【摘要】 锂离子电池被广泛用作各种设备的电源，因此对锂离子电池S_OH（健康状态）的快速准确预测是降低电池故障的重要手段。由于LSTM（长短期记忆）网络可以从时间序列中找出变量变化的特征、趋势以及发展规律，进而对变量的未来变化进行有效地预测，因此已成为预测锂离子电池S_OH的一种流行的深度学习网络方法。未优化超参数的LSTM方法很容易导致电池S_OH预测模型的精度低。针对锂离子电池S_OH预测问题，提出一种基于SSA（麻雀搜索算法）优化LSTM的方法。提取一种新的健康指标-充电电压PDF（概率密度函数）曲线峰值处的峰度，并将其用作S_OH预测模型的输入，以实现对电池S_OH的准确预测。实验结果表明，SSA优化的LSTM模型的预测精度优于未优化模式。当训练集仅占总数据的20%时，NCA（镍钴铝）电池S_OH预测结果的均方根误差E_RMSE在0.7%以内，最大绝对误差<2.0%。SSA-LSTM可以在训练数据有限的情况下准确预测电池S_OH。更多还原

【Abstract】 Lithium-ion batteries are widely used as power sources for various devices, so rapid and accurate prediction of the S_OH（state of health） of lithium-ion batteries is an important means to reduce battery failures. Due to its ability to identify the characteristics, trends and development patterns of variable changes from time series, LSTM（long short-term memory） network is a popular deep learning network method for predicting the future changes of lithium-ion battery S_OH. The LSTM method without optimizing hyperparameters can easily lead to low accuracy in battery S_OH prediction models. A method based on SSA（sparrow search algorithm） was proposed to optimize LSTM for the prediction of S_OH in lithium-ion batteries. A new health indicator-the kurtosis at the peak of the charging voltage PDF（probability density function） curve was extracted and used as input for the S_OH prediction model to achieve accurate prediction of battery S_OH. The experimental results show that the prediction accuracy of the LSTM model optimized by SSA is better than that of the unoptimized model. When the training set only accounts for 20% of the total data, the root mean square error E_RMSE of the NCA（nickel cobalt aluminum） battery S_OH prediction results is within 0.7%, and the maximum absolute error is less than 2.0%. SSA-LSTM can accurately predict battery S_OH under limited training data.更多还原