.png){kind=icon}
返回
Cloud computing-based energy optimization control framework for plug-in hybrid electric bus
.png){kind=icon}
PRE
AI
DOI：10.1016/j.energy.2017.02.102.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Considering the complicated characteristics of traffic flow in city bus route and the nonlinear vehicle dynamics, optimal energy management integrated with clustering and recognition of driving conditions in plug-in hybrid electric bus is still a challenging problem. Motivated by this issue, this paper presents an innovative energy optimization control framework based on the cloud computing for plug-in hybrid electric bus. This framework, which includes offline part and online part, can realize the driving conditions clustering in offline part, and the energy management in online part. In offline part, utilizing the operating data transferred from a bus to the remote monitoring center, K-means algorithm is adopted to cluster the driving conditions, and then Markov probability transfer matrixes are generated to predict the possible operating demand of the bus driver. Next in online part, the current driving condition is real-time identified by a well-trained support vector machine, and Markov chains-based driving behaviors are accordingly selected. With the stochastic inputs, stochastic receding horizon control method is adopted to obtain the optimized energy management of hybrid powertrain. Simulations and hardware in-loop test are carried out with the real-world city bus route, and the results show that the presented strategy could greatly improve the vehicle fuel economy, and as the traffic flow data feedback increases, the fuel consumption of every plug-in hybrid electric bus running in a specific bus route tends to be a stable minimum. (C) 2017 Elsevier Ltd. All rights reserved.
Keyword:
Plug-in hybrid electric bus
Energy optimization control framework
Driving conditions clustering
Energy management
Stochastic receding horizon control
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.4
论文数:
4.3W
被引数:
20.2W
机构
引用论文
Real time energy management strategy for a fast charging electric urban bus powered by hybrid energy storage system基于混合储能系统的快速充电电动城市客车实时能量管理策略.png)
ENERGY
OAAI
ENERGYIF9.4
OAAI分享收藏Bus-Stop Control Strategies Based on Fuzzy Rules for the Operation of a Public Transport System
PREAI
分享收藏A Stochastic Optimal Control Approach for Power Management in Plug-In Hybrid Electric Vehicles插电式混合动力汽车功率管理的随机最优控制方法
PREAI
分享收藏Advanced Power-Source Integration in Hybrid Electric Vehicles: Multicriteria Optimization Approach混合动力汽车中的高级电源集成: 多准则优化方法
PREAI
分享收藏
查看更多内容