A machine learning approach for the estimation of fuel consumption related to road pavement rolling resistance for large fleets of trucks

Abstract

There remains a level of uncertainty concerning the methodological assumptions and parameters to consider in the estimation of road vehicle fuel consumption due to the condition of road pavements. In fact, recent studies highlighted how existing models can lead to very different results and that because of this, they are not fully ready to be implemented as standard in the life-cycle assessment (LCA) framework. This study presents an innovative approach, based on the application of the Boruta algorithm (BA) and neural networks (NN), for the assessment and calculation of the fuel consumption of a large fleet of truck, which can be used to estimate the use phase emissions of road pavements. The study shows that neural networks are suitable to analyse the large quantities of data, coming from fleet and road asset management databases, effectively and that the developed NN model is able to estimate the impact of rolling resistance-related parameters (pavement roughness and macrotexture) on truck fuel consumption.

Citation

Perrotta, F., Parry, T., Neves, L. C., & Mesgarpour, M. (2018). A machine learning approach for the estimation of fuel consumption related to road pavement rolling resistance for large fleets of trucks.

• Conference Name: The Sixth International Symposium on Life-Cycle Civil Engineering (IALCCE 2018)
• Start Date: Oct 28, 2018
• End Date: Oct 31, 2018
• Acceptance Date: Apr 15, 2018
• Publication Date: Oct 28, 2018
• Deposit Date: Apr 26, 2018
• Publicly Available Date: Oct 28, 2018
• Peer Reviewed: Peer Reviewed
• Keywords: Fuel Consumption, Big Data, Neural Networks, Machine Learning, LCA
• Public URL: https://nottingham-repository.worktribe.com/output/950687