Life prediction model of lithium-ion batteries in the early-cycle stage based on convolutional long short-term memory with attention mechanism

Abstract

Accurately predicting the battery cycle life of lithium-ion batteries in the early-cycle stage can provide a basis for long-term planning, bring economic benefits and avoid safety risks. However, it is very difficult to accurately predict the cycle life due to the weak degradation of battery performance in the early cycle stage. In this paper, an early stage prediction model of lithium-ion battery based on convolutional long short-term memory (ConvLSTM) with attention mechanism is proposed, which is called ConvLSTM-Attention model. ConvLSTM can not only extract the characteristics of single cycle information, but also mine the temporal relationship among each cycle data. For the features extracted by ConvLSTM, the attention mechanism is added, so that the model can pay attention to the important features and thus improve the prediction accuracy of the model. Experiments show that the model can predict the battery cycle life only by using the information of the first 10 cycles of the battery, and the model can predict whether the battery belongs to high-lifetime or low-lifetime only by using the information of the first 5 cycles of the battery. Comparison with other early prediction models show that the proposed model can achieve better prediction results by using less cycle data.