• 인터넷정보학회논문지
• /
• 제5권4호
• /
• pp.115-124
• /
• 2004

본 논문에서는 가중 퍼지 페트리네트에 기반을 둔 규칙기반시스템을 위한 가중 퍼지 후진추론 알고리즘을 제안한다. 규칙기반시스템에 있는 퍼지 생성규칙은 가중 퍼지 페트리네트로 모형화된다. 여기에서 퍼지 생성규칙에 나타나는 퍼지 명제의 진리값과 규칙의 확신도는 퍼지 숫자로 표현한다. 그리고 규칙에 나타나는 퍼지 명제의 가중값도 퍼지 숫자로 표현하다. 제안한 가중 퍼지 후진추론 알고리즘은 목표노드에서 초기노드까지 후진추론 통로를 생성한 후 목표노드의 확신도를 계산한다. 우리가 제안한 알고리즘은 규칙기반시스템이 더 유연하고 사람과 같은 방법으로 가중 퍼지 후진추론을 하는 것을 가능하게 한다.

• Corrosion Science and Technology
• /
• 제7권4호
• /
• pp.219-223
• /
• 2008

In 2006, as a means to minimize early corrosion failure of ships, thus to enhance marine safety, International Maritime Organization (IMO), proposed a mandatory regulation for Performance Standards for the Protective Coatings (PSPC) for ballast tanks of newly built ships to satisfy 15 years of target useful life. In this regulation, several unprecedented strict rules are adopted as minimum, mandatory requirements for protective coatings of ship's water ballast tanks, and all type of ships sailing international sea are subjected to this regulation which is to be effective as early as June of 2008. The PSPC addresses many technical issues in the areas of surface pretreatment (primary and secondary), coating materials, coating application procedure and inspection as well as necessary documentation. The PSPC rules are new and unproven concepts, which calls for rigorous incorporation of reality-based evidences currently available, since there are no practical experiences in terms of the validity of the PSPC rules. There has been much controversy surrounding these regulations and considerable effort has been made by both shipyards and ship owners alike to achieve a performance standard for ballast tank coatings, which is acceptable to all. In this paper, the background and overview of the PSPC rules are given, and several issues in the PSPC are reviewed as a base to achieve robustness of the proposed PSPC, which will serve as a means to minimize early corrosion and to ensure 15 year target useful life of ships.

• 한국정보과학회논문지:데이타베이스
• /
• 제34권3호
• /
• pp.179-192
• /
• 2007

본 논문에서는 주식 데이타베이스로부터 과거 주가 변화 패턴에 대한 규칙을 탐사함으로써 투자자에게 주식 투자 유형을 추천해 주는 방안에 관하여 논의한다. 먼저, 본 논문에서는 주식 투자 유형의 추천을 위한 새로운 규칙 모델을 정의한다. 제안된 모델에서는 빈번하게 발생하는 주가 변화 패턴의 이후의 주가 변화 경향이 투자자의 투자 조건과 매치하는 경우, 이 종목에 대한 투자 유형을 추천하도록 하는 방식을 사용한다. 이때, 빈번하게 발생하는 패턴을 규칙의 헤드로 간주하며, 이후의 주가 변화 경향을 규칙의 바디로 간주한다. 본 연구에서는 규칙 헤드는 투자자의 특성에 별다른 영향을 받지 않는 반면, 규칙 바디에 대한 조건은 투자자마다 다르다는 점에 착안하여 규칙 탐사 과정에서 전체 규칙이 아닌 규칙 헤드들만을 탐사하여 저장해 두는 새로운 방식을 제안한다. 이 결과, 투자자 별로 달라질 수 있는 규칙 바디에 대한 조건을 유연하게 정의하는 것을 허용하며, 규칙의 수를 줄임으로써 전체 규칙 탐사 성능을 개선할 수 있다. 효율적인 규칙 탐사와 매칭을 위하여 빈번 패턴들을 효과적으로 탐사하는 방법, 빈번 패턴 베이스를 구축하는 방법, 그리고 이들을 인덱싱 하는 방법을 제안한다. 또한, 투자자의 질의가 발생하는 경우, 빈번 패턴 베이스로부터 이와 매치되는 규칙을 발견하고, 이 결과를 이용하여 투자자에게 투자 유형을 추천해 주는 방법을 제안한다. 실제 주식 데이타를 이용한 다양한 실험을 통하여 제안된 기법의 우수성을 규명한다.

