• 한국추진공학회지
• /
• 제17권2호
• /
• pp.71-83
• /
• 2013

항공기 가스터빈의 운용율을 극대화 하고 정비 비용을 최소화하기 위해 최근 모델기반방법이나 인공지능방법을 이용한 첨단상태진단기법들을 적용하고 있다. 이 진단 방법들 중 비선형 GPA방법과 유전자 알고리즘을 이용한 엔진 진단방법들이 선형 GPA, 퍼지 로직 및 신경망 이론 등의 타 방법들에 비해 장점을 가지고 있는 것으로 알려졌다. 이에 본 연구에서는 항공기용 AE3007H 터보팬엔진의 상태진단에 비선형 GPA기법과 유전자 알고리즘을 적용한 후 비교를 통해 센서 노이즈와 바이어스가 있는 경우 유전자 알고리즘이 보다 우수한 진단 기법임을 확인하였다.

• 자원ㆍ환경경제연구
• /
• 제18권2호
• /
• pp.217-239
• /
• 2009

최근 화석에너지가 가진 환경 및 고갈 문제들을 경감시킬 수 있는 에너지 자원으로서 가스하이드레이트가 주목을 받으며, 우리나라에서는 2005년부터 2014년까지 10개년 계획 하에 가스하이드레이트 개발사업을 진행하고 있다. 가스하이드레이트 개발사업은 수력원자력을 제외하면 사용 에너지의 대부분을 수입에 의존하고 있는 우리나라의 경제사회에 미치는 파급효과가 상당히 클 것으로 예상되지만, 성공여부는 불확실하다. 그러므로 사업의 가치평가를 사전에 수행하여 타당성을 제고하고, 효과적인 수행 전략을 제시하는 것이 매우 중요하다고 할 수 있다. 본 논문에서는 가스하이드레이트 개발사업의 가치평가를 수행하기 위해 퍼지위험분석을 실물옵션모형에 적용시킴으로써 기존의 방법론에서 측정하지 않았던 정보들을 포함시키고, 가치평가 결과에 나타나는 편의나 오류를 감소시키고자 하였다. 퍼지위험분석을 적용한 실물옵션모형은 무형요인들에 대한 판단의 모호성과 부정확성을 적당한 언어척도로 모형화함으로써 이 요인들을 명시적으로 평가하고, 재무적 성과측정치와 함께 통합될 수 있도록 해주는 장점을 가진다. 이는 의사결정자의 직관에 의해서도 부분적으로 평가가 가능하겠으나, 직관에 따른 판단은 여러 가지 요인들을 동시에 고려하여 일관성 있는 평가를 내리는 데 한계가 있을 것이다. 하지만 퍼지위험분석을 적용하면 복합적인 여러 가지 속성의 의사결정 문제가 단순화된 부분적 문제들로 분해되어 분석이 가능하게 된다. 고유가의 지속과 함께 청정에너지에 대한 시대적 요구로 인하여 에너지 자원 또는 기술 개발 사업의 필요성이 더욱더 증대되고 있다. 이 가운데 본 연구의 결과가 가스하이드레이트 개발 사업뿐 아니라, 향후 에너지 산업과 관련된 정책의사결정에 하나의 가이드라인을 제시할 수 있으리라 기대된다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권1호
• /
• pp.7-11
• /
• 2004

This paper proposes a new immunotronic approach for the fault detection in hardware. The suggested method is, inspired by biology and its implementation is based on genetic algorithm. Tolerance conditions in the immunotronic system for fault detection correspond to the antibodies in the biological immune system. A novel algorithm of generating tolerance conditions is suggested based on the principle of the antibody diversity and GA optimization is employed to select mature tolerance conditions in immunotronic fault detection system. The suggested method is applied to the fault detection for MCNC benchmark FSMs (finite state machines) and its effectiveness is demonstrated by the computer simulation.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.73-82
• /
• 2013

