Degradation prediction of PEM water electrolyzer under constant and start-stop loads based on CNN-LSTM  

作　　者：Boshi Xu Wenbiao Ma Wenyan Wu Yang Wang Yang Yang Jun Li Xun Zhu Qiang Liao 

机构地区：[1]Key Laboratory of Low-grade Energy Utilization Technologies and Systems,Ministry of Education,Chongqing University,Chongqing 400030,China [2]Institute of Engineering Thermophysics,School of Energy and Powering Engineering,Chongqing University,Chongqing 400030,China

出　　处：《Energy and AI》2024年第4期76-85,共10页能源与人工智能(英文)

基　　金：financial supports of National Key Research and Development Program of China(No.2021YFB4000100);National Natural Science Foundation of China(No.52322604).

摘　　要：The performance degradation is a crucial factor affecting the commercialization of proton exchange membrane electrolyzer.However,it is difficult to establish a mechanism model incorporating all degradation categories due to their different time and spatial scales.In this paper,the data-driven method is employed to predict the electrolyzer voltage variation over time based on a convolutional neural network-long short term memory(CNNLSTM)model.First,two datasets including constant operation for 1140 h and start-stop load for 660 h are collected from the durability tests.Second,the data-driven models are trained through the experimental data and the model hyper-parameters are optimized.Finally,the electrolyzer degradation in the next few hundred hours is predicted,and the prediction accuracy is compared with other time-series algorithms.The results show that the model can predict the degradation precisely on both datasets,with the R2 higher than 0.98.Compared to con-ventional models,the algorithm shows better fitting characteristic to the experimental data,especially as the prediction time increases.For constant and start-stop operations,the electrolyzers degradate by 4.5%and 2.5%respectively after 1000 h.The proposed method shows great potential for real-time monitoring in the electrolyzer system.

关 键 词：Pem water electrolyzer DEGRADATION Dynamic operation Machine learning CNN-LSTM 

分 类 号：O57[理学—粒子物理与原子核物理]