• 품질경영학회지
• /
• 제18권2호
• /
• pp.18-24
• /
• 1990

The location of inspection stations is a significant component of production systems. In this paper, a prototype expert system is designed for deciding the optimal location of inspection stations. The production system is defined as a single channel of n serial operation stations. The potential inspection station can be located after any of the operation stations. Nonconforming units are generated from a compound binomial distribution with known parameters at any given operation station. Traditionally Dynamic programming, Zero-one integer programming, or Non-linear programming techniques are used to solve this problem. However a problem with these techniques is that the computation time becomes prohibitively large when t be number of potential inspection stations are fifteen or more. An expert system has the potential to solve this problem using a rule-based system to determine the near optimal location of inspection stations. This prototype expert system is divided into a static database, a dynamic database and a knowledge base. Based on defined production systems, the sophisticated rules are generated by the simulator as a part of the knowledge base. A generate-and-test inference mechanism is utilized to search the solution space by applying appropriate symbolic and quantitative rules based on input data. The goal of the system is to determine the location of inspection stations while minimizing total cost.

• 한국도서관정보학회지
• /
• 제21권
• /
• pp.459-483
• /
• 1994

The purpose of the study is to design and implement a prototype expert system for library classification in the literature field of the DDC 20. The system was largely consisted of a knowledge base, an inference engine, a knowledge acquisition facility, an explanation facility and an user interface facility. The knowledge base was represented by inference rules and frames. The name file for authors and titles was designed separately. The forward chaining technique was chosen for the inference engine and the menu-driven dialog technique was also taken for the user interface. The conclusions of the study can be summarized as follows: 1) The difficulty of document classification work is due to the complex and stringent classification rules. Such problems can be considerably alleviated by using the present system. 2) Even the novice with a knowledge about the DDC 20 can easily access the system. And also librarian other than the professional classifier can easily be accustomed to the classification work. 3) The system can be used as an online classification scheme. 4) By adding any local language other than English or Hangeul on the menu screen, the language problem relating classification can be overcome. 5) The system can be employed as the intensification tool for the education of classification as well as library automation.

• 대한산업공학회지
• /
• 제19권2호
• /
• pp.83-93
• /
• 1993

Conventional computer programs developed and used by practicing engineers can be considered to contain expert knowledge and design experience. If these conventional programs are converted into expert systems, the difficult and time consuming process of knowledge acquisition can be simplified. Also the constructed knowledge-base can have higher confidence level than that constructed by the usual knowledge acquisition method of interviews. An existing computer program which is being used by ship structural designers has been reformulated as a design expert system by applying an expert system development shell-Nexpert. Utilizing the callable interface provided by the development shell, external design tools have also been integrated. The interfaced external functions are a graphical user interface (GUI) for the design process control, and graphics functions for the visualization of design results. It is observed that the developed system for design support is useful in two aspects. The trace-back function shows what portion of design rules are applied in arriving at certain design decisions. Also the knowledge-base can be conveniently updated as design rules of the classification societies are updated.

