To improve the accuracy and stability of state of health(SoH)estimation for lithium-ion batteries,a SoH estimation model based on the Northern Goshawk Optimization(NGO)algorithm for optimizing the Gated Recurrent Unit(GRU)network was proposed.Multiple health factors from the historical data of battery charging and discharging voltage and temperature are extracted as input data for the model,and NGO intelligent optimization of hyperparameters such as the number of hidden units,learning rate,and maximum training period of the GRU network are used.A mapping rela-tionship between lithium battery health factors and SoH is constructed through the optimized NGO GRU estimation model to achieve rapid estimation of SoH.NASA datasets are used to verify the effectiveness of the algorithm.Compared with other models,the results show that the NGO-GRU estimation model has higher estimation accuracy and stability.
维普
万方数据