• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.340-343
• /
• 2000

본 논문에서는 선박에서 퍼지 데이터베이스를 이용하여 지능형 화재진압통제시스템의 성능을 개선시키는 방법에 대하여 논의하였다. 규칙과 사례가 통합된 화재진압통제 전문가시스템(C-FFES)에서는 사례기반 추론을 하기 위한 사례베이스가 일반적인 데이터베이스로 구성되어 있어서, 이전에 화재가 발생했던 사례와 현재의 사례가 유사한지를 구별하기가 쉽지 않은 문제점을 지니고 있다. 제안하는 시스템에서는 예외적인 상황에서 화재가 발생하는 사례를 퍼지데이터베이스로 구성하고, 현 상황과 예외적인 상황에서 화재가 발생하는 사례를 조회하기 위하여 퍼지 유사도 개념을 적용하여 현재 입력된 사례와 가장 유사한 사례가 조회될 수 있도록 하였다. 또한 기존의 규칙 기반 FFES(Fire Fighting Expert System), 사례기반 추론에 의해 확장된 C-FFES(Combined-Fire Fighting Expert System) 그리고 제안하는 A-FFES(Advanced Fire fighting Expert System)를 비교를 통해, 제안하는 A-FFES가 화재탐지율을 향상시킴을 보였다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2007년도 한국지능정보시스템학회
• /
• pp.375-381
• /
• 2007

Cognitive map (CM) has long been used as an effective way of constructing the human thinking process. In literature regarding CM, a number of successful researches were reported, where CM based what-if analysis could enhance firm's performance. However, there exit very few researches investigating the CM generation method. Therefore this study proposes a GENCOM (Genetic Algorithm based Cognitive Map Generator). In this model combined with CM and GA, GA will find the optimal weight and input vector so that the CM generation. To empirically prove the effectiveness of GENCOM, we collected valid questionnaires from expert in S/W sales cases. Empirical results showed that GENCOM could contribute to effective CM simulation and very useful method to extracting the tacit knowledge of sales experts.

• 제어로봇시스템학회논문지
• /
• 제3권5호
• /
• pp.435-442
• /
• 1997

The roof crane system is used for transporting a variable load to a target position. The goal of crane control system is transporting the load to a goal position as quick as possible without rope oscillation. The crane is generally operated by an expert operator, but recently an automatic control system with high speed and rapid tansportation is required. In this paper, we developed a simple fuzzy controller which has been introduced expert's knowledge base for anti-swing and rapid tranportation to goal position. In particular, we proposed the synthesis reasoning method which synthesizes on the basis of expert knowledge of the angle control input and position control input which are inferenced parallel and simultaneously. And we confirmed that the performance of the developed controller is effective as a result of applying it to crane simulator and also verified whether the proposed synthesis rules have been applied correctly using clustering algorithm from the measured data.

• 대한산업공학회지
• /
• 제23권1호
• /
• pp.95-113
• /
• 1997

This paper outlines a framework for a diagnosis of a complex system with uncertain information. Sensor validation ploys a vital role in the ability of the overall system to correctly determine the state of a system monitored by imperfect sensors. Here, emphases are put on the heuristic technology and post-processor for reasoning. Heuristic Sensor Validation (HSV) exploits deeper knowledge about parameter interaction within the plant to cull sensor faults from the data stream. Finally the modified probability distributions and validated data are used as input to the reasoning scheme which is the runtime version of the influence diagram. The output of the influence diagram is a diagnostic mapping from the symptoms or sensor readings to a determination of likely failure modes. Once likely failure modes are identified, a detailed diagnostic knowledge base suggests corrective actions to improve performance. This framework for a diagnostic expert system with sensor validation and reasoning under uncertainty applies in $HEATXPRT^{TM}$ a data-driven on-line expert system for diagnosing heat rate degradation problems in fossil power plants [1].

• International Journal of Precision Engineering and Manufacturing
• /
• 제8권3호
• /
• pp.54-59
• /
• 2007

It is widely recognized that increasing the accuracy and diversity of rotating machinery necessitates an appropriate diagnostic technique and maintenance system. Until now, operators have monitored machinery using their senses or by analyzing simple changes to root mean square output values. We developed an expert diagnostic system that uses fuzzy inference to expertly assess the condition of a machine and allow operators to make accurate judgments. This paper describes the hardware and software of the expert diagnostic system. An assessment of the diagnostic performance for five fault phenomena typically found in pumps is also described.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.1069-1072
• /
• 1996

In modern control engineering, the model following system is a typical method. The model following system's performance is due to algorithm of control law, accuracy of modeling to the plant, and dynamics of the reference model. But the determination of the reference model depends on knowledge of an expert. Using an expert system, the determination method of the reference model was proposed in this paper. So, the reference model can be selected by user who has no Knowledge of dynamics and parameters.

