• 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.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.5
• /
• pp.53-59
• /
• 2019

Continuous ship unloaders (CSUs) are used for the uninterrupted transport of material in processing industries, power plants, and harbors in accordance with the stream rate of the material. This study analyzed the structural integrity and fatigue life of a CSU structure using finite element structural analysis in ANSYS APDL software. The stress varied greatly depending on the luffing angle and the slew angle of the boom conveyor. The structural integrity of the CSU girder was evaluated by applying ASME BPVC Section VIII Division 2. The fatigue cycle at the angle with the greatest stress difference was calculated. The fatigue cycle was calculated by applying the JIS B 8821:2013 fatigue curve. It was confirmed that the fatigue cycle of the CSU satisfies the allowable fatigue of 200,000 cycles.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.109-116
• /
• 2023

This paper presents a network-based automation system for the detection of metallic objects in food and livestock. A metal detector is a core equipment used for the inspection required by HACCP. Since the existing metal detectors are manufactured as a single-body equipment, it is difficult to take into account various user requirements for the system. In order to overcome the drawback, this study presents a network-based automation system for metal detector utilizing an industrial fieldbus and modular components. The proposed system can effectively consider the various customer requirements and control schemes. The proposed system can also achieve the improvement in speed and success rate of detecting metallic objects. The effectiveness of the proposed system is demonstrated through a various experiments.

• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.15-16
• /
• 2020

본 논문에서는 산업 현장에서 사용되는 기계들의 건전성을 유지하고 예측하는 시스템을 개선할 수 있는 연구 결과를 비교하고 설명한다. 이번 연구에서는 딥러닝 기술을 이용함으로서 특정장치에 종속되지 않고 범용적으로 수집된 소음데이터를 사용하여 현장 적용의 유연성을 높이고, 딥러닝 모델 중 GRU를 이용하여 기존 연구 결과와 비교 실험을 하여 더 우수한 결과를 얻었다.

• Journal of the Korean Society for Precision Engineering
• /
• v.11 no.6
• /
• pp.136-142
• /
• 1994

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 described for te 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 from the step input. The performance of the algorithm is illustrated in digital simulation. Discussions are extended to the development of fast converging algorithm. 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.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2003.07a
• /
• pp.309-316
• /
• 2003

Generally, sesame are dried on the field after being harvested in Korea. Since harvesting season is rainy autumn and sesame drying is mainly affected sun and natural wind, it is difficult to dry sesame in time. Moreover, sesame threshing by hand is very laborious work. Therefore, tractor mounted sesame thresher which threshes sesame bundles fed in upside down and conveyed along threshing bar was developed to mechanize sesame threshing and to reduce labor cost in this research. the thresher was equipped with a threshing bar which beats sesame bundles and a three layer sieve which screens sesame. The results are summarized as follows ; 1 The sesame thresher was consisted of a hitting-stick, a feeding chain conveyor, a threshing bar, conveyor belt, and the three-layer shaking sieve. 2. In threshing test, prototype thresher showed maximum threshing ratio 98.5%, 98.7% at 14, 17 cpm beating rate respectively. 3. In screening test, prototype sieve showed maximum threshing ratio 97.2% at 12$^{\circ}$ of inclined angle and 220 cpm of sieve vibrating rate. 4. Prototype showed 98.7% of threshing ratio, 1.3% of threshing loss, 97.0% of screening ratio, 0.7% of screening loss on the rest condition of 15 sesame bundles/min of feeding rate, 14 cpm of beating rate, 220 cpm of sieve vibrating rate. 5. The working performance of prototype was 0.5hr/10a. It was 9.6 times more efficient than manual work. And, operation cost of prototype was saved by 45.9% compared to manual work.

• Resources Recycling
• /
• v.18 no.5
• /
• pp.63-71
• /
• 2009

Recyclable wastes coming into material recovery facilities(MRFs) is mostly packed by plastic bag or sack bag. Bag rupturing device is essential to improve capacity and efficiency of MRFs. Bag opening works of MRFs is mostly done by numerous workers and shredder-type bag rupturing device. It often makes a problems; decreased capacity, shredded recyclables, worker safety by explosion and broken glasses, etc. In the present work, bag rupturing device with octagonal rotating blade drums has been developed to solve the existing problems and environment assessment is also performed during operation of the device. Capacity of the device was about 5.6 ton/hr at 8.2 rpm of drum revolution speed and 1.25 m/min of belt conveyor speed. It satisfied initial designed capacity(5.0 ton/hr) and max. capacity 8.8 ton/hr was achieved at 12.5 rpm of drum revolution speed and 1.50m/min of belt conveyor speed. Bag rupturing efficiencies on outer and inner bag were obtained at 100% and about 95.6% as average, respectively and original form of glass bottles in the bag was maintained without broken by about 96.5%. This result shows that the safety in hand sorting by the workers could be improved. As result of environmental assessment on the noise, vibration and particulates, the measured levels on noise, vibration and particulates show the below standard regulatory limits. It could be concluded that the problems of existing devices in MRFs could be solved by adopting the bag rupturing device with octagonal rotating blade drums in on-site operation.

• Journal of Bio-Environment Control
• /
• v.14 no.1
• /
• pp.7-14
• /
• 2005

This study was conducted to develop a chain conveyor-type, row-spacing system for a plant factory. The developed system was evaluated for its practical use in growing plants. Results are intended to provide technical suggestions on the row spacing for hydroponically grown vegetables in a plant factory. The designed row-spacing system for a plant factory could be adjusted by four stages with a conveying speed range of $5.3\~15.8cm{\cdot}s^{-1}$ and with a row-space range of 10-25cm. The torque of driving shaft was measured with a torque range of 11.7-33.3 N$\cdot$m according as a trough weight changes with a range of $17\~935$ N. A measured value was $5.9\~9.8\;N{\cdot}m$ lower than a theoretical value. Travel reduction rate was shown up $1.6\~1.9\%$. The conveying time of trough was shown up 2.24 seconds in case that the designed value was 2.26 seconds. The system was evaluated to be functioning effectively according to the initial design factors in the test.