CNC / MACHINE TOOL · TELEMETRY NORMALIZATION
16,908 confirmed mappings·18 OEM families·14 protocols·99% field coverage
Forge turns raw Haas tags into one clean, governed schema your AI agent already understands. One MCP call, no per-machine integration project.
Haas Next Gen Control publishes over MTConnect, but production state lives in Q-variables and macro registers (macro_1102, Q600) that need decoding before an agent can reason about the cut.
Typical Haas equipment communicates over MTConnect, Modbus TCP, HTTP / REST. 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 Haas telemetry into Forge's canonical field set, the same 366 canonical fields used across all 18 manufacturers. Point Forge at the machine, pass oem: "haas", and spindle speed is spindle_speed_rpm whether it came from a Haas controller or anything else on the floor.
Confirmed canonical fields your agent gets from Haas machines, drawn from Forge's 16,908-mapping corpus:
| Raw tag in | Canonical field out | Meaning | |
|---|---|---|---|
| Q600_1: 3400 | → | spindle_speed_rpm: 3400 | NGC spindle rpm |
| macro_1102: 78 | → | spindle_load_pct: 78 | spindle load macro |
| prog_active: "O00012" | → | program_name: "O00012" | active program |
| parts_counter: 4821 | → | part_count: 4821 | M30 parts counter |
No SDK, no per-tag mapping, no historian project. Connect the MCP server and normalize live Haas 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.