• Journal of Advanced Marine Engineering and Technology
• /
• 제30권2호
• /
• pp.253-259
• /
• 2006

There is few study which automatically diagnoses the fault from ship's monitored data. The bigger control and monitoring system is. the more important fault diagnosis and maintenance is to reduce damage caused by system fault. This paper proposes fault diagnosis system using a correlation analysis algorithm which is able to diagnose and forecast the fault from monitored data and is composed of fault detection knowledge base and fault diagnosis knowledge base. For all kinds of ship's engine room monitored data are classified with combustion subsystem, heat exchange subsystem and electric motor and pump subsystem, To verify capability of fault detection, diagnosis and prediction, FMS(Fault Management System) is developed by C++. Simulation by FMS is carried out with population data set made by the log book data of 2 months duration from a large full container ship of H shipping company.

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2005년도 전기학술대회논문집
• /
• pp.251-256
• /
• 2005

There is few study which automatically diagnose the fault from ship's monitored signal. The bigger control and monitoring system is, the more important fault diagnosis and maintenance is to reduce damage brought forth by system fault. This paper proposes fault diagnosis system using a correlation analysis algorithm which is able to diagnose and forecast the fault and is composed to fault detection knowledge base and fault diagnosis knowledge base. For this all kinds of ship's engine room monitored data are classified with combustion subsystem, heat exchange subsystem and electric motor and pump subsystem by analyzing ship's operation data. To verifying capability of fault detection, diagnosis and prediction, Fault Management System(FMS) is developed by C++. Simulation experiment by FMS is carried out with population data set made by log book data of 2 months duration from a large full container ship of H shipping company.

• 한국국방경영분석학회지
• /
• 제24권1호
• /
• pp.88-97
• /
• 1998

It is critical to determine the appropriate actions for safe landing of an aircraft in an emergency situation. An expert system can be very useful for this purpose. An expert system specifically for jet fighter $F-\bigcirc\bigcirc$ has been developed. Its knowledge base contains the standard procedures provided by various flight manuals and the expertise of human specialists such as pilots and emergency management personnels. Advising procedures are represented by an IF-THEN format in the developed rule-based expert system. Advises are provided in real time during the entire flight processes of ground, takeoff, inflight, and landing. The developed system would significantly increase the survivability of pilots and aircraft, while decreasing operational costs of emergency management personnels. By modifying the knowledge base, the developed system can also be applied to other types of aircrafts including civilian airlines.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.632-635
• /
• 2002

There are more than five dozen different RP(rapid prototyping) systems in the world and they are fairly expensive. All those systems have different capabilities and requirements in that each of them gives different tolerance, application field and part strength, etc. This situation may cause a problem of selecting an appropriate RP system. This paper presents an expert system, utilizing an algorithm that is composed up of rules to derive recommendations and answers to queries of the RP users. The expert system incorporates RP machines commercially available and adopts multi-selection criteria, namely, machine price, accuracy, build size, adopted process, etc. In the expert system, forward reasoning method is adopted and external spreadsheet for sub-data of the RP systems is used. The rules and knowledge are obtained from interviews and discussions with RP vendors and users, appropriate research publications and other reference materials.

• 산업공학
• /
• 제7권3호
• /
• pp.125-135
• /
• 1994

This thesis reports the development of a Computer-Aided Process Planning system for rotational parts. The developed system ultimately generates process plans for rotational parts through a knowledge-base. The knowledge-base and decision-making algorithms are represented by Pascal computer programming language. We have developed a process planning system which adjusts the sequence of processes by itself to ensure the quality of the parts. This system generates more detailed job sequence and descriptions than other well-known process planning systems. We present realistic and efficient process plans through the integration of process planning and scheduling. This system optimizes flow time of parts by decreasing the number of machine set-ups.

• 한국전자거래학회지
• /
• 제6권3호
• /
• pp.63-80
• /
• 2001

The construction of the students knowledge in e-Learning systems, namely the student modeling, is a core component used to develop e-Learning systems. However, existing e-Learning systems have many problems to share the knowledge in a heterogeneous student model and a distributed knowledge base. Because the methods of the knowledge representation are different in each e-Learning systems, the accumulated knowledge cannot be used or shared without a great deal of difficulty. In order to share this knowledge, existing systems must reconstruct the knowledge bases. Consequently, we propose a new a Case Markup Language based on XML in order to overcome these problems. A distributed e-Learning systems fan have the advantage of easily sharing and managing the heterogeneous knowledge base proposed by CaseML. Moreover students can generate and share a case knowledge to use the communication protocol of agents. In this paper, we have designed and developed a CaseML by using a knowledge markup language. Furthermore, in order to construct an intelligent e-Learning systems, we have done our research based on the design and development of the intelligent agent system by using CaseML.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -3
• /
• pp.1764-1767
• /
• 2002

Recent explosive increases in information 'volume have led to a rapid development or a change of information technology which stores, searches, and manages a vast amount of information. It is considered that an effective share and utilization of a large amount of digital information produced by work performances is a pivotal element which can make decisive contributions to a great success of business management. This common property of information reflects a changing social paradigm including a change of business processes. This paper is aimed at designing and embodying the construction of knowledge base in an efficient project management system using unsupervised data mining techniques in order to extract information and utilize it as knowledge about standard data (statistical data, template etc.,), size prediction and a danger precaution notice which are needed for a plan and a scheduling of a new project from data coming from already-established projects.

