• Journal of Astronomy and Space Sciences
• /
• 제14권1호
• /
• pp.166-178
• /
• 1997

위성의 수와 복잡도가 증가함에 따라서 다양한 고장이 생기는 경우를 예측하고 고장이 발생한 경우 이를 감지하여 신속히 감지하여 처리하는 노력의 필요성이 증가하게 된다. 현재는 위성 관제소의 전문요원들이 이러한 작업을 수행하고 있지만, 많은 부분이 일상적인 작업이므로 이러한 진단 작업을 자동화할 필요성이 있다. 즉, 일상적인 작업은 전문가시스템이 수행하고, 보다 복잡하고 고차원적인 문제는 전문요원이 해결하는 방식이 바람직하다. 이 논문에서는 이러한 노력의 일환으로 인공지능의 사례기반 방식을 도입한 위성 고장진단 전문가시스템을 구축하기 위한 방법론과 이에 따른 프로토타입 시스템을 설계하고 구현하였다. 사례기반 시스템은 과거의 사례를 기억하고 있는 사례베이스를 구축하고 고장의 증상이 발생한 경우에 이러한 사례베이스로부터 가장 근사한 경우를 인덱스하여 처리하는 기능을 가지고 있다. 이 논문은 이러한 기능을 가지는 사례기반 시스템의 구조와 활용방안에 대해서 서술하고자 한다.

• 한국실내디자인학회논문집
• /
• 제7호
• /
• pp.70-78
• /
• 1996

Artificial Intelligence is generally concerned with tasks whose execution appears to involve some intelligence if done by humans, and knowledge-based system ( in other word, expert system) is the research about the specific domain. This concept also can be applied to interior design field. So the purpose of this study is in reconstructing the accomplishment of artificial Intelligence and knowledge engineering, searching basic theories and cased to knowledge engineering , searching basic theories and cases to formulate knowledge -based design system, and testing the posibilities how the design information can be dealt in computer system. Given that recognition , two major problems must be solved before knowledge-based CAD systems could be come practical : Firstly , identification of the interior of designers use .Secondly , representing this knowledge in a computationally effective manner. I had discussed the basic concepts on which to base a knowledge- based design model, knowledge representation schemes, and problem solving, I could find the possibility which the knowledge-based system can be applied to the interior design according to this study. But there are non-deductive, often irrational and now easily computerized design process in interior design. Those are problems which are relevant to the machine learning and the creativity in design. So there should be a lot of research about the machine learning and the creatively in design in order to construct successfully intelligent knowledge-based design system.

• 지식경영연구
• /
• 제6권2호
• /
• pp.91-108
• /
• 2005

In recent years, organizations have chosen a team-organization as a standard activity level and it leads a significant change in process of knowledge producing. Nevertheless team-organization for building up effective performance and a good communication in organization has influenced knowledge management performance, the empirical analysis and survey have not proved yet. This study, therefore, makes an analysis that the change of organization base on team activity influences knowledge management performance. This study, based on 312 data by using LISREL as a model for studying, provides a result that a team-based activity positively influences knowledge management efficiency.

• Journal of the Korean Data and Information Science Society
• /
• 제8권1호
• /
• pp.1-7
• /
• 1997

전문가 시스템에서의 추론은 주로 IF-THEN 형태의 규칙을 기반으로 하는 지식베이스에 기초한다. 그러나, 한의 전문가 시스템의 지식은 불확실한 지식 특히 애매한 개념의 지식을 많이 포함하고 있으므로 이에 대한 처리가 요구된다. 본 논문에서는 한의 진단 과정을 추론에 기준하여 분석하고 한의 진단 과정에서 발생하는 불확실한 진단 지식을 제약 조건 논리 프로그래밍언어의 일종인 CLP( R ) 언어를 이용하여 표현하고 처리하는 방법을 제안하였다.

