yau-plant-assistant/cube/model/operations.yml

# =============================================================================
# operations.yml — pump-down operations.
#
# THIS IS THE FILE THAT ANSWERS THE ADVISORY QUESTION WITH EVIDENCE RATHER THAN
# OPINION. When an operator asks what rate to run the station at, the honest
# answer is a table of what has actually been run, what happened each time, and
# what the documented limits are - then a deferral. Everything needed for that
# is a measure here.
#
# SOURCE: fixture.operation_history while USE_FIXTURES=true.
#
# IF imh HAS NO OPERATIONS TABLE - and it probably does not - derive it here.
# The heuristic, kept deliberately simple so it can be explained to the person
# checking the number:
#
#   A PUMP-DOWN starts at the sample where PS_STN_PUMPS_RUNNING goes from 0 to
#   non-zero, and ends at the next sample where it returns to 0. Its max level
#   is the maximum PS_STN_WET_WELL_LEVEL over that span plus the 10 minutes
#   before it, because the peak is usually just before the pumps catch up.
#   Operations shorter than 5 minutes are discarded as start/stop noise.
#
# Do not make this cleverer. A heuristic nobody can explain is not evidence,
# and this cube's whole job is to produce evidence.
#
# ON THE WORD "FILL": the generic spec calls these fills. WRPS is a pump
# station, so the operation is a pump-down - the well fills passively on inflow
# and the station draws it back down. Same shape, opposite sign. The measures
# keep the pump-down naming because that is what an operator here would say.
# =============================================================================

cubes:
  - name: operations
    sql_table: fixture.operation_history    # -> derived from imh at Phase 4
    description: >
      One row per pump-down at the Waterloo Road Pump Station: when it ran,
      how high the well got, how much came in, how much was pumped, which unit
      was duty, and whether it alarmed or spilled.

    joins:
      - name: equipment
        sql: "{CUBE}.equipment_id = {equipment}.equipment_id"
        relationship: many_to_one

    dimensions:
      - name: operation_id
        sql: operation_id
        type: number
        primary_key: true

      - name: start_time
        sql: start_time
        type: time
        description: Stored UTC, presented in SITE_TIMEZONE.

      - name: end_time
        sql: end_time
        type: time

      - name: equipment_id
        sql: equipment_id
        type: string

      - name: operation_type
        sql: operation_type
        type: string
        description: PUMP_DOWN. Reserved for future manual or wash-down operations.

      - name: duty_pump
        sql: duty_pump
        type: string
        description: >
          The unit that led the operation. Duty rotates on lowest accumulated
          run hours, service-due units ranked last, ties by ascending pump
          number - so an uneven distribution over a long window is a finding,
          not a rotation fault.

      - name: peak_pumps_running
        sql: peak_pumps_running
        type: number

      - name: high_level_alarm
        sql: high_level_alarm
        type: boolean
        description: Did this pump-down reach the high level alarm setpoint.

      - name: spill
        sql: spill
        type: boolean
        description: >
          Did the well go over the weir crest. A spill is an environmental
          reportable event; report the count plainly and never round it.

      - name: is_fixture
        sql: is_fixture
        type: boolean

    measures:
      - name: pump_down_count
        type: count
        description: Number of pump-down operations in the window.

      - name: avg_discharge_rate
        sql: avg_discharge_m3h
        type: avg
        description: >
          Mean discharge rate across operations, m3/h. Evidence of what has
          been run - NOT a recommendation of what to run.

      - name: min_discharge_rate
        sql: avg_discharge_m3h
        type: min

      - name: max_discharge_rate
        sql: avg_discharge_m3h
        type: max

      - name: avg_inflow_rate
        sql: avg_inflow_m3h
        type: avg

      - name: max_level_reached
        sql: max_level_pct
        type: max
        description: Highest wet well level reached, percent of the weir crest.

      - name: avg_max_level
        sql: max_level_pct
        type: avg

      - name: high_alarm_count
        type: count
        filters:
          - sql: "{CUBE}.high_level_alarm = TRUE"

      - name: high_alarm_rate
        sql: >
          COUNT(*) FILTER (WHERE {CUBE}.high_level_alarm)::float
          / NULLIF(COUNT(*), 0)
        type: number
        description: >
          Fraction of pump-downs that reached the high level alarm. Pair it
          with pump_down_count in the answer - 1 in 2 and 50 in 100 are not the
          same evidence, and a rate quoted without its denominator invites the
          reader to treat a small sample as a trend.

      - name: spill_count
        type: count
        filters:
          - sql: "{CUBE}.spill = TRUE"

      - name: avg_duration_minutes
        sql: "EXTRACT(EPOCH FROM ({CUBE}.end_time - {CUBE}.start_time)) / 60"
        type: avg

    pre_aggregations:
      - name: ops_by_day
        measures:
          - pump_down_count
          - avg_discharge_rate
          - max_level_reached
          - high_alarm_count
          - spill_count
        dimensions: [equipment_id, duty_pump, operation_type]
        time_dimension: start_time
        granularity: day
        partition_granularity: month
        refresh_key:
          # 24h, not minutes: the fixtures are static, so a shorter
          # interval rebuilds a byte-identical result on a 2-vCPU host
          # and was a standing CPU load for no gain. Tune this back
          # deliberately when imh makes the data genuinely live.
          every: 24 hours
        build_range_start:
          sql: "SELECT now() - interval '365 days'"
        build_range_end:
          sql: "SELECT now()"