• 대한조선학회논문집
• /
• 제30권4호
• /
• pp.1-7
• /
• 1993

전문가시스템을 개발하고, 이를 현업에 적용하려는 노력이 꾸준하게 이어져 왔다. 조선분야에의 전문가시스템 개발은 외국에서 활발하게 이루어지고 있으며, 최근 국내에서도 관심이 증대되고 있다. 본 연구에서는, 초기설계시에 선박의 주기관선정을 지원할 수 있는 설계지원 전문가시스템을 상용 전문가시스템 개발도구를 사용하여 개발하였다. 개발된 시스템은, 성능 추정 모듈, 주기관 데이타베이스, 지식베이스, 그래픽 사용자 인터페이스 및 이들을 연결하는 모듈로 구성되어 있다. 지식베이스에는 약 100여개의 지식이 Rule의 형태로 구축되어 있다. 본 시스템은 설계전문가에게는 설계의 보조수단으로, 초보자에게는 교육용으로 사용가능할 것이다.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권1호
• /
• pp.79-84
• /
• 2021

The fundamental element to be kept for big data analysis, artificial intelligence technologies and asset management system is a data quality, which could directly affect the entire system reliability. For this reason, the momentum of data cleaning works is recently increased and data cleaning methods have been investigating around the world. In the field of electric power, however, asset data cleaning methods have not been fully determined therefore, automatic cleaning algorithm of asset data for transmission cables has been studied in this paper. Cleaning algorithm is composed of missing data treatment and outlier data one. Rule-based and expert opinion based cleaning methods are converged and utilized for these dirty data.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.1146-1149
• /
• 1995

The CAD/CAM System for deep drawing transfer die in mechanical press proess has been developed. The developed CAD system can generate the drawing of drawing of transfer die in mechanical press. Using these results from CAD system, it can generate the NC data to machine die's elements on the CAD system. This system can reduce design man-hours and human errors. In order to construct the system, it is used to automate the design process using knowledge base system. The developed system is based on the knowledge base system which is involved a lot of expert's technology in the practice filed. Using AutoLISP language under the AutoCAD system, CTK customer language of SmartCAM is used as the overall CAD/CAM environment. Results of this system will be provide effective aids to the designer and mannufacturer in this field.

• Structural Engineering and Mechanics
• /
• 제51권6호
• /
• pp.973-988
• /
• 2014

This paper presents a factor-analysis based questionnaire categorization method to improve the reliability of the evaluation of working conditions without influencing the completeness of the questionnaire both in Taiwanese and Chinese construction enterprises for structural engineering applications. The proposed approach springs from the AI application and expert systems in structural engineering. Questions with a similar response pattern are grouped into or categorized as one factor. Questions that form a single factor usually have higher reliability than the entire questionnaire, especially in the case when the questionnaire is complex and inconsistent. By classifying questions based on the meanings of the words used in them and the responded scores, reliability could be increased. The principle for classification was that 90% of the questions in the same classified group must satisfy the proposed classification rule and consequently the lowest one was 92%. The results show that the question classification method could improve the reliability of the questionnaires for at least 0.7. Compared to the question deletion method using SPSS, 75% of the questions left were verified the same as the results obtained by applying the classification method.

• 경영과정보연구
• /
• 제2권
• /
• pp.169-193
• /
• 1998

Case- based reasoning(CBR) offers a new approach for developing knowledge based systems. Unlike the rule-based paradigm, in which domain knowledge is encoded in the form of production rules, in the case-based approach the problem solving experience of the domain expert is encoded in the form of cases stored in a casebase(CB). CBR allows a reasoner (1) to propose solutions in domains that are not completely understood by the reasoner, (2) to evaluate solutions when no algorithmic method is available for evaluation, and (3) to interprete open-ended and ill-defined concepts. CBR also helps reasoner (4) take actions to avoid repeating past mistakes, and (5) focus its reasoning on important parts of a problem. Owing to the above advantages, CBR has successfully been applied to many kinds of problems such as design, planning, diagnosis and instruction. In this paper, I propose case-based DSS(CBDSS). CBDSS is an intelligent DSS using CBR technique. CBDSS consists of interface, case-based reasoner, maintainer, casebase management system, domain dependent CB, domain independent CB, and so on.

