• Journal of Power Electronics
• /
• 제9권3호
• /
• pp.403-409
• /
• 2009

Automatically tuned passive filters can improve power quality to a great extent in power systems. A novel three-phase shunt auto-tuned filter is designed to effectively compensate source current harmonics and to provide reactive power required by the non-linear load, which draws a highly reactive, harmonic-rich current from the supply. An artificial neural network (ANN) based controller selects filter component values in accordance with reactive power requirement and harmonic compensation. Traditional passive filters are permanently connected to the system and draw large amounts of source current even under light load conditions. By using auto-tuned filters, the passive filter components can be controlled according to load variations and, hence, draw only required source currents. The selection is done by the ANN with the help of a properly tuned knowledge base to provide instantaneous compensation using a digital controller.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2018년도 제30회 한글 및 한국어 정보처리 학술대회
• /
• pp.465-469
• /
• 2018

본 논문에서는 지식베이스 완성을 위한 새로운 모델, KBCNN을 소개한다. KBCNN 모델은 CNN을 기반으로 지식베이스의 개체들과 관계들 사이의 연관성을 포착한다. KBCNN에서 각 트리플 <주어 개체, 관계, 목적어 개체>는 3개의 열을 가진 행렬로 표현되며, 각각의 열은 트리플의 각 원소를 표현하는 임베딩 벡터다. 트리플을 나타내는 행렬은 여러 개의 필터를 가지고 있는 컨볼루션 레이어를 통과한 뒤, 하나의 특성 벡터로 합쳐진다. 이 특성 벡터를 가중치 행렬과 내적 하여 최종적으로 해당 트리플의 신뢰도를 출력하게 된다. 이 신뢰도를 바탕으로 트리플의 진실 여부를 가려낼 수 있다. 지식베이스 완성 연구에서 가장 많이 사용되는 데이터셋인 FB15k-237을 기반으로 한 실험을 통해 KBCNN 모델이 기존 임베딩 모델들보다 뛰어난 성능을 보이는 것을 확인하였다.

• 한국시뮬레이션학회논문지
• /
• 제5권2호
• /
• pp.25-40
• /
• 1996

Modeling of systems for intensive knowledge-based processing requires a modeling methodology that makes efficient access to the information in huge data base models. The proposed level access mothodology is a modeling approach applicable to systems where data is stored in a hierarchical and modular modules of active memory cells(processor/memory pairs). It significantly reduces the effort required to create discrete event simulation models constructed in hierarchical, modular fashion for above application. Level access mothodology achieves parallel access to models within the modular, hierarchical modules(clusters) by broadcasting the desired operations(e.g. querying information, storing data and so on) to all the cells below a certain desired hierarchical level. Level access methodology exploits the capabilities of object-oriented programming to provide a flexible communication paradigm that combines port-to-port coupling with name-directed massaging. Several examples are given to illustrate the utility of the methodology.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2000년도 춘계학술대회
• /
• pp.339-349
• /
• 2000

Inchon Port is the second largest import-export port of Korea, and has the point at issue such as the excessive logistics cost because of the limits of handling capacity and the chronic demurrage. There are few research activities on the analysis and improvement of the whole port operation, because Inchon Port not only has the dual dock system and various facilities but also handles a various kind of cargo. The purpose of this paper is to develop the simulation program as a long-term strategic support tool, considering the dual dock system and the TU(Terminal Operation Company) system executed since March, 1997 in Inchon Port. The basic input parameters such as arrival intervals, cargo tons, service rates are analyzed and the probability density functions for these parameters are estimated. The main mechanism of simulation model is the discrete event-driven simulation and the next-event time advancing. The program is executed based on the knowledge base and database. From the simulation model, it is possible to estimate the demurrage status through analyzing various scenarios and to establish the long-term port strategic plan.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.570-575
• /
• 1993

화학 공정에서의 이상 진단 시스템 개발 및 응용에 대한 연구는 지난 5년간 많은 발전이 이루어졌다. 화학 공정의 본질적인 특성으로 대형 시스템, 비선형 특성, 모델링 자체의 어려움, 공정 변수의 large dead time 및 복잡한 인과 관계등을 들수 있으며, 이러한 어려움에도 불구하고 적절한 이상 진단 시스템의 중요성을 인식하여, 초기에는 주로 rule-based approach가 도입되어 현장에서의 조업에 많은 도움을 주었었다. 그러나 개발 기간의 단축화, 개발 과정의 표준화 뿐 아니라 개발된 시스템 자체의 일관성 등을 위하여 체계적인 접근 방법이 필요하게 되었으며, 그중 지식 베이스 합성 문제는 그 동안 활발하게 연구되어 오고 있는 분야이다. 이에 본 연구에서는 기호화된 정성적인 정보를 얻기위한 기존의 실험 방법의 한계를 극복하고자 동적 모사를 이용하여 정량적인 정보로부터 정성적인 정보를 생성시키는 방법론에 대해 연구하였다. CSTR(Continuous Stirred Tank Reactor)에서 나타날수 있는 이상의 종류에 대한 동적 모사를 수행하여 이상 진단 시스템을 위한 지식이 생성되는 과정을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.445-448
• /
• 1996

