State of Charge Estimation Based on State of Health Correction for Lithium -ion Batteries

In most studies, the state of he alth (SOH) effect is rarely co ns ide red in state o f charge (SOC) estimation of the battery. The estimation error gradually increases in the late decline oflithium battery. In this study, the SOC estimation method based on SOH correction and the back -propagation neural network optimized by mind evolutionary algorithm (MEA) is proposed. First, SOH is estimated based on Thevenin battery model and BP neural network. Then, together with the current, voltage and temperature, the SOH is added to the input ofthe BPne ural network, battery capacity can be estimated as the output of the neural network. The next, the initial weights and thresholds ofthe BP neural network are optimized by the MEA algorithm to achieve better estimation results. The application range of SOC estimation method is further broadened for both the new and old battery.