With the widespread adoption of electric vehicles and energy storage systems,predicting the remaining useful life(RUL)of lithium-ion batteries(LIBs)is critical for enhancing system reliability and enabling predictive ...With the widespread adoption of electric vehicles and energy storage systems,predicting the remaining useful life(RUL)of lithium-ion batteries(LIBs)is critical for enhancing system reliability and enabling predictive maintenance.Traditional RUL prediction methods often exhibit reduced accuracy during the nonlinear aging stages of batteries and struggle to accommodate complex degradation processes.This paper introduces a novel adaptive long short-term memory(LSTM)approach that dynamically adjusts observation and prediction horizons to optimize predictive performance across various aging stages.The proposed method employs principal component analysis(PCA)for dimensionality reduction on publicly available NASA and Mendeley battery datasets to extract health indicators(HIs)and applies K-means clustering to segment the battery lifecycle into three aging stages(run-in,linear aging,and nonlinear aging),providing aging-stage-based input features for the model.Experimental results show that,in the NASA dataset,the adaptive LSTM reduces the MAE and RMSE by 0.042 and 0.043,respectively,compared to the CNN,demonstrating its effectiveness in mitigating error accumulation during the nonlinear aging stage.However,in the Mendeley dataset,the average prediction accuracy of the adaptive LSTM is slightly lower than that of the CNN and Transformer.These findings indicate that defining aging-stage-based adaptive observation and prediction horizons for LSTM can effectively enhance its performance in predicting battery RUL across the entire lifecycle.展开更多
针对云服务器中存在软件老化现象,将造成系统性能衰退与可靠性下降问题,借鉴剩余使用寿命(Remaining useful life,RUL)概念,提出基于支持向量和高斯函数拟合(Support vectors and Gaussian function fitting,SVs-GFF)的老化预测方法.首...针对云服务器中存在软件老化现象,将造成系统性能衰退与可靠性下降问题,借鉴剩余使用寿命(Remaining useful life,RUL)概念,提出基于支持向量和高斯函数拟合(Support vectors and Gaussian function fitting,SVs-GFF)的老化预测方法.首先,提取云服务器老化数据的统计特征指标,并采用支持向量回归(Support vector regression,SVR)对统计特征指标进行数据稀疏化处理,得到支持向量(Support vectors,SVs)序列数据;然后,建立基于密度聚类的高斯函数拟合(Gaussian function fitting,GFF)模型,对不同核函数下的支持向量序列数据进行老化曲线拟合,并采用Fréchet距离优化算法选取最优老化曲线;最后,基于最优老化曲线,评估系统到达老化阈值前的RUL,以预测系统何时发生老化.在OpenStack云服务器4个老化数据集上的实验结果表明,基于RUL和SVs-GFF的云服务器老化预测方法与传统预测方法相比,具有更高的预测精度和更快的收敛速度.展开更多
锂离子电池剩余使用寿命(remaining useful life,RUL)预测对电池的使用维护极为重要,提出一种基于差分电压和Elman神经网络预测锂离子电池RUL的方法。首先,根据美国国家航天航空局(National Aeronautics and Space Administration,NASA...锂离子电池剩余使用寿命(remaining useful life,RUL)预测对电池的使用维护极为重要,提出一种基于差分电压和Elman神经网络预测锂离子电池RUL的方法。首先,根据美国国家航天航空局(National Aeronautics and Space Administration,NASA)的锂离子电池数据集,分析电池差分电压曲线和充放电曲线,提取电池容量退化特征量;其次,通过Pearson法分析特征量之间的相关性,将充电差分电压曲线初始拐点值、放电差分电压曲线峰值、放电时间、静置时间作为电池RUL预测的间接健康因子;最后,建立以上述间接健康因子为输入,电池容量为输出的Elman神经网络,进行锂离子电池的RUL预测。基于不同间接健康因子和不同神经网络的四种电池容量预测对比实验表明,在间接健康因子中加入充电差分电压曲线初始拐点值和放电差分电压曲线峰值可以提高电池寿命预测精度,Elman神经网络可准确预测电池容量。基于不同循环次数预测电池RUL,预测的平均均方根误差为1.55%。展开更多
基金supported by National Natural Science Foundation of China(Grant No.62403475).
文摘With the widespread adoption of electric vehicles and energy storage systems,predicting the remaining useful life(RUL)of lithium-ion batteries(LIBs)is critical for enhancing system reliability and enabling predictive maintenance.Traditional RUL prediction methods often exhibit reduced accuracy during the nonlinear aging stages of batteries and struggle to accommodate complex degradation processes.This paper introduces a novel adaptive long short-term memory(LSTM)approach that dynamically adjusts observation and prediction horizons to optimize predictive performance across various aging stages.The proposed method employs principal component analysis(PCA)for dimensionality reduction on publicly available NASA and Mendeley battery datasets to extract health indicators(HIs)and applies K-means clustering to segment the battery lifecycle into three aging stages(run-in,linear aging,and nonlinear aging),providing aging-stage-based input features for the model.Experimental results show that,in the NASA dataset,the adaptive LSTM reduces the MAE and RMSE by 0.042 and 0.043,respectively,compared to the CNN,demonstrating its effectiveness in mitigating error accumulation during the nonlinear aging stage.However,in the Mendeley dataset,the average prediction accuracy of the adaptive LSTM is slightly lower than that of the CNN and Transformer.These findings indicate that defining aging-stage-based adaptive observation and prediction horizons for LSTM can effectively enhance its performance in predicting battery RUL across the entire lifecycle.
文摘针对云服务器中存在软件老化现象,将造成系统性能衰退与可靠性下降问题,借鉴剩余使用寿命(Remaining useful life,RUL)概念,提出基于支持向量和高斯函数拟合(Support vectors and Gaussian function fitting,SVs-GFF)的老化预测方法.首先,提取云服务器老化数据的统计特征指标,并采用支持向量回归(Support vector regression,SVR)对统计特征指标进行数据稀疏化处理,得到支持向量(Support vectors,SVs)序列数据;然后,建立基于密度聚类的高斯函数拟合(Gaussian function fitting,GFF)模型,对不同核函数下的支持向量序列数据进行老化曲线拟合,并采用Fréchet距离优化算法选取最优老化曲线;最后,基于最优老化曲线,评估系统到达老化阈值前的RUL,以预测系统何时发生老化.在OpenStack云服务器4个老化数据集上的实验结果表明,基于RUL和SVs-GFF的云服务器老化预测方法与传统预测方法相比,具有更高的预测精度和更快的收敛速度.
文摘锂离子电池剩余使用寿命(remaining useful life,RUL)预测对电池的使用维护极为重要,提出一种基于差分电压和Elman神经网络预测锂离子电池RUL的方法。首先,根据美国国家航天航空局(National Aeronautics and Space Administration,NASA)的锂离子电池数据集,分析电池差分电压曲线和充放电曲线,提取电池容量退化特征量;其次,通过Pearson法分析特征量之间的相关性,将充电差分电压曲线初始拐点值、放电差分电压曲线峰值、放电时间、静置时间作为电池RUL预测的间接健康因子;最后,建立以上述间接健康因子为输入,电池容量为输出的Elman神经网络,进行锂离子电池的RUL预测。基于不同间接健康因子和不同神经网络的四种电池容量预测对比实验表明,在间接健康因子中加入充电差分电压曲线初始拐点值和放电差分电压曲线峰值可以提高电池寿命预测精度,Elman神经网络可准确预测电池容量。基于不同循环次数预测电池RUL,预测的平均均方根误差为1.55%。
