• 한국정보통신학회논문지
• /
• 제12권1호
• /
• pp.122-129
• /
• 2008

기동 시나 갑작스런 토크명령 변동에 빠른 토크응답 특성을 갖는 퍼지 논리 제어기를 이용한 농형 유도 전동기의 직접 토크제어 방식을 제안하였다. 퍼지 제어 알고리즘은 기존의 DSC(Direct Self Controller) 제어 원리를 기저로 하여 제안하였으며 퍼지 추론 및 비 퍼지화를 거쳐 수행된다. 유도전동기의 자속과 토크는 광범위한 속도 영역에서 비 간섭 및 우수한 동특성을 갖는 회전자 자속 기준 동특성 모델을 사용하였다. 실험 결과 제시한 퍼지 제어 알고리즘은 우수한 동특성 및 적응적 특성을 갖으며 전동기 변수와 동작 조건의 변동에 민감하지 않고 강인하다.

• 대한전자공학회논문지
• /
• 제27권6호
• /
• pp.954-962
• /
• 1990

Experties of recognizing an object despite of every possible occlusions among objects is difficult to be provided directly to a system. In this paper, we propose a method for inferring inherent shape-characteirstics of an object from training views provided. The method learns rules incrementally by alternating the rule induction process from limited number of training views and the rule verification process from the following taining views. The learned rules are represented using logical expressions to enhance the readability. Thr proposed method is tested by simulating occlusions on 2-dimensional objects to examine the learning process and to show improvement of recognition rate. Thr result shows that it can be applied to a practical system for 3-dimensional object recognition.

• 한국정보과학회논문지:데이타베이스
• /
• 제29권4호
• /
• pp.311-320
• /
• 2002

래퍼(wrapper)는 미리 입력된 추출 규칙을 바탕으로 특정 정보 소스에서 원하는 정보를 추출, 가공하는 모듈이다. HTML-XML 래퍼(HTML Wrapper for XML)는 HTML로 이루어진 웹 정보에서 특정 정보를 XML 문서 형태로 추출한다. 사람이 추출 규칙을 직접 작성하는 일은 단순 반복적이고 지루한 일이므로, 최소의 노력으로 쉽고 빠르게 이를 생성할 수 있어야 한다. 본 논문에서는 기존의 스크립팅 방식에 GUI를 통한 학습 추론 방법을 통합하여 추출 규칙 생성 작업을 최소화 하는 방법을 제시한다.

• 한국산업정보학회논문지
• /
• 제20권3호
• /
• pp.61-69
• /
• 2015

본 논문에서는 이산 웨이블릿 변환을 통해 추출된 시간 영역과 주파수 영역의 특징들을 활용하여 심박수변이도를 확률적인 지식으로 분석할 수 있는 방법을 제안하였다. 제안된 방법에서 지식획득 알고리즘은 규칙생성과 규칙평가 단계로 구성되어 있으며, 규칙생성에서는 ROC 분석을 통해 수치적인 속성값을 이산화된 구간으로 변환하고, 서로 다른 의사결정값을 포함하는 구간들 사이에 일관성 정도를 비교함으로써 감축된 규칙-집합을 생성한다. 이때 규칙-집합 내에 각 규칙에 대해서 확률적 해석을 위한 3가지 척도를 추정하였다. 제안된 모형의 효과성은 심혈관질환 병력을 가진 58명의 심전도 데이터로부터 심방세동을 식별할 수 있는 5가지 규칙을 생성하였고, 이들 규칙의 분별력을 평가하였다. 실험결과, 제안된 모형으로부터 생성된 지식은 4가지 성능평가 척도에 대해서 각각 93%의 정확도를 보여주었다.

• 한국경영과학회지
• /
• 제30권4호
• /
• pp.117-130
• /
• 2005

It is effective and desirable for a proper customer relationship management or marketing to focus on the specific customers rather than a number of non specific customers. This study forecasts the prospective purchasers with high probability to purchase a specific product. Artificial Neural Network( ANN) can classily the characteristics of the prospective purchasers but ANN has a limitation in comprehending of outputs. ANN is integrated into IRANN with IR of decision tree program C5.0 to comprehend and analyze the outputs of ANN. We compare and analyze the accuracy of ANN, IR, and IRANN each other.

• 대한기계학회논문집A
• /
• 제29권4호
• /
• pp.518-525
• /
• 2005

The electromagnetic noise generates when natural frequencies of a stator core with wingdings and frame coincide with or approach natural frequencies of the magnetic motive force. In order to suppress such noise, the estimation of natural frequencies of the motor is important at the design stage. However, the natural frequency analysis is not so easy because motor stator is in the laminated plate structure and windings are composed of wires, insulation sheets and vanishs. Thus the accurate prediction of the equivalent material properties of windings becomes an essential task. In this paper, we derive the equivalent material properties using homogenization methods.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 1998년도 Proceedings ICPE 98 1998 International Conference on Power Electronics
• /
• pp.7-10
• /
• 1998

Because of simple control algorithm and easy implementation, the conventional PI controller has been widely used in industrial application. But, it is very difficult to find the optimal PI control gain. Therefore, in improperly tuned PI controller or parameter variation, to obtain optimal performance, the novel PI controller, which consist of conventional PI controller and 4-rule based fuzzy logic, are presented in this paper. The novel PI controller which exhibits a stabilizing effects on the closed-loop system, has good robustness regarding the improperly tuned PI controller or parameter variation. The simulations are performed to verify the capability of proposed control method on induction motor.

• 한국수학사학회지
• /
• 제31권3호
• /
• pp.151-166
• /
• 2018

The rule of the game of Chomp is simple and the existence of a winning strategy can easily be proved. However, the existence tells us nothing about what strategies are winning in reality. Like in Chess or Baduk, many researchers studied the winning moves using computer programs, but no general patterns for the winning actions have not been found. In the paper, we aim to construct practical winning strategies based on backward induction. To do this we develop how to analyze Chomp and prove and find the winning strategies of the simple games of Chomp.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 F
• /
• pp.2012-2014
• /
• 1998

The conventional PI controller has been widely used in industrial applications. If a PI control gain is selected suitable, the PI controller shows very good control performance. But it is very difficult to find the optimal PI control gain. Therefore, in this paper, the 4-rule based fuzzy logic modifier of the conventional PI controller are presented. The fuzzy logic modifier which exhibits a stabilizing effects on the closed-loop system, has good robustness regarding the improperly tuned PI controller. The simulation are performed to verify the capability of proposed control method on vector controlled induction motor drive system.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2003년도 학술대회논문집
• /
• pp.69-76
• /
• 2003

In this paper, a novel speed control system that implements the fuzzy logic controller(FLC) is proposed. Fuzzy controller is shown more excellent efficency than a conventional controllers in the strength aspect and non-linear controller using IF-THEN rule which can control without process the accurate mathematical modeling about induction motor. But we cannot expect that conventional fuzzy controller divide equally the space of input and output parameter and use the certain shape of triangle membership function. Therefore to develop the efficiency of conventional fuzzy controller, We need to scale the range of membership functions. In this study, proposed fuzzy controller has the ability controlling scale of membership functions using by output scaling factor.