• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.339-340
• /
• 2018

산업 현장에서 사용되는 산업용 로봇은 자동화 시스템 도입에 따라 큰 성장세를 보이고 있다. 본 논문에서는 컨베이어 벨트에 올라온 물체의 무게를 측정하고, 로봇 팔이 무게별로 물건을 지정 위치에 분류하는 시스템을 구현하였다. 또 로봇 팔끼리 서로 데이터를 주고받으며 데이터 값에 따른 동작을 수행하고 클라우드에 데이터 값을 업로드하여 쉽게 모니터링 가능한 로봇 팔을 이용한 무게 분류 시스템을 설계하였다.

• IE interfaces
• /
• v.20 no.1
• /
• pp.33-40
• /
• 2007

In this paper, we consider a scheduling problem of shipyard sub-assembly process. We introduce a skid conveyor system in a shipbuilding company. We develop a mathematical model and a genetic algorithm for shipyard sub-assembly process. The objective of the scheduling is to minimize the makespan which is the final completion time of all jobs. Numerical experiments show that the genetic algorithm performs efficiently.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1999.10a
• /
• pp.217-217
• /
• 1999

The main objective of this study is to simulate the design and operational policies of the assembly shop of an automotive plant for planning purposes and to find possible improvements. The simulation study was used to answer the following questions: How does the sequence affect the daily throughput\ulcorner What are the bottlenecks to the assembly lines in a given scenario\ulcorner A Simulation model was developed in accordance with the objective of this study. The model incorporates detailed workstation logic to accurately model downtime results through the use of a pull cord system. It is written with SIMAN. The discrete event feature of SIMAN does not adequately model the conveyor systems of the asembly shop. As a result, a few subroutines were added to the SIMAN modeling structures to mimic the operations of the assembly shop. Use of the model uncovered attractive improvement opportunities, such as a tremendous gain in annual volume if four additional spaces were added to a between-line buffer.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.39 no.5
• /
• pp.453-461
• /
• 1990

In this paper, a short primary-short secondary single-sided linear induction motor which is used as the driving source for an automatic conveyor system, is selected as an analysis model. The finite element method in which the current vector potential is introduced is adopted to analyze the eddy current distribution and thrust force which are produced according to the relative position of the primary and the secondary. Also, the analysis results are compared with experimental ones, to show the propriety of this model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.11a
• /
• pp.653-656
• /
• 2002

본 논문에서는 연속된 영상 정보를 이용하여 물체를 추적하는 시스템에 대하여 기술한다. 물체를 추적하는 시스템은 물체를 구별하는 단계에서 자동으로 물체를 추적하는 단계로 구성된다. 물체를 구별 하기 위해서는 영상에서 사용자가 원하는 물체를 추출해야 한다. 이를 위해서 여러 가지 전처리 과정을 거쳐서 물체를 추출하고, 물체에 대한 정보를 추출한다. 추출된 정보와 미리 입력된 물체에 대한 정보와 비교하여 사용자가 원하는 물체인지를 구별한다. 사용자가 원하는 물체라고 판단이 될 경우 추적 시스템은 추적 알고리즘을 이용하여 물체를 추적한다. 이 시스템을 평가하기 위해서 본 논문은 conveyor belt에서 물체를 추적, 추적된 물체를 잡는 실험을 하였고 성공적인 결과를 보였다.

• IE interfaces
• /
• v.6 no.2
• /
• pp.53-65
• /
• 1993

This paper deals with the development of a software module for production planning and scheduling activities of an existing Flexible Machining and Assembly System (FMAS). The Production Planning Module uses the hierarchical and sequential scheme based on "divide and conquer" philosophy. In this module, routes are determined based on the production order, orders are screened, tools are allocated, and order adjustments are executed according to the allocated tools. The Scheduling Module allocates the resources, determines the task priority and the start and completion times of tasks. Re-scheduling can be done to handle unforeseen situations such as lumpy demands and machine breakdowns. Since all modules are integrated with a central database and they interface independently, it is easy to append new modules or update the existing modules. The result of this study is used for operating the real FMAS consisting of a machining cell with 2 domestic NC machines and a part feeding robot, an assembly cell with a conveyor and 3 robots, an inspection cell, an AGV, an AS/RS, and a central control computer.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.22 no.49
• /
• pp.1-10
• /
• 1999

A cost minimization model for designing AS/RS (Automated Storage/Retrieval Systems) has been developed, whose objective function includes penalty cost caused by the incapability of meeting throughput rate requirements as well as S/R machine cost, storage rack cost, and interface conveyor cost. Since the model is a nonlinear integer programming problem which is very hard to solve with large problem size the problem is divided into four cases according to the ratio of horizontal S/R machine speed to its vertical speed and the existence of the penalty cost. A solution procedure is developed which solves each problem exactly under the different number of S/R machines.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.59-60
• /
• 2019

WCS에서 AGV의 스케줄링과 동적, 정적 장애물 인식 및 충돌 회피문제는 오래전부터 다뤄져 온 중요한 문제이다. 본 논문에서는 위의 문제를 해결하기 위해 Lidar 센서를 중심으로 다양한 데이터를 기반으로 한 강화학습 시스템을 제안한다. 제안하는 시스템은 기본의 명시적인 알고리즘에 비해 다양하고 유동적인 환경에서 경로 계획과 동적 정적 장애물을 인식하고 안정적으로 회피하는 것을 확인하였으며 산업 현장에 도입 가능성을 확인하였다. 또한 강화학습의 적용 범위, 적용 방안과 한계에 대해서 시사한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.9-10
• /
• 2019

본 논문은 구동장치의 진동에서 특징 데이터를 추출하고 인공신경망에 학습을 시킨 후, 구동 장치의 결함을 분류하는 시스템을 구현하였다. 딥러닝 기술을 이용함으로써 특정 장치에 종속되지 않고 학습할 데이터의 특징에 따라 쉽게 변경 가능하다. 또한, 실제 적용될 현장에서 발생할 수 있는 예측외의 진동 환경에 유연하게 대처하기 위해 딥러닝 모델 중 CNN을 적용한 시스템을 설계하였으며, 본 연구팀의 이전 연구에서 제안된 DNN 기반의 진단시스템을 학습데이터의 환경과 다른 처리배제가 필요한 진동 환경에서 비교 실험하여 제안된 시스템이 새로운 환경적응 성능향상에 대하여 우수한 결과를 얻었음을 확인하였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1993.10a
• /
• pp.328-332
• /
• 1993

This study presents an algorithm and related techniques which could satisfy the important properties of check weighers and conveyor scales. The algorithm of Recursive Least Squares Regression is applied for the weighing system simulated as a dynamic model of the second order. Using the model and the algorithm, model parameters and then the mass being weighed can be determined form the step input. The performance of the algorithm was tested on a check weigher. Discussions were extended to the development of noise reduction techniques and to the lagged introduction of objects on the moving plate. It turns out that the algorithm shows several desirable features suitable for microcomputer assisted real-time signal processing, which are high precision and stability in noisy environment.