In pattern classification, feature selection is an important factor in the performance of classifiers. In particular, when classifying a large number of features or variables, the accuracy and computational time of the classifier can be improved by using the relevant feature subset to remove the irrelevant, redundant, or noisy data. The proposed method consists of two parts: a wrapper part with an improved genetic algorithm(GA) using a new reproduction method and a filter part using mutual information. We also considered feature selection methods based on mutual information(MI) to improve computational complexity. Experimental results show that this method can achieve better performance in pattern recognition problems than other conventional solutions.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권1호
• /
• pp.59-64
• /
• 2002

In the sender-initiated load balancing algorithms, the sender continues to send an unnecessary request message fur load transfer until a receiver is found while the system load is heavy. Meanwhile, in the receiver-initiated load balancing algorithms, the receiver continues to send an unnecessary request message for load acquisition until a sender is found while the system load is light. These unnecessary request messages result in inefficient communications, low CPU utilization, and low system throughput in distributed systems. To solve these problems, in this paper, we propose a genetic algorithm based approach fur improved sender-initiated and receiver-initiated load balancing. The proposed algorithm is used for new adaptive load balancing approach. Compared with the conventional sender-initiated and receiver-initiated load balancing algorithms, the proposed algorithm decreases the response time and increases the acceptance rate.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 합동 추계학술대회 논문집 정보 및 제어부문
• /
• pp.87-91
• /
• 2002

The problem of maneuvering target tracking has been studied in the field of the state estimation over decades. The Kalman filter has been widely used to estimate the state of the target, but in the presence of a maneuver, its performance may be seriously degraded. In this paper, to solve this problem and track a maneuvering target effectively, a DNA coding-based interacting multiple model (DNA coding-based IMM) method is proposed. The proposed method can overcome the mathematical limits of conventional methods by using the fuzzy logic based on DNA coding method. The tracking performance of the proposed method is compared with those of the adaptive IMM algorithm and the GA-based IMM method in computer simulations.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권3호
• /
• pp.283-287
• /
• 2004

In this paper, a method of designing the efficient batch blind equalization with low complexity using a micro genetic algorithm (GA), is presented. In general, the blind equalization techniques that are focused on the complexity reduction might be carried out with minor effect on the performance. Among the advanced various subjects in the field of GAs, a micro genetic algorithm is employed to identity the unknown channel impulse response in order to reduce the search space effectively. A new cost function with respect to the constant modulus criterion is suggested considering its relation to the Wiener criterion. We provide simulation results to show the superiority of the proposed techniques compared to other existing techniques.

• 전자공학회논문지S
• /
• 제34S권3호
• /
• pp.63-73
• /
• 1997

For the practical applications of the EIT technology, it is essential to reconstruct sttic images iwth a higher spatial resolution in a reasonalble amount of processing time. Using the conventional EIT static image reconstruction algorithms, however, the processing time increases exponential with poor convergence characteristics as we try to get a higher spatial resolution. In order to overcome this problem, we developed a recursive mesh grouping method based on the Fuzzy-GA like algorithm. Computational simulation using the well-known improve dewton-raphson method with the proposed recursive mesh grouping algorithm shows a promising result that we can significantly reduce the processing time in the reconstruction of EIT static images of a higher spatial resolution.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
• /
• pp.118-121
• /
• 2002

The problem of maneuvering target tracking has been studied in the field of the state estimation over decades. The Kalman filter has been widely used to estimate the state of the target, but in the presence of a maneuver, its performance may be seliously degraded. In this paper, to solve this problem and track a maneuvering target effectively, DNA coding-based intelligent Kalman filter (DNA coding-based IKF) is proposed. The proposed method can overcome the mathematical limits of conventional methods and can effectively track a maneuvering target with only one filter by using the fuzzy logic based on DNA coding method. The tracking performance of the proposed method is compared with those of the adaptive interacting multiple model (AIMM) method and the GA-based IKF in computer simulations.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권4호
• /
• pp.275-280
• /
• 2009

A Genetic Algorithm (GA) is a kind of search techniques used to find exact or approximate solutions to optimization and searching problems. This paper discusses the design of a genetic algorithm-based intelligent parking system. This is a search strategy based on the model of evolution to solve the problem of parking systems. A genetic algorithm for an optimal solution is used to find a series of optimal angles of the moving vehicle at a parking space autonomously. This algorithm makes the planning simpler and the movement more effective. At last we present some simulation results.