• 전력전자학회논문지
• /
• 제20권5호
• /
• pp.421-428
• /
• 2015

An advanced direct torque control (DTC) with pulse width modulation (PWM) method is presented in this paper. The duty ratio calculation of the selected voltage vector is based on the voltage functions of the selected voltage vector according to the sector angle. The proposed DTC uses a conventional DTC scheme with six sector divisions and switching rules. However, the winding voltages are supplied by the PWM approach. Furthermore, the duty ratio of the switching voltage vector is determined by the flux, torque error, and motor speed. The base voltage that shall determine the duty ratio can be calculated by approximate voltage functions according to the voltage angle. For the calculation of base voltages, second-order quadratic functions are used to express the output voltage of the selected voltage vector according to voltage angle. The coefficients for the second-order quadratic functions are selected by the voltage vector, which is determined by the switching rules of the DTC. In addition, the voltage functions are calculated by the coefficients and voltage angle between the voltage vector and rotor position. The switching voltages from the calculated duty ratio can supply the proper torque and flux to reduce the ripple and error. The proposed control scheme is verified through practical experimental comparisons.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2005년도 춘계학술대회
• /
• pp.316-320
• /
• 2005

We developed Intelligent Product Search Agent based on SWRL, and this agent can search product information with knowledge(facts and rules) on the web, implement price comparison for searched products considering delivery rates. Existing keyword based product search engines is poor at searching intent products though a user has already prefect knowledge about intent produces. Furthermore if a user has insufficient knowledge, it is impossible to implement search. Also, existing price comparison shopping mall gives users comparison service considering total price(product prices, taxes, delivery rates), this service is valid to single product and has limitations of system expansion and up-dating because of not rule base but programming base. If there is appropriate knowledge on the Semantic web and this makes product information retrieval possible, above problems can be solved clearly. In this research, we developed Intelligent Product Search Agent based on SWRL that can search product information efficiently by making agent to handle facts and rules by itself.

• 한국멀티미디어학회논문지
• /
• 제7권4호
• /
• pp.559-566
• /
• 2004

일반적으로 퍼지 생성규칙의 확신도와 규칙에 나타나는 퍼지 명제의 확신도는 0과 1사이의 실수로 표현한다. 만일 퍼지 생성규칙의 확신도와 퍼지 명제의 확신도를 구간값 퍼지 집합으로 표현한다면, 규칙기반시스템이 더 유연한 방법으로 퍼지 추론을 하는 것이 가능하게 된다. 본 논문에서는 퍼지 페트리네트와 이 네트에 기반을 둔 규칙 기반시스템을 위한 구간값 퍼지 집합 후진추론 알고리즘을 제안한다. 규칙 기반시스템에 있는 퍼지 생성규칙은 퍼지 페트리네트로 모형화된다. 여기에서 퍼지 생성규칙에 나타나는 퍼지 명제의 확신도와 규칙의 확신도는 구간값 퍼지 집합으로 표현한다. 여기에서 제안한 알고리즘은 목표노드에서 시작노드까지 후진추론 통로를 찾아낸 후 목표노드의 확신도를 계산한다. 구간값 퍼지 집합 후진추론 알고리즘은 규칙 기반 시스템이 더 유연하고 사람들이 하는 것과 같은 퍼지 후진추론을 가능하게 한다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권5호
• /
• pp.625-631
• /
• 2004

일반적으로 퍼지 생성규칙의 확신도와 규칙에 나타나는 퍼지 명제의 확신도는 0과 1사이의 실수로 표현한다. 만일 퍼지 생성규칙의 확신도와 퍼지 명제의 확신도를 구간 값 퍼지 집합으로 표현한다면, 규칙기반시스템이 더 유연한 방법으로 퍼지 추론을 하는 것이 가능하게 된다[15］. 본 논문에서는 퍼지 페트리네트와 이 네트에 기반을 둔 규칙기반시스템을 위한 구간 값 퍼지 집합 추론 알고리즘을 제안한다. 규칙기반시스템에 있는 퍼지 생성규칙은 퍼지 페트리네트로 모형화 된다. 여기에서 퍼지 생성규칙에 나타나는 퍼지 명제의 확신도와 규칙의 확신도는 구간 값 퍼지 집합으로 표현한다. 제안한 구간 값 퍼지집합 추론알고리즘은 규칙기반시스템에서 더 유연한 퍼지추론을 하는 것을 가능하게 한다.