Archive
Every issue, searchable.
The full run of Setpoint. Industrial AI, control systems, product reviews, and deep dives written for engineers. Filter by category or topic. Search the body of every issue.
Category
Topics
8 issues
- Field NotesJun 15, 2026
Tool-change auto-detection, and the case for asking the controller instead of guessing from the signal
The last unbuilt feature from the issue 06 vendor comparison. A signature detector on the spindle stream can learn what a tool change looks like, but the controller already knows. This issue builds the controller-fed path with MTConnect and keeps the matched-filter detector as the fallback for machines that will not talk.
Issue 06 priced a vendor condition-monitoring quote line by line against the open stack and left four features to build. Issues 06 and 07 built three of them: the single-asset Isolation Forest, the cross-asset common-mode gate, and the threshold alerting. The fourth was tool-change auto-detection, the feature that stops the model from paging on the large vibration and current transient a planned tool change produces, which issue 06 logged as a false positive that turned out to be a real but miscategorized event. Issue 08 builds it. The signal-only approach treats the tool-change transient as a known signature and matches it with a matched filter, the optimal detector for a known template in noise. It works, and it has the failure mode every blind detector has: it fires on anything that resembles the template and stays silent on the tool change that does not. The controller-fed approach skips the inference entirely. The CNC already knows it is changing a tool, and MTConnect exposes that as a structured data item the edge can read and publish alongside the sensor stream. The model gates its own scoring on the controller's ground truth. Both are built. The controller-fed path is the recommendation, the matched filter is the fallback for machines with no open data interface, and the honest failure mode of gating any planned event is named: a real fault that begins inside the gate window is suppressed until the window closes.
Mtconnect·Tool Change·Anomaly Detection·Matched Filter·Dtw·Change Point - Field NotesJun 8, 2026
Cross-asset correlation on the open stack, and what it actually buys: fewer false alarms, not more catches
Two spindles, one PyOD model that scores them jointly, rendered on the same Grafana dashboard. The cross-asset feature the vendor quote priced at a premium, built for the cost of the second carrier the second asset needed anyway. The result is mostly a false-positive filter, which is the opposite of how the feature is sold.
Issue 06 deployed a single-asset Isolation Forest in 80 lines of Python and priced the vendor quote against it line by line. One line item survived as genuinely not built: cross-asset correlation, which the SaaS markets as ensemble-learning anomaly detection with cross-asset correlation and which issue 06 estimated at roughly one engineer-week. Issue 07 builds it. A second i.MX 8M Plus carrier on a second spindle publishes to the same broker, a PyOD model scores both assets in one joint feature frame, and a common-mode detector flags the case where both assets move together. The result reframes what cross-asset correlation is for. It catches almost nothing the single-asset model does not. Its real value is the inverse: it rejects the environmental false positives from issue 06, the cooling-system cross-talk and the floor-vibration bleed-through, by recognizing them as plant-wide rather than asset-specific. That is a meaningful feature, and it is not the feature the marketing describes.
Pyod·Cross Asset Correlation·Anomaly Detection·Ecod·Common Mode Rejection·Self Hosted - Field NotesJun 1, 2026
Isolation Forest in 80 lines of Python, against the vendor 'AI/ML machine health' pitch
The model layer on top of the open IIoT stack. Scikit-learn trained on InfluxDB data, anomaly scores written back, Grafana renders the result on the same dashboard. What the model catches that the threshold rules miss, and what the $1,200-per-asset SaaS sells on top.
Issue 05 stood up Grafana, InfluxDB, and Telegraf on the same $5.50/mo Hetzner VM that runs the Sparkplug B broker. The alerts in that issue were threshold rules: RMS velocity above ISO 10816 Class II, drive current above 110% nameplate, anomaly score above a fixed line. Issue 06 builds the model that produces the anomaly score, in 80 lines of Python. Scikit-learn Isolation Forest, trained nightly on the prior 14 days of telemetry from InfluxDB, scoring live frames every 10 seconds and writing the score back as its own measurement. The comparison: the same vendor SaaS quote from issue 05, this time looking at what its 'AI-driven machine health' line item actually buys on top of the open implementation. The model catches one real failure pattern that the threshold rules miss. It also produces a class of false positives that the threshold rules do not. The honest read on which of the two layers should sit in front of the maintenance team.
