基于差分进化优化的支持向量机燃料电池故障诊断

Fuel cell fault diagnosis for support vector machines optimized based on differential evolution algorithm

质子交换膜燃料电池是一种多耦合非线性的复杂系统,电堆内部的水淹和膜干故障是其运行过程中最常见的故障。基于差分进化算法优化的支持向量机方法,可以用于燃料电池故障诊断,该方法在传统的支持向量机模型上增加了主成分提取和差分进化算法寻找最优参数,使模型得到更好的训练效果。采用电堆20片单电池电压为数据集进行相关的故障验证分析,结果表明:通过差分进化算法优化的支持向量机在燃料电池故障诊断中有着较高的准确度,具有一定的工程应用价值。

Proton exchange membrane fuel cell is a complex system with multiple coupling nonlinearities,water flooding and membrane dry failure inside the stack are the most common fault during its operation.A support vector machine fault diagnosis method was proposed based on differential evolution algorithm optimization,this method added principal component extraction and differential evolution algorithms to the traditional support vector machine model to find the optimal parameters,and the model could get the best training effect.The voltage of 20 single cells of the stack was used as the data set for relevant fault verification analysis.The results show that the support vector machine optimized by differential evolution algorithm has higher accuracy in fuel cell fault diagnosis and has certain engineering application value.