A ~$60 clamp-on sensor to watch spindle load on a 1998 Haas
A detailed guide on giving an old CNC with no data output a spindle-load monitor using a clamp-on current sensor and an ESP32.
Evidence: How-to guide from an engineering blog. A design write-up, not a measured deployment. Source date: not stated · Checked 2026-10-23 · Tech: split-core current transformer, ESP32 microcontroller, relay
The problem
Older machines show spindle load only on a screen, so you can't log it or get an alert when a tool dulls or hits a hard spot.
What they did
The guide clamps a split-core current sensor around one phase of the spindle motor supply, has an ESP32 calculate true current, converts that to a load percentage after a simple calibration, logs it, and can trigger an alert when it crosses a threshold.
Reported results
The author estimates parts cost under $60 CAD and about two hours to install, and claims roughly ±5% load accuracy versus far more expensive aftermarket monitors. These are the author's estimates, not measured results from a shop.
Our take
The sensing approach is the same one commercial tools like Amper use, which makes it a good learning project. One big caution: the guide also describes wiring into the machine's feed-hold circuit. Anything touching machine safety circuits or a live electrical cabinet should be done by a qualified electrician or your machine dealer, not from a blog post.
Try this on Monday: Start with logging only (no machine stop). A week of spindle-current data on one machine tells you a lot about cutting vs. idle time.
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.