• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2000년도 THE THIRD INTERNATIONAL CONFERENCE ON AGRICULTURAL MACHINERY ENGINEERING. V.III
• /
• pp.729-735
• /
• 2000

Moisture loss of fresh fruits and vegetables is a main cause of deterioration. It resulted not only in the direct quantitative loss, but also in change in appearance, texture and nutrition. To reduce the loss of moisture content during the distribution in the market, fresh products are packaged using plastic films. But, most of the fresh products are packaged manually in Korea. In order to minimize the labor requirement, the packaging machine for fruits and vegetables was developed and tested. Prototype was composed of film feeding unit, bag former, products feeding conveyor, film feeding roller, center sealer, end sealer and discharge conveyor. Green peppers, carrots and perilla leaves were tested with prototype. Prototype could pack 1780, 1390, 1780 bags per hour at the feeding speed of 0.08m/s respectively and 2250, 1810, 2640bags per hour at the feeding speed of 0.10m/s respectively. And packaging speed of green peppers and carrots was improved by 3.7 and 3.4 times compared with manual packaging. The packaging condition with the prototype was good and the products had almost no damages.

• 로봇학회논문지
• /
• 제15권3호
• /
• pp.233-239
• /
• 2020

The aims of this paper is to develop a modular agricultural robot and its autonomous driving algorithm that can be used in field farming. Actually, it is difficult to develop a controller for autonomous agricultural robot that transforming their dynamic characteristics by installation of machine modules. So we develop for the model based control algorithm of rotary machine connected to agricultural robot. Autonomous control algorithm of agricultural robot consists of the path control, velocity control, orientation control. To verify the developed algorithm, we used to analytical techniques that have the advantage of reducing development time and risks. The model is formulated based on the multibody dynamics methods for high accuracy. Their model parameters get from the design parameter and real constructed data. Then we developed the co-simulation that is combined between the multibody dynamics model and control model using the ADAMS and Matlab simulink programs. Using the developed model, we carried out various dynamics simulation in the several rotation speed of blades.

• 한국농림기상학회지
• /
• 제22권1호
• /
• pp.1-12
• /
• 2020

토양수분은 농업에서 필수적인 자원으로 이의 변화와 부족을 예측함으로써 관리되어왔다. 최근 현장에서의 적용 용이성과 다양한 지역에 대한 일반화 가능성이 뛰어난 통계 및 기계학습 알고리즘을 활용한 토양수분 예측 연구가 활발히 진행되고 있다. 하지만 국내에서 생성되는 데이터를 이용한 연구들은 부족한 실정이다. 이에 본 연구는 1) 국내 공공기상 데이터만으로 충분한 성능을 내는 토양수분 예측 모델을 만들 수 있는지, 2) 어떠한 기계학습 모델이 국내에서 생산되는 데이터와 토양환경에서 가장 높은 예측 성능을 보이는지, 3) 단일 기계학습 모델을 이용해 다양한 지역에 적용 가능한지를 확인해보려 한다. 본 연구에서 Support Vector Machines (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting Machines (GBM), and Deep Feedforward Network (DFN) 알고리즘과 종관기상관측 자료, 농업기상관측자료를 활용하여 안동, 보성, 철원, 순천 지역의 토양 수분을 예측하는 모델을 만들었다. 그 결과, GBM을 이용한 모델이 R² : 0.96, Root Mean Squared Error(RMSE) : 1.8로 가장 낮은 예측 오차를 보였다. 또한 GBM을 사용한 모델이 가장 낮은 지역간 예측 오차 분산을 보여 가장 일반화하기에 적절한 모델로 확인되었다.

• 한국작물학회지
• /
• 제45권4호
• /
• pp.232-236
• /
• 2000

To obtain a basic information on the development of effective control strategies for weedy rice in direct seeding rice cultivation, occurrence patterns of weedy rice as influenced by different cultural practices such as cultivation method, water management, seeding time, and tillage were investigated in field or pot experiments. High occurrence of weedy rice was observed in a continuous direct seeding paddy field as compared to machine transplanted one. Based on the percent of weedy rice panicle over three years trial, high ridged dry seeding was highest with 36.9%, followed by wet seeding with 30.9%, water seeding with 14.6% and machine transplanting rice with 0.8%, indicating 97.8% reduction in weedy rice occurrence by machine transplanting rice as compared with high ridged dry seeding. Germination of weedy rice was promoted to 83-94 % when rice panicle was flooded from September 30 to October 10 for 6 days and 74-88% for 9 days on October 20. Weedy rice occurrence was also substantially reduced by delayed seeding on June 10 and intensive tillage. The results suggest that machine transplanting rice be more effective cultural practice than flooding treatment, delayed seeding and intensive tillage when weedy rice problem occurs in direct seeded paddy field.

