• Proceedings of the KIEE Conference
• /
• 2000.07a
• /
• pp.125-127
• /
• 2000

Multiple faults are hard to diagnose correctly because the operation of circuit breakers tripped by former fault changes the topology of power systems. The information including operating time of actuated relays and tripped circuit breakers is used for considering changes of the network topology in fault section diagnosis. This paper presents a method for fault section diagnosis using a set of matrices which represent changes of the network topology due to operation of circuit breakers. The proposed method uses fuzzy relation to cope with the unavoidable uncertainties imposed on fault section diagnosis of power systems. The inference executed by the proposed matrices provides the fault section candidates in the form of a matrix made up of the degree of membership. Experimental studies for real power systems reveal usefulness of the proposed technique to diagnose multiple faults.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2846-2848
• /
• 2005

This paper proposes a pattern classification algorithm for the defect distribution of Hard Disk Drive (HDD). In the HDD productions, the defect pattern of defective HDD set is important information to diagnosis of defective HDD set. In this paper, 5 characteristics are determined for the classification to six standard defect pattern classes. A fuzzy inference system is proposed, the inputs of which are 5 characteristic values and the outputs are the possibilities that the input pattern is classified to the standard patterns. Classification result is the pattern with maximum possibility. The proposed algorithm is implemented with a PC system for defective HDD sets and shows its effectiveness.

• Annual Conference of KIPS
• /
• 2003.11a
• /
• pp.291-294
• /
• 2003

많은 양의 유즈넷 뉴스 중에서 찾고자 하는 정확한 정보를 빠른 시간 안에 검색하고, 원하는 정보만 필터링 하는 것은 중요하다. 하지만 뉴스 문서는 이메일과 달라서 미리 자신에게 맞는 뉴스그룹을 등록해 주어야만 정보를 얻을 수 있다. 본 연구에서는 다양한 뉴스그룹들 중에서 사용자와 취향이 가장 유사한 뉴스그룹을 코호넨 신경망을 이용하여 분류하는 서비스를 제공한다. 신경망을 학습시키기 위한 뉴스 문서의 키워드들을 선택하기 위해 예제 문서들로부터 후보 용어들을 추출하고 퍼지 추론을 적용하여 대표 용어들을 선택한다. 뉴스 필터링 시스템의 분류 성능을 평가하기 위하여 유클리드 거리 면에서 비교한 결과, 제안한 방법의 유용성을 확인할 수 있었다.

• Proceedings of the ESK Conference
• /
• 1997.04a
• /
• pp.196-199
• /
• 1997

This paper describes the implementation process of Virtual Modeling system for a customer-oriented product. The human sense is measured and analyzed by physical design factors and can be applied also for the product design. The first step implementing virtual modeling is to make a human sensibility("Kansei") database. Human sensibility database is constructed with the relational data of Kansei words and design factors. The next step is extraction the design information from the human sensibility database by fuzzy inference algorithm. This design information is used for the input data for the graphic database. Virtual implementation software compounds 3D shape of product. The final product can be modified according to the customer's requirement.quirement.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.415-418
• /
• 1996

Etching Process, one of the most important process in semiconductor fabrication, has input control part of which components are pressure, gas flow, RF power and etc., and plasma gas which is complex and not exactly understood is used to etch wafer in etching chamber. So this process has not real-time feedback controller based on input-output relation, then it uses EPD(End Point Detection) signal to determine when to start or when to stop etching. Various type EPD controller control etching process using EPD signal obtained from optical intensity of etching chamber. In development EPD controller we concentrate on compensation of this signal intensity and setting the relative signal magnitude at first of etching. We compensate signal intensity using neural network learning method and set the relative signal magnitude using fuzzy inference method. Potential of this method which improves EPD system capability is proved by experiences.

• Journal of Ocean Engineering and Technology
• /
• v.12 no.3 s.29
• /
• pp.103-111
• /
• 1998

This paper describes the initial hull form design process which generate a hull form using a neurofuzzy modeling. Neurofuzzy system is to combine the merits of fuzzy inference system and neural networks. Therefore it has structured knowledge representations as well as adaptive capacities. Initial hull form design stage is the process which generate an adoptable hull form from the limited design information and multi-decidions condidering correlations with design factors. It can be assidted efficiently by neurofuzzy system. This paper suggests two methods of an initial hull form generation using the neurofuzzy modeling and B-spline theory. and examines the usefulness of suggested method through its application examples.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.269-272
• /
• 2004

본 논문은 비선형 시스템의 퍼지모델을 위해 정보 granules 기반 퍼지 추론 시스템의 새로운 설계 및 이의 최적화를 제시한다. 퍼지모델은 주로 경험적 방법에 의해 추출되기 때문에 보다 구체적이고 체계적인 방법에 의한 동정 및 최적화 될 필요성이 요구된다. 일반적으로, 정보 granules는 근접성, 유사성 또는 기능성 둥에 인하여 서로 결합되는 요소(특히, 수치 데이터)의 실체이다. 제안된 퍼지 모델은 정보 데이터의 특성을 살리기 위해 HCM 클러스터링 방법에 의해 전반부/후반부 구조 및 파라미터 동정을 시행한다. 두 가지 형태의 퍼지 추론 방법은 간략 추론과 선형추론에 의해 수행되며 삼각형 멤버쉽 함수를 사용한다. 구축된 정보 granule 기반 퍼지 모델은 유전자 알고리즘을 이용하여 전반부 파라미터를 최적으로 동정한다. 제안된 비선형 모델의 성능평가는 수치적인 예를 통해 비교 평가한다.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.8 no.1
• /
• pp.40-47
• /
• 2003

A low-cost current-sensing scheme for the motor drives with MOSFET is described. Many motor drives usually employ the common current sensors to measure current for the purpose of control or protection. These current sensors, however, significantly burden the power circuit with the size and cost. The proposed current-sensing scheme utilizes information concerning MOSFET's On-voltage and On-resistance. An analogue circuit detecting On-voltage can overcome the above disadvantages because the circuit is small and is made at a low cost, and the fuzzy inference for On-resistance is also simply designed based on MOSFET's characteristics. The validity of this scheme will be experimentally verified by adopting the current control of a battery car.

• Proceedings of the KIEE Conference
• /
• 1999.07c
• /
• pp.1082-1084
• /
• 1999

A fault detection of power system must be fast and correctly over input signal without relation to any disturbance. But, it is difficult to detect fault state for digital relay comparison of fault perfectly. In this Paper, we measure each Phase current and infer type of fault using ANFIS(Adaptive Neuro-Fuzzy Inference System).

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.179.2-179
• /
• 2001

This paper is about to consist of neutralization public decision system which is level controled the amount of inflow and outflow water to make use of PLC in automatic system and according to numerical value of PH, which is projected into a water tank counteragent automatically. But neverthless, appearance of extended PLC, there is a limit to realize from automatic system to intellectual system which is more efficient and active. There are two problems in PLC. First, there is not generalized that a module of PLC (which is installed in PLC) is realized control algorithm form. Second, there is a difficulty of expression that provided PLC control language is realized. There fore I take fuzzy inference control technique of various intellectual algorithm and 1 make a control rule and ...