• 산업경영시스템학회지
• /
• 제40권4호
• /
• pp.112-119
• /
• 2017

Selecting suppliers in the global supply chain is the very difficult and complicated decision making problem particularly due to the various types of supply risk in addition to the uncertain performance of the potential suppliers. This paper proposes a multi-phase decision making model for supplier selection under supply risks in global supply chains. In the first phase, the model suggests supplier selection solutions suitable to a given condition of decision making using a rule-based expert system. The expert system consists of a knowledge base of supplier selection solutions and an "if-then" rule-based inference engine. The knowledge base contains information about options and their consistency for seven characteristics of 20 supplier selection solutions chosen from articles published in SCIE journals since 2010. In the second phase, the model computes the potential suppliers' general performance indices using a technique for order preference by similarity to ideal solution (TOPSIS) based on their scores obtained by applying the suggested solutions. In the third phase, the model computes their risk indices using a TOPSIS based on their historical and predicted scores obtained by applying a risk evaluation algorithm. The evaluation algorithm deals with seven types of supply risk that significantly affect supplier's performance and eventually influence buyer's production plan. In the fourth phase, the model selects Pareto optimal suppliers based on their general performance and risk indices. An example demonstrates the implementation of the proposed model. The proposed model provides supply chain managers with a practical tool to effectively select best suppliers while considering supply risks as well as the general performance.

• 한국식물병리학회지
• /
• 제10권2호
• /
• pp.99-104
• /
• 1994

A computer-based diagnosing system for diseases of grasses, ornamental plant and fruit trees was developed using a 16 bit personal computer (Model Acer 900) and BASIC was used as a programing language. the developed advisory system was named as Korean Plant Disease Advisory System (KOPDAS). The diagraming system files were composed of a system operation file and several database files. The knowledge-base files are composed of text files, code files and implement program files. The knowledge-base of text files are composed of 79 files of grasses diseases, 122 files of ornamental plant diseases and 67 files of fruit tree diseases. The information of each text file include disease names, causal agents, diseased parts, symptoms, morphological characteristics of causal organisms and control methods for the diagnosing of crop diseases.

• Journal of Mechanical Science and Technology
• /
• 제15권8호
• /
• pp.1108-1118
• /
• 2001

The purpose of this study is to establish a CAD (Computer Aided Design) system for research and development(R&D) of a new product. In the R&D process of a new product, the design objects are frequently redesigned based on the experimental results obtained with prototypes. The CAD/CAE systems (which is based on computer simulation of physical phenomena) are effective in reducing the number of useless prototypes of a new product. These kinds of conventional CAD/CAE systems do not provide a function to reflect the experimental results to the redesign process, however. This paper proposes a methodology to establish the CAD system, which possesses the engineering model of a designed object in the model database, and refines the model on the basis of experimental results of prototype. The blackboard inference model has been applied to infer model refinement and redesign counterplan by using insufficient knowledge of R&D process of new products.

• 산업공학
• /
• 제13권1호
• /
• pp.37-43
• /
• 2000

With the rapid changes of business environments and the tremendous amount of information generated from those environments, most companies must learn to manage those changes and information more effectively. Furthermore, within those amounts of information, the information that meets with achieving the goal of each company should be selected and managed as a core competency, i.e. the knowledge, visible and invisible assets of the company. Knowledge management, as a tool of creating, sharing, and applying such knowledge, has pursued those requirements of companies and been studied by many researchers and consultants, especially focusing on the Knowledge Map'. It is said that a knowledge map is a powerful tool for scanning and managing the knowledge that exists in a company and that it is the most important part of establishing a knowledge management base. Until now, however, there have been no specific or practical models for establishing a knowledge map, in spite of the concern. For this reason, this paper suggests a practical model for establishing a knowledge map in terms of a knowledge acquisition procedure based on the traditional research concerning concept maps. In addition to this, for examining the validity of the model, a case study on the 'P' steel and iron company has been performed. This paper's methodology on developing a knowledge map and the procedures to apply them to the real business environment will suggest a cornerstone in the field of practical implementation of knowledge management.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1995년도 춘계공동학술대회논문집; 전남대학교; 28-29 Apr. 1995
• /
• pp.79-90
• /
• 1995

The material handling equipment selection, that is a key task in the material handling system design, is a complex, difficult task, and requires a massive technical knowledge and systematic analysis. It is invaluable to justify the selected equipment model by the performance evaluation before its actual implementation. This paper presents an intelligent knowledge-based expert system called "IMESE" created by authors, for the selection and evaluation of material handling equipment model suitable for movement and storage of materials in a manufacturing facility. The IMESE is consisted of four modules: a knowledge base to select an appropriate equipment type, a multiple criteria decision making procedure to choose the most favorable commercial model of the selected equipment type, a database to store the list of commercial models of equipment types with their specifications, and simulators to evaluate the performance of the equipment model. The whole process of IMESE is executed under VP-Expert expert system environment.vironment.

• 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.