• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.6
• /
• pp.1007-1016
• /
• 2007

In power system, substation facilities have become too complex and larger according to an extended power system. Also, customers require the high quality of electrical power system. However, some facilities become old and often break down unexpectedly. The unexpected failure may cause a break in power system and loss of profits. Therefore it is important to prevent abrupt faults by monitoring the condition of power systems. Among the various power facilities, power transformers play an important role in the transmission and distribution systems. In this research, we develop intelligent diagnosis technique for predicting faults of power transformer by FCM(Fuzzy c-means) and Euclidean based distance measure. The proposed technique make it possible to measures the possibility and degree of aging as well as the faults occurred in transformer. To demonstrate the validity of proposed method, various experiments are performed and their results are presented.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.05a
• /
• pp.329-337
• /
• 2007

Case-based reasoning (CBR) methods are applied to various target problems on the supposition that previous cases are sufficiently similar to current target problems, and the results of previous similar cases support the same result consistently. However, these assumptions are not applicable for some target cases. There are some target cases that have no sufficiently similar cases, or if they have, the results of these previous cases are inconsistent. That is, the appropriateness of CBR is different for each target case, even though they are problems in the same domain. Thus, applying CBR to whole datasets in a domain is not reasonable. This paper presents a new hybrid datamining technique called two-step filtering CBR and Rule Induction (TSFCR), which dynamically selects either CBR or RI for each target case, taking into consideration similarities and consistencies of previous cases. We apply this method to three medical diagnosis datasets and one credit analysis dataset in order to demonstrate that TSFCR outperforms the genuine CBR and RI.

• Journal of Intelligence and Information Systems
• /
• v.6 no.1
• /
• pp.97-112
• /
• 2000

The basic idea of case-based reasoning is to solve a new problem using the previous problem-solving experiences. In this research we develop a case-based reasoning system for equipment malfunction diagnosis. We first divide the case base into clusters using the case-based clustering technique. Then we develop an appropriate case-based diagnostic system for each cluster. In other words for individual cluster a different case-based diagnostic system which uses different weights for attributes is developed. As a result multiple case-based reasoning system are operating to solve a diagnostic problem. In comparison to the performance of the single case-based reasoning system our system reduces the computation time by 50% and increases the accuracy by 5% point.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.435-442
• /
• 2000

만성질병, 식습관, 영양등 스트레스에 시달리는 현대인의 건강 상태를 파악하는 일은 매우 중요하며 또한 필요하다. 그러나 식이 섭취 평가는 많은 분야의 자료와 지식을 필요로 하기 때문에 손쉽게 일반인이 신뢰성 있는 평가는 얻기는 쉽지 않다. 본 연구는 식품, 영양, 조리, 만성질병, 식습관 등의 여러 전문 분야의 자료와 지식을 기반으로 한 웹 상에서의 영양 평가 시스템으로 '건강 관리를 위한 사이버 식생활 자가 진단 시스템(Cyber Food Self Diagnosis Program, 이하 Cyber-FSDP)'의 설계 및 구축에 관한 것이다. 바탕으로 한다. 초고속 통신망을 이용하여 사람들의 건강문제와 관련된 식생활 정보를 수집하고, 개인별 식생활을 사용자와 상호작용하게 온라인으로 평가·진단하여 이를 개선하고 궁극적으로는 만성질병 위험도를 감소시키고 건강을 증진시킬 수 있는 영양 및 만성 질병 평가 전문가 시스템을 구축한 사례에 대한 Web 응용 프로그램 개발을 소개하며, 개발환경으로는 서버를 엔터프라이즈 3000 Solaris 2.5.1을 사용했으며, DBMS는 IUS (Illustra Universal Server)를 사용하였고, APB(App Page Builder), JabaScript, HTML 등의 언어로 구현되었다.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.5
• /
• pp.110-123
• /
• 1994

The development of automatic production systems have required inteligent diagnostic and monitoring function to repair system failure and reduce production loss by the failure. In order to perform accurate functions of intelligent system, inferencing about total system failure and fault analysis due to each mechanical component failures are required. Also the solution about repair and maintenance can be suggested from these analysis results. As an essential component of mechanical system, a bearing system is investigated to define the failure behavior. The bearing failure is caused by lubricant system failure, metallurgical defficiency, mechanical condition(vibration, overloading, misalignment) and environmental effect. This study described roller bearing fault train due to stress variation and metallurgical defficiency from lubricant failure by using FTA.

