Skip to content
aiqbench takeMachine Learning

aiqbench analysis

This research advances machine learning techniques for battery state-of-health estimation by rigorously comparing health indicators derived from constant-current and constant-voltage charging phases. The study demonstrates that combining data from both charging stages yields superior predictive accuracy compared to using either phase alone, while also highlighting significant overestimation errors in standard cross-validation methods versus realistic leave-one-battery-out testing. These findings provide critical methodological guidance for developing robust battery management systems powered by AI models.
Source coveringarXiv
What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Charging Phase Health Indicators for Battery State-of-Health Estimation: A Systematic Comparison of CC, CV, and Combined Approaches under Cross-Battery Validation

arXiv2 min read

arXiv:2607.23482v1 Announce Type: new Abstract: Accurate State-of-Health estimation is essential for safe battery operation and cost-effective maintenance. Although numerous health indicators have been derived from constant-current (CC) and constant-voltage (CV) charging phases, their effectiveness under realistic cross-battery validation remains insufficiently studied. This work addresses this gap through a systematic comparison of CC-only, CV-only, and combined indicator sets using rigorous Leave-One-Battery-Out (LOBO) validation on the NASA battery aging dataset. Four CV-phase indicators and CC phase duration are evaluated individually and in combination. Results show that the combined CC+CV approach achieves the best performance (R2 = 0.874), confirming that CC and CV phases capture complementary degradation information. Moreover, a 119% performance gap is observed between standard 5-fold cross-validation and LOBO validation, indicating that conventional evaluation overestimates practical accuracy. Based on these findings, practical guidelines are provided for indicator selection under data and computational constraints.

Abstract:Accurate State-of-Health estimation is essential for safe battery operation and cost-effective maintenance. Although numerous health indicators have been derived from constant-current (CC) and constant-voltage (CV) charging phases, their effectiveness under realistic cross-battery validation remains insufficiently studied. This work addresses this gap through a systematic comparison of CC-only, CV-only, and combined indicator sets using rigorous Leave-One-Battery-Out (LOBO) validation on the NASA battery aging dataset. Four CV-phase indicators and CC phase duration are evaluated individually and in combination. Results show that the combined CC+CV approach achieves the best performance (R2 = 0.874), confirming that CC and CV phases capture complementary degradation information. Moreover, a 119% performance gap is observed between standard 5-fold cross-validation and LOBO validation, indicating that conventional evaluation overestimates practical accuracy. Based on these findings, practical guidelines are provided for indicator selection under data and computational constraints.

This paper has been published in Eksploatacja i Niezawodnosc. Please cite the published version

Machine Learning (cs.LG)

arXiv:2607.23482 [cs.LG]

(or arXiv:2607.23482v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.23482 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

https://doi.org/10.17531/ein/220211 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Full text under the publisher's open licence · 255 words

Related coverage