Extreme Learning Machine for SOC Estimation of Lithium-ion battery Using Gravitational Search Algorithm

This paper develops a state of charge (SOC) estimation model for a lithium-ion battery using an improved extreme learning machine (ELM) algorithm. ELM is suitable for SOC estimation since ELM algorithm has fast estimation speed, good generalization performance, and high accuracy. However, the performance of ELM is highly dependent on training accuracy and number of neurons in a hidden layer. Hence, gravitational search algorithm (GSA) is applied to improve the ELM computational intelligence by searching for the optimal value hidden layer neurons. The optimal ELM based GSA model does not require internal battery knowledge and mathematical model for SOC estimation. The model robustness is validated at different temperatures using different EV drive cycles. The performance of ELM-GSA model is verified with two popular neural network methods; back-propagation neural network (BPNN) and radial basis function neural network (RBFNN). The results are evaluated using different error rates and computation cost. The results demonstrate that the ELM-GSA model offers high accuracy and low SOC error rate than BPNN-GSA and RBFNN-GSA models. Furthermore, a detailed comparative study between the proposed model and existing SOC strategies is conducted which also demonstrates the superiority of the proposed model.