Degradation prediction method of PEMFC based on deep learning hybrid model integrating ARIMA and LSTM | Xibei Gongye Daxue Xuebao/Journal of Northwestern Polytechnical University

Open Access

表2

预测结果评估对比

方法	E_MS	E_MA	E_RMS	R²
SVR	0.000 04	0.004 76	0.006 56	0.973 96
NARX	0.000 03	0.002 61	0.005 47	0.942 95
ARIMA	0.000 04	0.003 62	0.006 09	0.854 14
ARIMA-LSTM	0.000 01	0.002 65	0.001 89	0.966 01

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.