CNC / MACHINE TOOL · TELEMETRY NORMALIZATION
16,908 confirmed mappings·18 OEM families·14 protocols·99% field coverage
Forge turns raw Fanuc tags into one clean, governed schema your AI agent already understands. One MCP call, no per-machine integration project.
Fanuc controllers expose data through the FOCAS library and PMC addresses. Spindle speed, load and part counts come back as opaque register reads (PMC_R, D-addresses) that mean nothing to an AI agent until they're named.
Typical Fanuc equipment communicates over MTConnect, OPC UA, Modbus TCP. Each firmware revision, model line and integrator names the same physical quantity differently, so every AI or analytics project pays the integration tax again, the tax that cancels 40% of industrial AI deployments before they ship.
Forge normalizes Fanuc telemetry into Forge's canonical field set, the same 366 canonical fields used across all 18 manufacturers. Point Forge at the machine, pass oem: "fanuc", and spindle speed is spindle_speed_rpm whether it came from a Fanuc controller or anything else on the floor.
Confirmed canonical fields your agent gets from Fanuc machines, drawn from Forge's 16,908-mapping corpus:
| Raw tag in | Canonical field out | Meaning | |
|---|---|---|---|
| Spindle_Speed: 2200 | → | spindle_speed_rpm: 2200 | FOCAS actual spindle speed |
| spd_load: 85 | → | spindle_load_pct: 85 | spindle load % |
| actual_feed: 1200 | → | feed_rate: 1200 | actual cutting feed |
| prg_num: 1042 | → | program_number: 1042 | active O-program |
No SDK, no per-tag mapping, no historian project. Connect the MCP server and normalize live Fanuc data:
Unknown tags never get force-mapped. Fields below the confidence floor abstain rather than guess, so your agent never acts on a bad reading.