IBKA-ELM-based state-of-charge estimation for lithium-ion batteries in electric vehicles

The State of charge (SOC) of lithium batteries is one of the core parameters of the battery management system of electric vehicles. How to accurately and quickly achieve the estimation of the state of charge has important practical significance for the safe use of electric vehicles. This paper proposes a model combining the improved Black-wing kite algorithm and the Extreme Learning Machine (ELM) to estimate the state of charge of lithium batteries. The novelty of this model lies in the fact that the optimization algorithm for black-wing kites is prone to fall into local optimum and has a slow convergence speed. The introduction of Tent chaotic mapping, adaptive nonlinear dynamic inertia weights and Levy flight strategy has been improved, effectively solving the problems of inconsistent and unstable performance caused by the random initialization of hidden layer weights and deviations in ELM. The performance of state of charge estimation under different temperatures, working conditions, battery materials and algorithms was verified. The results show that the MAE of state of charge estimation of the proposed model is 0.96% and the RMSE is 1.12%, which can provide a reliable basis for the efficient application of lithium-ion batteries in electric vehicles.