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...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。展开更多
Some representative working conditions were measured, and the amplitude distribution rule of each representative working condition after analysis of measured data was got. The building of 2 D distributing function be...Some representative working conditions were measured, and the amplitude distribution rule of each representative working condition after analysis of measured data was got. The building of 2 D distributing function between the range and the mean of random load was discussed. Experiment was carried out to get the fatigue strength data of the material of transmission component. Accessing the P S a S m N camber of combined load of bending and torsion on this material after analysis. And the process of calculating the 2 D fatigue life in multi working condition was discussed.展开更多
文摘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。
文摘Some representative working conditions were measured, and the amplitude distribution rule of each representative working condition after analysis of measured data was got. The building of 2 D distributing function between the range and the mean of random load was discussed. Experiment was carried out to get the fatigue strength data of the material of transmission component. Accessing the P S a S m N camber of combined load of bending and torsion on this material after analysis. And the process of calculating the 2 D fatigue life in multi working condition was discussed.