Simultaneous Estimation of SOH and SOC of Batteries Based on SVM

Batteries are widely used in various vital energy storage occasions, so it is particularly important to monitor the state-of-charge (SOC) and the state-of-health (SOH). To estimate SOC and SOH quickly and accurately, the battery's shock response characteristic is analyzed in this paper while fully considering the degree of aging that could impact their operating status. In this paper, a SOC and SOH simultaneous-estimation scheme is proposed based on shock response characteristics. Firstly, the effective and representative features of the voltage impulse response curve are extracted by combining different feature extraction methods. Then, the Support Vector Machine (SVM) is introduced to estimate the SOH and SOC simultaneously. The feature comes from the voltage impulse response curve, which is very convenient to obtain in practical applications. The simulation results show that this method can accurately estimate SOH and SOC for batteries in any SOH state and SOC state, which has strong robustness and generalization ability.