• Journal of the Korean Society for Precision Engineering
• /
• v.23 no.5 s.182
• /
• pp.51-58
• /
• 2006

The necessities for heightening fuel efficiency as well as lightweight design, lead to an increase of the use of aluminum alloys in the automobile industry. Extruded aluminum profile channels are used widely for the design of frame parts as lightweight assemblies, especially if a high stiffness is needed. While many applications can be realized with forming of hollow square-sectioned extruded profiles such as a stretch bending and a hydro-forming, some applications demand the use of a press bending which can be hardly found in the previous study. In this study, by introducing the use of a press bending into car sub-frames, the demands for higher accuracy as well as higher flexible method than the conventional methods will be satisfied. With respect to the design of sub-frames, the process planning was performed from the shape of a sub-frame product. The designed processes were analyzed by the commercial FEM code, DEFORM-3D. Forming dies for the each process were designed and prototypes of sub-frames were manufactured by the verified farming process. In addition, some of the important features of design parameters in the press bending were reviewed.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.9
• /
• pp.978-985
• /
• 2012

Starfish are a critical problem for fishermen since they eat every farming product including shellfish. The number of starfish is increasing dramatically because they have no natural enemy underwater. We consider the concept of capturing starfish using a semi-autonomous robot. A new underwater robot design to capture starfish is proposed using cooperation between humans and the robot. A requirements list for the robot is developed and two conceptual designs are proposed. Each robot is designed as a modular platform. The kinematic and dynamic performance of each robot is analyzed and compared. This study is a starting point for developing a starfish capture robot and designing underwater robots for other applications. In the near future, a prototype will be assembled and tested in a marine environment.

• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.11-16
• /
• 2019

Wireless sensor network is important for precision farming to monitor the growth environment of crops in open field, but radio signals are susceptible to different types of interference such as weather and physical objects. This paper designs and implements an environmental monitoring and weather forecast acquisition systems for smart field irrigation based on LoRa(Long Range) and then applies it to a test bed. And we evaluate the network reliability in terms of packet transmission success rate by comparing its condition on two criteria; the existence of obstacle or rain. The results show that much rain falls can affect on packet loss in LoRa field networks with obstacles.

• Smart Media Journal
• /
• v.11 no.7
• /
• pp.94-103
• /
• 2022

Weeds bring disadvantages to crops since they can damage them, and a clean treatment with less pollution and contamination should be developed. Artificial intelligence gives new hope to agriculture to achieve smart farming. This study delivers an automated weeds growth point detection using deep learning. This study proposes a combination of semantic graphics for generating data annotation and U-Net with pre-trained deep learning as a backbone for locating the growth point of the weeds on the given field scene. The dataset was collected from an actual field. We measured the intersection over union, f1-score, precision, and recall to evaluate our method. Moreover, Mobilenet V2 was chosen as the backbone and compared with Resnet 34. The results showed that the proposed method was accurate enough to detect the growth point and handle the brightness variation. The best performance was achieved by Mobilenet V2 as a backbone with IoU 96.81%, precision 97.77%, recall 98.97%, and f1-score 97.30%.

• Agricultural and Biosystems Engineering
• /
• v.3 no.1
• /
• pp.18-28
• /
• 2002

Neural network based models were developed and evaluated for predicting corn yield from aerial images based on 1998 and 1994 image data. The model used images in multi-spectral bands such as R, G, B, and IR (Red, Green, Blue and Infrared). The inputs to the neural network consisted of mean and standard deviation of multispectral bands of the aerial images. Performances of several neural network architectures using back-propagation with momentum were compared. The maximum yield prediction accuracy obtained was 97.81%. The BPNN model prediction accuracy could be enhanced by using more number of observations to the model, other data transformation techniques, or by performing optical calibration of the aerial image.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1999.07a
• /
• pp.165-170
• /
• 1999

