• Journal of Welding and Joining
• /
• 제27권5호
• /
• pp.62-67
• /
• 2009

Welding deformation during the assembly process is affected by not only local shrinkage due to rapid heating and cooling, but also root gap and misalignment between parts to be welded. Therefore, the prediction and control of welding deformation have become of critical importance. In this study, it was focused on the development of the 3-axis apparatus for real-time measurement of the welded deformation. To achieve the objective, a D-H algorithm has been carried out to check the behavioral and performance evaluation for the developed robot. The sequence experiments were taken the base materials of $400{\times}200{\times}4.5mm$ plate for butt welding. The real-time experimental measurements are in good agreement with the measured results.

• Journal of Advanced Research in Ocean Engineering
• /
• 제3권3호
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제15권1호
• /
• pp.53-59
• /
• 2015

This paper proposes a novel method for acoustically and wirelessly transmitting data underwater with a high transmission rate. The method uses the most promising physical layer and multiple access technique (i.e., the code division multiple channel access technique) to divide the channel into subchannels. Data is transmitted through these subchannels. The codes are pseudo-random noise (PN) sequences. In the spread-spectrum technique, a signal such as electrical, electromagnetic, acoustic signal generated in a particular bandwidth is deliberately spread in the frequency domain, which results in a signal with a wider bandwidth. This paper reviews the possibility of application of the direct-sequence code division multiple access (DS-CDMA) technique in an underwater system using MATLAB. As the result of our review, we recognize that the DS-CDMA technique can be applied to underwater environments.

• 전기학회논문지
• /
• 제66권10호
• /
• pp.1508-1515
• /
• 2017

This paper proposes the defect detection method for automatic inspection machines in printed circuit boards (PCBs) manufacturing system. The defects of PCB such as open, short, pin hole and scratch can be detected by comparing the standard image and the target image. The standard image is obtained from CAD file such as ODB++ format, and the target image is obtained by arranging, filtering and binarization of captured PCB image. Since the PCB size is too large and image resolution is too high, the image processing requires a lot of memory and computational time. The wavelet transform is applied to compress the standard and target images, which results in reducing the memory and computational time. To increase the inspection accuracy, we utilize the he HH-domain as well as LL-domain of the transformed images. Experimental results are finally presented to show the performance improvement of the proposed method.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1391-1399
• /
• 2015

In recent times, studies sentiment analysis are being actively conducted by implementing natural language processing technologies for analyzing subjective data such as opinions and attitudes of users expressed on the Web, blogs, and social networking services (SNSs). Conventionally, to classify the sentiments in texts, most studies determine positive/negative/neutral sentiments by assigning polarity values for sentiment vocabulary using sentiment lexicons. However, in this study, sentiments are classified based on Thayer's model, which is psychologically defined, unlike the polarity classification used in opinion mining. In this paper, as a method for classifying the sentiments, sentiment categories are proposed by extracting sentiment keywords for major sentiments by using hashtags, which are essential elements of Instagram. By applying sentiment categories to user posts, sentiments can be determined through the similarity measurement between the sentiment adjective candidates and the sentiment keywords. The test results of the proposed method show that the average accuracy rate for all the sentiment categories was 90.7%, which indicates good performance. If a sentiment classification system with a large capacity is prepared using the proposed method, then it is expected that sentiment analysis in various fields will be possible, such as for determining social phenomena through SNS.

• 전자공학회논문지SC
• /
• 제41권3호
• /
• pp.17-24
• /
• 2004

동일한 작업을 반복하여 수행하는 불확실한 로봇 시스템을 위한 P형 반복 학습 제어기를 제안한다. 제안된 반복 학습 제어기는 조인트 위치 오차로 구성되는 선형 피드백 제어기와 현재의 조인트 속도 오차로 갱신되는 피드포워드 및 피드백 학습 제어기로 구성된다. 반복 작업 동작이 계속 진행됨에 따라 조인트 위치와 속도 오차는 균일하게 0으로 수렴한다. 반복 횟수에 따라 변화하는 학습 이득을 채택함으로서 반복 횟수 영역에서 임의적으로 수렴 비율을 조절할 수 있는 조인트 위치, 속도 오차한계를 제시하고, 조인트 위치와 속도 오차는 그 한계 내에서 반복 횟수 영역에서 0으로 수렴한다. 기존의 P형 반복 학습 제어기와는 달리 제안된 반복 학습 제어 알고리즘은 학습 이득을 적절하게 설계함으로써 반복 횟수 영역에서 오차 수렴 비율의 분석과 조정을 가능하게 하는 장점이 있다.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제8권3호
• /
• pp.243-251
• /
• 2016

