燃料电池汽车用电磁铁的优化设计  

Optimization design of electromagnet for hydrogen fuel cell vehicles

作　　者：梁禹[1] 蔡胜年[1] 王娜[1] 

机构地区：[1]沈阳化工大学信息工程学院,辽宁沈阳110142

出　　处：《电工电能新技术》2015年第1期62-68,共7页Advanced Technology of Electrical Engineering and Energy

基　　金：辽宁省教育厅重点实验室计划(2008S178)资助项目

摘　　要：对于氢燃料电池汽车,高压储氢瓶中电磁铁的吸合面的形状和位置对电磁力影响很大,而且呈现复杂的非线性关系。在有限元分析基础上,为了提高优化效率,提出基于吸合面支持向量机模型的优化设计方法。利用均匀设计方法在设计空间中选择建模样本点,用有限元方法计算建模样本点的电磁力,构成建模样本。基于支持向量机建立吸合面形状和位置与电磁力的非线性模型。对该模型采用遗传算法优化,计算出了最优吸合面形状和位置,并对优化结果进行了仿真和样机对比试验。结果证明了优化设计方法的有效性。The shape and position of electromagnet contact-surface have much effect on electromagnetic force in high-pressure hydrogen storage bottle for hydrogen fuel cell vehicles and the relationship between the contact-surface and electromagnetic force is complex and nonlinear. In order to improve the efficiency of finite element methods,this article provides an optimization design method that deals with the complex relationship by support vector machine model to avoid a large number of finite element calculations. Authors of this article selected modeling sample points in the design space by uniform design,and used the finite element method to calculate the electromagnetic force of modeling sample points that have been selected. The non-linear model which indicates the relationship between shape and position of contact-surface of electromagnets and electromagnetic force is built by support vector machine. The genetic algorithm is used to optimize the model to calculate the optimal surface shape and position,and the optimization results are verified by the simulations and experiments. The result indicates that the optimization method is effective.

关 键 词：电磁铁 吸合面建模 支持向量机 遗传算法 

分 类 号：TM57[电气工程—电器]