| description abstract | Accurately estimating the state of charge (SOC) of batteries is crucial for the objective of extending battery life and enhancing power supply reliability. Currently, machine learning methods are commonly used to predict the SOC of batteries, however, their accuracy in capturing the sequential nature of battery charging and discharging is insufficient. To address the problem of the SOC prediction, a deep learning model that employs long short-term memory (LSTM) with Attention mechanism is proposed. The LSTM model is designed to connect the current SOC with historical time data and to extract multidimensional features from groups of batteries. Additionally, introducing the Attention mechanism allows for the model to prioritize key information while disregarding insignificant data. This work utilizes two different approaches to the multi-cell case and the single-cell case for several reasons. Considering that the failure of a single cell can affect the entire group of batteries, the SOC prediction models for individual batteries need not take a long training time. Thus, the LightGBM model is developed to predict the SOC of a single battery whose training speed surpasses that of the deep learning model and has superior prediction accuracy and greater speed when employed with small-scale data, error within 3%. Conversely, the LSTM-Attention model yields higher prediction accuracy when processing large-scale datasets, error within 5%. Two models are proposed: one for predicting the SOC of groups of batteries and another for a single battery. | |
