An Incremental Capacity Analysis‐based State‐of‐health Estimation Model for Lithium‐ion Batteries in High‐power Applications

Abstract

The Incremental Capacity (IC) is a rich source of data for the state‐of‐health estimation of lithium‐ion batteries. This data is typically collected during a low C‐rate (dis)charge of the battery which is not representative of many real‐world applications outside the research laboratories. Here, this limitation is showcased to be mitigated by employing a new feature‐extraction technique applied to a large dataset including 105 batteries with cycle lives ranging from 158 to 1637 cycles. The state‐of‐health of these batteries is successfully predicted with a mean‐absolute‐percentage error below 0.7 % by using three regression models of support vector regressor, multi‐layer perceptron, and random forest. The methodologies proposed in this work facilitate the development of accurate IC‐based state‐of‐health predictors for lithium‐ion batteries in on‐board applications.

Towards Long-Term Monitoring of Commercial Lithium-Ion Batteries Enabled by Externally Affixed Fiber Sensors and Strain-Based Prognostic Strategies

“…46 For this purpose, incremental capacity analysis (ICA) has been widely employed as a non-invasive in situ electrochemical technique to estimate the internal cell state and explore degradation mechanisms. 47 The ICA plots are obtained by differentiating the cell capacity over potential (i.e., dQ/dV) during charge or discharge, with the peaks representing the electrochemical reactions and phase transitions. Previously, we demonstrated that the peaks and features of ICA analysis on LFP-LTO coin-cells located at the same potential as those of the incremental strain analysis (ISA), obtained by differentiating the strain over potential (i.e., dɛ/dV), in the first 16 cycles.…”

Bayesian optimization algorithm‐based Gaussian process regression for in situ state of health prediction of minorly deformed lithium‐ion battery

“…To overcome this limitation, a new feature extraction technique has been applied to a large data set of batteries with different cycling lifetimes. This technique uses three regression models, support vector regression (SVR), multilayer perceptron, and random forest, to successfully predict the health status of batteries 16 . Zhang et al 17 proposed a new method for estimating the SOH of batteries based on an integrated analysis of incremental capacity analysis (ICA) and SVR using a voltage‐capacity model.…”

“…This technique uses three regression models, support vector regression (SVR), multilayer perceptron, and random forest, to successfully predict the health status of batteries. 16 Zhang et al 17 proposed a new method for estimating the SOH of batteries based on an integrated analysis of incremental capacity analysis (ICA) and SVR using a voltage-capacity model. Xu 18 proposed a new method for estimating the SOH of LIBs based on discrete ICA.…”