Skip to content

How it works

Observable signals in. Honest error bars out.

The pipeline is built so the estimator can never cheat. It reads only what a BMS actually emits, its features never see the latent truth, and its uncertainty is calibrated on held-out packs rather than asserted.

Model card soh-quantile-1.0.1The error bars are published. Read the methodology.

The scoring pipeline, stage by stage

  1. 01

    Observable BMS signals only

    Equivalent full cycles, temperature exposure, an internal resistance proxy, coulombic efficiency, depth of discharge, fast-charge fraction. Signals every compliant pack already emits.

    • cycles
    • temperature
    • resistance proxy
    • coulombic efficiency
    • depth of discharge
    • fast-charge fraction
  2. 02

    A feature layer that never sees the truth

    Features are computed from the observables alone. The latent state of health stays hidden from the estimator, in training and in production.

  3. 03

    Gradient-boosted quantile regression

    The model predicts a P10, P50, and P90 for every pack: a central estimate inside an explicit band, never a bare point.

    • P10
    • P50
    • P90
  4. 04

    Conformal calibration

    The band is widened on held-out calibration packs (conformalized quantile regression), so quoted coverage is honest: a stated 80 percent band covers close to 80 percent.

  5. 05

    The decision lenses

    The calibrated estimate becomes the six lenses: grades, values, and risk figures, one per decision that touches the pack.

  6. 06

    Reason codes and drift monitoring

    Every score ships with its attribution, and the fleet is watched for drift that calls for recalibration.

Run the pipeline on your fleet.

A pilot scores a sample of your packs end to end, with the same calibrated bands and reason codes described here.

Request a pilot