readily, and make fast development of new product. This software will carry out prompt development of new product and derive satisfaction of customers from high quality. Also, saving time and expense naturally raise competitive power in consequence.

• KIEAE Journal
• /
• 제9권6호
• /
• pp.81-87
• /
• 2009

The purpose of the present study is to establish structural noise analyzing method for apartments building floor with structural-acoustic coupling analysis modeling. Noise through floor in the room is recognized as a significant problem with the consequence that noise isolation technique has been studied in the various fields of industry. From among noise factors, resonance sound is the main reason for solid noise of the floor, which is occurred by mechanical vibrations of the acoustic boundary line and the change of velocity. To analyse this phenomenon, numerical computation methods are provided in many fields, In this study, evaluation method for slab is established using finite element method, and a case study for analyzing acoustic phenomenon was suggested. The results show that numerical method, especially F.E.M, has a good approximation to predict noise at floors.

• 디지털산업정보학회논문지
• /
• 제16권2호
• /
• pp.105-115
• /
• 2020

This study examines the influence of the betweenness centrality on tertius gaudens orientation, relationship commitment, and individual learning performance within the university environment. The betweenness centrality explored the antecedent factor of tertius gaudens orientation. The relationship commitment explored the consequence factor of tertius gaudens orientation, and the learning performance explored the consequence factor of the relationship commitment. This survey was carried out by university students. Data were obtained from 74 respondents who have been studying tourism data analytics at one of the leading universities, in Seoul, Korea. In order to validate the research model, social network analysis tool, UCINET 6.689, and a structural equation modeling tool, SmartPLS 3.3.2, were used. The empirical result showed that all antecedent factors (betweenness centrality position, tertius gaudens orientation, and relationship commitment) of the learning performance were significant. In conclusion, this study discusses the research findings and implications. Then the limitations and future directions of the study were suggested.