Clip-on sensors plus an edge computer to know when a milling tool is really worn
At Bosch's Homburg plant, milling machines were retrofitted with sensors so a model could judge tool wear instead of changing tools on a fixed, conservative schedule.
Evidence: Published pilot project (German Green-AI Hub) at a large manufacturer. Source date: not stated · Checked 2026-10-23 · Tech: current clamps, sound and vibration sensors, edge computer, machine learning
The problem
Tools were swapped early to be safe (wasting carbide and regrinding energy), yet some still broke and scrapped parts.
What they did
They added current clamps on the spindle, a microphone, vibration sensors and axis-current signals, logged everything on an edge computer, and recorded every tool change and its reason. That labeled data trained per-tool models to estimate wear and catch anomalies.
Reported results
The project reports roughly 10% longer tool life with unchanged cycle time, plus fewer breakages and rejects. It says the setup can be retrofitted without converting the machine.
Our take
Bosch is not a job shop, but the recipe scales down: a clamp-on current sensor is cheap and non-invasive. The hard, unglamorous part is the logbook: recording when and why each tool was changed. Without that, there's nothing to learn from.
Try this on Monday: Start a simple tool-change log on one machine this week (tool, time, reason: worn, broken, scheduled). It's free and it's the foundation for any future tool-wear AI.
Brian Roemmele reports wiring an AI agent into an existing flexographic carton-box printing line, with small local models watching the machine and cameras feeding it visual data.
Evidence: Self-reported by the builder on X. Early, no independent verification yet. · via @BrianRoemmele
Brian Roemmele showed a Raspberry Pi with an attached camera running the open LLaVA 1.5 model locally to describe and recognize what passed in front of it.
Evidence: Hobbyist demo shared on X (2023). Not a factory deployment. · via @BrianRoemmele
Neo Industries, a small machine shop in Colleyville, Texas, used automatic production monitoring to see how much of each cycle every tool was responsible for, then optimized tool by tool.
Evidence: Vendor-published customer story with named shop owner.