For a lightly damped system, IIR based filter can have better performance than FIR filter as an adaptive filter in ANC algorithm. IIR based filter which has an infinite impulse response can model a lightly damped acoustic system with a small number of weights compared that of FIR filter and has no nonlinearity and instability problems on weight updating process which are associated to the conventional IIR filters. There are, however, some drawbacks such as design parameters to be determined earlier to get better performance and much increased computational power especially in the presence of error path. In this study, base filter parameters are determined in systematic manner, with the knowledge of the nominal impulse response of the system which should be identified, by Prony's method. Three methods reducing the computational load are proposed and their performance and application limits are discussed. Simulation and experimental results demonstrate the feasibility of the proposed method.

• 한국정보시스템학회지:정보시스템연구
• /
• 제3권
• /
• pp.147-169
• /
• 1994

This paper present s a pattern generation scheme from financial charts. The patterns constitute knowledge which consists of patterns as the conditional part and the impact of the pattern as the conclusion part. The patterns in charts are represented in a syntactic approach. If the pattern elements and the impact of patterns are defined, the patterns are synthesized from simple to the more highly credible by evaluating each intermediate pattern from the instances. The overall process is divided into primitive discovery by Genetic Algorithms and pattern synthesis from the discovered primitives by the Syntactic Pattern-based Inductive Learning (SYNPLE) algorithm which we have developed. We have applied the scheme to a chart : the trend lines of stock price in daily base. The scheme can generate very credible patterns from training data sets.

• 한국CDE학회논문집
• /
• 제2권1호
• /
• pp.1-10
• /
• 1997

Finding the optimum route of ship's pipes is complicated and time-consuming process. Experience of designers is the main tool in this process. To reduce design man-hours and human errors a design expert system shell and a geometric modeler is used to automate the design process. In this paper, a framework of the intelligent CAD system for pipe auto-routing is suggested, which consists of general-purpose expert system shell and a geometric modeler. The design expert system and the geometric modeling kernel have been integrated. The CADDS5 of Computervision is used as the overall CAD environment. The Nexpert Object of Neuron Data is used as the expert system shell. The CADDS5 ISSM is used as the interface that creates and modifies geometric models of pipes. Existing algorithms for the routing problem have been analyzed. Most of them are to solve the 2-D circuit routing problems. Ship piping system, specially within the engine room, is a complicated, large scale 3-D routing problem. Methods of expert system have been used to find the route of ship pipes on the main deck.

• 한국주거학회논문집
• /
• 제16권5호
• /
• pp.39-48
• /
• 2005

The purpose of this study was to analyze environment-behavior concepts included in environmental design characteristics of facilities for elderly with dementia. Major method was contents analysis of actual environmental designs. For comparison between the environment-behavior concepts and actual cases, an analytical framework was developed. Eleven cases of facilities designed for people with dementia were analyzed. Those were published ones in periodicals in USA. The analytical data used included floor plans, texts, and visual materials including photographs. Under the framework for analysis, a total of 296 criteria were used to analyze the actual cases of environmental design. This study was expected to offer a knowledge base for better environmental design for elderly with dementia and to help establish guidelines for designing such facilities which can meet the cultural characteristics and traditional conditions of Korea.

• 한국지능시스템학회논문지
• /
• 제5권3호
• /
• pp.52-63
• /
• 1995

A neuro-fuzzy algorithm is presented for nuclear reactor power control in a pressurized water reactor. Automatic reacotr power control is complicated by the use of control rods because of highly nonlinear dynamics in the axial power shape. Thus, manual shaped controls are usually employed even for the limited capability during the power maneuvers. In an attempt to achieve automatic shape control, a neuro-fuzzy approach is considered because fuzzy algorithms are good at various aspects of operator's knowledge representation while neural networks are efficinet structures capable of learning from experience and adaptation to a changing nuclear core state. In the proposed neuro-fuzzy control scheme, the rule base is formulated based ona multi-input multi-output system and the dynamic back-propagation is used for learning. The neuro-fuzzy powere control algorithm has been tested using simulation fesponses of a Korean standard pressurized water reactor. The results illustrate that the proposed control algorithm would be a parctical strategy for automatic nuclear reactor power control.