One bar per day for the night-end voltage delta, coloured by trend
(blue better, grey stable, red worse), with the 0.05 V dead band.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Day-over-day trend from DAILY_BATTERY_STATE: a state change decides
(FULL > PARTIAL > NO_CHARGE > BELOW_PLATEAU), otherwise the night-end
voltage delta with a 0.05 V dead band. No verdict (anomaly = None).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The night end and rise were anchored on the first daily maximum,
which can be the 00:00 tail of the previous evening: 2026-05-05 was
read NO_CHARGE despite a +0.079 V rise, 2026-09-30 showed a wrong
night end, and 2026-09-26 stayed unknown from 04:00 to 11:00 when
evaluated mid-day. The rise now starts from an earlier minimum and
the knee is tested on the daily minimum (min_v). VERMONT: 139 / 31 /
14 / 0.
Docs: sheet 02 page order, battery_state.py in the CLAUDE.md map,
phase C exception to "anomaly = None means UNKNOWN".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
src/analyse_03.py launches the common page; sheet 03 moves to
"prototype en place" with VERMONT results; CLAUDE.md, README and
sheet 01 list the third panel.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Daily maximum and night-end voltage, 14.0 V and 12.8 V thresholds,
one marker colour and symbol per day state.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
One state per UTC day from BusVoltage: FULL_CHARGE, BELOW_PLATEAU,
NO_CHARGE, PARTIAL_CHARGE or unknown, with hardware thresholds
(14.0 V end of charge, 12.8 V LiFePO4 knee). No verdict yet.
Includes the implementation plan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Background bands for discharge (12.0-13.2 V), charging (13.1-13.8 V)
and full charge (14.0-14.4 V), from the battery voltage report.
Display only, no effect on the analyses.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Analysis 02 MOVING_AVERAGE_7_DAYS_MIDNIGHT_UTC_DROP: same rule as
analysis 01 on the 00:00 UTC BusVoltage sample only, one point per
day. Shared computation in energy_check._ma_drop(); analysis 01
results unchanged on VERMONT.
- Common page: one panel per analysis (02 under 01), then the time
series (D-016); src/analyse_02.py launches that page.
- Analysis panel reduced to two curves on one volt axis: 7-day mean
and threshold; gap and reference moved to hover (D-015).
- Date tick labels under every subplot.
- Rule IDs spelled out: MA7D_DROP -> MOVING_AVERAGE_7_DAYS_DROP,
MA7D_MIDNIGHT_DROP -> MOVING_AVERAGE_7_DAYS_MIDNIGHT_UTC_DROP (D-017).
- Docs: analysis sheet 02, sheet 01, CLAUDE.md, README, decisions
D-015..D-017, analysis rule and nouvelle-analyse skill.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- src/analyse_01.py: single entry point, analyses data/, writes and
opens the HTML report (switches to .venv for plotly).
- Plot: analysis on top, one subplot per time series below; zoom in
time only, y axes rescaled to the visible range on every zoom.
- Tests removed: experimental prototype phase (D-008).
- Ignore __pycache__/.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- doc/: AIMsight reference documentation and station manual.
- data/: VERMONT complete dataset (7 system metrics) and expert
diagnostics; other incomplete stations set aside in data/archive/.
- src/__main__ (3).py: reference copy of the embedded system_info
collector (INA219 units, LiFePO4 OCV table).
- architecture.drawio: user-maintained architecture diagram.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- NaN/inf values are treated as missing instead of poisoning the
running sum (which produced a false "not observed").
- Unreadable CSV files are skipped with a message naming the file;
a station whose analysis fails is skipped with its name and the
scan continues.
- The summary now states hours without verdict and the longest
UNKNOWN stretch (5 months on MISSISSIPPI were silent).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>