A Multitime-Scale Deep Learning Model for Lithium-ion Battery Health Assessment Using Soft Parameter-sharing Mechanism

Abstract

Efficient assessment of battery degradation is important to effectively utilize and maintain battery management systems. This study introduces an innovative residual convolutional network (RCN)-gated recurrent unit (GRU) model to accurately assess health of lithium-ion batteries on multiple time scales. The model employs a soft parameter-sharing mechanism to identify both short-and long-term degradation patterns. The continuously looped $Q(V), T(V), \frac{\mathrm{d}Q}{\mathrm{d}V}$ , and $\frac{\mathrm{d}T}{\mathrm{d}V}$ are extracted to form a four-channel image, from which the RCN can automatically extract the features and the GRU can capture the temporal features. By designing a soft parameter-sharing mechanism, the model can seamlessly predict the capacity and remaining useful life (RUL) on a dual time scale. The proposed method is validated on a large MIT-Stanford dataset comprising 124 cells, showing a high accuracy in terms of mean absolute errors of 0.004 77 for capacity and 83 for RUL. Furthermore, studying the partial voltage fragment reveals the promising performance of the proposed method across various voltage ranges. Specifically, in the partial voltage segment of 2.8-3.2 V, root mean square errors of 0.010 7 for capacity and 140 for RUL are achieved.