• 한국항해항만학회지
• /
• 제31권7호
• /
• pp.563-568
• /
• 2007

In this paper, an adaptive neural network controller and its application to automatic berthing control of ship is presented. The neural network controller is trained online using adaptive interaction technique without any teaching data and off-line training phase. Firstly, the neural networks used to control rudder and propeller during automatic berthing process are presented. Secondly, computer simulations of automatic ship berthing are carried out in Pusan bay to verify the proposed controller under the influence of wind disturbance and measurement noise. The results of simulation show good performance of the developed berthing control system.

• 한국정보통신학회논문지
• /
• 제18권7호
• /
• pp.1525-1530
• /
• 2014

본 논문은 산업용 로봇을 위한 힘 피드백 제어 기반의 연마면의 보정과 작업자의 감각을 기반으로 한 정확한 연마면 작업을 대체하기 위한 교시방법을 적용한 연마 결과를 제시하였다. 교시방법은 연마작업의 위치, 경로, 반응에 대한 정밀도 개선을 위해서 연마로봇에 적용하였다. 힘 센서 기반의 교시방법에 의해 연마가 가능한 선박용 연마로봇을 제시하였고, 힘 센서에 의한 교시방법을 연마로봇에 적용하여 실험한 결과를 제시함으로써 그 유효성을 검증하였다. 또한, 로봇교시 포인터의 수를 줄이기 위하여 가공면의 특이점들만을 이용하여 곡면 가공이 가능하도록 로봇 궤적을 생성하는 방안을 제시하여 실험결과를 제시하였다.

• 의료ㆍ복지 건축 : 한국의료복지건축학회 논문집
• /
• 제16권1호
• /
• pp.43-53
• /
• 2010

This study purports to investigate the status quo of the environmentally-friendly green healthcare in teaching hospitals through the questionnaire survey. Data were collected from a total of 46 hospitals. The survey results revealed that most teaching hospitals did not meet the global standard of environmentally-friendly green hospitals. Especially, such items as alternative energy system, water recycling, CO2 emission reduction, green building construction, installation of pond or spring were found to be significantly below global standard. Based upon the study results, various strategies for establishing green hospitals were discussed. For example, energy saving design, such as solar heating, natural wind cooling, automatic temperature controller, green material use, wall surrounded by ivy, were recommended. In conclusion, the strategy and evaluation tool developed in the study will provide a good guide for establishing environmentally-friendly green hospitals.

• 한국지구과학회지
• /
• 제28권4호
• /
• pp.431-444
• /
• 2007

인터넷상에서 관측할 수 있는 36 츠 자동화 망원경이 개발되었다. 이 시스템의 추적 오차는 약 1"/분이고, 지향 정밀도는 적경 방향에서 약 ${\pm}10"$, 적위 방향에서 약 ${\pm}20"$였다. 이것은 계속 개선되어나갈 것이다. 예비관측을 통해 얻은 영상자료를 IRAF를 통해 분석해본 결과 비교적 안정적인 결과를 보여주었다. 이러한 결과는 원격천체관측 교육에 활용할 수 있음을 의미한다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1995년도 Proceedings of the Korea Automation Control Conference, 10th (KACC); Seoul, Korea; 23-25 Oct. 1995
• /
• pp.83-86
• /
• 1995

This paper proposes an auto-tuning method of feedforward signal in boiler control of thermal power plants by using the neural network. The neural network produces an optimal feedforward signal by tuning the weights of the network. The weights are adapted effectively by using the teaching signal of PI control output. The proposed method was evaluated based on a detailed simulator which expressed non-linear characteristics of the 600 MW actual thermal power plant at load chaning operations, showed effectiveness in the learning of the weights of the neural network, and gave an accurate control performance in the temperature control of the system. Through the evaluation, the proposed method was proved to be effectively applicable to the actual thermal plants as the automatic adjustment tool.

• 전기학회논문지
• /
• 제61권3호
• /
• pp.472-478
• /
• 2012

The inspection machine in PCB (printed circuit board) assembly line checks assembly errors by inspecting the images inside of the component inspection region. The component inspection region consists of region of component package and region of soldering. It is necessary to extract the regions automatically for auto-teaching system of the inspection machine. We propose an image segmentation method to extract the component inspection regions automatically from images of PCB. The acquired image is transformed to HSI color model, and then segmented by several regions by clustering method. We develop a modified K-means algorithm to increase the accuracy of extraction. The heuristics generating the initial clusters and merging the final clusters are newly proposed. The vertical and horizontal projection is also developed to distinguish the region of component package and region of soldering. The experimental results are presented to verify the usefulness of the proposed method.

