In this paper, an Extended Non-Linear State Observer (ENSO) is proposed for the estimation of accurate State of Charge (SOC) of lithium-ion battery. The Two-RC equivalent circuit model is utilized to describe the dynamic behaviour of the lithium-ion battery, based on the circuit state equations the proposed ENSO is designed for the estimation of SOC. The ninth-order polynomial fitting curve is assumed to be a representation of a highly non-linear relationship between Open Circuit Voltage (OCV) and the SOC. Moreover, the stability and convergence rate of the proposed ENSO is guaranteed by Lyapunov’s stability analysis. The performance of the proposed observer is compared with well-extinguished methods i.e., Unscented Kalman Filter (UKF) and Sliding Mode Observer (SMO) algorithms. The proposed method has given better dynamic performance with accurate SOC, reducing computational cost and enhance the convergence capability as compared to conventional methods. The Proposed model effectiveness has been validated through the MATLAB/Simulink platform.