State of health estimation for the lithium-ion batteries based on CNN-MLP network

With the rapid development of new energy vehicles, it is recognized that predicting the state of health (SoH) of lithium-ion battery is crucial for ensuring the safety of networked vehicles. However, the selection of health indicators greatly influences the accuracy of SoH prognostics. To obtain an accurate estimation of SoH, this paper proposes an SoH estimation model based on incremental capacity features. First, the incremental capacity curve is extracted from battery discharge data and filtered using a Gaussian filtering algorithm to remove noise. Second, statistical features extracted from the incremental capacity curve are considered health factors, and multiple optimal features are selected using Pearson's correlation coefficient. Finally, the innovative integration of spatiotemporal feature extraction with advanced pattern recognition and nonlinear modeling led to the proposal of a hybrid Convolutional Neural Network-Multi-Layer Perceptron (CNN-MLP) model for estimating the SoH of lithium-ion batteries. To validate the high accuracy of the proposed method, experiments are conducted using the CALCE battery dataset and compared with other popular models. The experimental results indicate that the proposed method can predict the SoH of the battery with superior performance, such as higher speed and accuracy.