Proton Exchange Membrane Fuel Cell Degradation Prediction Based on GWO-LSTM
A method combining Long Short-Term Memory networks and the Grey Wolf Optimization algorithm is proposed to address the issues of low prediction accuracy and poor generalization performance in predicting the degradation trend of Proton Exchange Membrane Fuel Cells using LSTM networks.The GWO algorithm is used to optimize the LSTM model's hyperparameters—learning rate and dropout probability—to improve the prediction results.Finally,simulation experiments are conducted to predict the degradation trend of PEMFCs,and the predicted results are compared with actual degradation data to validate the proposed degradation prediction model.The results show that this method not only improves the generalization performance of the LSTM model but also enhances the prediction accuracy by 56%compared to traditional LSTM-based prediction methods.
万方数据
维普
