PhyMamba: Physics-Modulated Mamba for Robust Battery Health Prognostics

PhyMamba is a two‑stage physics‑modulated Mamba framework designed for robust battery health prognostics. The first stage uses a lightweight Mamba encoder to process BMS signals and generate latent representations, which are then transformed into physics‑informed aging features via an aging parameterization module. The second stage employs a customized Mamba forecasting backbone that integrates physics to guide temporal updates, enabling multi‑cycle predictions that outperform diverse baselines with a 31.8% mean error reduction across three public datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.