基于随机动态规划的燃料电池城市客车能量管理策略优化

Optimized Energy Management Strategy for Fuel Cell City Bus Based on Stochastic Dynamic Programming

设计了一种新型的燃料电池混合超级电容的城市客车动力系统结构,在理论计算和工程分析的基础上,对该动力系统进行了参数匹配。提出一种基于随机动态规划的燃料电池城市客车能量管理策略的设计思想,将驾驶员需求功率模拟为一个离散的随机动态过程,并建立相应的马尔可夫模型,在此基础上采用策略迭代的算法对能量管理策略进行了优化。并对优化后的策略进行仿真,结果表明该策略下的整车燃料经济性有明显提高。

The powertrain framework of a new model of fuel cell city bus which combines fuel cell with ultracapacitor was designed. The related parameters of driveline were designed on the basis of theory deduction and engineering analysis. A stochastic dynamic programming algorithm was developed for the energy management of this fuel cell city bus. The driver＇s power demand was modeled as a discrete-time stochastic＂ dynamic process, then the related Markov chain was set up. The policy iteration algorithm was used to optimize the control strategy. The optimization scheme was validated by simulation. The result indicates that the fuel economy of the bus is improved obviously under this strategy.