Joint Estimation of State of Charge and State of Energy of Lithium-Ion Batteries Based on Optimized Bidirectional Gated Recurrent Neural Network

The state of charge (SOC) and state of energy (SOE) of lithium-ion batteries (LIBs) are fundamental parameters in the battery management system (BMS). However, the simultaneous estimation of the two states is challenging since the SOC and SOE are highly affected by the battery's uncertain operating conditions. In this article, a joint SOC and SOE estimation method is proposed based on a bidirectional gated recurrent unit neural network (BiGRU) with an improved pigeon-inspired genetic (PG) optimization algorithm. The BiGRU network is first used to capture bidirectional information embedded in the battery data and to make up for the loss of information, in general, recurrent neural networks (RNNs) learning. Then, the hyperparameters of the BiGRU are optimized by the PG algorithm to make the data features of LIBs match the network topology. In two dynamic driven cycles, the average root mean square errors (RMSEs) of SOC and SOE estimations with the proposed PG-BiGRU method reach 1.3%. Furthermore, compared with the long short-term memory (LSTM) network, GRU, BiGRU, and pigeon-inspired optimized BiGRU (PIO-BiGRU), the PG-BiGRU algorithm yields the best SOC and SOE joint prediction accuracy, with RMSE values of 0.83% and 0.94%, respectively, which means that the proposed method can effectively reduce the complexity of parameters' adjustment and improve the prediction accuracy.