CNC / MACHINE TOOL · TELEMETRY NORMALIZATION
16,908 confirmed mappings·18 OEM families·14 protocols·91% field coverage
Forge turns raw Komatsu NTC tags into one clean, governed schema your AI agent already understands. One MCP call, no per-machine integration project.
Every controller names the same physical quantity differently (spindle speed alone ships as a dozen tag names across firmware revisions), and most shops still bridge it through MTConnect or a hand-rolled OPC UA server.
Typical Komatsu NTC equipment communicates over MTConnect, OPC UA. 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 Komatsu NTC telemetry into Forge's canonical field set, the same 366 canonical fields used across all 18 manufacturers. Point Forge at the machine, pass oem: "komatsu", and spindle speed is spindle_speed_rpm whether it came from a Komatsu NTC controller or anything else on the floor.
Confirmed canonical fields your agent gets from Komatsu NTC machines, drawn from Forge's 16,908-mapping corpus:
| Raw tag in | Canonical field out | Meaning | |
|---|---|---|---|
| spindle_rpm: 4200 | → | spindle_speed_rpm: 4200 | actual spindle speed |
| sp_load_pct: 63 | → | spindle_load_pct: 63 | spindle load |
| active_prog: "KOMATSU-01" | → | program_name: "KOMATSU-01" | active program |
| part_ct: 1540 | → | part_count: 1540 | part count |
No SDK, no per-tag mapping, no historian project. Connect the MCP server and normalize live Komatsu NTC 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.