본 연구의 주요 목적은 회귀기반의 다양한 머신러닝 알고리즘을 개발하고 다양한 농업 분야에서 사용되는 트랙터의 연료 소비량을 예측하는 것이다. 비포장 도로주행 농업 기계중에서도 사용 비중이 가장 높은 트랙터를 선정하였다. 실제 농가에 방문하여 현업 전문가 조언을 바탕으로 연구하여 설문지를 작성하였으며, 설문 대상은 경남 사천시에 있는 농가 10곳, 진주시에 있는 농가 62곳 등, 총 72곳의 농가이다. 농작업으로는 벼농사, 보리농사, 밭농사 등이 있으며, 작업내용으로는 쟁기, 로터리, 비료살포, 베토, 모내기작업 등이 있다. 다중 회귀분석을 통해 연료 소비량 예측에 영향을 미치는 변수(마력, 기계사용연수, 경작면적, 작업 시간)를 추출하였고. 머신러닝 회귀 학습기 모형으로 학습하여 예측 모형의 성능을 검증하였다. 연료 소비량을 예측하는 모델의 성능은 결정 계수(R), RMSE (제곱 평균 제곱근 오차), MSE (평균 제곱 오차) 및 MAE (평균 절대 오차)를 포함한 4가지 통계적 품질 매개변수를 사용하여 결정되었다. 연구 결과 4가지 모델(다중회귀, 랜덤포레스트, 아다부스트, K-최근접 이웃) 중 K-최근접 이웃의 성능이 제일 높은 것으로 나타났다. 결론적으로 본 연구의 결과는 실제 농가의 연료 소비량을 예측하여 면세유 유통의 투명성을 확보하고 추후 개발 모델의 의사결정에 활용될 수 있을 것으로 기대된다.

Recently, the annual emission rate of CO2 that is the main reason for domestic greenhouse gases is the third highest globally, which means it is an extremely serious issue. It is considered that these greenhouse gases affect climate changes. Especially, the emissions of CO2 in the fishing industry are nearly 4.11 million tons each year, occupying 0.7 percent of domestic total emissions. Therefore, this study clearly analyzed fuel consumption of major fish species over the recent five years focusing on large purse seines. It was revealed that mackerels occupied 55.7 percent of total fish catches of large purse seines and 57.5percent of total fishing earnings. Also, fuel consumption was 236.62 liters per ton caught and 179.51liters per million won earned.

Since 2020, according to the International Convention for the Prevention of Pollution from Ships (MARPOL) amended in 2016, each Administration shall transfer the annual fuel consumption of its registered ships of 5,000 gross tonnage and above to the International Maritime Organization (IMO) after verifying them. The Administration needs stacks of materials, which must not be manipulated by ship companies, including the Engine log book and also bears an administrative burden to verify them by May every year. This study considers using the Automatic Identification System (AIS), mandatory navigational equipment, as an objective and efficient tool among several verification methods. Calculating fuel consumption using a ship’s speed in AIS information based on the theory of a relationship between ship speed and fuel consumption was reported in several examples of relevant literature. After pre-filtering by excluding AIS records which had speed errors from the raw data of five domestic cargo vessels, fuel consumptions calculated using Excel software were compared to actual bunker consumptions presented by ship companies. The former consumptions ranged from 96 to 123 percent of the actual bunker consumptions. The difference between two consumptions could be narrowed to within 20 percent if the fuel consumptions for boilers were deducted from the actual bunker consumption. Although further study should be carried out for more accurate calculation methods depending on the burning efficiency of the engine, the propulsion efficiency of the ship, displacement and sea conditions, this method of calculating annual fuel consumption according to the difference between two consumptions is considered to be one of the most useful tools to verify bunker consumption.

There is a need to reduce fuel consumption in order to reduce GHG emissions from the transport sector, which accounts for large volumes. In this study, the fuel consumption rate can be compared with the method using the CAN communication data in the engine controller through the OBD II interface and the direct measurement method using the fuel flow meter. For this purpose, we measured the fuel consumption rate in the engine controller and the fuel flow meter with the chassis dynamometer, and confirmed the reliable data of the fuel flow meter. As a result, the fuel consumption rate in the engine controller and the fuel consumption rate in the fuel flow meter were directly measured. After that, the running test was carried out using the chassis dynamometer and the reliability of the fuel consumption rate using the flow meter was confirmed.

