Performance degradation prediction method of PEM fuel cells using bidirectional long short-term memory neural network based on Bayesian optimization

Proton exchange membrane (PEM) fuel cell is the core equipment that can directly convert hydrogen energy into electricity. In the process of long-term operation, due to the aging of membrane electrode assembly and other components, the fuel cell performance gradually deteriorates. The voltage predic...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Energy (Oxford) Ročník 285; s. 129469
Hlavní autoři:	Chen, Dongfang, Wu, Wenlong, Chang, Kuanyu, Li, Yuehua, Pei, Pucheng, Xu, Xiaoming
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 15.12.2023
Témata:	algorithms Bayesian optimization algorithm Bayesian theory data collection electric potential difference electricity electrodes fuel cells fuels hydrogen Long short-term memory neural network neural networks PEM fuel cell Performance degradation prediction prediction Sampling time interval Long short-term memory neural network Sampling time interval Bayesian optimization algorithm Performance degradation prediction PEM fuel cell
ISSN:	0360-5442
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Proton exchange membrane (PEM) fuel cell is the core equipment that can directly convert hydrogen energy into electricity. In the process of long-term operation, due to the aging of membrane electrode assembly and other components, the fuel cell performance gradually deteriorates. The voltage prediction of fuel cells is very important for performance and lifetime optimization. Long short-term memory neural network is one of the widely used prediction methods. Based on the prediction method of bidirectional long short-term memory neural network, the hyperparameters of the neural network model by Bayesian optimization algorithm is optimized to improve the accuracy of fuel cell performance degradation prediction. When the sampling time interval is 25 min and the training set is 45 %, the root mean square error and the average absolute percentage error of the prediction results is reduced to 6.3 mV and 0.1245 %, respectively. Moreover, by analyzing the influence of different sampling time intervals and training set proportion on the prediction results, a data set that takes into accounts both efficiency and accuracy is obtained. The proposed method based on Bayesian optimization can achieve more accurate performance degradation prediction. •A performance prediction method for fuel cells based on Bi-LSTM is proposed.•Bayesian algorithm was adopted to optimize the hyperparameters.•The effect of training set ratio on performance prediction is studied.•A reasonable frequency range of data sampling is proposed.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	0360-5442
DOI:	10.1016/j.energy.2023.129469