Abstract Using a typical driving cycle to implement and evaluate the established control strategy is quite essential in the investigation of electric vehicles (EVs) power management issue. How to build a representative driving cycle remains a challenge due to the complex urban driving conditions. In this paper, the principal component analysis (PCA) and k-means cluster are employed to develop the driving cycle with case of Shenyang, China. First of all, a large amount of road conditions test data are collected, which are made up of a series of data including driving time and the instantaneous velocity. On top of that, the PCA is applied to extract the main components of overall road information and the K-means cluster is used to select representative kinematic fragments. Several most representative fragments are chosen to form the driving cycle. At last, the proposed driving cycle is simulated and verified. The result shows that the proposed driving cycle can well match to overall road information.
[1]
Zeyu Chen,et al.
Particle swarm optimization-based optimal power management of plug-in hybrid electric vehicles considering uncertain driving conditions
,
2016
.
[2]
Xiaofang Wang,et al.
Bayesian wavelet PCA methodology for turbomachinery damage diagnosis under uncertainty
,
2016
.
[3]
Mutasim A. Salman,et al.
Energy management strategies for parallel hybrid vehicles using fuzzy logic
,
2000
.
[4]
Jonas Sjöbergh,et al.
Effects of weather conditions, light conditions, and road lighting on vehicle speed
,
2016,
SpringerPlus.
[5]
Hai-Jun Huang,et al.
Analysis of the equilibrium trip cost without late arrival and the corresponding traffic properties using a car-following model
,
2016
.