• Proceedings of the KIEE Conference
• /
• 2008.07a
• /
• pp.404-405
• /
• 2008

This paper is analyzed that the development of intelligent terminal unit for the switchgear partial discharge diagnosis. It is the core technology for supplying with stable and trust electric as a technology that be economic of the high efficient, the maintain, the confidence and the repair. So the condition diagnosis of the switchgear is necessary by developing inteligent terminal unit.

• Journal of Intelligence and Information Systems
• /
• v.4 no.1
• /
• pp.103-114
• /
• 1998

본 논문은 화력발전소 적용을 위한 경보처리 기반 고장진단 전문가 시스템(APDX(Alarm Processing and Diagnosis Expert System)개발에 관하여 논의한다. 본 연구에서 제시된 경보처리 알고리즘은 근본적으로는 경보 인과관계 트리를 사용하고 있으나 최종 원인 경보선택에 있어서는 경보 발생시간과 경보 우선순위 Meta-Rul를 활용한다. 경보처리 모듈에서 처리된 원인경보를 근거로 하여 본 원인경보와 관련된 고장부위를 진단하게 된다. 진단모듈에서는 경보에 관련된 센서들과 고장들 사이의 관계를 정상적으로 모델링하고 센서들의 트랜드를 정성적 해석기로 분석하여 증가, 정상, 감소의 세가지 상태에 대한 신뢰도를 출력한다. 또한 각 경보로부터 고장이 예상되는 고장타입을 센서 천이도로 모델링하여 진단에 활용된다. 최종적으로 추론모듈에서 퍼지(Fuzzy) 추론 알고리즘을 이용하여 모델된 고장 타입과 계산된 고장과의 매칭과정을 통하여 진단을 수행하게 되며, 계산 창 (Window)를 변경하면서 고장을 재 확인하게 된다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.386-392
• /
• 2001

We design the intelligent diagnosis system for deciding on operation state of TMS Analyzer in this paper. We propose the method to model the neuro-fuzzy model for diagnosing theoperation state of analyzer by using input and output signals of TMS to measure Nox and SOx. By using experiment data, neuro-fuzzy model is investigated. Validity of the proposed system is asserted by numerical simulation.

• Proceedings of the KIPE Conference
• /
• 2013.07a
• /
• pp.329-330
• /
• 2013

In this research, a novel battery charge system with embedded diagnosis function is proposed by using online impedance spectroscopy. The impedance spectroscopy technique is employed to investigate the impedance variation of the battery thereby estimating the state of health of the battery. A small voltage perturbation is applied to the battery by the voltage controller of the bidirectional converter with no additional hardware and the impedance of the battery is then calculated by the digital lock-in amplifier embedded in the DSP of the charger. The design procedure of the proposed charger is detailed and the feasibility of the system is verified by the experiments.

• Journal of Information Processing Systems
• /
• v.16 no.3
• /
• pp.523-529
• /
• 2020

Future information and communication technology (ICT) is constantly evolving and converging in diverse fields depending on the wireless environment, and the trend is being further developed to increase the speed of wireless networks. Future ICT is needed in many areas such as active senior & solo-economy, hyper-connected society, intelligent machine, industrial boundary collapse, secured self, and the sharing economy. However, a lot of research is needed to solve problems such as machine learning, security, prediction, unmanned technology, etc. Therefore, this paper describes some technologies developed in the areas of blockchain, fault diagnosis, security, agricultural ICT, cloud, life safety and care, and climate monitoring in order to provide insights into the future paradigm.