Summary
Battery health predictions typically promise accuracy on average across many batteries but often fail for individual cells. The authors show that standard interval predictions cover most cells poorly, sometimes as low as 0.1 to 2% accuracy for the worst cells. They propose a new method using hierarchical weighting that uses extra information available at prediction time to improve individual cell coverage significantly without raising uncertainty or needing to discard uncertain predictions. The method also comes with a new protocol for reporting coverage that makes it clear how trustworthy predictions are for each cell before use.
What this means in practice
- •For battery monitoring engineers: Improve confidence in battery health intervals for individual cells within large fleets using hierarchical weighting without increasing deferrals.
- •For electric vehicle maintenance teams: Use per-cell calibrated health interval reports to better detect and address weak battery cells before they fail.
Abstract
Interval predictions from conformal prediction are usually read as "90% coverage", but on nested battery data that number promises the fleet average, not the individual cell. We measure the gap on 124 public LFP cells under a preregistered three-tier reporting protocol (fleet, batch, cell): pooled coverage looks healthy (0.875-0.906 across splits) while the worst cell is covered 0.1-2% of the time, with exact binomial tests against the nominal level. We then repair part of the gap with a hierarchically weighted conformal engine whose weights consume only side information frozen at prediction time - signature features, batch labels, cycle indices - and never touch residuals. The preregistered repair criterion passes: 10th-percentile cell coverage moves 0.750 to 0.830 (53% of the gap), the worst cell 0.642 to 0.694, with zero deferrals and a flat sensitivity spectrum. What the engine does not repair is localized rather than left open: under protocol drift the frozen weights harm monotonically on the SOH scale (the absolute scale is reported in full), a structural dead end we report instead of tuning away; and repair capacity is bounded by calibration-pool battery diversity, measured on both datasets. On a cross-chemistry external set the calibrated intervals collapse (0.286), while the within-domain skeleton replicates (pooled 0.933, worst cell 0.686). The deliverable is a reporting protocol - three tiers of promise anchored to measured regimes, worst-cell statistics, deferral share - that makes per-cell interval claims auditable before deployment.