基于人工智能的锂电池SOC预测建模与优化

为了实现退役动力锂电池荷电状态(State of Charge,SOC)的预测,针对退役锂离子电池特殊的非线性关系,提出自适应法和列文伯格算法(Levenberg-Marquardt,LM)相结合优化BP神经网络估算退役锂电池SOC的VLLM动态模型,并验证了随机工况下退役锂电池SOC预测的可靠性。实验结果表明,该模型用优化神经网络法估算SOC的误差能控制在1%以内,随机工况误差在5%以内,提高了退役锂电池SOC的预测精度,为退役锂电池的梯次利用奠定了基础。

Modeling and Optimization of SOC Prediction for Lithium Battery Based on Artificial Intelligence

In order to realize the prediction of the state of charge (SOC) of the retired lithium battery,and with the nonlinear relationship of lithium ion battery taken into consideration,the adaptive method and Levenberg-Marquardt(LM) are combined to optimize the VLLM dynamic model of BP neural network to estimate the SOC of the decommissioned lithium battery,and the reliability of SOC prediction of decommissioned lithium battery under random conditions is verified.The test results show that the model uses BP neural network method to estimate the error of SOC which can be controlled within 1 %,and the error under random operating conditions is less than 5 %,which improves the prediction accuracy of neural network and has a good application prospect.