Reproduce “NOCE-Net: Representation Learning for Battery Operational Context via Nested Sequence Modelling” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Arnab Bhattacharjee, Wayes Tushar, Tapan Kumar Saha
NOCE-Net predicts battery voltage responses across a battery’s lifetime from planned operational inputs and its changing use history. It segments histories into full equivalent cycles, models within-cycle patterns, and carries context between cycles with a recurrent state. On five datasets excluded from training, it achieves 13.710% macro-average MAPE, versus 24.414% for the baseline; this is prediction, not demonstrated closed-loop control.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.