Neural Network-based Prediction of Fuel Consumption of a Conventional Delivery Vehicle based on GPS-collected Tracking Data (CROSBI ID 693586)
Prilog sa skupa u zborniku | izvorni znanstveni rad
Podaci o odgovornosti
Hihlik, Mislav ; Topić, Jakov ; Škugor, Branimir ; Deur, Joško
engleski
Neural Network-based Prediction of Fuel Consumption of a Conventional Delivery Vehicle based on GPS-collected Tracking Data
This paper deals with finding an appropriate data- driven model for a prediction of vehicle fuel consumption on destination. Several models are considered for this purpose, ranging from a simple polynomial-based models which include only vehicle travelled distance and payload mass as inputs to more complex neural network (NN)-based ones. Special effort is devoted to preparation of inputs for considered NNs, since driving cycles for which the fuel consumption is being predicted can vary in length, while NNs assume an input with fixed dimensions. To this end, two input types are defined and analysed: (i) 1D vector which contains counted discrete vehicle velocity values, and (ii) 2D matrix which contains counted combinations of discrete vehicle velocity and acceleration values. The structures of considered NN architectures are optimised to find the optimal number of their hidden layers and corresponding number of neurons. The proposed models are developed and validated based on a dataset collected by using GPS/GPRS equipment on a set of 10 delivery vehicles during 24h per day over three-month period. Finally, the impact of payload mass on the fuel consumption and its contribution to improvement of fuel prediction accuracy is comprehensively analysed.
Delivery vehicles ; fuel consumption prediction ; deep neural networks ; big data
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1-24.
2020.
objavljeno
Podaci o matičnoj publikaciji
Podaci o skupu
15th Conference on Sustainable Development of Energy, Water and Environment Systems (SDEWES 2020)
predavanje
01.09.2020-05.09.2020
Köln, Njemačka; online