Gaussian Process Regression for In Situ Capacity Estimation of Lithium-Ion Batteries

By Robert R. Richardson, Christoph R. Birkl, Michael A. Osborne, David A. Howey. IEEE Transactions on Industrial Informatics, 2017

315 citations recorded by the source corpus.

Accurate on-board capacity estimation is of critical importance in lithium-ion battery applications. Battery charging/discharging often occurs under a constant current load, and hence voltage versus time measurements under this condition may be accessible in practice. This paper presents a data-driven diagnostic technique, Gaussian process regression for in situ capacity estimation (GP-ICE), which estimates battery capacity using voltage measurements over short periods of galvanostatic operation. Unlike previous works, GP-ICE does not rely on interpreting the voltage–time data as incremental capacity (IC) or differential voltage (DV) curves. This overcomes the need to differentiate the voltage–time data (a process that amplifies measurement noise), and the requirement that the range of voltage measurements encompasses the peaks in the IC/DV curves. GP-ICE is applied to two datasets, consisting of 8 and 20 cells, respectively. In each case, within certain voltage ranges, as little as 10 s of galvanostatic operation enables capacity estimates with approximately 2%–3% root-mean-squared error (RMSE).

Subfields: Automotive Engineering, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/7cefe60ad6f56e3bffa04d6c1cf38b63d3867e71

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Automotive Engineering

In Electrical and Electronic Engineering

Citations in the corpus

Machine learning pipeline for battery state-of-health estimation (2021, methodology): “Notably, Richardson et al. [32] operated on sections of the voltage-time data itself by ﬁrst smoothing the curve using a Savitsky-Golay ﬁlter and then used equispaced voltage values as the input to a Gaussian process regression (GPR) algorithm.”
Identifying degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning (2020, methodology): “We use a zero mean function and a linear (LIN) covariance function Although GPR has been used in the literature in the context of Li-ion batteries 17,33,34 , we depart from those pioneering works by employing impedance spectra as input, as well employing ARD to shed light on salient frequencies.”
Online capacity estimation of lithium-ion batteries with deep long short-term memory networks (2021, methodology): “Regression methods, e.g. linear models [42] and Gaussian processes [35], need feature extraction from the raw charging data, which requires a lot of domain-specific experiences.”
Battery Health Prediction Using Fusion-Based Feature Selection and Machine Learning (2020, methodology): “diagnostic technique based on GPR for in situ capacity estimation is conducted, which estimates capacity over a short period of galvanostatic operation [92].”
A Data-Driven Approach With Uncertainty Quantification for Predicting Future Capacities and Remaining Useful Life of Lithium-ion Battery (2021, methodology): “Through using the Savitzky–Golay filter to reduce measurement noises of corresponding currents and voltages [28], final capacity degradation curves versus cycle number for different batteries are shown in Fig.”
Gaussian Process Regression With Automatic Relevance Determination Kernel for Calendar Aging Prediction of Lithium-Ion Batteries (2020, methodology): “Through formulating specific input features, GPR-based models have been applied successfully in both academic and industrial domains [24]–[26].”
State-of-Health Estimation Based on Differential Temperature for Lithium Ion Batteries (2020, unknown): “form the training datasetD [38].”