mirror of
https://github.com/Hestia-Homes/Model.git
synced 2026-06-08 11:17:27 +00:00
c0328f4e18
SAP 10.2 Table 4e (PDF p.172-173) "Heating system controls", GROUP 2:
HEAT PUMPS WITH RADIATORS OR UNDERFLOOR HEATING:
Code Description Type
---- ------------------------------------------------- ----
2201 No time or thermostatic control 1
2202 Programmer, no room thermostat 1
2203 Room thermostat only 1
2204 Programmer and room thermostat 1
2205 Programmer and at least two room thermostats 2
2206 Programmer, TRVs and bypass 2
2207 Time + temp zone control by plumbing/electrical 3 ← cert 000565
2208 Time + temp zone control by PCDB device 3
2209 Room thermostat and TRVs 2
2210 Programmer, room thermostat and TRVs 2
Pre-S0380.87 `_CONTROL_TYPE_BY_CODE` contained only Group 1 BOILER
codes (21XX); every Group 2 HP code (22XX) fell through to the
default `return 2`. Cert 000565 lodges `main_heating_control=2207`
on its HP main 1 → silently routed to type 2 → MIT_elsewhere
over-counted by ~+0.5 °C in winter.
The bug: SAP 10.2 Table 9 (PDF p.182) elsewhere off-hours differ
between type 2 and type 3:
Type 1, 2: off-hours (7, 8) — elsewhere heated longer
Type 3: off-hours (9, 8) — elsewhere has separate, shorter
heating schedule per §9.4.14
Wrong control type → wrong off-hours → wrong off-period temperature
reduction (Table 9b) → wrong MIT_elsewhere (line (90)m) → wrong
blended MIT (line (92)/(93)m) → wrong space heating demand
(line (98c)).
Diagnosis chain: post-S0380.86 cert 000565 had structural SH
over-count of +7924 kWh independent of fabric. Diff vs worksheet
intermediates traced it to MIT cascade higher by avg +0.45 °C
(+5.42 °C-months). Per-zone breakdown showed MIT_elsewhere over by
+6.25 °C-months while Th2 setpoint matched. Reverse-engineered the
off-period reduction (cascade u≈4.12 vs worksheet u≈5.14, Jan)
matched off-hours (9, 8) — control type 3 — vs cascade (7, 8) —
control type 2. Verified against Table 4e GROUP 2 spec text:
2207 → type 3 spec-correct.
Cohort + golden + cert 9501 unaffected:
- Elmhurst U985 cohort (000474..000516): all lodge code 2106
(Group 1, type 2) — unchanged
- 20 golden API certs lodge code 2206 (Group 2 HP, type 2 per
spec, type 2 via cascade default) — adding 2206:2 to the
dispatch dict makes the type explicit, behaviour unchanged
- Cert 9501: not lodging 22XX codes
- Only cert 000565 lodges 2207 (and exercises the 22XX→3 fix)
Test (1 new, AAA-structure parametrised across all 10 Group 2 codes
in `test_cert_to_inputs.py`).
**Cert 000565 closure (post-S0380.87 vs post-S0380.86):**
Pin Pre Post Δ worksheet
--- ---- ---- --- ---------
sap_score 23 27 +4 29
sap_score_continuous 22.64 27.35 +4.71 28.51
ecf 6.02 5.51 -0.51 5.39
total_fuel_cost_gbp 5233 4784 -449 4680
co2_kg_per_yr 7165 6581 -584 6448
space_heating_kwh 66932 60468 -6464 59008
main_heating_fuel 39372 35570 -3802 34711
Space heating residual closed +7924 → **+1460 (82% closed)**.
Integer SAP closed Δ-6 → Δ-2 (was the 9th-largest residual; now
gates only on continuous SAP rounding boundary at 28.5).
Test baseline: 561 pass (was 560 + 1 new) + 9 expected
`test_sap_result_pin[000565-*]` fails unchanged. Pyright net-zero
per touched file. SAP 10.2 spec citation included in dispatch dict
comment per [[feedback-spec-citation-in-commits]].
Per [[feedback-spec-floor-skepticism]] + [[feedback-verify-handover-claims]]:
the handover post-S0380.86 listed several candidate SH-channel
root causes (solar gains, internal gains, η, T_int, ventilation).
The single-line spec-dispatch gap was the dominant driver. The
remaining +1460 kWh residual splits roughly: ~+750 kWh from HLC
over-count (+42 W/K, mostly ventilation +27 W/K), ~+700 kWh from
remaining MIT residual.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
||
|---|---|---|
| .. | ||
| addresses | ||
| sap10_calculator | ||
| sap10_ml | ||
| tasks | ||
| postcode.py | ||