Liu Xiaohui, Chen Jianhua, Wei Yian, Liu Shengjie, Zhou Yilin
School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.
Heliyon. 2024 Jul 19;10(15):e34783. doi: 10.1016/j.heliyon.2024.e34783. eCollection 2024 Aug 15.
In this paper, the degradation of PEMFC under different operating conditions in dynamic cycle condition is studied. Firstly, according to the failure mechanism of PEMFC, various operating conditions in dynamic cycle condition are classified, and the health indexes are established. Simultaneously, the rates and degrees of the output voltage decline of the PEMFC under different operating conditions during the dynamic cycling process were compared. Then, a model based on variational mode decomposition and long short-term memory with attention mechanism (VMD-LSTM-ATT) is proposed. Aiming at the performance of PEMFC is affected by the external operation, VMD is used to capture the global information and details, and filter out interference information. To improve the prediction accuracy, ATT is used to assign weight to the features. Finally, in order to verify the effectiveness and superiority of VMD-LSTM-ATT, we respectively apply it to three current conditions under dynamic cycle conditions. The experimental results show that under the same test conditions, RMSE of VMD-LSTM-ATT is increased by 56.11 % and MAE is increased by 28.26 % compared with GRU attention. Compared with SVM, RNN, LSTM and LSTM-ATT, RMSE of VMD-LSTM-ATT is at least 17.26 % higher and MAE is at least 5.65 % higher.
本文研究了质子交换膜燃料电池（PEMFC）在动态循环条件下不同运行工况下的退化情况。首先，根据PEMFC的失效机理，对动态循环条件下的各种运行工况进行分类，并建立健康指标。同时，比较了PEMFC在动态循环过程中不同运行工况下输出电压下降的速率和程度。然后，提出了一种基于变分模态分解和带注意力机制的长短期记忆网络（VMD-LSTM-ATT）的模型。针对PEMFC性能受外部运行影响的问题，采用VMD捕捉全局信息和细节，并滤除干扰信息。为提高预测精度，采用ATT对特征进行加权。最后，为验证VMD-LSTM-ATT的有效性和优越性，将其分别应用于动态循环条件下的三种电流工况。实验结果表明，在相同测试条件下，与门控循环单元（GRU）注意力模型相比，VMD-LSTM-ATT的均方根误差（RMSE）提高了56.11%，平均绝对误差（MAE）提高了28.26%。与支持向量机（SVM）、递归神经网络（RNN）、长短期记忆网络（LSTM）和带注意力机制的长短期记忆网络（LSTM-ATT）相比，VMD-LSTM-ATT的RMSE至少高17.26%，MAE至少高5.65%。
