• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1995.10b
• /
• pp.174-179
• /
• 1995

본 논문데서는 부하외란이나 시스템 내부 파라미터의 변동시에 적응력이 저하되는 종래의 PI제어기와, 정상상태 잔류편차가 존재하는 퍼지 제어기의 단점을 극복하기 위한 적 응 퍼지 제어 기법을 제안하였고, 이를 도립 진자 시스템에 적용하였다. 운송차의 위치 및 진자 각도의 오차, 오차의 변화량에 따라 퍼지 추론을 행하여 PI 제어기의 가중치를 결정하 는 구조로, P제어기는 운송차 및 진자의 오차가 과도 상태에서의 영역에서 사용되어 속응성 과 고정도의 특성을 얻는다. 1제어기는 정상상태에서의 정도 향상에 이용되었다. 특히, 제안 하는 적응 퍼지 제어기는 운송차의 위치 오차에 대한 PI 동작과, 진자의 각도 오차에 대한 PI 동작을 각각 퍼지 추론에 의해 부드럽게 전환함으로서 고유 불안정의 시스템인 도립 진 자 시스템의 안정화 제어에 적용하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.353-356
• /
• 2002

본 논문은 카오스 신호를 이용하여 안전한 음성신호의 전송을 위한 아날로그 비화통신 시스템의 성능분석에 관한 연구이다. 기존의 카오스 동기화 및 카오스 변조통신 알고리즘을 개선하여 실제 통신환경에서 발생하는 다양한 조건들을 적용하여 음성신호의 복원능력을 모의실험으로 분석하였다. 일반적인 PC 제어기법과 제안한 피드백 마스킹 기법을 사용하여 송신단에서 음성신호를 카오스 신호로 마스킹하여 변조하고, 통신채널에 잡음신호를 추가하여 전송하였다. 수신단에서는 카오스 응답시스템을 이용하여 음성신호를 복조하고, 복원성능을 계산하기 위하여 아날로그 복원 에러신호의 평균전력을 제안하여 계산하였다. 실험결과 마스킹 정도, 파라미터들의 민감성, 채널잡음 등에 대하여 PC 제어기법보다 피드백 제어기법의 복원성능이 우수함을 확인할 수 있었다. 또한 로렌쯔 카오스 시스템을 비화통신시스템에 사용할 경우 파라미터들의 조합으로 암호키를 구성해야 하므로 키값들의 선정에 기준이 되는 파라미터 변화율에 대응하는 복원에러율의 관계를 실험 값으로 구하였다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.89-92
• /
• 2002

최근 들어 급증하고 있는 해양 충돌 사고 증가의 원인은 선박을 조종하는 항해사의 잘못된 판단 에 의한 부주의가 대부분이다. 이러한 문제를 해결하기 위한 가장 적극적인 방법은 선박에 자동화 및 지능화를 부여하여 항해사의 실수를 최소화하는 것이다. 대표적인 연구는 선박의 자율운항시스템(autonomous navigation system)이 있는데, 이는 선박운항에 있어 항해계획을 수립하고 현재의 선박의 상태를 파악하여 선박을 적절히 제어하는 항해 전문가시스템이다. 선박 자율운항시스템은 실세계의 선박에 장착되어 실험하여야하나, 선박은 고가의 운송수단이고, 자율운항시스템을 장착하기 위한 하부장치 인터페이스를 설계 및 구현에 많은 시간이 소요되므로 실제 선박을 모방하는 선박시뮬레이터를 이용하는 방법이 타당하다. 선박시뮬레이터는 선박의 물리적 운항특성을 모방하는 선박운동시뮬레이터와 선박 운항 주변에 변화하는 장애물을 시뮬레이터 하는 주변 객체시뮬레이터로 구성된다. 본 연구에서는 선박 운항 주변에 등장하는 장애물 변화를 시뮬레이션하고, 이에 기반한 ARPA RADAR를 모의 가동하는 주변객체시뮬레이터를 개발한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.9 no.5
• /
• pp.480-489
• /
• 1999

Design and experimental results of yaw rate controller is described for electricallydriven four wheel vehicle without steering mechanism. Yaw rate controller has been known to be necessary to cope with nonlinear char-acteristics of the wheel/road conditions with respect to different road condition and steering angle. For an effective yaw rate control, a fuzzy PID gain scheduler is considered with changing control parameters. In order to apply proposed algorithm to the system a downsized four wheel drive electrically driven vehicle without steering mechanism was manufactured. With these techniques the proposed yaw rate controller is shown by experiment results to be obtained suficient performance in the whole steering regions.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.4
• /
• pp.331-334
• /
• 2006

