<![CDATA[Fuel consumption efficiency is a key indicator in the development of modern vehicles, as it directly affects operating costs and exhaust emissions. This study aimed to analyze the characteristics of Electronic Control Unit (ECU) data as predictive parameters for fuel consumption and to develop a regression-based Machine Learning model for predicting vehicle fuel consumption. The dataset consisted of 597 vehicle records, with Engine Size, Cylinders, CO₂ Emissions, and Fuel Type serving as predictor variables, while Combined Fuel Consumption was used as the target variable. Data were analyzed using multiple linear regression, and model performance was evaluated based on the coefficient of determination (R²), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Standard Error of Estimate (SEE). The results demonstrated that the proposed model achieved excellent predictive performance, with an R value of 0.989, an R² of 0.977, an adjusted R² of 0.977, an SEE of 0.432 L/100 km, an MAE of 0.24 L/100 km, and an RMSE of 0.430 L/100 km. Among the predictor variables, CO₂ Emissions was identified as the most influential factor affecting fuel consumption. These findings indicate that ECU data can provide accurate fuel consumption predictions and have significant potential to support the development of vehicle fuel-efficiency monitoring systems and data-driven decision-making in the automotive industry.]]>
Copyrights © 2026
