Research papers · Posted 2026.02.24 · Publication / acceptance: author-reported

KAN-Koopman Based Rapid Detection Of Battery Thermal Anomalies With Diagnostics Guarantees

KAN-Koopman Based Rapid Detection Of Battery Thermal Anomalies With Diagnostics Guarantees

Overview

The authors combine KAN core-temperature estimation with online Koopman prediction for battery diagnostic residuals. Analytical conditions describe diagnostic guarantees, while simulation compares thermal-anomaly detection against a Koopman-only baseline.

Publication and version information

Publication, acceptance or venue information is author-reported on arXiv. The exact source wording is preserved below.

Author-supplied source information

Author-supplied information on arXiv.

9 pages, 1 figure, Accepted to The 2026 American Control Conference

Version: arXiv v2 — manuscript revision

PARTICIPATION ENQUIRY

Participation enquiry

Your enquiry will be delivered by email. We will reply to the address you provide.

Email enquiries: info@battermachine.com