• 제어로봇시스템학회:학술대회논문집
• /
• 1988.10a
• /
• pp.579-583
• /
• 1988

As the power facilities grow up, the optimal operation and the best maintenance of power plant can not be overestimated too much, which can enhance the plant availability and reliability much further. In this respect, fault diagnosis methodologies of dynamic system which is time-varing and strongly nonlinear have been studied. On of them is to use algorithm which is based on time-invariant, linear system, but this is not so nice a method for applying to power Plant. Therefore, the study on other techniques using Artificial Intelligence (AI) is under way. In this paper, the existing ways of fault detection are surveyed and their problems are also discussed.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.206-206
• /
• 2000

This paper is ai ed to handle quick work for all the workers and to improve the productivity by adding more effective content in Crane Monitoring System. The contributing proportion of the increase of port productivity is more increasing concerning not only the port industry, but also all the informations of container crane which is the representative equipment by the rapid increase of the volume of freight of port. The basic of rapid service is the improvement of the productivity, the information of operation as to the productivity of crane for the quick handling within yard and especially the informations of breakdown and to handle breakdown as soon as possible has a great enect on the increase of productivity.

• The Journal of Korea Robotics Society
• /
• v.13 no.1
• /
• pp.1-7
• /
• 2018

The image-to-image translation is one of the deep learning applications using image data. In this paper, we aim at improving the performance of object transfiguration which transforms a specific object in an image into another specific object. For object transfiguration, it is required to transform only the target object and maintain background images. In the existing results, however, it is observed that other parts in the image are also transformed. In this paper, we have focused on the structure of artificial neural networks that are frequently used in the existing methods and have improved the performance by adding constraints to the exiting structure. We also propose the advanced structure that combines the existing structures to maintain their advantages and complement their drawbacks. The effectiveness of the proposed methods are shown in experimental results.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.1
• /
• pp.54-59
• /
• 2006

The smart space is composed of the wire and/or wireless network, multi-sensor-based environment, and many various controllers. For the smart space, this paper presents a new design method of multirate digital decentralized controller using the intelligent digital redesign technique. In specific, the proposed method is based on the delta-operator and the multirate sampling and takes the form of the LMIs. To shows the feasibility of the suggested method, the computer simulations for Heating, ventilating, and ai. conditioning (HVAC) system are provided.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.307-310
• /
• 2002

인공지능 로봇 계획 문제는 초기상태, 동작, 목적상태로 구성되며, 초기상태를 목적상태로 변화시키는 일련의 동작을 찾는 문제로서, 지수 복잡도 문제이다. 이러한 문제에 대한 접근 방법으로 인공지능 탐색이 널리 쓰인다. 본 논문에서는 아일랜드 탐색을 사용하는 방법을 소개한다. 아일랜드 탐색을 적용하려면 초기상태에서 목적상태로 변환하는 도중 꼭 거쳐야 하는 아일랜드를 제공해야 한다. 그러나 그러한 아일랜드를 찾는 것은 불가능한 일이다. 그러므로, 본 논문에서는 선취관계를 이용하여 적당한 아일랜드를 생성하여 사용한다. 로봇 계획 문제의 목적 상태를 구성하는 부분목적 사이에 어떤 부분 목적이 반드시 다른 어떤 부분 목적 보다 먼저 성취되어져야 하는 관계를 선취관계라 한다. 아일랜드를 프로세서 수만큼 생성하여, 각 프로세서에 하나의 아일랜드를 원래의 계획 문제와 함께 할당한다. 각 프로세서는 초기상태에서 아일랜드까지 가는 문제를 휴리스틱 방법으로 풀고, 아일랜드에서 목적 상태로 도달하는 문제를 또한 휴리스틱 방법으로 풀어 결합함으로써 원래의 문제에 대한 해를 구하여 주 프로세서에게 되돌려 준다. 주 프로세서는 되돌아 온 해 중에서 가장 효율적인 해를 선택하여 최적해를 찾는다.

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.270-275
• /
• 2021

Most of the initial forms of cooperative robots were intended to repeat simple tasks in a given space. So, they showed no significant difference from industrial robots. However, research for improving worker's productivity and supplementing human's limited working hours is expanding. Also, there have been active attempts to use it as a service robot by applying AI technology. In line with these social changes, we produced a mobile manipulator that can improve the worker's efficiency and completely replace one person. First, we combined cooperative robot with mobile robot. Second, we applied speech recognition technology and deep learning based object detection. Finally, we integrated all the systems by ROS (robot operating system). This system can communicate with workers by voice and drive autonomously and perform the Pick & Place task.

• The Journal of Korea Robotics Society
• /
• v.16 no.3
• /
• pp.216-222
• /
• 2021

Recently, various robots are being used for the purpose of structural inspection or safety diagnosis, and their needs are also rising rapidly. Among the structural inspection using robots, a lot of researches has recently been conducted on inspection of various facilities and structures using an unmanned aerial vehicle (UAV). However, since GNSS (Global Navigation Satellite System) signals cannot be received in an environment near or below structures, the operation of UAVs has been done manually. For a stable autonomous flight without GNSS signals, additional technologies are required. This paper proposes the autonomous flight system for structural inspection consisting of simultaneous localization and mapping (SLAM), path planning, and controls. The experiments were conducted on an actual large bridge to verify the feasibility of the system, and especially the performance of the proposed SLAM algorithm was compared through comparative analysis with the state-of-the-art algorithms.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.122-126
• /
• 2023

An unexpected occlusion in a real life, not in a laboratory, can be more fatal to neural networks than expected. In addition, it is virtually impossible to create a network that learns all the environmental changes as well as occlusions. Therefore, we propose an alternative approach in which the architecture and number of parameters remain unchanged while adapting to occlusion circumstances. Learning method with the term Conversion Learning classifies them more robustly by converting the weights from various occlusion situations. The experiments on MNIST dataset showed a 3.07 [%p] performance improvement over the baseline CNN model in a situation where most objects are occluded and unknowing what occlusion will appear in advance. The experimental results suggest that Conversion Learning is an efficient method to respond to environmental changes such as occluded images.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.586-588
• /
• 2022

산업용 설비의 결함을 예측하기 위해 기기에 탑재된 다양한 센서의 시계열 데이터를 이용한 결함 진단 연구가 확대되고 있다. 센서의 시계열 데이터는 값의 특성이 명확하지 않을 경우, 특징 추출이 제한적이지만, 주파수 영역으로 변환하면 진폭, 피크 주파수 등 데이터의 정보를 다각도로 담고 있어 특성을 추출하는 데에 이점이 있다. 따라서, 본 논문은 FFT(Fast Fourier Transform) 기법을 이용해 분해된 데이터를 조합하여 학습에 적용하는 선택적 FFT 기법을 제안한다. 제안 기법은 협동 로봇의 진동 신호를 이용한 결함 진단에 적용하였으며, 기존 결함 진단 정확도 대비 최대 41.81% 향상된 성능을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.129-131
• /
• 2022

본 논문에서는 다양한 인공지능을 모듈화하고 모듈들을 서로 결합하여 서비스를 제공할 수 있는 지능형 서비스 로봇에서, 인공지능 모듈들을 라이브러리 간의 의존성을 해소하기 위한 방법 중 하나인 가상 머신의 일종인 도커(Docker)를 활용하여 컨테이너화하여 사용할 때, 인공지능 모듈 내부에서 사용하는 신경망 데이터에 해당하는 지능 모델에 대해 버전 관리를 수행하면서 클라우드 등 외부 서버를 이용하여 증강시킨 지능 모델을 공유하는 기술 개발에 대해 설명한다.