为提高对动力电池的荷电状态(state of charge, SOC)估算精度、动力电池的健康状态(state of health, SOH)对锂电池性能的影响,提出一种扩展卡尔曼滤波(extended kalman filtering, EKF)联合估算算法。根据现有的实验数据,分析锂电池特...为提高对动力电池的荷电状态(state of charge, SOC)估算精度、动力电池的健康状态(state of health, SOH)对锂电池性能的影响,提出一种扩展卡尔曼滤波(extended kalman filtering, EKF)联合估算算法。根据现有的实验数据,分析锂电池特性,构建二阶RC等效电路模型,并进行参数辨识,搭建MATLAB仿真平台联合EKF算法进行SOC估算,将仿真结果与真实数据进行对比,结果表明,EKF联合估算SOC比EKF估算SOC误差精度约高1.2%,且抗干扰能力更强。展开更多
Accurate prediction of the state-of-charge(SOC)of battery energy storage system(BESS)is critical for its safety and lifespan in electric vehicles.To overcome the imbalance of existing methods between multi-scale featu...Accurate prediction of the state-of-charge(SOC)of battery energy storage system(BESS)is critical for its safety and lifespan in electric vehicles.To overcome the imbalance of existing methods between multi-scale feature fusion and global feature extraction,this paper introduces a novel multi-scale fusion(MSF)model based on gated recurrent unit(GRU),which is specifically designed for complex multi-step SOC prediction in practical BESSs.Pearson correlation analysis is first employed to identify SOC-related parameters.These parameters are then input into a multi-layer GRU for point-wise feature extraction.Concurrently,the parameters undergo patching before entering a dual-stage multi-layer GRU,thus enabling the model to capture nuanced information across varying time intervals.Ultimately,by means of adaptive weight fusion and a fully connected network,multi-step SOC predictions are rendered.Following extensive validation over multiple days,it is illustrated that the proposed model achieves an absolute error of less than 1.5%in real-time SOC prediction.展开更多
针对传统方法在电动汽车锂电池荷电状态(State of Charge,SOC)预测中的局限和不足,提出了一种基于遗传神经网络的电池SOC预测算法。该算法的整体方案首先给出了车载锂电池状态监测系统的软硬件实现,在该系统上以不同的放电倍率对磷酸铁...针对传统方法在电动汽车锂电池荷电状态(State of Charge,SOC)预测中的局限和不足,提出了一种基于遗传神经网络的电池SOC预测算法。该算法的整体方案首先给出了车载锂电池状态监测系统的软硬件实现,在该系统上以不同的放电倍率对磷酸铁锂电池进行了放电实验,获取了其放电过程中电压、电流和SOC的样本数据,然后利用遗传算法全局寻优能力对神经网络中的连接权值和阈值进行了优化,用实验所得的样本数据训练BP神经网络,根据训练好的神经网络对锂电池SOC进行了预测并将其与真实SOC进行对比,以验证算法的可行性。研究结果表明,该方案可通过电压、电流的实时测量值获知锂电池的剩余电量,具有收敛速度快、预测误差小、适应范围广的特点,有效解决了电动汽车锂电池的SOC预测问题。展开更多
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
文摘为提高对动力电池的荷电状态(state of charge, SOC)估算精度、动力电池的健康状态(state of health, SOH)对锂电池性能的影响,提出一种扩展卡尔曼滤波(extended kalman filtering, EKF)联合估算算法。根据现有的实验数据,分析锂电池特性,构建二阶RC等效电路模型,并进行参数辨识,搭建MATLAB仿真平台联合EKF算法进行SOC估算,将仿真结果与真实数据进行对比,结果表明,EKF联合估算SOC比EKF估算SOC误差精度约高1.2%,且抗干扰能力更强。
基金supported in part by the National Natural Science Foundation of China(No.62172036).
文摘Accurate prediction of the state-of-charge(SOC)of battery energy storage system(BESS)is critical for its safety and lifespan in electric vehicles.To overcome the imbalance of existing methods between multi-scale feature fusion and global feature extraction,this paper introduces a novel multi-scale fusion(MSF)model based on gated recurrent unit(GRU),which is specifically designed for complex multi-step SOC prediction in practical BESSs.Pearson correlation analysis is first employed to identify SOC-related parameters.These parameters are then input into a multi-layer GRU for point-wise feature extraction.Concurrently,the parameters undergo patching before entering a dual-stage multi-layer GRU,thus enabling the model to capture nuanced information across varying time intervals.Ultimately,by means of adaptive weight fusion and a fully connected network,multi-step SOC predictions are rendered.Following extensive validation over multiple days,it is illustrated that the proposed model achieves an absolute error of less than 1.5%in real-time SOC prediction.
文摘针对传统方法在电动汽车锂电池荷电状态(State of Charge,SOC)预测中的局限和不足,提出了一种基于遗传神经网络的电池SOC预测算法。该算法的整体方案首先给出了车载锂电池状态监测系统的软硬件实现,在该系统上以不同的放电倍率对磷酸铁锂电池进行了放电实验,获取了其放电过程中电压、电流和SOC的样本数据,然后利用遗传算法全局寻优能力对神经网络中的连接权值和阈值进行了优化,用实验所得的样本数据训练BP神经网络,根据训练好的神经网络对锂电池SOC进行了预测并将其与真实SOC进行对比,以验证算法的可行性。研究结果表明,该方案可通过电压、电流的实时测量值获知锂电池的剩余电量,具有收敛速度快、预测误差小、适应范围广的特点,有效解决了电动汽车锂电池的SOC预测问题。
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。
