VERTICAL · EQUIPMENT FLEETS
2,461 mappings·1,027-field schema·ISA-95 categorized·deterministic
The average commercial fleet runs equipment from around thirteen manufacturers, and each one ships its own telematics portal.
Telematics research consistently puts the typical mixed fleet in the region of a dozen or more manufacturers. Geotab and peers report averages around thirteen. Each vendor offers a portal, and none of them offers a common definition of engine hours, idle time or utilisation. So the fleet manager exports thirteen CSVs and reconciles them by hand, monthly.
For anyone financing the asset the gap is sharper. Roughly $1.3T of equipment is financed against utilisation and condition covenants that the lessor cannot independently verify, because verification would mean reading thirteen vendor APIs and trusting each one's definition of an hour.
Utilisation, condition and consumption fields resolve to the same canonical names regardless of which manufacturer emitted them, and operating_hours means the same thing on every one.
| Raw vendor tag | Canonical field | ISA-95 category | |
|---|---|---|---|
| POWER ON TIME (h) | → | operating_hours | equipment_state |
| MACHINE_HOURS | → | operating_hours | equipment_state |
| Betriebsstunden | → | operating_hours | equipment_state |
| BearingTemp_DegC | → | bearing_temperature | 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.
Three different vendors' words for powered-on time resolving to one field is the entire product in one table. Send your own fleet export and check it.
Independent, vendor-neutral condition data is the point. See platform licensing for embedding the canonical data model in your own product, or pricing for usage-based API access.