mirror of
https://github.com/lynchaos/ashvale-station.git
synced 2026-09-12 20:52:23 +00:00
kemalandClaude Opus 5
f48cd61c10
Two changes to the same signal path, one large and one small. The large one: all three filters were tuned to track one to three decades faster than their signals move. In a still room the temperature filter reported a median rate of 12.4 C/h while the air moved 0.4 C/h, and it overshot a real -36 C/h event by 77%. Sweeping q against the RMSE of the reported rate versus the true rate, using noise measured on the board (temperature 0.088 C, pressure 0.022 hPa, humidity 0.40 %): temperature 6.45 -> 0.37 C/h RMSE 2e-6 -> 1e-9 pressure 2.15 -> 0.24 hPa/h RMSE 1e-5 -> 1e-8 humidity 27.94 -> 3.55 %/h RMSE 5e-5 -> 2e-8 Tracking does not suffer. Lag against a genuine 2 C/h ramp is 0.003 C at both the old and new values, and the peak response to a five-minute event moves closer to the truth rather than further from it, because the overshoot goes away. What is given up is response to sub-minute transients, which for a station forecasting fifteen minutes to a day ahead is noise to reject. This matters most for pressure, whose tendency drives the precipitation forecast, and which was the worst tuned of the three. config.yaml shadowed kalman_q_temp, so editing the dataclass alone changed nothing. All six values are now listed there with that hazard spelled out, because a silent shadow cost real time here. The small one: temp_raw was the plain average of two thermometers whose white-noise sds differ by 7x (LPS25HB 0.007 C, HTS221 0.049 C), which throws the quiet one away. Inverse-variance weighting cuts the raw noise 3.5x. The trap is that the chips do not agree. They sit at different distances from the SoC and stand about 1.3 C apart, so weighting by variance alone drags temp_raw 0.48 C onto the LPS25HB, which after the 1.55x gain of the inverse compensator is 0.75 C of silent bias on every reading, since k was fitted against the mean of the two. The gradient is therefore tracked and removed before weighting and only the deviations are fused: measured mean shift 0.0001 C, noise still 3.5x lower. The tracked gradient is retained because it is a second observation of self-heating. Also corrected: the earlier claim that the HTS221 was the quieter channel was wrong, taken from twelve samples at a cadence slow enough that real drift dominated. At 0.5 s over 120 samples the LPS25HB is quieter by 7x and takes 98% of the weight. Co-Authored-By: Claude Opus 5 <[email protected]>
47 lines
1.6 KiB
YAML
47 lines
1.6 KiB
YAML
# Ashvale Station configuration. Every field is optional: anything omitted
|
|
# falls back to the dataclass default in ashvale/config.py.
|
|
|
|
site:
|
|
name: ashvale-labs-weather-station
|
|
latitude: 52.2053 # Cambridge, UK
|
|
longitude: 0.1218
|
|
altitude_m: 15.0 # matters more than you would think, see README
|
|
timezone: Europe/London
|
|
indoors: true # be honest here, it changes how forecasts are worded
|
|
|
|
sensor:
|
|
sample_period_s: 2.0
|
|
persist_period_s: 30.0
|
|
rotation_deg: 90
|
|
cpu_heat_k: 0.55 # starting point only, calibrate from the dashboard
|
|
# Process noise. Raise to track faster, lower to smooth harder. These were
|
|
# retuned against noise measured on a real board by sweeping each q against
|
|
# the RMSE of the reported rate versus the true rate. The originals tracked
|
|
# two to three decades faster than any of these signals move: in a still room
|
|
# the temperature filter reported a median rate of 12.4 C/h while the air
|
|
# moved 0.4 C/h. All three are listed because this file shadows the defaults
|
|
# in ashvale/config.py, and a value present here silently wins.
|
|
kalman_q_temp: 1.0e-9
|
|
kalman_r_temp: 0.02
|
|
kalman_q_press: 1.0e-8
|
|
kalman_r_press: 0.05
|
|
kalman_q_hum: 2.0e-8
|
|
kalman_r_hum: 0.60
|
|
|
|
model:
|
|
grid_s: 300
|
|
horizons_s: [900, 3600, 10800, 21600, 43200, 86400]
|
|
rls_forgetting: 0.9985 # effective memory ~ 11 h on a 5-minute grid
|
|
conformal_alpha: 0.10 # 90% prediction intervals
|
|
train_period_s: 600
|
|
min_rows_to_train: 120
|
|
|
|
storage:
|
|
raw_retention_days: 7.0
|
|
five_min_retention_days: 90.0
|
|
|
|
server:
|
|
host: 0.0.0.0
|
|
port: 8000
|
|
led_enabled: true
|