State‐of‐charge prediction of lithium ion battery through multivariate adaptive recursive spline and principal component analysis

Abstract

The main aim of this research work is to provide a comprehensible state of art for the intensification of the utmost decisive task performed by a modern BMS system to monitor and estimate battery states through a well‐entrenched statistical analysis method. In the present work, “multivariate adaptive regression splines” (MARS) method along with principal component analysis (PCA) has been used to develop a predictive model‐based state of charge (SoC) estimator for an NCR 18650PF Lithium ion battery at constant charging c‐rate of 0.3 C and 0.3 C and 0.5 C constant discharge profiles. Time‐weighing factors, that is, voltage‐current and temperature are employed as training datasets, to provide greater impact for developing a SoC MARS model of with high coefficient of correlation R2 (0.9984). The SoC MARS model adequacy is then validated for voltage prediction of the same battery for two different profiles of discharging using NIPALS algorithm for principal component analysis (PCA) with SS2 of 93.69% and 94.23% for profile A and profile B, respectively.

A review of the technologies, challenges and policies implications of electric vehicles and their future development in India

“…Rapid charging stations and a high‐power grid connection are required to support this configuration. As a disadvantage, these EV batteries are only tethered to the grid for rapid charging, preventing V2G operations 39,42,65 …”

Artificial Intelligence Applied to Battery Research: Hype or Reality?

“…However, limited works using MARS have been reported in the field of battery SOC prediction, due to problems associated with pruned data. Vyas et al 405 adopted the PCA to mitigate the problem related to a very large number of input variables and outcome targets, without admitting sufficient observations. In his research study, the MARS technique was used to predict the SOC of a nickel−cobalt rechargeable 18650PF LIB (3.6 V/2700 mAh).…”

Single point diagnosis of short circuit abuse condition in lithium‐ion battery through impedance data

“…The EIS data are fitted using Randles equivalent electrical circuit model (ECM; RC-circuit) to obtain electrical parameters of the electrode. 5,26,32 Figure 2 shows the equivalent ECM for a semi-infinite diffusion-controlled faradaic reaction to a planar electrode.…”

“…Robust efforts to improve the safety of the battery energy storage systems (BESS) are desired among the whole application chain, from smarter vehicle designs, to snugged components for smart energy management and battery management systems (BMS). 5,6 With the advancement of electric automotive (EV/HEV) and power system applications, rechargeable lithium-ion battery have lifted a large share of interest in public utility concern for past decades due to their highpower density, energy density and lifespan. 7 These batteries have widely used electrochemical energy storage devices with most prominent technical support for automotive applications.…”