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...

Full description

Saved in:
Bibliographic Details
Published in:Energy (Oxford) Vol. 285; p. 129469
Main Authors: Chen, Dongfang, Wu, Wenlong, Chang, Kuanyu, Li, Yuehua, Pei, Pucheng, Xu, Xiaoming
Format: Journal Article
Language:English
Published: Elsevier Ltd 15.12.2023
Subjects:
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
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0360-5442
DOI:10.1016/j.energy.2023.129469