• Transactions on Control, Automation and Systems Engineering
• /
• 제3권1호
• /
• pp.43-50
• /
• 2001

In this paper, we propose the design procedure of advance Polynomial Neural Networks(PNN) architecture for optimal model identification of complex and nonlinear system. The proposed PNN architecture is presented as the generic and advanced type. The essence of the design procedure dwells on the Group Method of Data Handling(GMDH). PNN is a flexible neural architecture whose structure is developed through learning. In particular, the number of layers of the PNN is not fixed in advance but is generated in a dynamic way. In this sense, PNN is a self-organizing network. With the aid of three representative numerical examples, compari-sons show that the proposed advanced PNN algorithm can produce the model with higher accuracy than previous other works. And performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• 전기학회논문지
• /
• 제60권5호
• /
• pp.913-920
• /
• 2011

Distribution systems for operating the various systems should be operated organically. Distribution systems for organic operations extend the functionality of the system and system integration for the extension is doing. However, in systems integration for each unique non-standard definition of linkage and exchange systems are used. Non-standard definition of a unique linkage and exchange systems in the maintenance and expansion will result in many negative results. To solve these problems, the system and the exchange of information about the links between systems should define standards. IEC (International Electrotechnical Commission) power to solve these problems in the field of the Common Information Model (Common Information Model, CIM) standard (IEC61970, IEC61968) is defined as the transmission and distribution system integration and standardization for the exchange of information. In this paper, standardized system for building CIM-based distribution automation system should describe the process of building. In addition, the process of establishing a common information model needed (CIM) defined and associated services for a defined set of models is proposed in the standardization process.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.403-411
• /
• 2013

The quality of the products/processes has been improved remarkably since robust design (RD) methodology is applied into the practice manufacturing processes. A model building method based on the dual responses methods for multiple and time oriented responses on a drug development process is employed in this paper instead of the previous methods that handle the static nature of data and single response. Subsequently, the optimal solutions of a multiple and time series RD problem are obtained by using the proposed augmented weighted Tchebycheff method that has a significant flexibility on assigning weights. Finally, a pharmaceutical case study associated with a generic drug development process is conducted in order to illustrate the efficient optimal solutions from the proposed model.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 추계학술대회 논문집 학회본부 D
• /
• pp.806-808
• /
• 2000

We propose a new Dynamic Multilayer Perceptorn(DMP) architecture for optimal model identification of complex and nonlinear system in this paper. The proposed DMP scheme is presented as the generic and advanced type based on the GMDH(Group Method of Data Handling) method for the limitation of GMDH under only two system input variables. It is worth stressing that the number of the layers and the nodes in each layer of the DMP are not predetermined, unlike in the case of the popular multilayer perceptron structure, but these are generated in a dynamic manner. The experimental part of the study comes with representative nonlinear static system. Comparative analysis is included and shows that a new DMP can produce the model with higher accuracy than previous other works.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 춘계종합학술대회
• /
• pp.134-138
• /
• 2002

The human faces do not have distinct features unlike other general objects. In general the features of eyes, nose and mouth which are first recognized when human being see the face are defined. These features have different characteristics depending on different human face. In this paper, We propose a face recognition algorithm using the hidden Markov model(HMM). In the preprocessing stage, we find edges of a face using the locally adaptive threshold scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability values calculated by the HMM to input data. Then the input face is recognized by the euclidean distance of face feature vector and the cross-correlation between the input image and the database image. Computer simulation shows that the proposed HMM algorithm gives higher recognition rate compared with conventional face recognition algorithms.

• 전자공학회논문지B
• /
• 제33B권9호
• /
• pp.97-106
• /
• 1996

In this paper, we propose a face recognition algorithm using the hidden markov model and neural networks (HMM-NN). In the preprocessing stage, we find edges of a face using the locally adaptive threshold (LAT) scheme and extract features based on generic knowledge of a face, then construct a database with extracted features. In the training stage, we generate HMM parameters for each person by using the forward-backward algorithm. In the recognition stage, we apply probability vlaues calculated by the HMM to subsequent neural networks (NN) as input data. Computer simulation shows that the proposed HMM-NN algorithm gives higher recognition rate compared with conventional face recognition algorithms.