• 전자공학회논문지B
• /
• 제29B권1호
• /
• pp.18-25
• /
• 1992

In this paper, a rule checker which aids in composing a consistent knowledge base by checking redundancies and inconsistencies in a knowledge base is proposed. The proposed algorithm checks the rules by representing the rule connections as a network . The standard model of the rules adapted in this algorithm is in the Conjunctive Normal Form which includes NOT's, and rules of conventional expert system can be checked by converting them into the standard form by a rule form at converter. When compared with Ginsberg's KB-reducer which is conceptually most similar to the proposed algorithm among existing methods,it is shown by a computer simulation that with 360 rules, the checking time is three times faster and the rate increased as the number of rules increased, but the total memory requirement of the proposed agorithm is 1.2 times larger. The proposed algorithm has further advantages in that it can check circular rule chains and can find the paths of the redundant and inconsistent rules.

• 한국통신학회논문지
• /
• 제31권8B호
• /
• pp.716-729
• /
• 2006

최근 대부분 기업들 환경에서의 정보 시스템들은 지역적으로 분산되어 있고 다양한 이종의 데이터 소스들로 구성되어 있다. 따라서 사용자가 의사 결정을 위해 정보를 얻는 것은 어렵다. 이러한 문제를 효율적으로 해결하기 위해 사용자에게 단일 인터페이스를 제공하고, 이기종 시스템들 간에 구축된 데이터베이스 시스템들은 각각 독립성을 유지하면서 하나의 인터페이스처럼 투명성을 제공할 필요성이 있다. 본 논문에서는 카테고리, 표준 온톨로지, 로케이션 온톨로지, 지식베이스로 구성된 XMDR을 제안한다. 표준 온톨로지는 데이터 표현에 사용되는 명칭, 속성, 관계성에 대한 이질적인 문제를 해결한다. 로케이션 온톨로지는 각 레거시 시스템을 연결하는 중간자(mediation)역할을 수행한다. 지식 베이스는 용어 공유를 위한 관계성을 정의한다. 적응적 검색은 로케이션 온톨로지에 의한 사이트 가중치의 반영과 지식 베이스의 다양한 형태의 지식 공유 및 통합을 통한 검색 시스템을 제안하고, 구조화되지 않은 지식들을 어떻게 공유할 것인가에 대한 개념적인 도메인 모델을 제시한다.

• 인지과학
• /
• 제16권4호
• /
• pp.369-386
• /
• 2005

지능형 교수 시스템(ITS: Intelligent Tutoring System)이 기존의 CAI의 제한적 기능을 극복하고, 내장한 지식베이스에 의해 다양한 학습자들의 변인들을 고려한 개별화된 학습 환경을 제공하지만, 교육현장에는 교수내용지식 표현 방법의 부재와 투자 비용의 비효율성으로 인하여 실제적인 개발물은 전무한 상태이다. 이러한 문제점을 해소하기 위하여 ITS에서의 지식표현 기법과 구축된 지식베이스의 재사용에 대한 연구가 필요하다. 교수내용지식의 특성을 고려하여 본 연구에서는 기존의 신경논리망의 한계점을 해결할 수 있도록 지식의 다중 결합체 구성, 이를 이용한 학습의 맥락 설명을 연구의 대상으로 삼았다. 또한 형성된 지식결합체는 군집화하여 지식베이스 객체로 사용하고, 결합체의 자기 학습에 의해 적응적인 지식베이스 객체로의 성장 가능성을 제고한다. 따라서 본 연구에서는 신경논리망의 논리추론, 그리고 인지구조에서 노드의 위상적 불변성을 근거로, 교수내용지식과 객체지향적 개념이 포함된 '확장된 개념의 신경논리망(X-Neuronet: eXtended Neural Logic Network)'을 제안하고, 이 기법에 대한 타당성을 검증하였다. X-Neuronet은 표현의 대상이 되는 지식을 관성과 가변성을 가지는 방향성 결합체로 정의하고, 표현을 위한 기본 개념, 노드의 처리와 연산을 위한 논리연산자, 노드값과 가중치의 결정, 노드활성을 위한 전파 규칙 학습 알고리즘 등을 제공한다.