关键词:

"> 锂离子电池；荷电状态SOC；RBF神经网络；状态转移算法

Abstract: Concerning the problem of the prediction accuracy of the State of Charge (SOC) of lithium-ion battery, a method of SOC estimation for lithium-ion batteries based on a Radial Basis Function (RBF) neural network optimized by a dual state transfer algorithm is proposed. The number of hidden layers in RBF neural network is determined by the K-means algorithm and the K-means clustering algorithm is optimized by state transition algorithm (STA), so that the network structure of RBF neural network is determined reasonably. Based on the optimal network structure, the parameters of network, including the center, width and connection weight, are adjusted by STA. Then using the trained RBF neural network to estimate the SOC of lithium-ion battery. The effectiveness of the proposed method is compared with the ampere-hour integral method and a back propagation (BP) neural network. The results show that the method is superior to other methods.

Key words:  Lithium Ion Battery, state of Charge, radial basis function neural networks, state transition algorithm