Introduction Accurate estimation of the Li-ion batteries' State of Health (SoH) is essential for future intelligent battery management systems. To solve the problems of poor quality of data features and difficulties in adjusting model parameters, this study proposes a method for estimating the SoH of lithium batteries based on singular value fixed-order noise reduction and the sparrow search algorithm which can optimize the gated recurrent unit (GRU) neural network.
Method Firstly, three indicators highly correlated with SoH decay were extracted from the battery charge and discharge data. Noise reduction was applied to the features using singular value decomposition techniques to improve their correlation with SoH. Next, using the sparrow search algorithm to optimize the model structure and parameters of the GRU neural network improve the accuracy of estimation of SoH. Finally, the battery data sets from Centre for Advanced Life Cycle Engineering (CALCE) were used to verify the validity of the proposed model.
Result The experimental results show that the model proposed in this study applies to the battery SoH estimation, with a maximum root mean square error (RMSE) of only 0.018 4. After data noise reduction and algorithm optimization, the RMSE of the GRU model is reduced by 55.41% compared to the initial model.
Conclusion The method proposed in this paper accurately estimates SoH and can be used as a reference for practical engineering applications.
DownLoad: