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

# =============================================================================
# process_values.yml — sampled analogue history.
#
# SOURCE: fixture.process_value_history while USE_FIXTURES=true; the agreed imh
# process value table from Phase 4.
#
# THE THING THAT WILL BITE WHEN imh IS CONNECTED: CI Server historises with a
# deadband, so real samples are IRREGULAR. The fixtures are regular 1-minute
# samples. Any measure that averages rows rather than time-weighting them will
# look correct on fixtures and be wrong on imh - a flat period compresses to
# one row and a noisy period to hundreds, so a plain avg is weighted by how
# interesting the signal was. avg_value below is a plain average and is
# documented as an approximation; time_weighted_avg is the one to trust, and it
# must be re-verified against imh at the Phase 5 gate.
#
# SENTINELS: PS_STN_TIME_TO_SPILL_WEIR and PS_STN_TIME_TO_LSHH use 32767 to
# mean "drawing down or holding" - it is not a duration. Every measure here
# excludes it. Do not remove that filter to make a number look tidier.
#
# QUALITY: rows with quality other than GOOD are excluded from every measure.
# A BAD sample from a failed transmitter is not a low reading.
#
# UNITS: whatever the historian stores, which is not always what the PLC works
# in. Wet well level is historised as percent of the spill weir crest (raw mm
# divided by 60): 100.0 % = 6000 mm. See db/seed/tags.csv for every conversion.
# =============================================================================

cubes:
  - name: process_values
    sql_table: fixture.process_value_history    # -> imh PV table at Phase 4
    description: >
      Sampled analogue history - wet well level, inflow, discharge flow, drive
      speed, run hours. This is what makes an advisory question answerable with
      evidence; you cannot answer a flow question from alarms.

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

    dimensions:
      - name: id
        sql: "{CUBE}.tag_id || '@' || {CUBE}.sample_time"
        type: string
        primary_key: true

      - name: sample_time
        sql: sample_time
        type: time
        description: Stored UTC, presented in SITE_TIMEZONE. Converted once, here.

      - name: tag_id
        sql: tag_id
        type: string

      - name: equipment_id
        sql: equipment_id
        type: string

      - name: engineering_unit
        sql: engineering_unit
        type: string
        description: >
          Always report this with the number. A level of 86.7 is a percentage
          of the weir crest, not a metre reading.

      - name: quality
        sql: quality
        type: string

      - name: is_fixture
        sql: is_fixture
        type: boolean

    measures:
      - name: sample_count
        type: count
        filters:
          - sql: "{CUBE}.quality = 'GOOD' AND {CUBE}.value <> 32767"

      - name: avg_value
        sql: value
        type: avg
        filters:
          - sql: "{CUBE}.quality = 'GOOD' AND {CUBE}.value <> 32767"
        description: >
          APPROXIMATION. Plain average of samples. Correct on the regular
          fixture data; biased on deadband-compressed imh data. Prefer
          time_weighted_avg for anything an engineer will check.

      - name: time_weighted_avg
        sql: >
          SUM({CUBE}.value * EXTRACT(EPOCH FROM (
            LEAD({CUBE}.sample_time) OVER (
              PARTITION BY {CUBE}.tag_id ORDER BY {CUBE}.sample_time
            ) - {CUBE}.sample_time)))
          / NULLIF(SUM(EXTRACT(EPOCH FROM (
            LEAD({CUBE}.sample_time) OVER (
              PARTITION BY {CUBE}.tag_id ORDER BY {CUBE}.sample_time
            ) - {CUBE}.sample_time))), 0)
        type: number
        description: >
          Time-weighted average - each sample weighted by how long it stood.
          This is the honest average on deadband-compressed history. Verify it
          against imh by hand at the Phase 5 gate before trusting it in prose.

      - name: max_value
        sql: value
        type: max
        filters:
          - sql: "{CUBE}.quality = 'GOOD' AND {CUBE}.value <> 32767"

      - name: min_value
        sql: value
        type: min
        filters:
          - sql: "{CUBE}.quality = 'GOOD' AND {CUBE}.value <> 32767"

      - name: p95_value
        sql: "PERCENTILE_CONT(0.95) WITHIN GROUP (ORDER BY {CUBE}.value)"
        type: number
        filters:
          - sql: "{CUBE}.quality = 'GOOD' AND {CUBE}.value <> 32767"
        description: >
          95th percentile. More useful than max for "how high does it normally
          get", because max is one sample and often a transient.

      - name: seconds_above_high_level_alarm
        sql: >
          SUM(CASE WHEN {CUBE}.tag_id = 'PS_STN_WET_WELL_LEVEL'
                    AND {CUBE}.value >= 86.7 THEN 60 ELSE 0 END)
        type: number
        description: >
          Seconds the wet well spent above the high level alarm setpoint
          (86.7 % = 5200 mm, the %MW8 default). ASSUMES A 60 SECOND SAMPLE
          INTERVAL, true of the fixtures and NOT true of imh. When imh is
          connected this must be rewritten to sum actual sample gaps - it is on
          the Phase 5 gate list for exactly that reason. If the setpoint itself
          was changed during the window (PS_STN_HIGH_LEVEL_ALARM_SP), this
          measure is wrong and the answer must say so.

      - name: seconds_above_lshh
        sql: >
          SUM(CASE WHEN {CUBE}.tag_id = 'PS_STN_WET_WELL_LEVEL'
                    AND {CUBE}.value >= 91.7 THEN 60 ELSE 0 END)
        type: number
        description: >
          Seconds above LSHH (91.7 % = 5500 mm). Same 60 second assumption as
          above. Any non-zero value here is worth reporting explicitly.

    pre_aggregations:
      - name: pv_by_hour
        measures: [avg_value, max_value, min_value, sample_count]
        dimensions: [tag_id, equipment_id, engineering_unit]
        time_dimension: sample_time
        granularity: hour
        partition_granularity: month
        refresh_key:
          every: 10 minutes
        build_range_start:
          sql: "SELECT now() - interval '180 days'"
        build_range_end:
          sql: "SELECT now()"