정밀농업의 기본개념은, 작물 생육상태를 포함한 포장정보가 위치마다 다르므로 포장정보에 따라 위치별로 적합한 농자재 투입과 생육관리를 통하여 수확량은 극대화하면서도 불필요한 농자재의 투입을 최소화해서 농자재 낭비와 환경오염을 줄이는 것이다. 이러한 정밀농업을 위해서는 무엇보다도 다양한 위치별 포장정보를 정확하고 빠르게 수집하는 기술이 선행되어야 한다 포장정보는 일반적으로 비교적 장기간에 걸쳐 변화가 일어나는 정보와 단기간에 변화가 일어나는 정보 두 가지로 나누어 볼 수 있다. 장기간에 걸쳐 변화가 일어나는 정보는 포장의 크기 및 형태, 진입로, 수로, 토성, 토양 유기물 함량 등이고, 단기간에 변화가 일어나는 정보는 병충해, 성장중인 작물의 건강상태 등을 예로 들 수 있다. 이러한 정보 중 단기간에 변화가 일어나는 정보는 빠른 시간 내에 적절한 처리를 해 주어야만 수확량 및 수확된 곡물의 질에 미치는 나쁜 영향을 최소화할 수 있으며, 실시간으로 분석이 되어야만 작업기를 이용한 정밀한 포장관리가 가능하다. (중략)

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.28-33
• /
• 2003

Achievements in the real-time soil spectro-photometer are: an improved soil penetrator to ensure a uniform soil surface under high speed conditions, real-time collecting of underground soil reflectance, getting underground soil color images, use of a RTK-GPS, and all units are arranged for compactness. With the soil spectrophotometer, field experiments were conducted in a 0.5 ha paddy field. With the original reflectance, averaging and multiple scatter correction, Kubelka-Munk (KM) transformation as soil absorption, its 1st and 2nd derivatives were calculated. When the spectra was highly correlated with the soil parameters, stepwise regression analysis was conducted. Results include the best prediction models for moisture, soil organic matter (SOM), nitrate nitrogen (NO$_3$-N), pH and electric conductivity (EC), and soil maps obtained by block kriging analysis.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.619-622
• /
• 2015

Recently, there are growing fluctuations of productivity and price caused by severe weather conditions in the agriculture. Yield forecasting methods have been studied to solve the problems. This paper predicted yield per area, production area, and elements of weather based on the linear equation. A yield is calculated by multiplying the production area times the yield per area that is compensated using the weighted sum of the elements of weather. In experiments, proposed method shows that a forecasting precision is the more than 90%.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2002.02a
• /
• pp.507-513
• /
• 2002

본 연구에서는 정밀농업 구현을 위해 필수 불가결의 요소인 데이터베이스 구축의 필요성에 착안하여 공간 및 속성 데이터 구축 알고리즘의 설계와 데이터베이스를 구성하는 테이블의 스키마 설계를 통해 공간 및 비공간 데이터를 구축하고 구축된 데이터베이스와의 통신을 통해 농작업 기계의 위치에 따른 토양 속성값을 추출해 내는 과정을 보임으로써 의사결정 지원시스템으로서의 기능을 시뮬레이션을 통해 제시하였다. 연구에 사용된 공간 및 비공간 데이터 구축에 있어서의 수작업은 작업자로 하여금 노동 소모적인 작업을 요구하므로 차후의 연구에 있어 보다 자동화되고 개선된 알고리즘의 개발이 요구된다. 또한 구축되어야 하는 경작지의 규모가 커지고 비공간 데이터의 양이 많아지게 되면 데이터베이스내의 검색 성능 향상에 대한 고찰 또한 병행되어야 할 것으로 판단된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.130-133
• /
• 2020

Smart pig farm which is based on IoT has been widely adopted by many pig farmers. In order to achieve optimal control of smart pig farm, the relation between environmental conditions and performance metric should be characterized. In this study, the relation between multiple environmental conditions including temperature, humidity and various performance metrics, which are daily gain, feed intake, and MSY, is analyzed based on data obtained from 55 real pig farm. Especially, based on preprocessing of data, various regression based machine learning algorithms are considered. Through performance evaluation, we show that the performance can be predicted with high precision, which can improve the efficiency of management.