Isolation Forest·Scikit Learn·Anomaly Detection·Machine Learning·Self Hosted·Influxdb - Field NotesMay 25, 2026
Grafana plus InfluxDB on $5.50/mo, against the vendor 'machine health platform'
Self-hosted observability on the same Hetzner VM that runs the Sparkplug B broker. What the open stack delivers, what it does not, and the honest read on the $1,200-per-asset-per-year quotes.
Issue 04 put OPC UA and Sparkplug B on the carrier and pointed both at a HiveMQ broker on a $5.50/mo Hetzner VM. Issue 05 puts the dashboards, the historian, and the alerting on top of it. Grafana plus InfluxDB plus Telegraf, all self-hosted on the same VM, fed by the Sparkplug subscriber. The result is a working machine-health dashboard with anomaly alerts, vibration trend, and 90-day retention for under six dollars a month. The comparison: a representative vendor 'machine health' SaaS quote at $1,200 per asset per year. What the open stack delivers that the SaaS does, what it does not, and which of the two should sit on a real plant floor.
Grafana·Influxdb·Telegraf·Self Hosted·Observability·Machine Health - Field NotesMay 18, 2026
OPC UA, Sparkplug B, and the Unified Namespace question
The network layer for the i.MX 8M Plus bench — open62541 server, Sparkplug B broker, and whether Unified Namespace is real architecture or a brand sticker on conventional pub/sub.
Issue 03 stood up the i.MX 8M Plus bench. Issue 04 puts the network layer on it. open62541 OPC UA server vs an Eclipse Tahu / HiveMQ Sparkplug B broker — same data, two stacks, side-by-side measurements. Then the harder question: is Unified Namespace a real architectural shift or a marketing label on top of MQTT pub/sub anyone could have built in 2014. The numbers say one of those is more true than the other.
Opc Ua·Open62541·Mqtt·Sparkplug B·Unified Namespace·Uns - Field NotesMay 11, 2026
When the $240 pilot graduates
The mid-range step — a real industrial accelerometer on an NXP i.MX 8M Plus carrier — and the moment in-house ML stops being cheaper than a vendor service.
Issue 02 ran a $240 edge-ML bench on a 1995 spindle. Issue 03 is the next hop: industrial IEPE accelerometers on an NXP i.MX 8M Plus carrier with a hardware NPU. BOM $2,847, inference latency 4 ms, recall 96%. The build is real. The harder question is when it stops being cheaper than a vendor service like Augury or Sight Machine — and the answer is sharper than I expected.
Edge Ml·Anomaly Detection·Imx8m Plus·Iepe Accelerometer·Predictive Maintenance·Augury - Field NotesMay 4, 2026
The $240 spindle retrofit
An edge-ML anomaly bench on a twenty-year-old spindle motor — exact BOM, exact data pipeline, exact failure modes.
Last week's scorecard ranked Edge Impulse on the Arduino Opta the highest-floor pilot in the AI-on-the-PLC category. This week the bench. Total BOM $238.94, two days of data capture, three failure-mode labels, GMM model running 23 ms inference. What worked, what didn't, and the four mistakes that nearly killed the pilot.
Edge Ml·Anomaly Detection·Arduino Opta·Edge Impulse·Spindle·Predictive Maintenance - Deep DiveApr 27, 2026
AI at the PLC — what ships, what doesn't
Five AI-on-the-PLC products, graded honestly against production.
Eighteen months after the first Industrial Copilot previews, five real products are in the field. Siemens Engineering Copilot TIA (B+), Rockwell FactoryTalk Design Studio Copilot (Incomplete), Siemens TM NPU (A-), Edge Impulse + Arduino Opta (A), Beckhoff TwinCAT CoAgent (B). A scorecard, three pre-pilot tests, and the edge retrofit I would install Monday.
AI Copilots·PLC·Siemens·Rockwell·Beckhoff·Arduino