Driving condition recognition for genetic-fuzzy HEV Control

This paper presents a genetic-fuzzy approach for hybrid electric vehicle control based on driving pattern recognition and prediction. In this approach, data collection in the real traffic conditions is employed for classification of several driving patterns. These driving patterns represent different traffic conditions e.g. congested, urban and so on. The analysis used for the driving pattern recognition is based on the definition of microtrips. In addition, a Markov chain modeling is used for traffic condition prediction based on the modeling of probability of the sequence of microtrips. The driving pattern prediction is then utilized for optimization of the HEV control parameters using a genetic-fuzzy approach. In this approach, a fuzzy logic controller (FLC) is designed to be intelligent so as to manage the internal combustion engine (ICE) to work in the vicinity of its optimal condition. The fuzzy membership function parameters are then tuned using the genetic algorithm (GA). Finally, simulation results are presented to show the effectiveness of the approach for reducing the HEV fuel consumption and emissions.