基于搜寻者优化算法的质子交换膜燃料电池模型优化

搜寻者优化算法(seeker optimization algorithm，SOA)是模拟人的随机搜索行为的一种应用于连续空间的群体智能优化算法。根据质子交换膜燃料电池(proton exchange membrane fuel cell，PEMFC)极化曲线模型的建模原理，采用SOA算法对该模型的参数进行优化，用以得到一组模型的最优参数。通过仿真结果与实验结果的对比分析，证明SOA算法能够使仿真结果和实验测试数据之间达到很高的拟合精度，对于优化PEMFC的极化曲线模型参数具有明显的优越性。因此，SOA算法对于改善PEMFC极化曲线模型的性能将起到重要的作用，并有望成为模型优化领域的一种新的有效工具。

Proton Exchange Membrane Fuel Cell Model Optimization based on Seeker Optimization Algorithm

Seeker optimization algorithm (SOA) which mimicked the stochastic searching behavior of human was applied to continuous space of swarm intelligence. According to the modeling principle of proton exchange membrane fuel cell (PEMFC) polarization curve model, SOA was proposed to research a set of optimized parameters in the PEMFC polarization curve model. The comprehensive comparison between simulation results and experimental results demonstrate that SOA can make the simulation results fitted the experiment data with higher precision and has manifest superiority for optimizing PEMFC polarization curve model. Therefore, SOA makes important effect for improving the performance of PEMFC polarization curve model and becomes a new effective tool in the fields of model optimization.