• 한국컴퓨터정보학회논문지
• /
• 제11권5호
• /
• pp.53-58
• /
• 2006

본 논문에서는 영상처리 기법을 이용하여 골프 스윙 자동 분석을 위한 특징 추출 방법을 제안하였다. 기존 대부분의 스윙 분석 시스템들이 골프 코치와 같은 전문가가 필요한 반면 제안한 특징 추출 방법을 이용하면 전문가의 도움 없이 중요한 스윙 특징을 추출할 수 있다. 추출한 특징은 어드레싱, 백스윙, 스윙탑, 포워드 스윙, 임팩트, 팔로우쓰루와 같은 키 프레임뿐만 아니라 손, 어깨, 클럽헤드, 발, 무릎과 같은 골퍼의 신체부위와 클럽의 위치까지 포함 한다. 제안한 방법의 효용성을 알기 위하여 스윙영상에 대하여 실험한 결과 제안한 방법이 중요한 골프 스윙 특징 추출에 유용함을 확인하였다.

• 정보처리학회논문지D
• /
• 제13D권7호
• /
• pp.931-938
• /
• 2006

통합 운영의 중요성이 대두되고 있으나 기존 교육 정보 시스템은 표준화 기반으로 개발되지 못하고 있다. 이로 인해 교육적 Asset의 필요성과 재사용 가능한 교육 서비스의 확보가 시급한 실정이다. 이미 개발된 컨텐츠의 활용도를 높이기 위해 특히 국제적 표준인 Sharable Content Object Reference Model(SCORM)을 기반으로 컨텐츠를 관리하고, 교육용 어플리케이션 개발도 재사용이 가능한 Asset을 이용하여 조립, 생산할 수 있는 방안이 필요하다. 본 논문에서는 체계적인 교육자원을 개발하고 지원하기 위한 교수-학습지원 시스템 개발에 초점을 두었다. 교육적 도메인의 접근과 Model Driven Architecture(MDA) 개발 프로세스의 각 단계별 Asset을 통해 시스템을 개발한다. 또한, 학습 컨텐츠 메타 모델을 기반으로 컨텐츠 저장소에 관한 분석과 설계를 통하여 MDA 자동화 도구를 이용한 교수-학습지원 시스템을 개발하고자 한다. 이를 통해 교수자와 학습자가 필요로 하는 교육컨텐츠 재사용성을 높이고 전체 개발 프로세스의 Asset을 이용하여 교육용 응용소프트웨어 개발 기간의 단축과 개발비용의 절약 및 생산성을 높일 수 있다.

• 공학교육연구
• /
• 제19권2호
• /
• pp.3-7
• /
• 2016

A flow control system was designed and fabricated to control the flow rate of liquid through the pipe. This control system was composed of hardwares and software, hardwares as controller, gate valve, orifice meter and data aquisition board and software as National instruments Labview program. Control of flow rate was executed by adjusting the pneumatic valve located at the center of pipe line based on the control signal generated by LabView PID control algorithm, which converts analog signal measured by pressure difference of orifice to digital signal to adjust pneumatic valve. For the controller setup Ziegler-Nichols tuning technique was applied and control performances were investigated for not only the disturbance but also the set point changes. Developed system showed good control performances in flow control enough to use as teaching tool of feedback control theory and practice in university, and also as industrial application.

• Educational Technology International
• /
• 제25권1호
• /
• pp.67-92
• /
• 2024

This study aims to verify the practical effectiveness of learning management system (LMS) by introducing a LMS enhancing digital assessment utilizing automatic item generation in order to strengthen college student's mathematics performance. Teaching assisted with digital assessment in the LMS was applied to college mathematics classes, and the research question is whether or not students in the classes utilizing the LMS perform better than the regular classes. In particular, a calculus course, which is the foundation of important artificial intelligence technology in the future, was utilized in this study. The participants of this study were 248 freshmen in science and engineering who were taking calculus courses at a small to mid-size university. A total of 156 freshmen were selected after applying a propensity score matching method (PSMM), 78 from classes utilizing the LMS and 78 from regular classes without the LMS assisted with the digital assessment. As a result, it was found that there was a statistically significant difference in the math academic growth of students who used the LMS and those who did not. In other words, when LMS was used in calculus, students' academic growth was greater. The results of this study are meaningful in that they observed students' academic growth and confirmed that LMS enables a positive role in students' academic growth. In addition, if digital assessment is strengthened and LMS that enables individualized learning analysis is introduced and implemented in educational institutions, it is expected to play a major role in strengthening students' academic performance.