• Journal of Biosystems Engineering
• /
• 제25권5호
• /
• pp.409-414
• /
• 2000

A machine vision system was built to obtain single stationary image from an egg. This system includes a CCD camera, an image processing board and a lighting system. A computer program was written to acquire, enhance and get histogram from an image. To minimize the evaluation time, the artificial neural network with the histogram of the image was used for eggshell evaluation. Various artificial neural networks with different parameters were trained and tested. The best network(64-50-1 and 128-10-1) showed an accuracy of 87.5% in evaluating eggshell. The comparison test for the elapsed processing time per an egg spent by this method(image processing and artificial neural network) and by the processing time per an egg spent by this method(image processing and artificial neural network) and by the previous method(image processing only) revealed that it was reduced to about a half(5.5s from 10.6s) in case of cracked eggs and was reduced to about one-fifth(5.5s from 21.1s) in case of normal eggs. This indicates that a fast eggshell evaluation system can be developed by using machine vision and artificial neural network.

• Journal of Biosystems Engineering
• /
• 제34권6호
• /
• pp.411-419
• /
• 2009

This study was carried out to develop a shredding-burying machine for application of gramineae green manure crops that were tall and had high biomass yield such as sudan grass and rye. We made a prototype to operate both shredding and burying concurrently to attach at middle-sized tractors. Field tests were performed with the prototype to treat rye and sudan grass. The test results showed that the average cutting length became shorter and the quantity of entwined stem became obviously decreased when the PTO shaft speed was fast and running speed was slow. Also, We found, when the cut stem length became shorter, the burying ratio became more increasing and the PTO power requirement became more decreasing. Working efficiency of the prototype was better than conventional Rotary. The test results for treating rye/sudan grass with prototype showed that average cutting length was 21.2/22.5 cm and burying ratio was 98.4/98.1% when the PTO shaft speed was 1,000/1,000 rpm and running speed was 0.25/0.17 m/s. Also, the working performance of the prototype was 0.79 and 1.14 h/10 a for rye and sudan grass, respectively. Finally, we found that the prototype of shredding-burying machine was better for labor than conventional method that required at least 3 times bigger tractor.

• 식물병연구
• /
• 제26권2호
• /
• pp.72-78
• /
• 2020

클로버씨스트선충은 국내 고랭지배추 재배지에서 가장 문제되고 있는 식물기생선충 중 하나이다. 본 연구는 새로 개발한 훈증성 약제 처리기의 성능을 시험하기 위하여 고랭지배추 문제 클로버씨스트선충을 대상으로 훈증성 약제 2종(dimethyl disulfide [DMDS], metam sodium [MNa])의 살선충 활성을 검정하였다. 훈증성 약제의 방제 효과는 약제 처리 4주 후 처리구별 토양으로부터 씨스트를 채집하여 클로버씨스트선충 알 부화율을 조사하였고, 씨스트 내부의 알을 배추에 접종하여 얻은 암컷 증식 수를 조사하여 평가했다. DMDS (39 l/10 a)는 클로버씨스트선충 알 부화율과 암컷 증식 수를 각각 99.0% 이상 억제하였으나, MNa (29 l/10 a)는 알 부화율은 78.3-99.4%, 암컷 증식 수는 34.7-49.3% 정도 억제하였다. 훈증성 약제 2종의 처리 깊이에 따른 클로버씨스트선충 알 부화율과 암컷 증식수는 통계적으로 유의미한 차이를 보이지 않았다. 본 연구에서 개발된 토양 소독기를 이용하여 DMDS를 토양 처리하면 클로버씨스트선충 방제 효과가 있을 것으로 보인다.

