Capacity estimation for lithium-ion batteries with short-time working condition in specific voltage ranges

Abstract

The data-driven methods for estimating battery capacity utilize complete charging/discharging cycle data and extract characteristic parameters to provide accurate battery capacity, but the method is consuming long time, limiting application in reality. In order to overcome this limitation, we propose a short-time equivalent power working condition as the battery aging condition method and obtain the training dataset, and introduce the K-means clustering algorithm to determine high-middle-low three specific voltage segments of the discharge curve. Eight feature parameters are extracted from the battery-specific voltage segments and dimension-reduction using principal component analysis (PCA) method for capacity estimation. Convolutional neural network- long short-term memory network-attention (CNN-LSTM-ATT) is used to establish capacity estimation model in specific voltage, and its performance is compared with other machine learning algorithms. Finally, different SOH batteries are selected for short-time equivalent working condition discharges to verify the validity of the estimation model. This work emphasizes the application potential of combining short-time equivalent power work condition with deep learning algorithms for capacity estimation of lithium-ion batteries.