锂离子电池的健康状态(state of health,SOH)准确估计对于储能电站的稳定高效运行至关重要。为了进一步提高数据驱动方法对SOH估计的精度,本团队提出了一种利用交叉验证训练的线性回归加权融合模型的方法。首先,从放电电压曲线、充电和...锂离子电池的健康状态(state of health,SOH)准确估计对于储能电站的稳定高效运行至关重要。为了进一步提高数据驱动方法对SOH估计的精度,本团队提出了一种利用交叉验证训练的线性回归加权融合模型的方法。首先,从放电电压曲线、充电和放电温度曲线中提取了健康特征,并使用Pearson相关系数对所选特征进行了相关性分析,确定了网络模型输入的健康因子参数。随后,通过在LSTM与GRU中加入注意力机制,建立了LSTM-Attention与GRU-Attention模型,分别以NASA电池老化数据集B0005、B0006、B0007和B0018电池的前50%作为模型训练集,用剩余数据对模型进行验证,分别得到了模型对应的ŷ_(L-A)与ŷ_(G-A)估计值,然后使用所提融合模型方法对两个估计值进行线性回归加权,结果显示该方法的最大均方根误差和平均绝对误差分别为0.00291和0.00200。最后,为验证所提模型的抗干扰能力,在输入模型的健康因子中加入不同比例的高斯白噪声,实验结果显示融合模型的抗干扰能力较强,最大均方根误差和平均绝对误差仅为0.03562和0.02889。展开更多
The material balance in CFB furnace is important for the performance of the boiler The bed inventory consists of coal ash and desulfurizing agent In order to design properly the boiler and auxiliary,the engineers need...The material balance in CFB furnace is important for the performance of the boiler The bed inventory consists of coal ash and desulfurizing agent In order to design properly the boiler and auxiliary,the engineers need to know the ash formation characteristics Generally, the most reliable method to get ash formation data of a coal is to burn it in the real industrial CFB boiler Due to the high cost and difficulties in sampling in such a test,people have to present other simple method on ash formation.The present investigation is proposing a simple laboratory test procedure to study ash formation by static combustion and sieving.Validation of the method is given.展开更多
文摘锂离子电池的健康状态(state of health,SOH)准确估计对于储能电站的稳定高效运行至关重要。为了进一步提高数据驱动方法对SOH估计的精度,本团队提出了一种利用交叉验证训练的线性回归加权融合模型的方法。首先,从放电电压曲线、充电和放电温度曲线中提取了健康特征,并使用Pearson相关系数对所选特征进行了相关性分析,确定了网络模型输入的健康因子参数。随后,通过在LSTM与GRU中加入注意力机制,建立了LSTM-Attention与GRU-Attention模型,分别以NASA电池老化数据集B0005、B0006、B0007和B0018电池的前50%作为模型训练集,用剩余数据对模型进行验证,分别得到了模型对应的ŷ_(L-A)与ŷ_(G-A)估计值,然后使用所提融合模型方法对两个估计值进行线性回归加权,结果显示该方法的最大均方根误差和平均绝对误差分别为0.00291和0.00200。最后,为验证所提模型的抗干扰能力,在输入模型的健康因子中加入不同比例的高斯白噪声,实验结果显示融合模型的抗干扰能力较强,最大均方根误差和平均绝对误差仅为0.03562和0.02889。
文摘The material balance in CFB furnace is important for the performance of the boiler The bed inventory consists of coal ash and desulfurizing agent In order to design properly the boiler and auxiliary,the engineers need to know the ash formation characteristics Generally, the most reliable method to get ash formation data of a coal is to burn it in the real industrial CFB boiler Due to the high cost and difficulties in sampling in such a test,people have to present other simple method on ash formation.The present investigation is proposing a simple laboratory test procedure to study ash formation by static combustion and sieving.Validation of the method is given.
基金supported by the National Natural Science Foundation of China(51346001,51106051)Fundamental Research Funds for the Central Universities,China(2016YQ07,2014ZD14)~~
基金supported by the National Natural Science Foundation of China(51106051)111 Project,China(B12034)Fundamental Research Funds for the Central Universities,China(2014MS36,2014ZD14)~~