• 생물환경조절학회지
• /
• 제32권3호
• /
• pp.190-196
• /
• 2023

본 연구는 등유를 사용하는 농업용 난방기에서 배출되는 가스를 포집하고, 농업용 난방기의 사용 연식에 따른 이산화탄소의 배출농도를 파악하고자 수행되었다. 선형 회귀분석의 결과로 농업용 난방기의 연식에 따른 이산화탄소의 배출량은 R² = 0.84로 y = 26.99x+721.98의 식을 따른다고 나타났다. 농업용 난방기의 사용 연식에 따라 세 그룹으로 분류하여 분산분석을 수행하였다. 분산분석을 수행한 결과, 분석을 위해 설정한 유의확률0.05보다 작은 2.1961×10^-13으로 나타났으며 이는 적어도 한 그룹에서 차이가 나타난다는 것을 의미한다. 본 연구에서는 농업용 난방기의 기본적인 배출농도의 차이를 분석하고자 기기의 제작사와 상관없이 농업용 난방기의 기기 연식만을 고려하여 배출가스 데이터를 수집하였다. 기기의 연소 방식에는 제작사에 따라 연소 방식에 차이가 미미하게 있었을 것으로 판단되며 데이터 변수의 개수가 늘어난다면, SVR(support vector regression) 기반의 선형회귀 분석 등을 실시하여 농업용 난방기의 이산화탄소 데이터가 온실가스발생량 파악에 더욱 활용도가 높아질 것으로 판단된다. 추후 연구에서는 더욱 세분화된 데이터의 수집 방식을 따라 더욱 높은 정확도를 가진 결과값을 도출할 수 있다고 판단된다. 이처럼 우리나라의 농업 분야에서 용도별 온실가스 발생량을 조사하기 위하여 고정형 농기계인 농업용 난방기의 이산화탄소 발생량을 정확히 파악하여 온실가스 배출량 조사에 활용할 수 있을 것으로 판단된다.

• 한국토양비료학회지
• /
• 제48권5호
• /
• pp.564-569
• /
• 2015

In highland crop fields, saprolite is piled up approximately every three years as deep much as 20 to 30 cm because farmers expect that adding new materials may improve productivity and mitigate hazards by continuous cultivation of a single crop. Piling saprolite, however, has been reported to induce poor soil drainage. Effects of deep ploughing with a spading machine and an excavator were studied in sites located in Daekwanryeong-myeon, Pyeongchang in which soil physical properties were deteriorated by piled saprolite. The soil made of parent material of Samgag series was piled up over surface soil of Haggog series naturally developed in the area. Carrot was cultivated in the field. Productivity and growth factors of carrot were compared among control and deep ploughing by a spading machine and an excavator. Effective soil depth extended to 60 cm or greater by 60 cm deep ploughing by an excavator or 50 cm deep ploughing by a spading machine. On the other hand, effective soil depth was within 50 cm at control plot. Productivity of carrot responded to amelioration of soil physical properties. The productivity was greater in deep ploughing treatments than that of control or 30 cm ploughing. It suggested that increased productivity by deep ploughing was mainly related to breaking plough pan which inhibited extension of rooting zone.

• 한국정보전자통신기술학회논문지
• /
• 제12권3호
• /
• pp.201-210
• /
• 2019

본 논문에서는 농장의 위성 사진 혹은 드론 사진을 이용하여 농장을 구분하고 농장 드론과 트랙터의 자율주행 및 행동을 제어하는 'AMCS(Agricultural Machine Control System)'를 제안한다. AMCS는 드론과 트랙터의 센서 데이터 및 비디오 영상 데이터로부터 농장 경계를 구분하고, 메인 서버에서 원격 제어 명령어를 읽어 들인 후 드론 및 트랙터 스프링클러와의 연동을 통해, 관리지역 내의 원격 제어 명령을 전달하는 'LSM(Local Server Module)'과 드론과 트랙터가 농장 밖에서 농장으로 이동하는 경로와 농장 안에서 저비용, 고효율로 일을 처리할 수 있는 경로를 설정하는 'PSM(Path Setting Module)'으로 구성된다. 본 논문에서 제안하는 AMCS의 성능분석 결과 AMCS의 PSM은 외부 출발점에서 농장까지 도달하는 경로를 설정할 때 다익스트라 알고리즘보다 약 100% 향상된 성능을 보였으며, 농장 내부 작업 경로를 설정할 때 기존 경로보다 약 13% 높은 작업 효율을 보였고 36% 낮은 작업 거리를 설정했다. 따라서 PSM은 기존 방식보다 더 효율적으로 트랙터와 드론을 제어할 수 있다.