Research on Optimization Energy Management Strategies Based on Driving Cycle Recognition for Plug-in Hybrid Electric Vehicle
- DOI
- 10.2991/icmmcce-15.2015.475How to use a DOI?
- Keywords
- Plug-in Hybrid Electric Vehicle; Extreme Learning Machine; driving cycle recognition; optimization energy management strategies; energy consumption economy
- Abstract
In order to make the plug-in hybrid electric vehicle obtain optimal energy consumption economy and adapt to more complex working environment, the optimization energy management strategies based on driving cycle recognition were made. First, six kinds of cycle as standard working were selected to represent urban congestion, city suburban and highway, and the characteristic parameters of block segmentation were calculated by use of composite uniform method. Second, the extreme learning machine was applied to train and identity working conditions. Third, the optimum algorithm was applied to calculate the energy distribution rules of six standard cycles, which was stored control parameter library in order to call. On the MATLAB/SIMULINK platform, the optimization mode was built and the energy management strategy of conditions recognition and conditions without recognition were simulated. Simulation results indicate that the energy consumption economy of control strategy based on driving cycle recognition have improved 13.8%,16.4%, 14.8%, 11.1%,when the initial value of SOC is 0.95,0.75,0.55 and 0.35.
- Copyright
- © 2015, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Yong Ren AU - Guanlong Yang AU - Wei Liang AU - Jie Liu AU - Xueyong Tian PY - 2015/12 DA - 2015/12 TI - Research on Optimization Energy Management Strategies Based on Driving Cycle Recognition for Plug-in Hybrid Electric Vehicle BT - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015 PB - Atlantis Press SP - 850 EP - 854 SN - 2352-538X UR - https://doi.org/10.2991/icmmcce-15.2015.475 DO - 10.2991/icmmcce-15.2015.475 ID - Ren2015/12 ER -