Original Support Vsctor Machines (SVMs) by Vapnik were used for binary classification problems. Some researchers have tried to extend original SVM to multiclass classification. However, their studies have only focused on classifying samples into nominal categories. This study proposes a novel multiclass SVM model in order to handle ordinal multiple classes. Our suggested model may use less classifiers but predict more accurately because it utilizes additional hidden information, the order of the classes. To validate our model, we apply it to the real-world bond rating case. In this study, we compare the results of the model to those of statistical and typical machine learning techniques, and another multi class SVM algorithm. The result shows that proposed model may improve classification performance in comparison to other typical multiclass classification algorithms.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.2
• /
• pp.108-112
• /
• 2012

A sustainable production of electricity is essential for low carbon green growth in South Korea. The generation of wind power as renewable energy has been rapidly growing around the world. Undoubtedly wind energy is unlimited in potential. However, due to its own intermittency and volatility, there are difficulties in the effective harvesting of wind energy and the integration of wind power into the current electric power grid. To cope with this, many works have been done for wind speed and power forecasting. It is reported that, compared with physical persistent models, statistical techniques and computational methods are more useful for short-term forecasting of wind power. Among them, support vector regression (SVR) has much attention in the literature. This paper proposes an SVR based wind speed forecasting. To improve the forecasting accuracy, a fuzzy clustering is adopted in the process of SVR modeling. An illustrative example is also given by using real-world wind farm dataset. According to the experimental results, it is shown that the proposed method provides better forecasts of wind power.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.3
• /
• pp.255-260
• /
• 2002

This paper describes a fuzzy-based system for analyzing the stress intensity factors (SIFs) of three-dimensional (3D) cracks. A geometry model, i.e. a solid containing one or several 3D cracks is defined. Several distributions of local node density are chosen, and then automatically superposed on one another over the geometry model by using the fuzzy knowledge processing. Nodes are generated by the bucketing method, and ten-coded quadratic tetrahedral solid elements are generated by the Delaunay triangulation techniques. The singular elements such that the mid-point nodes near crack front are shifted at the quarter-points, and these are automatically placed along the 3D crack front. The complete finite element(FE) model is generated, and a stress analysis is performed. The SIFs are calculated using the displacement extrapolation method. To demonstrate practical performances of the present system, semi-elliptical surface cracks in a inhomogeneous plate subjected to uniform tension are solved.

• 한국방재학회:학술대회논문집
• /
• 2008.02a
• /
• pp.609-612
• /
• 2008

Since most of the industries have adopted automation system, the industrial disaster has been declined sharply. Also automation system has offered many benefits such as productivity and assured quality. However, the construction industry is still relying on man power and because of this there are many victims occurring due to the industrial disaster. Construction industry has to overcome uncertainty of incidents and changing natural surroundings to actualize automation. Therefore, the efficient working plan and intelligent decision making process are needed to run more developed techniques and automations. Specially to decline the rate of industrial accidents occurred in basic construction in earth work, the automation via excavator is necessary and also the development of planning process system is too. This research is to establish Task Planning System to prevent disaster which is used for planning automated earth work.

• International Journal of High-Rise Buildings
• /
• v.8 no.3
• /
• pp.185-192
• /
• 2019

Citic Tower is the first over-500 m-tall super highrise building in the world, located in the high seismic intensity area with paek ground acceleration over 0.2g in 475 years. This project is unique in its complexity, large volume, and challenging site conditions (zero site for construction). The traditional techniques can hardly meet safty, quality and schedule requirements of the construction. This article introduces the key construction technologies that are innovatively developed and applied in Citic Tower project construction, including intelligent super-high-rise building integrated construction platform system, independently developed by the CCTEB; Jump-Lift Elevator, which is the first of the kind with service height over 500 meters; combined temporary-and-permanent fire protection systems. The BIM technology is also applied in this project. Through technical innovation, and utilization of technologies, construction speed and safety had been greatly improved.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.25-33
• /
• 2019

In this paper, we propose an intelligent CCTV technology which is applied to a recent attracted attention real-time object detection technology in a disaster alarm system. Natural disasters are rapidly increasing due to climate change (global warming). Various disaster alarm systems have been developed and operated to solve this problem. In this paper, we detect object through Neuron Network algorithm and test the difference from existing SVM classifier. Experimental results show that the proposed algorithm overcomes the limitations of existing object detection techniques and achieves higher detection performance by about 15%.