Predicting Fuel Consumption in Motorcycles Using Numerical Interpolation and Regression
Main Article Content
Abstract
Accurate prediction of fuel consumption in motorcycles is vital for optimizing performance, enhancing fuel efficiency, and informing environmentally conscious transportation strategies. This study integrates mathematical modeling—specifically numerical interpolation and regression analysis—to establish a robust predictive framework for fuel consumption patterns across different engine capacities and operational conditions. Drawing on officially recorded data from globally recognized sources such as the U.S. Environmental Protection Agency (EPA) and International Energy Agency (IEA), the research employs Newton’s Divided Difference interpolation and multiple linear regression techniques to estimate fuel consumption values under varying conditions of speed, load, and terrain. Numerical results demonstrate that interpolation methods provide higher accuracy in scenarios with irregular data gaps, while regression models effectively capture the general consumption trends with statistically significant confidence intervals. The integration of these mathematical techniques not only enhances precision but also supports data-driven policy formulation and engineering design. The findings affirm the effectiveness of hybrid numerical approaches in the automotive energy sector, offering a scalable and replicable model for motorcycle fuel prediction in low-resource settings.