To enhance the accuracy of neural network models in predicting the remaining useful life of lithium-ion batteries,this paper proposes a method based on the Attention-GRU (Gated Recurrent Unit) model.Firstly,utilizing the Random Walk battery data publicly available from NASA,health factors significantly correlated with battery capacity degradation were extracted from direct measurement data such as battery voltage,current,and time,and the correlation between these health factors and battery capacity was calculated.Secondly,an Attention-GRU model was constructed to learn the patterns of change in health factors,allocate attention weights based on correlation,obtain attention vectors,and adjust the hidden layer output accordingly.Finally,predictions for the remaining useful life of the batteries were made,with additional predictions for the B05 series of batteries to explore the model's generalization capability.Experimental results indicated that when using the proposed Attention-GRU model to predict the remaining useful life of Random Walk batteries,the MAE (Mean Absolute Error) and RMSE (Root Mean Square Error) were around 0.015,and for the B05 series batteries,the MAE and RMSE were below 0.01.These results show that the prediction accuracy of the proposed model is superior to that of comparative methods,demonstrating high precision and good generalization ability.