Water management fault diagnosis for proton-exchange membrane fuel cells based on deep learning methods
Water management fault diagnosis for proton-exchange membrane fuel cells based on deep learning methods
复制标题
DOI：
10.1016/j.ijhydene.2023.03.097
复制
发表时间：
2023-04
影响因子：
7.2
通讯作者：
Fei Xiao;Tao Chen;Jiwei Zhang;Shaojie Zhang
中科院分区：
文献类型：
--
作者：
Fei Xiao;Tao Chen;Jiwei Zhang;Shaojie Zhang
水管理失效是质子交换膜燃料电池（PEMFC）最常见的故障，直接影响燃料电池的耐久性和稳定性。提出了一种基于1DCNN-XGB的水故障诊断方法。为了促进其商业应用，阴极压降，电压和电流密度被用作特征诊断变量，这考虑了电池堆负载的变化，也有利于分层故障诊断。首先，通过改变电堆的工作条件，模拟不同电流密度下的淹没和干燥实验，并对实验数据进行归一化处理，消除特征不平衡。然后，它们被重建为1D数据集作为模型的输入。通过1DCNN进行自动特征提取，并将提取的特征图用作XGBoost分类器的输入。最后，在测试集上对训练后的模型进行了故障诊断验证。实验结果表明，该模型能够准确、有效地区分电池堆两种典型故障状态（水淹和干涸）的正常和不同程度，总体准确率为98.10%。对比实验表明，该模型上级单个1DCNN和XGBoost模型，表现出更高的准确性和更好的泛化能力。
Water management failure is the most common fault in proton-exchange membrane fuel cells (PEMFCs), and it directly affects the durability and stability of fuel cells. This paper proposes a water fault diagnosis method based on 1DCNN-XGB. To promote its commercial applications, the cathode pressure drop, voltage, and current density were used as the characteristic diagnostic variables,which considered variations in the stack load and also facilitated hierarchical fault diagnosis. First, flooding and drying experiments under different current densities were simulated by changing the operating conditions of the stack, and the obtained experimental data were normalized to eliminate feature imbalances. Then, they were reconstructed into a 1D data set as the input of the model. Automatic feature extraction was performed by a 1DCNN, and the extracted feature maps were used as the input of the XGBoost classifier. Finally, the trained model was validated on the test set for fault diagnosis. The experimental results showed that the model accurately and efficiently distinguished normal and different degrees of two typical fault states (flooding and drying) of the stack with an overall accuracy of 98.10%. The comparative experiments revealed that the model was superior to the individual 1DCNN and XGBoost models, showing greater accuracy and better generalization ability.