recipe_phase_adherence

recipe_phase_adherence

Recipe-phase adherence: check each batch phase against a spec.

Batch processes execute a sequence of named phases (heat-up, hold, cool-down, ...). Each phase has a development-defined spec: an expected duration window, a hold-value window, a maximum ramp rate, sometimes a peak ceiling. This detector iterates the phase intervals in a batch and emits one event per phase carrying pass/fail plus which criterion failed.

The spec format is intentionally a plain dict so it can be authored by a process engineer (or loaded from YAML/JSON) without inventing a new schema class -- see :meth:evaluate for the recognised keys.

RecipePhaseAdherenceEvents

RecipePhaseAdherenceEvents(
    dataframe: DataFrame,
    phase_uuid: str,
    value_uuid: str,
    spec: dict[str, dict[str, Any]],
    *,
    event_uuid: str = "dev:recipe_phase_adherence",
    value_column: str = "value_double",
    time_column: str = "systime"
)

Bases: Base

Evaluate batch recipe phases against a declarative spec.

The spec is a mapping {phase_name: criteria_dict}. Recognised criteria keys (all optional) per phase:

• duration_s -- (min, max) seconds.
• hold_value -- (min, max) for the mean value during the phase.
• ramp_rate_max -- maximum absolute slope (value-units per second) computed from the first to the last sample.
• peak_value -- (min, max) for the phase max.
• trough_value -- (min, max) for the phase min.

Missing criteria are not checked. A phase whose name is absent from the spec is reported with pass=True and an empty criteria_failed list (the phase was observed but not constrained).

evaluate

evaluate() -> pd.DataFrame

Evaluate every observed phase interval against the spec.

Returns:

Name	Type	Description
	DataFrame	Interval-shape DataFrame, one row per phase occurrence,
columns	DataFrame	start, end, duration_seconds, uuid,
	DataFrame	phase, mean_value, min_value, max_value,
	DataFrame	observed_ramp_per_s, criteria_failed (list[str]),
	DataFrame	pass.