The effect of EGR on fuel economy was investigated in a gasoline direct injection engine. The 1-D cycle simulation program of GT-Power was utilized to evaluate fuel consumption rate. At high load, fuel consumption increased by about 2~6% according to EGR rate. Knock mitigation was the main effects, gaining about 80% of the total fuel consumption improvement. At low load, fuel consumption reduction was 0.6~2%, which was much lower than that for high load. The lower improvement of fuel consumption at low load is attributed to solely dilution and chemical effects of exhaust gas.

PURPOSES :This study aims to improve complex modeling of multivariable, nonlinear, and overdispersion data with an artificial neural network that has been a problem in the civil and transport sectors.METHODS :Deep learning, which is a technique employing artificial neural networks, was applied for developing a large bus fuel consumption model as a case study. Estimation characteristics and accuracy were compared with the results of conventional multiple regression modeling.RESULTS :The deep learning model remarkably improved estimation accuracy of regression modeling, from R-sq. 18.76% to 72.22%. In addition, it was very flexible in reflecting large variance and complex relationships between dependent and independent variables.CONCLUSIONS :Deep learning could be a new alternative that solves general problems inherent in conventional statistical methods and it is highly promising in planning and optimizing issues in the civil and transport sectors. Extended applications to other fields, such as pavement management, structure safety, operation of intelligent transport systems, and traffic noise estimation are highly recommended.

The test was done on cars travelling at the speeds of 20km/h, 60km/h and 100km/h using the performance testing mode for chassis dynamometer. In this test, the secondary ignition waveform, exhaust emissions and fuel consumption were measured in case of faulty MAP sensor, faulty oxygen sensor and spark plugs. The following results from the related analysis of secondary waveform, emission and fuel consumption measurements were obtained : 1) The fuel consumption was higher in the order of oxygen sensor trouble, MAP trouble, spark plug trouble, before maintenance and after maintenance. Maximum fuel economy is 9.3km/L, the minimum fuel economy is 3.2km/L, the difference between max. and min. is 65.5%. 2) If you compare the oxygen sensor trouble with after maintenance, the CO has improved an average of 98%, fuel economy average of 60%. And the HC has improved an average of 87%, fuel economy average of 60%. The fuel consumption and exhaust gas was bad in the order of oxygen sensor trouble, MAP trouble and S/P trouble.

본 연구에서는 동절기 시설원예 난방에너지 절감을 위해 방울토마토의 온도민감부인 생장부를 추종하면서 난방을 수행할 수 있는 국소난방 시스템을 개발하고자 하였다. 방울토마토 생장부 추종형 국소난방시스템은 온실 하류로의 균일한 열분배를 위해 내/외부 덕트와 온풍난 방기를 연결하는 이중덕트 분배장치, 정식 후 작물 유인에 따라 덕트를 토마토 줄기끝 생장점과 개화화방을 추종하여 상하로 이동시키기 위한 권취장치 등으로 구성되었다. 국소난방 시스템의 운용은 토마토 정식 직후에는 덕트를 작물 상부에 위치시키며 작물 생장에 따라 생장부 국소난방과 차광 회피를 위해 덕트를 상하로 이동시켰다. 방울토마토 수경재배 온실을 대상으로 생장부 국소난 방구와 관행의 바닥덕트 난방구에 대해 난방성능과 작물 생육 비교시험을 수행하였다. 그 결과 생장부 국소난방구는 야간 난방시간에 작물 군락내 상부 기온이 하부에 비해 0.9~2.0oC 높으며, 바닥덕트 난방구에 비해 군락 상부 기온은 0.3~1.8oC 높고, 하부 기온은 1.4~1.8oC 낮게 나타나 온도에 민감한 상부 생장부를 상대적 고온으로 관리하고, 군락하부는 상대적 저온으로 관리 가능하며, 관행 바닥덕트 난방구의 높이별 온도분포를 역전시킬 수 있음을 확인하였다. 토마토 군락에 대한 적외선 열화상 측정을 통해 정식 직후부터 줄기내림 유인재배 기간에 걸쳐 생장부 국소난방구는 군락내에 높이별 엽온의 온도성층화를 형성하여 생장부 추종 국소난방이 가능 함을 확인하였다. 난방방식별 작물생육 분석결과 초장을 제외한 나머지 항목은 유의적인 차이가 없었으며, 수확량에서도 생장부 국소난방구가 초기 수량이 약간 우세하였으나 총 수확량은 동일한 수준으로 나타났다. 온풍난 방비 경유소비량은 생장부 국소난방구가 군락의 높이별 최적 온도관리로 관행 바닥덕트 난방구에 비해 약 23.7% 절감되는 것으로 나타났다. 본 시스템은 길이 90m 온실에 대한 적용시험에서 열 분배 성능의 한계로 온실 상/하류간 온도편차가 발생하였으며, 시스템 개선을 위해 내부덕트의 직경 또는 두께 상향, 열복사 억제 재질의 덕트 사용 등 열분배 성능 최적화를 위한 추가연구가 필요한 것으로 판단되었다.

