聚合物电解质膜燃料电池空气供应系统故障诊断  

Fault diagnosis of polymer electrolyte membrane fuel cell air supply system

作　　者：田颖[1] 韩峰 李贺[2] 张龙海 TIAN Ying;HAN Feng;LI He;ZHANG Longhai(Beijing Key Laboratory of New Energy Vehicle Power Assembly,Beijing Jiaotong University,Beijing 100044,China;Zhengzhou Yutong Bus Co.,Ltd.,Zhengzhou 450061,China)

机构地区：[1]北京交通大学北京市新能源汽车动力总成重点实验室,北京100044 [2]郑州宇通客车股份有限公司,郑州450061

出　　处：《北京交通大学学报》2020年第4期116-123,共8页JOURNAL OF BEIJING JIAOTONG UNIVERSITY

基　　金：国家重点研发计划(2018YFB0105500)。

摘　　要：聚合物电解质膜燃料电池(Polymer Electrolyte Membrane Fuel Cell,PEMFC)空气供应系统中的故障通常会导致系统性能衰减甚至对电堆造成损害.针对PEMFC空气供应系统的故障诊断问题,提出了一种基于改进的人工蜂群算法(IABC)优化支持向量机(SVM)的故障诊断方法.采用文献中的非线性燃料电池系统模型,并在系统中加入方差为1的高斯噪声.通过引入Levy飞行策略,对标准人工蜂群算法(ABC)进行改进,提高了人工蜂群算法的全局搜索的能力,进而通过改进的人工蜂群算法优化支持向量机的惩罚因子C和核函数参数g,利用优化后的SVM分类器模型对PEMFC空气供应系统进行故障诊断研究.结果表明,该IABC-SVM算法故障诊断的准确率达到96.12%,具有良好的故障诊断效果.Faults in Polymer Electrolyte Membrane Fuel Cell(PEMFC)air supply system usually lead to system performance degradation and even cause damage to the stack.To improve the fault diagnosis of PEMFC air supply system,this paper proposes a fault diagnosis method based on Improved Artificial Bee Colony algorithm(IABC)optimized Support Vector Machine(SVM).The nonlinear fuel cell system model in the literature is applied and Gaussian noise with variance of 1 is added to the system.By introducing the Levy flight strategy to optimize the standard Artificial Bee Colony algorithm(ABC),the global search ability of the artificial bee colony algorithm is improved.The penalty factor C and kernel function parameter g of SVM are optimized by the IABC algorithm,and the optimized SVM model is used for fault diagnosis of PEMFC air supply system.The results show that the accuracy of the IABC-SVM algorithm is 96.12%,which shows good fault diagnosis ability.

关 键 词：聚合物电解质膜燃料电池 空气供应系统 故障诊断 支持向量机 人工蜂群 

分 类 号：TM911.4[电气工程—电力电子与电力传动]