基于深度学习的锂离子电池SOC和SOH联合估算

锂离子电池常被作为储能元件以实现电能的存储和转化,然而其荷电状态(state of charge,SOC)和健康状态(state of health,SOH)无法被直接测量。为了实现锂离子电池SOC和SOH联合估算,该文分析SOC和SOH之间的关联性,并提出一种基于深度学习的锂离子电池SOC和SOH联合估算方法。该方法能够基于门控循环单元循环神经网络(recurrent neural network with gated recurrent unit,GRU-RNN)和卷积神经网络(convolutional neural network,CNN),利用锂离子电池电压、电流、温度,实现锂离子电池全使用周期内SOC和SOH的同时估算,而且由于将锂离子电池的SOH估算值考虑到SOC估算中,能够消除锂离子电池老化因素对锂离子电池SOC估算造成的负面影响,从而提升SOC估算精度。两个锂离子电池测试数据集上的实验结果表明,提出的估算方法能够在不同温度和不同工况下实现锂离子电池全使用周期SOC和SOH联合估算,且获得较高的精度。

Joint Estimation of the State of Charge and the State of Health Based on Deep Learning for Lithium-ion Batteries

Lithium-ion batteries are being extensively used as the energy storage element to store and transform the electric energy. Nevertheless, its state of charge(SOC) and state of health(SOH) can not be directly measured. To address this problem, the correlation between SOC and SOH was analyzed and a SOC and SOH joint estimation method based on deep learning was proposed. In detail, the SOC and SOH can be estimated simultaneously in the whole life cycle of lithium-ion batteries by voltages, currents and temperatures of lithium-ion batteries based on recurrent neural network with gated recurrent unit(GRU-RNN) and convolutional neural network(CNN). Considering the estimated SOH during SOC estimation, the proposed method can eliminate the effects of aging to the SOC estimation, which can improve the accuracy of estimated SOC. The experimental results on two lithium-ion battery test datasets show that the proposed joint estimation method can realize the SOC and SOH joint estimation with high accuracy in the whole life cycle of lithium-ion batteries at different temperatures and working conditions.