The several experiments of Diesel vehicles using EFT were completed. The experiments were performed on chassis dynamometer and road driving test using test mode such as FTP-75 and LA-4. The experiments were employed to measure the effect eco-friendly EFT additives on exhaust emissions and fuel consumption efficiency. In this experiment, the following results are obtained by analyzing the data relativity between exhaust emissions and EFT additives. The value of exhaust emissions such as NOX, SOX, CO2 and PM were improved as Diesel mixed EFT additives at th ratio of 200:1. The improvement of resulting data value was best PM, NOX, SOX, CO₂and fuel consumption rate in the order named.

The two experiments of gasoline vehicle using eco-friendly treatment(Ecoburn) were completed. The experiments was done on traveling using the performance testing mode for chassis dynamometer and road driving test. The experiments were employed to measure exhaust emissions and fuel consumption. In this experiment, the correlation between CO₂and fuel consumption were found in gasoline vehicle. The following results are obtained by analyzing the data relativity between exhaust emissions and additives. 1) If the value of exhaust emissions such as CO, HC, NOX, CO₂were improved as gasoline mixed additives at th ratio of 300:1. The value of fuel consumption were worse compare to those of exhaust emission. The improvement of resulting data value was best CO, HC, NOX and fuel consumption in the order named. 2) The value of CO₂ were to be nearly proportional to the fuel consumption value.

The two experiments were done on stationary car at 800rpm, 1500rpm and running car on oscilloscope and chassis dynamometer at the speeds of 20km/h, 60km/h. In this experiment, the relativity between waveform, exhaust emissions and fuel consumption through two experimental methods were measured in case of cars with failures in MAP sensor, O sensor, spark plugs. The following results are obtained by analyzing the data relativity between two experimental methods, such as stationary and running tests. A simple stationary test under the maintenance of a decrepit gasoline vehicle would be realistic possibility to predict the fuel consumption and the exhaust emission comparable to results of running test with a chassis dynamometer.

This paper is on developing the advanced method in diagnosis electronic control of gasoline and LPG engine. The experimental methods using oscilloscope were employed to measure waveform of hot wire, hot film, oxygen, ignition coil and injector. Through these analysis, emission reduction and fuel economy improvement were expected by depict vehicles. The experiment was carried out during no-load condition. A summary of the important results are as follows. 1. The factors affecting the secondary ignition waveform from the primary ignition waveform were reverse surge voltage and induced voltage . Actually shape of primary ignition waveform was normal, but a secondary ignition waveform was measured badly. 2. The area of the voltage-time diagram of secondary ignition waveform means the value of the effective discharge of energy. This value is negative, the fuel economy could be predicted badly and is positive, good value of fuel economy could be predicted. 3. Inspection and maintenance of DLI ignition vehicles compared to DIS ignition vehicles were essential. The secondary ignition waveform of the C type vehicle were worst compare to those of the different type vehicles. The injection duration of injector was largest C, D types in the order named, was shortest E, F type. As a result, E, F type are most effective among Gasoline vehicles.

