online state of charge estimation of lithium-ion batteries using gated recurrent unit neural network and a least mean square adaptive filter

State of charge (SOC) estimation of lithium-ion batteries is the most important role of a battery management system. to improve the SOC estimation speed and accuracy in the operational environment, a novel method is proposed by combining a gated recurrent unit (GRU) neural network and a least mean square (LMS) adaptive filter. First a GRU network is used to estimate the SOC based on the battery measurement data. Then the LMS filter is used for online error reduction through unpredicted operation conditions, the LMS is a lite adaptive filter that updates its coefficient based on operation conditions with low computation cost. To verify the method robustness, its performance was checked under constant and varying temperature for standard drive cycles like UDDS and LA92. The proposed method is able to estimate SOC with less than 10-min discharge voltage, current and temperature data as the input with an error of less than 0.6% during working hour. Therefore, compared with conventional methods like LSTM and GRU the proposed GRU-LMS method has better speed and accuracy in the SOC estimation.