State of Health Prediction of Li-ion Batteries using Incremental Capacity Analysis and Support Vector Regression

Lithium-ion battery is introduced recently as a key solution for energy storage problems both in stationary and mobile applications. However, one main limitation of this technology is the aging, i.e., the degradation of storage capacity. This degradation happens in every condition, whether the battery is used or not, but in different proportions dependent on the usage and external conditions. Due to the complexity of aging phenomena to characterize, lifetime modeling and state of health (SoH) prediction of Li-ion cells attract the attention of researchers in recent years. This paper investigates the use of incremental capacity analysis (ICA) method to estimate the SoH for NCA lithium-ion batteries. To find the IC curves, it is essential to calculate the dQ/dV of the V-Q curves of the battery, which is infeasible due to the presence of noise and sampling intervals in the voltage measurements. Therefore, a simple and robust smoothing method is proposed, based on support vector regression (SVR), to fit a continuous function to the noisy voltage curves of the battery. By differentiating the fitted function, it is shown that the peak values of the IC curves can predict the SoH of the batteries cycled with different temperature, current rate, and state of charge. More than five hundred Q-V curves from testing 22 different cells in 8 different testing conditions are investigated. An average error of 1.86% for the SoH prediction shows that the developed SoH estimator is able to robustly predict the SoH of the cells cycled under different conditions. This technique can use partial charging voltage curves, and therefore testing time can be largely reduced, making it possible to be implemented in the battery management system (BMS).