Autonomous Underwater Vehicles (AUVs) generally work in complex marine environments. Any fault in AUVs may cause significant losses. Thus, system reliability and automatic fault diagnosis are important. To address the actuator failure of AUVs, a fault diagnosis method based on the Gaussian particle filter is proposed in this study. Six free-space motion equation mathematical models are established in accordance with the actuator configuration of AUVs. The value of the control (moment) loss parameter is adopted on the basis of these models to represent underwater vehicle malfunction, and an actuator failure model is established. An improved Gaussian particle filtering algorithm is proposed and is used to estimate the AUV failure model and motion state. Bayes algorithm is employed to perform robot fault detection. The sliding window method is adopted for fault magnitude estimation. The feasibility and validity of the proposed method are verified through simulation experiments and experimental data.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2017년도 제55차 동계학술대회논문집 25권1호
• /
• pp.147-150
• /
• 2017

지능형 로봇의 사용자 품질을 결정하는 주요 요소들 중 하나는 짧은 부트 시간이다. 로봇 시스템에서는 부팅 과정 중에 침입자인지, 자택 순찰, 개인 비서, 엔터테인먼트와 같은 다수의 응용들이 동시에 초기화되는데, 고품질의 사용자 경험을 제공하기 위해서는 사용자 응답성이 중요한 응용들이 우선적으로 초기화되어야한다. 이를 위해 리눅스 기반 로봇 시스템에서 부트 시간을 단축하기 위한 다양한 연구들이 진행되어 왔다. 하지만 이들은 단일 응용 각각에 대한 초기화 시간을 단축하는 연구들이며, 응용들 간에 CPU, 메모리, I/O와 같은 자원 경쟁에 의한 지연 요소를 고려하지 않고 있다. 본 논문에서는 응용들 간의 각종 자원경쟁들을 고려하여 사용자 응답성이 중요한 응용을 우선적으로 초기화하기 위한 외부 컨텍스트 기반 선별적 자원 사용률 조정기법을 제안한다. 이를 리눅스 기반 시스템 상에 구현하여 검증한 결과 응용의 부트 시간이 기존 대비 33.02% 단축됨을 확인했다.

• 한국정밀공학회지
• /
• 제22권11호
• /
• pp.82-90
• /
• 2005

Recently, the in-line vision inspection has become the subject of growing research area in the visual control systems and robotic intelligent fields that are required exact three-dimensional pose. The objective of this article is to study the pc based in line visual inspection with the hand-eye structure. This paper suggests three dimensional structured light measuring principle and design method of laser sensor header. The hand-eye laser sensor have been studied for a long time. However, it is very difficult to perform kinematical analysis between laser sensor and robot because the complicated mathematical process are needed for the real environments. In this problem, this paper will propose auto-calibration concept. The detail process of this methodology will be described. A new thinning algorithm and constrained hough transform method is also explained in this paper. Consequently, the developed in-line inspection module demonstrate the successful operation with hole, gap, width or V edge.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 1996년도 International Conference on Agricultural Machinery Engineering Proceedings
• /
• pp.142-159
• /
• 1996

Engineering of automated tools for the agro-food industries and the rural world activities have to pick up two challenges : to answer the immediate important problems related to the situation of these industries, and to imaging the tools that their professional will need next century. Creating or modifying automated tools in the next few will be made taking into account parameters either technical (environmental protection, health and safety), or social and economical (investment , employment). There will be a strong interaction with disciplines like ecology, medicine, ergonomy, psycho-sociology , etc. , The partners for such a research, tools manufactures and users, should have an early involvement in its content, in order to find rapidly the solution to the drastic problems they are meeting. On a longer term , during the next 20 years , there will be an important evolution of the rural space management and of the food processes. This will imply the emergence of new types of activities and know-how's , with lines of automated tools to be invented and developed , like : micro-system for organic localized tasks -mobile and adaptive equipments highly autonomous for natural space actions - device for perception , decision and control reproducing automatically the expert behaviors of human operators. Design of such automated tools need to overcome technological difficulties like the automation of the expert-decision process, or the management of complex design.