• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.343-346
• /
• 1996

A new method for on-line induction motor fault detection is presented in this paper. This system utilizes unsupervised-learning clustering algorithm, the Dignet, proposed by Thomopoulos etc., to learn the spectral characteristics of a good motor operating on-line. After a sufficient training period, the Dignet signals one-phase ground fault, or a potential failure condition when a new cluster is formed and persists for some time. Since a fault condition is found by comparison to a prior condition of the machine, on-line failure prediction is possible with this system without requiring information on the motor of load characteristics.

• 아동학회지
• /
• 제25권4호
• /
• pp.177-190
• /
• 2004

Training for mothers and children first included information on water, ground, and air pollution, saving energy, and reducing trash. In the second phase, the family followed steps outlined in an environmental preservation guidebook. The experiment was of 16 weeks duration, conducted with 120 subjects, comprised of sixty 4-year-old children and their mothers. Measures included environmental preservation knowledge and the actual practice of environmental preservation on the part of the subjects. Mothers performed self-evaluations while teachers measured the children. SPSS was used for data collection and analysis. The results of this study indicate that the program increased perceptions on environmental preservation and the actual practice of the experimental group. The program application also resulted in meaningful co-relationships between perceptions and practice and between mothers and their children.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2005년도 춘계 학술발표회 논문집
• /
• pp.1324-1334
• /
• 2005

This study investigated the applicability of the Artificial Neural Network (ANN) technique for prediction of tunnel behavior. For training data collection, a series of finite element analyses were conducted for actual tunnel project site. Using the data, optimimzed ANNs were developed through a sensitivity study on internal parameters. The developed ANNs can make tunneling related predictions such as tunnel crown settlement, shotcrete lining stress, ground surface settlement, and groundwater inflow rate. The results indicated that the developed ANNs can be used as an effective and efficient tool for tunnelling related prediction in practical tunneling situations.

• 한국터널공학회:학술대회논문집
• /
• 한국터널공학회 2005년도 학술발표회 논문집
• /
• pp.105-116
• /
• 2005

This study investigated the applicability of the Artificial Neural Network(ANN) technique for prediction of tunnel behavior. For training data collection, a series of finite element analyses were conducted for actual tunnel project site. Using the data, optimimzed ANNs were developed through a sensitivity study on internal parameters. The developed ANNs can make tunneling related predictions such as tunnel crown settlement, shotcrete lining stress, ground surface settlement, and groundwater inflow rate. The results indicated that the developed ANNs can be used as an effective and efficient tool for tunnelling related prediction in practical tunneling situations.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 C
• /
• pp.1114-1117
• /
• 1998

Recent applications of neural networks to power system fault diagnosis have provided positive results and have shown advantages in process speed over conventional approaches. This paper describes the application of neural network to fault detection and classification in distribution lines using the fundamental component, 2-5th harmonics index, even and odd harmonics index, and zero phase current. The Electromagnetic Transients Program (EMTP) is used to obtain fault patterns for the training and testing of neural networks. The proposed fault detection and classification method in distribution lines is obtained by analysing the difference among normal, HIF, ground fault, short circuit fault condition.

• 한국산림과학회지
• /
• 제20권1호
• /
• pp.51-60
• /
• 1973

The trend and achievments of soil erosion control research in Japan were investigated through observation tours and reference work and following facts were found to be important aspects which should be considered in the soil erosion control research program in Korea. Experiments on forest and water relations, and ground water phenomena at the water source zone in Tokyo University. Studies on land-slides and erosion control dam in Kyoto University. Studies on mud-flow and snow avalanches in Hokkaido University. Studies on sanddune fixation and disaster damage prevention forests in Kyushu University. Studies on forest denudations in Nagoya University. Studies on Greening-works and soil erosion prevention chemicals in Tokyo Agriculture University. Training on planning of erosion control works and prevention of disaster damages in Forest Research Institute. Experiments on soil erosion phenomena and infiltration in Tohoku Branch, FRI. Experiments on erosion and surface stratum failure of steep slopes and their prevention methods in Railway Technical Research Institute.

