CNC / MACHINE TOOL · TELEMETRY NORMALIZATION
16,908 confirmed mappings·18 OEM families·14 protocols·99% field coverage
Forge turns raw Siemens Sinumerik tags into one clean, governed schema your AI agent already understands. One MCP call, no per-machine integration project.
Sinumerik 840D/828D controls surface data through OPC UA and S7 with deep BTSS paths like /Channel/Spindle/actSpeed. Expressive, but every integrator re-maps the same paths by hand.
Typical Siemens Sinumerik equipment communicates over OPC UA, PROFINET / S7, MTConnect. 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 Siemens Sinumerik telemetry into Forge's canonical field set, the same 366 canonical fields used across all 18 manufacturers. Point Forge at the machine, pass oem: "siemens", and spindle speed is spindle_speed_rpm whether it came from a Siemens Sinumerik controller or anything else on the floor.
Confirmed canonical fields your agent gets from Siemens Sinumerik machines, drawn from Forge's 16,908-mapping corpus:
| Raw tag in | Canonical field out | Meaning | |
|---|---|---|---|
| /Channel/Spindle/actSpeed: 6000 | → | spindle_speed_rpm: 6000 | BTSS actual speed |
| driveLoad: 62 | → | spindle_load_pct: 62 | drive load % |
| progName: "SHAFT_3.MPF" | → | program_name: "SHAFT_3.MPF" | main program |
| chanAlarm: 700010 | → | alarm_code: 700010 | channel alarm |
No SDK, no per-tag mapping, no historian project. Connect the MCP server and normalize live Siemens Sinumerik 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.