RUL prediction of lithium ion battery based on CEEMDAN-CNN BiLSTM model

Abstract

With the wide application of lithium ion batteries, the importance of life prediction is also highlighted. The prediction of the remaining life of lithium ion battery is an important part of its health management, and accurate prediction can improve the safety of equipment. In this paper, a method for predicting the residual life of lithium ion batteries based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), One-dimensional Convolutional Neural Network (1D CNN) and Bi-directional Long Short-Term Memory (BiLSTM) neural network is proposed. The capacity is selected as the health factor, and then CEEMDAN is used to decompose the complex and unstable data to obtain stable components. One-dimensional Convolutional Neural Network (1D CNN) is used to deeply mine the capacity data of lithium-ion batteries. Finally, BiLSTM neural network modeling is used to predict the remaining useful life (RUL) of lithium-ion batteries. The NASA data set is used for testing and prediction comparison with BiLSTM model and CNN-BiLSTM model. The prediction results show that CEEMDAN-CNN BiLSTM model has higher prediction accuracy.

Keywords

• Lithium ion battery
• Remaining service life
• CEEMDAN
• 1D CNN
• BiLSTM