• 국제학술발표논문집
• /
• The 3th International Conference on Construction Engineering and Project Management
• /
• pp.774-780
• /
• 2009

Simulation is becoming increasingly popular in construction for training, planning and for assessment of projects. There are, however, significant problems inherent in simulating construction which are not common to other simulations. This paper describes the development and use of computer-based game for teaching and learning of some aspects of construction project management. It is concerned with the development of a model used to simulate the construction of a rock- and clay-fill dam. It includes detailed physical modelling of the performance of individual pieces of equipment and their interaction with the ground, the geography of the project and the weather in which the equipment operates. The behaviour of all of the individual pieces of equipment when acting as fleets is also discussed. The paper also describes the modelling issues of non-technical aspects of earthmoving operations. These include environmental impact, safety, quality and risks. The problems of integrating these with the physics-based models of the equipment performance are discussed. The paper also draws on real experience of using the game in classes in three universities in different countries.

• ETRI Journal
• /
• 제45권5호
• /
• pp.735-745
• /
• 2023

This paper surveys recent multiagent reinforcement learning and neural Myerson auction deep learning efforts to improve mobility control and resource management in autonomous ground and aerial vehicles. The multiagent reinforcement learning communication network (CommNet) was introduced to enable multiple agents to perform actions in a distributed manner to achieve shared goals by training all agents' states and actions in a single neural network. Additionally, the Myerson auction method guarantees trustworthiness among multiple agents to optimize rewards in highly dynamic systems. Our findings suggest that the integration of MARL CommNet and Myerson techniques is very much needed for improved efficiency and trustworthiness.

• 전자통신동향분석
• /
• 제39권4호
• /
• pp.21-31
• /
• 2024

Major global powers are investing heavily in artificial intelligence (AI) and hyper-connected networks, demonstrating their crucial role in future warfare. To advance and utilize AI in national defense, it is essential to have policy support at the governmental or national level. This includes establishing a research and development infrastructure, creating a common development environment, and fostering AI expertise through education and training programs. To achieve advancements in hyper-connected networks, it is essential to establish a foundation for a robust and resilient infrastructure by comprehensively building integrated satellite, aerial, and ground networks, along with developing 5G & edge computing and low-orbit satellite communication technologies. This multi-faceted approach will ensure the successful integration of AI and hyper-connected networks, strengthening national defense and positioning nations at the forefront of technological advancements in warfare.

• 한국지반공학회논문집
• /
• 제18권5호
• /
• pp.37-42
• /
• 2002

인공신경망은 복잡한 상호관계를 가지는 문제의 해결을 위한 효과적인 컴퓨터 테크닉으로써 많은 분야에 활발히 활용되고 있다. 본 논문에서는 지반의 액상화 가능성을 판별하기 위하여 인공신경망 이론을 사용하였으며, 이를 위하여 반복삼축압축시험 결과와 토성자료, 지반조사자료 등을 학습인자로 사용하였다. 학습과 검증에 서해안지역의 43개의 반복삼축압축시험 데이터가 사용되었다. 여기서 인공신경망의 학습은 예측된 CSR과 실측한 CSR 사이의 오차가 적어지도록 신경망의 가중치를 수정하는 것으로 이루어진다. 전체 신경망에 대한 평균제곱의 오차가 허용치 이내로 감소할 때까지 학습은 반복되어 진행되며 일반적으로 15,000 이상의 학습이 요구되는 것으로 나타났다. 다양한 노드수를 가지는 신경망에 대한 학습을 수행한 결과, 1번째 은닉층의 수가 20개이고 2번째 은닉층의 수가 10개인 신경망이 72~98%에 해당되는 정밀도를 가지고 해당 전단변형률과 반복횟수에서의 CSR값을 예측할 수 있었다. 여기서 NOC(Number of Cycle)와$D_10$, ($N_1$)$_60$ 등의 입력변수가 지반의 액상화 거동에 주요한 영향인자로 나타났다. 연구결과 인공신경망을 이용한 지반의 액상화 거동의 예측이 비교적 정확하게 산정됨을 알 수 있었으며, CSR과 ($N_1$)$_60$, NOC와의 관계가 기존의 연구 결과에 부합하여 나타남을 알 수 있었다.