Abstract: The state of health（SOH） of lithium batteries plays a crucial role in the safe and stable operation of batteries. However,it is difficult to directly measure the internal resistance and capacity of the battery when it is running online. Therefore, this paper proposes a lithium battery SOH estimation method based on charging data fragments and genetic algorithm optimization with extreme learning machine（GA-ELM）. This paper extracts the integral of voltage versus time in different voltage intervals from the battery’s charging voltage segment data as the health factor（HF）, and uses Pearson correlation analysis to find the optimal voltage interval. Finally, the GA algorithm is used to find the optimal solution set of ELM network structure parameters, and the estimation model of HF and SOH of lithium battery is established to realize the online estimation of SOH. This paper uses the NASA data set to verify the proposed method, which proves that the proposed method has good accuracy and reliability.