• Dr.K.N.S Lakshmi
• Ijji Saikiran

In this study, we developed customised machine learning models for fuel consumption[1] using vehicle travel distance rather than the conventional time period. Seven predictors generated from vehicle speed and road grade are combined with this method to create a highly predictive neural network model for average fuel consumption in large vehicles. To reduce fuel usage across the board, the suggested methodology can be quickly established and implemented for each individual vehicle in a fleet. The model's predictors are combined over predetermined window sizes for distance travelled. The evaluation of various window sizes reveals that a 1 km window has a 0.91 coefficient of determination and a mean absolute peak-to-peak percent accuracy in predicting fuel usage.

Fuel consumption, machine learning, neural network, vehicle travel distance, road grade, fleet optimization, ANN, image classifier, neural network architecture

"Average Fuel Consumption in Heavy Vehicles Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.a102-a109, June-2023, Available :http://www.jetir.org/papers/JETIR2306015.pdf

"Average Fuel Consumption in Heavy Vehicles Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. ppa102-a109, June-2023, Available at : http://www.jetir.org/papers/JETIR2306015.pdf