• 지능정보연구
• /
• 제7권2호
• /
• pp.83-93
• /
• 2001

기업부실예측은 과거로부터 많은 연구가 이루어진 분야로, 주로 통계기법에 의한 분류예측문제로 다루어져 왔다. 최근에는 인공신경망, 의사결정나무 등 비선형성을 반영할 수 있는 인공지능 기법을 적용한 연구가 많이 수행되고 있다. 본 연구에서는 최적화에 주로 활용하는 인공지능 기법인 유전자 알고리즘을 규칙추출을 통한 기업부실예측 모형의 개발에 적용하고, 활용가능성을 검증하였다.

• 감성과학
• /
• 제5권1호
• /
• pp.17-24
• /
• 2002

본 연구는 객관적인 생리신호로부터 인간의 감성을 추론할 수 있는 감성평가 전문가 시스템을 개발하기 위한 첫 번째 단계로 측정된 생리신호를 이용하여 인간의 긴장도를 판단하는 알고리즘의 개발을 목표로 한다. 감성평가와 관련된 애매함을 수리적으로 취급하기 위해 퍼지이론을 적용하여 임의의 감성영역에 속하는 정도를 소속함수로 정량화함으로써 감성평가를 가능하게 하고자 하였다. 소속함수의 결정은 상상을 통해 유발된 긴장/이완의 생리신호 데이터베이스 결과를 사용하였다. 그리고 두 가지 이상의 생리신호 측정결과와 각 생리신호의 소속함수로부터 하나의 최종결과(긴장도)를 유추하기 위해서 Dempster-Shafer증거합 법칙을 적용하였고, 이를 통해 최종적인 긴장도를 도출할 수 있도록 하였다.

• 소성∙가공
• /
• 제8권6호
• /
• pp.591-603
• /
• 1999

A computer-aided process planning system for rotationally symmetric deep drawing products has been developed. The application for non-axisymmetric components, however, has been reported yet. Therefore, this study investigates process sequence design in deep drawing process and constructs a computer-aided process planning system for non-axisymmetric motor frame products with elliptical shape. The system developed consists of three modules. The first one os a 3-dimensional modeling module to calculate surface area for non-axisymmetric products. The second one is a blank design module that creates an oval-shaped blank with the identical surface area. The third one is a process planning module based on production rules that play the best important roles in an expert system for manufacturing. The production rules are generated and upgraded by interviewing with field engineers. Especially, drawing coefficient, punch and die radii are considered as main design parameters. The constructed system for elliptical deep drawing products would be very useful to reduce lead time and improve accuracy for production.

• 인지과학
• /
• 제10권4호
• /
• pp.51-62
• /
• 1999

본 논문에서는 규칙기반 전문가시스템의 퍼지 생성규칙을 표현할 수 있는 퍼지페트리네트 표현을 제안한다. 퍼지페트리네트 표현을 기반으로, 전진추론 알고리즘과 후진추론 알고리즘으로 구성된 퍼지 추론 알고리즘을 제안한다. 본 논문이 제안한 알고리즘은 단순히 min과 max 계산만을 하는 기존의 알고리즘과는 달리 퍼지 생성규칙의 전제 부와 결론 부에 퍼지 개념의 유무에 따라 적절한 믿음 값 평가 함수을 사용하여 보다 더 인간적인 추론을 한다. 전진추론 알고리즘은 유한한 방향성 나무인 도달나무로 표현할 수 있다. 후진추론 알고리즘은 목표노드에서 시작노드까지의 후진추론 통로를 구한 후에 믿음 값 평가함수를 이용하여 목표노드의 믿음 값을 구한다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.1529-1532
• /
• 2007

Failure Mode, Effects, and Criticality Analysis (FMECA) is an extension of FMEA which includes a criticality analysis. The criticality analysis is used to chart the probability of failure modes against the severity of their consequences. The result highlights failure modes with relatively high probability and severity of consequences, allowing remedial effort to be directed where it will produce the greatest value. However, there are several limitations. Measuring severity of failure consequences is subjective and linguistic. Since The result of FMECA only gives qualitative and quantitative informations, it should be re-analysed to prioritize critical units. Fuzzy set theory has been introduced by Lotfi A. Zadeh (1965). It has extended the classical set theory dramatically. Based on fuzzy set theory, fuzzy logic has been developed employing human reasoning process. IF-THEN fuzzy rule based assessment approach can model the expert's decision logic appropriately. Fault tree analysis (FTA) is one of most common fault modeling techniques. It is widely used in many fields practically. In this paper, a simple fault tree analysis is proposed to measure the severity of components. Fuzzy rule based assessment method interprets linguistic variables for determination of critical unit priorities. An rail-way transforming system is analysed to describe the proposed method.