Modeling the Driving Behavior of Electric Vehicles Using Smartphones and Neural Networks
- 21 July 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 6 (3), 44-53
- https://doi.org/10.1109/mits.2014.2322651
Abstract
The modeling of eco-driving behaviors is a key issue in the research of Intelligent Transportation Systems. Most efforts have been made regarding internal combustion vehicles, and few works have been reported in the field of electric vehicles. On the other hand, these behavior analyses are usually conducted through naturalistic driving researches that involve the use of instrumented vehicles, available in a small number, which reduces the impact of the results. This paper presents a system for estimating the remaining charge of an electric vehicle by considering the driving behavior measured using a smartphone. For this purpose, first of all, data measured by the smartphone and by the onboard instrumentation were compared in order to demonstrate that both sources are equivalent and that the former is sufficiently accurate. The driving profiles obtained were then used to estimate the expected battery consumption of the electric vehicle using a Neural Network to represent the model that uses the information provided from the smartphone as input, such as speed, acceleration and jerk. The system has been tested with 10 drivers with a prediction capability of the expected battery consumption higher than 95%. These results show that a smartphone is a tool with a sufficient degree of fidelity to capture data from drivers, and so avoid expensive, complex systems like instrumented vehicles, and it can also be used for estimating energy consumption and predicting the remaining battery charge.Keywords
This publication has 14 references indexed in Scilit:
- Validating the Impact on Reducing Fuel Consumption by Using an EcoDriving Assistant Based on Traffic Sign Detection and Optimal Deceleration PatternsIEEE Transactions on Intelligent Transportation Systems, 2013
- Modelo para la Conducción Eficiente y Sostenible basado en Lógica BorrosaRevista Iberoamericana de Automática e Informática Industrial, 2012
- Driving coach: A smartphone application to evaluate driving efficient patternsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- OPTIMIZACION DE CONSUMO DE COMBUSTIBLE DE VEHICULOS BASADA EN PROGRAMACION DINAMICADYNA Ingenieria e Industria, 2012
- Driving style recognition using a smartphone as a sensor platformPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Eco-driving: An overlooked climate change initiativeEnergy Policy, 2009
- Look-ahead control for heavy trucks to minimize trip time and fuel consumptionControl Engineering Practice, 2008
- Reliable Method for Driving Events RecognitionIEEE Transactions on Intelligent Transportation Systems, 2005
- Neural networksCommunications of the ACM, 1994
- What Size Net Gives Valid Generalization?Neural Computation, 1989