An on-line predictive energy management strategy for plug-in hybrid electric vehicles to counter the uncertain prediction of the driving cycle
An on-line predictive energy management strategy for plug-in hybrid electric vehicles to counter the uncertain prediction of the driving cycle
复制标题
DOI：
10.1016/j.apenergy.2016.01.071
复制
发表时间：
2017
期刊：
影响因子：
11.2
通讯作者：
Zeyu Chen;R. Xiong;C. Wang;Jiayi Cao
中科院分区：
文献类型：
--
作者：
Zeyu Chen;R. Xiong;C. Wang;Jiayi Cao
预测性能源管理可以实时实施，并对未来的驾驶循环进行短期预测。然而，对未来驾驶循环的完全精确预测仍然相当困难。本研究探讨了两个努力领域。第一个是实施的动态邻域粒子群优化算法的局部最优能量管理策略的插电式混合动力汽车的基础上的数据从未来的行驶周期的预测。其次，考虑了不精确的驾驶循环预测的影响，然后提出了一种在线校正算法的基础上备份控制策略和模糊逻辑控制器。除了这些努力，预测能源管理策略与在线校正算法，最后提出。与最优启发式方法相比，在对未来行驶周期预测准确的情况下，所提出的能量管理策略可以降低9.7%的能耗。对于预测不精确的情况，在线修正算法可以将与实际最优策略的偏差减小32.39%。
Predictive energy management could be implemented in real-time with a short period of future driving cycle prediction. However, the completely precise prediction of the future driving cycle remains quite difficult. Two areas of effort have been explored in this study. The first is the implementation of a dynamic-neighborhood particle swarm optimization algorithm in the local optimal energy management strategy of plug-in hybrid electric vehicles based on data from the prediction of the future driving cycle. Second, the influence of an imprecise driving cycle prediction is considered, and then an online correction algorithm is proposed based on the backup control strategy and a fuzzy logic controller. In addition to these efforts, a predictive energy management strategy with an online correction algorithm is finally proposed. Compared with the optimal heuristic method, the presented energy management strategy could reduce the energy by up to 9.7% if the prediction of the future driving cycle is precise. For the situation of imprecise prediction, the online correction algorithm could reduce the deviation from the actual optimal policy by up to 32.39%.