최근 국제 원유가의 폭등으로 선박의 연료비 부담이 상대적으로 가중되고 있으며, 또한 연료의 연소과정에서 발생하는 온실가스에 대한 국제적 규제 움직임도 가속되고 있다. 이와 같은 상황에서, 온실가스의 배출을 최소화하면서 연료소모량을 줄이기 위해 많은 선사들이 감속운항을 취하고 있으며, 선박용 엔진 개발 분야에서는 엔진의 연료 효율성 개선 문제와 대체에너지 사용 분야에 주력하고 있다. 따라서, 본 연구에서는 실제 해상에서의 선속대비 연료소모량을 계측하고, 건조과정에서 실시된 육상 엔진실험 자료와 2007~2009년까지의 AB-LOG를 분석하여, 특정 외력조건에서의 대상선박에 대한 연료소모량을 고려한 최적의 속력을 14~15노트, 주기관의 RPM을 140~150 RPM으로 제안하였다.

효율적인 도로의 설계와 관리를 위해서는 도로건설의 경제성 분석이 중요하며 이를 위해서는 도로 상태별 차량별 유류소모량의 평가가 필요하다. 도로에서는 초기 건설비용, 유지보수비용, 차량운행비용, 지정체비용 등이 발생되는데, 도로의 경제성 분석을 위해서는 초기 건설비용, 유지보수비용 등과 같은 관리자비용과 차량운행비용, 지정체비용 등과 같은 이용자비용을 모두 포함한 사회적 비용이 고려되어야 한다. 이 중 차량운행비용은 교통량에 따라 그 비용이 변화되므로 차량운행비용 항목의 큰 부분을 차지하는 유류소모량 또한 교통량에 따라 변화하게 된다. 그런데 유류소모량은 차량의 주행속도 및 도로포장의 상태, 특히 평탄성에 따라 크게 변화되므로 도로의 경제성 분석을 위한 차량운행비용의 산정을 위해서는 주행차량에 대해 도로 상태에 따른 유류소모량을 평가하여 경제성 분석에 반영해야 할 필요가 있으나 아직 이를 고려하지 못하고 있는 상황이다. 본 연구에서는 국내에서 운행되는 승용차에 대해서 도로 상태별 유류소모량 추정모델을 개발하였다. 우선 우리나라의 교통시설 투자평가 및 도로건설의 예비타당성 조사에서 차량운행비용 산정을 위해 사용되고 있는 주행속도와 유류소모량의 관계식을 고찰하고, 승용차를 대상으로 도로포장의 평탄성에 따른 유류소모량 변화의 관계를 실제 도로에서 실측하여 평탄성과 유류소모량 변화의 관계를 분석하였다. 실험 결과, 평탄성에 따른 유류소모량의 변화는 평탄성이 1m/km 증가하였을 경우 100km 주행시 약 80ml 정도의 비율로 유류소모량이 증가하는 것으로 확인되었다. 따라서 도로의 설계 및 유지관리에 있어서 보다 정확한 경제성 분석을 수행하기 위해서는 도로포장의 평탄성에 따른 유류소모량 변화를 고려해야 할 필요가 있다.

To estimate fuel consumption of a vehicle, a car can be tested on chassis dynamometer. In this case, test causes a lot of time and money. To predict the fuel efficiency of vehicles in the design stage or early stage of development, the development of computer simulation model is necessary. Using simulation to predict the fuel consumption, the driving model which consists of time-velocity profile and time-grade profile is necessary In this study, vehicle model is developed in MatLab/simulink to estimate real driving fuel consumption rate with time-velocity profile, time-shift gear profile and time-grade profile. Vehicle model consists of driver model, engine model, power train model, and so on. On-road vehicle tests to verify the vehicle model are carried out for analyzing the result of simulation and comparing with those of the experiments.