• 산업공학
• /
• 제6권2호
• /
• pp.3-17
• /
• 1993

Traditionally, programs for NC machine tools have been created using either a maunual method or a computer-assisted method. However, both methods are known to be complex, time-consuming and error-prone. This paper presents an intelligent system, called "INPPC" which is interfaced with a CAD system to generate APT NC part program automatically. The INPPC is developed by using VP-Expert rule-based expert system development tool, and obtains the information about the part shape by searching the CAD database, about the process by asking the related questions to the user, and about the machine tooling by searching the tool database. The INPPC is implemented on an IBM compatible PC/AT under MS-DOS, and its performance is demonstrated by consulting a simple example problem.

• 지능정보연구
• /
• 제22권1호
• /
• pp.63-82
• /
• 2016

최근 정보기술의 발달로 인해 소비자들은 온라인상에서 많은 정보를 쉽고 빠르게 획득할 수 있다. 소비자가 제품 구매시에는 소비자들이나 전문가들이 작성한 제품 후기 정보를 주로 탐색한다. 기존의 연구들이 소비자들이 창출한 제품 후기 중심으로 주로 진행되어 왔기 때문에, 전문가 제품 후기의 영향력에 대해서는 상대적으로 소수의 연구들만 존재하고 있다. 본 연구는 전문가가 생성하는 제품 후기에 초점을 맞추어, 방대한 실제 비정형데이터인 전문가의 후기를 어떻게 언어학적인 차원과 심리학적인 차원으로 나눌 수 있는지의 방법론을 제안하며, 실제 전문가 제품 후기를 사용하여 의미 있는 다섯 가지 차원의 새로운 변수들을 도출하였다. 그 결과 소비자들이 전문가 후기에서 반응하고 있는 언어적 특성은 제품에 대한 깊이 있는 정보의 양이나 충분한 설명을 나타내는 변수인 Review Depth, 그리고 전문가가 기술하는 방식이 제품에 대한 확신이 없는 듯한 말투를 나타내는 변수인 Lack of Assurance는 소비자의 전반적인 제품평가에 유의한 상관관계가 있는 것으로 밝혀졌다. 또한, 제품에 대한 칭찬이나 긍정적인 면을 서술하는 방식인 Positive Polarity가 소비자의 제품 평가에 영향을 미치지 않았지만, 전문가가 하는 제품에 대한 비관적인 평가인 Negative Polarity는 소비자들의 평가와 유의한 음의 상관관계가 있었다는 점이다. 전문가가 스토리텔링 관점에서 자주 사용하는 Social Orientation 특성은 유의한 관계를 미치지 못함이 밝혀졌다. 본 연구는 새로운 방법론을 제안하고 이를 실제로 활용한 결과를 보여준다는 차원에서 이론적이고 실무적인 공헌을 가진다.

• 한국국방경영분석학회지
• /
• 제36권3호
• /
• pp.83-93
• /
• 2010

본 논문에서는 훈련용 워게임모델의 근접전투 피해평가를 위한 새로운 근접전투전문가시스템을 제안하였다. 군에서 사용하고 있는 워게임모델에서 피해평가 모의논리는 아주 중요한 모의가능이다. 현재, 육군의 군사단급 워게임모델인 창조21 모델에서는 근접전투 피해평가의 핵심기능이 창조21 모델에서 계산되지 않고, 공개소스와 내부논리를 알 수 없는 미군에서 제작한 근접전투전문가시스템(일명 COBRA)에서 별도로 계산되고, 이 결과가 네트워크를 통해 창조21 모델로 전송되어 근접전투에 대한 피해평가가 이루어진다. 본 논문에서는 COBRA를 대체할 수 있는 근접전투전문가시스템을 의사결정나무를 이용해서 제안하였다. 제안하는 시스템은 실험결과 COBRA와 유사한 성능을 보였고, 시스템의 계산량이 적었고 군사작전 상황에 적합하였다.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.378-382
• /
• 2001

The purpose of this study was to develop an expert system supporting the diagnosis of diffuse interstitial lung disease by high resolution computed tomography. CLIPS(C language integrated production system) with rule-based reasoning was used to develop the system. Development of expert system had three stages knowledge acquisition, knowledge representation, and reasoning. Knowledge was obtained and integrated, from tables and figure legends of a representative textbook in the domain of this expert system, High-Resolution CT of the Lung, by Webb WR, Mueller NL, and Naidich DP. The acquired knowledge was analyzed to form a knowledge base. Overlapping knowledge was eliminated, similar pieces of knowledge were combined and professional terms were defined. The most important knowledge of findings was then selected for each disease. After groupings of combined findings were made, disease groups were analyzed sequentially to determine final diagnoses. The system was based upon the input of 69 diseases, 185 findings, 73 conditions, 387 status, and 62 rules. The system was set up to determine the diagnoses of diseases from the combination of findings using forward reasoning. In an empirical trial, the system was applied to support the diagnosis of 40 cases of diffuse interstitial lung diseases. The performance of two doctors with support of the system was compared to that of another two doctors without support of the system. The two doctors with the support of the system made more accurate diagnoses than the doctors without the support of the system. The system is believed to be useful for the diagnosis of rare diseases and for cases with many possible differential diagnoses. In conclusion, an expert system supporting the high resolution computed tomographic diagnosis of diffuse interstitial lung disease was developed and the system is thought to be useful for medical practice.