• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.1
• /
• pp.49-53
• /
• 2008

A fuzzy inference logic system is proposed for gas turbine engine fault isolation. The gas path measurements used for fault isolation are exhaust gas temperature, low and high rotor speed, and fuel flow. The fuzzy inference logic uses rules developed from a model of performance influence coefficients to isolate engine faults while accounting for uncertainty in gas path measurements. Inputs to the fuzzy inference logic system are measurement deviations of gas path parameters which are transferred directly from the ECM(Engine Control Monitoring) program and outputs are engine module faults. The proposed fuzzy inference logic system is tested using simulated data developed from the ECM trend plot reports and the results show that the proposed fuzzy inference logic system isolates module faults with high accuracy rate in the environment of high level of uncertainty.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1187-1194
• /
• 2020

We presented a method of deep quiz cropping for automatic construction of quiz pool in online quiz systems. The method detects question boxes and sunda boxes in images captured from test papers by a deep learning-based object detector, and makes pairs of question box and sunda box by the box coupling. We applied the deep quiz cropping to images captured from test papers and achieved successful results.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1999.07a
• /
• pp.177-182
• /
• 1999

시설농업의 정치식 자동화장치들을 비롯하여 노지 재배를 위한 자율주행형 로봇에 이르기까지 무인화를 위한 노력이 농업의 전반에 확대되고 있으며 원격제어와 무선통신은 이를 실현하기 위한 중요한 기술수단으로 인식되고 있다. 일반적인 무선제어 장치의 발전과정을 보면 보다 많은 제어채널에 대한 정보전송, 확실하고 오류 없는 신호의 전송을 위한 전파방해 대책, 소형 경량화라는 3가지의 기술적 실현과정으로 집약할 수 있다. (중략)

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.110-113
• /
• 2009

로봇을 이용한 체조 학습 시스템을 위해서는 영상을 통한 사람의 자세 인식기법이 필요하다. 본 논문에서는 Chamfer Matching을 이용한 두 영상간의 에지 윤곽 비교를 통해 자세를 인식한다. 또한, 비교대상이 되는 에지의 크기를 조절함으로서 여러 사람에 대한 신뢰성 있는 인식 결과를 얻는다. 실험결과를 통해 알 수 있듯 에지의 크기 조절에 의해 서로 다른 사람간의 비교값 편차를 줄임으로써 인식률을 향상시키고 인식 오류를 최소화 하였다.

• Journal of Korea Multimedia Society
• /
• v.16 no.2
• /
• pp.213-225
• /
• 2013

This paper proposes a design method of ball-plate robot controller using single camera and two motors to balance the ball on plate and reduce steady state control error. To design the ball-plate system, it is necessary to observe state of the ball and maintain balance of the plate. The state of the ball is tracked by using the CAMShift algorithm and position error of the ball is compensated by the Kalman filter. Balance of the plate is controlled by driving two motors and we used DC motors which has smaller measurement error. Due to surface condition of the plate or tracking error of ball's position, there are small errors remained. These errors are accumulated and disturb maintaining balance of the ball. To handle the problem, we propose a controller supplemented with an integrator.

• The Journal of the Korea Contents Association
• /
• v.18 no.7
• /
• pp.322-329
• /
• 2018

Teleoperation is defined with a master device that gives control command and a slave robot in a remote site. In this field, it is common that a human operator executes and experiences teleoperation with a virtual slave, and preliminary learns dynamic characteristic and network environment from both agents. Generally, a virtual slave has neglected forward dynamics and its kinematic model has been implemented in computer graphics. This makes a operator to experience actual feelings. This paper proposes a dynamic teleoperation model in which a robotic forward model is applied. Also, a novel compensation method is proposed to reduce the numerical error problems in forward dynamics caused by low control sampling rate. Finally, its results will be compared to the teleoperation in an actual environment.

• 한국정보교육학회:학술대회논문집
• /
• 2011.01a
• /
• pp.23-28
• /
• 2011

It is possible to solve many structural problems such as the occurrence of a lot of errors involving misspelling which may occur during the learning of existing programming language, difficulty in grammatical expression and understanding, and difficulty in the expression of algorithm if the program learning tool of the department of computer education in a college of education is utilized as an educational robot. This study developed a learning model (curriculum and a textbook) so that students who major in computer education may easily learn programming by using the NXT software of a Mindstorms robot.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.319-323
• /
• 2006

본 논문에서는 동작 모델과 작업 목표에 따라 지능 로봇 시스템의 작업 순서를 결정하는 작업 계획기의 설계와 데모시스템에 대해 설명한다. 블랙보드 중심의 분산 제어 구조에서 하나의 독립적인 지식원으로 동작하는 작업 계획기는 작업 관리기의 요청이 있을 때마다 지식베이스로부터 동작 모델과 월드 상태 정보를 제공받아 작업 목표 달성을 위한 작업 계획을 생성한다. 그리고 이렇게 생성된 작업 계획은 오류로 인해 재 계획이 필요할 때까지 작업 관리기를 통해 실행된다. 본 연구의 작업 계획기는 효율적인 작업 계획 생성을 위해 지역 상태공간 탐색법의 하나인 EHC+ 탐색법과 계획그래프-기반의 휴우리스틱 계산법을 적용한다. 본 논문에서는 작업 계획기의 효율성과 블랙보드와의 연계성을 시험하기 위한 데모 시스템에 대해 자세히 설명한다. 이를 통해 지식베이스, 작업 관리기, 컴포넌트 서비스기 등 로봇 제어 구조내의 다른 지식원들과의 인터페이스를 위한 메시지 설계도 소개한다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.8
• /
• pp.342-347
• /
• 2020

Recently, as the collaborative robot has been introduced into the domestic industrial robot market, it is installed mainly in the manufacturing industry. Collaborative robots are subject to the safety regulations of industrial robots by Article 93 of the Safety Inspection of the Industrial Safety and Health Act. The sites where collaborative robots are to be installed must perform risk assessments for robots-humans, work environments, and work methods and reduce the risks according to ISO 10218-2 and ISO 12100. On the other hand, because it is early in the introduction of collaborative robots, new risks for collaborative robots have not been issued, and risk assessments are unfamiliar and difficult to apply in the workplace. The risk assessment of collaborative robots aims to identify and reduce the risk of a high probability of occurrence by focusing on the abnormal behavior of humans, human errors, equipment defects, and interlock functions. In this study, a risk assessment was applied to a domestic automobile parts production plant, and improvement measures were drawn. This risk assessment is expected to be useful for improving the safety of small businesses by continuously discovering risk assessment examples of collaborative robots.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.8
• /
• pp.2975-2982
• /
• 2010

In this paper, embedded control system of segway robot using model based design is presented. Design of control program in embedded system can be implemented simply and easily by model based design method using MATLAB/SIMULINK. Segway robot is consisted of a NXT Mindstorms controller, two DC servo motors, a ultrasonic sensor, a gyro sensor, and a light sensor. It is a unstable nonlinear system and has a control problem of body pitch angle. So controller of segway robot is designed using state feedback LQR control. It is confirmed through design and experiment of controller that the model based design method, that is not depend on target processor, has merits compared with the text based design in aspects such as a program development, an error detection/modify, and an insight of software structure.