차량 연료소모량 예측을 위한 머신러닝 기법
Machine Learning Methods to Predict Vehicle Fuel Consumption
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구에서는 주행 차량의 실시간 연료소모량을 예측할 수 있는 머신러닝 기법을 제안하고 그특성을 분석하였다. 머신러닝 학습을 위해 실도로 주행을 실시하여 주행 속도, 가속도, 도로 구배와 함께 연료소모량을 측정하였다. 특성 데이터로 속도, 가속도, 도로구배를, 타깃으로 연료소모량을 지정하여 다양한 머신러닝 모델을 학습시켰다. 회귀법에 해당하는 K-최근접이웃회귀 및 선형회귀와 함께, 분류법에 해당하는 K-최근접이웃분류, 로지스틱회귀, 결정트리, 랜덤포레스트, 그래디언부스팅을 사용하였다. 실시간 연료소모량에 대한 예측 정확도는 0.5 ~ 0.6 수준으로 전반적으로 낮았고, 회귀법의 경우 분류법보다 정확도가 떨어졌다. 총연료소모량에 대한 예측 오차는 0.2 ~ 2.0% 수준으로 상당히 정확했고, 분류법보다 회귀법의 오차가 더 낮았다. 이는 예측 정확도의기준으로 결정계수(R2)를 사용했기 때문인데, 이 값이 작을수록 타깃의 평균 부근에 예측치가 좁게 분포하기 때문이다. 따라서 실시간 연료소모량 예측에는 분류법이, 총연료소모량 예측에는 회귀법이 적합하다고 할 수 있다.
Abstract
It’s proposed and analyzed ML(Machine Learning) models to predict vehicle FC(Fuel Consumption) in real-time. The test driving was done for a car to measure vehicle speed, acceleration, road gradient and FC for training dataset. The various ML models were trained with feature data of speed, acceleration and road-gradient for target FC. There are two kind of ML models and one is regression type of linear regression and k-nearest neighbors regression and the other is classification type of k-nearest neighbors classifier, logistic regression, decision tree, random forest and gradient boosting in the study. The prediction accuracy is low in range of 0.5 ~ 0.6 for real-time FC and the classification type is more accurate than the regression ones. The prediction error for total FC has very low value of about 0.2 ~ 2.0% and regression models are more accurate than classification ones. It’s for the coefficient of determination (R2) of accuracy score distributing predicted values along mean of targets as the coefficient decreases. Therefore regression models are good for total FC and classification ones are proper for real-time FC prediction.
참고문헌 (11)
- S. Tanaka, "When Tax Incentives Drive Illicit Behavior: The Manipulation of Fuel Economy in the Automobile Industry", J. Environ. Econ. Manag, 104 (2020)[DOI]
- W. Huang, "Evaluation of Real-time Vehicle Energy Consumption and Related Emissions in China: A Case Study of the Guangdong–Hong Kong–Macao Greater Bay Area", J. Clean. Prod, 263 (2020)[DOI]
- S. Baek, "Implementation of Integrated OBD-II Connector with External Network", Inf. Syst, 50, pp.69~75 (2015)[DOI]
- S. Lee, "Development of Greenhouse Gas Emissions Model for 2014-2017 Heavy- and Medium-duty Vehicle Compliance", SAE Tech. Pap (2011)[DOI]
- G. Fontaras, "Monitoring CO2 Emissions from HDV in Europe—An Experimental Proof of Concept of the Proposed Methodological Approach", Proceedings of the Conference on Transport and Air Pollution (2014)
- K. Ko, "An Economic Calibration Method for Fuel Consumption Model in HDM4", Wirel. Pers. Commun, 89, pp.959~975 (2016)[DOI]
- S. Alexander, "A Machine Learning Model for Average Fuel Consumption in Heavy Vehicles", IEEE Trans. Veh. Technol, pp.1~10 (2019)[DOI]
- S. Wickramanayake, "Fuel Consumption Prediction of Fleet Vehicles Using Machine Learning: A Comparative Study", Proceedings of the Moratuwa Engineering Research Conference, pp.90~95 (2016)
- J. Ziółkowski, "Use of Artificial Neural Networks to Predict Fuel Consumption on the Basis of Technical Parameters of Vehicles", Energies, 14(9) (2021)[DOI]
- H. Vdovic, "Eco-efficient Driving Pattern Evaluation for Sustainable Road Transport Based on Contextually Enriched Automotive Data", J. Clean. Prod, 311 (2021)[DOI]
- E. González, "Development of the Management Strategies of the ECU for an Internal Combustion Engine: Computer Simulation", Mech. Syst. Signal Process, 22, pp.1356~1373 (2008)[DOI]