• 한국해안해양공학회지
• /
• 제16권4
• /
• pp.241-257
• /
• 2004

전구해양순환모형인 Bryan-Cox-Semtner모형에서 파생된 NCAR의 NCOM모형을 이용하여 한반도 주변해역의 해수순환을 가능한 세밀하게 해상시킨 예단적 전구해양순환모형을 수립하였다. 모형영역은 남북방향으로 $80.6{^\circ}S~88.6{^\circ}N$의 범위로서 북극해가 제외되었으며, 한반도 주변이 약 $0.3^\circ$로 해상된 수평 가변격자와 연직방향으로 15층으로 구성하였다. 섬 주변해안의 순환을 적절히 재현하기 위한 구멍완화법(Hole-relaxation method)을 적용하여 22개의 섬처리가 고려되었으며, NCAR에서 CSM(Climate System Model)운용을 위해 300년동안 spin-up 계산된 결과를 초기자료로 하고, Choi et al.(2002)의 접합 대기해양모형의 결과로부터 얻은 바람응력자료가 사용되었다. 모형결과로부터, 전구와 북서태평양 해역의 순환패턴을 살펴보았으며, 한반도 주변의 5개해협에서의 용적수송량을 Choi et al.(2002)의 결과 및 관측치와 비교하였다.

• Nuclear Engineering and Technology
• /
• 제50권1호
• /
• pp.88-96
• /
• 2018

Concerns over reliability assessments of the main components in nuclear power plants (NPPs) related to aging and continuous operation have increased. The conventional reliability assessment for main components uses experimental correlations under general conditions. Most NPPs have been operating in Korea for a long time, and it is predictable that NPPs operating for the same number of years would show varying extent of aging and degradation. The conventional reliability assessment does not adequately reflect the characteristics of an individual plant. Therefore, the reliability of individual components and an individual plant was estimated according to operating data and conditions. It is essential to reflect aging as a characteristic of individual NPPs, and this is performed through prognostics. To handle this difficulty, in this paper, the general path model/Bayes, a data-based prognostic method, was used to update the reliability estimated from the generic database. As a case study, the authors consider the aging for steam generator tubes in NPPs and demonstrate the suggested methodology with data obtained from the probabilistic algorithm for the steam generator tube assessment program.

• 한국정보처리학회논문지
• /
• 제5권6호
• /
• pp.1431-1440
• /
• 1998

동영상 정보는 자료의 양이 방대하고 다양하여 압축된 형태로 저장하고 검색하는 것이 매우 중요하다. 본 논문에서는 동영상 문서의 구조를 추출하고 동영상 스트림의 인데싱에 대한 의미를 부여할 수 있는 일반적인 데이터 모델을 제시하고, 이 모델을 이용하여 MPEG-2로 압축된 동영상 자료를 데이터베이스에 저장하고 검색하는 MPEG-2 압축 동영상 정보 관리 시스템(CVIMS, Compressed Video Information Management System)을 제안한다. CVIMS는 MPEG-2 파일에서 I-프레임들을 추출하고, 그 중에서 키 프레임(대표 이미지)을 선택한 후, 선택된 키 프레임에 대한 축소그림(thumbnail)과 캡션 및 그림 설명 정보를 데이터베이스에 저장한다. 그리고 데이터베이스에 저장된 MPEG-2 동영상을 질의어나 키 프레임을 통해 검색한다.

• 설비공학논문집
• /
• 제7권2호
• /
• pp.184-195
• /
• 1995

A theoretical one-dimensional model for the charging process in stratified thermal storage tanks is established presuming that the fluid ensuing from the tank inlet creates a perfectly mixed, layer above the thermocline. Both the generic and asymptotic closed-form solutions are obtained via the Laplace transformation. The asymptotic solution describes the nature of the charging pertaining to the case of no thermal diffusion, whereas the generic solution is of practical importance to understand the role of operating parameters on the stratification. The present model is validated through comparison with available experimental data, where they agree well with each other within a reasonable limit. An interpretation of the exact solution entails two important features associated with the charging process. The first is that an in-crease in the mixing depth $h_m$ causes a relatively slow temperature rise in the perfectly mixed region, but on the other hand it results in a faster decay of the overall temperature gradient across the thermocline. Next is the predominance of the mixing depth in the presence of the prefectly mixed region. In such a case the effect of the Peclet number is marginal and there-fore the thermal characteristics are solely dependent on the mixing depth paticularly for large $h_m$. The Peclet number affects significantly only for the case without mixing. Variation of the storage efficiency in response to the change in the mass flow rate agrees favorably with the published experimental results, which confirms the utility of the present study.