CNC · HAAS MDC
2,461 mappings·1,027-field schema·ISA-95 categorized·deterministic
Haas MDC is terse. S1Temp is a spindle temperature; it is also, sometimes, 9999, and that number is not a temperature.
Haas MDC uses compact keys like S1Temp, ALARM and COOLANT_LEVEL, which mean nothing to a general-purpose model and collide with other vendors' conventions when a fleet is pooled.
The more expensive problem is the sentinel. Controls report faults in-band as extreme values: 9999, -9999, 65535. Averaged into a shift report, one 9999 moves the mean enough to trigger maintenance on a healthy machine. Forge nulls the value with a stated reason rather than passing it on or silently dropping it: a 9999 in a spindle temperature fails the physics bound and is reported as physics_violation, so the null is explained rather than mysterious.
258 Haas tag spellings resolve deterministically.
| Raw vendor tag | Canonical field | ISA-95 category | |
|---|---|---|---|
| S1Temp | → | spindle_temperature | equipment_condition |
| SPINDLE_SPEED | → | spindle_speed_rpm | equipment_performance |
| ALARM | → | alarm_code | equipment_state |
| PART_COUNT | → | part_count | production_performance |
| MACHINE_HOURS | → | operating_hours | equipment_state |
| COOLANT_LEVEL | → | sensor_readings.coolant_level | equipment_condition |
Every row above is produced by the shipping engine, not written by hand. This page fails to build if any of them stops resolving to the field shown.
Resolution is a lookup, not an inference. A tag is matched against a curated corpus of 2,461 confirmed vendor mappings; only if that misses does it fall to weaker layers: a normalized fold that strips unit suffixes and separators, then a signal classifier that reads structure and unit evidence. Each layer carries a lower confidence, and the layer that answered is named in the response. A mapping you disagree with is visible rather than buried.
Below a confidence threshold the engine abstains. An evidence gate refuses a match it cannot justify and reports the tag unresolved, by name, with the score and the reasons, because a wrong field at high confidence is far more expensive than an honest miss. Six read-time validators then check what survives: sentinel detection, physics bounds, stuck sensors, dropout, operating mode and correlation.
Units are converted to SI where the source unit is known, and every conversion is reported with its factor. A value that fails a physics bound is nulled with the bound it violated attached, not silently dropped.
It does not invent fields. A tag outside the corpus that the signal layer cannot justify comes back unresolved and counted, and those names feed the roadmap for the next pack rather than a plausible guess in your data. It is a translation layer, not a historian: it holds no time series and replaces no SCADA system. And the container is a sandbox: it ships the deterministic layers and the canonical schema, not the production embedding, research and corpus-learning layers.
No key, no account, no sales call. The sandbox runs locally and answers with the same canonical schema production does.
Send S1Temp: 9999 and watch it come back null with physics_violation: 9999 outside [-273.15, 3000.0] attached. Six independent validators run on every read.
The interesting test is not the happy path. See platform licensing for embedding the canonical data model in your own product, or pricing for usage-based API access.