A short, physical validation: take one to three of your least connectable machines, capture their real signals, prove the counts reconcile and the devices survive the environment — then write the installation standard the rest of the fleet will be quoted against.
Connect my legacy machinesTalk to a manufacturing engineerPrimary buyer: Automation Manager · Engineering Manager · IT / OT Manager · Production Manager · Digital Transformation Manager
Durations are typical, not guaranteed. What extends a schedule: missing or incomplete data, security and network approvals, hardware lead times, sample collection, installation access, the production schedule, ERP test access, and the time your team needs to review results.
No unplanned shutdown is expected. Any installation window or controlled interruption is agreed with you in advance and scheduled around production.
| Metric | How it is defined | Where the number comes from | Type |
|---|---|---|---|
| Cycle count reconciliation | Deviation between captured counts, the machine’s own counter and the operator’s manual count, per shift. | Sensor, meter or device data | Technical |
| Signal accuracy | Correct interpretation of each tapped signal, verified against observed machine behaviour. | Sensor, meter or device data | Technical |
| State detection accuracy | Correct classification of running, idle, stopped and setup, checked against observation. | Sensor, meter or device data | Technical |
| Event latency | Time from a physical event to it being visible in the platform, at the 95th percentile. | MSF platform data | Technical |
| Device and network uptime | Availability of the modules, panels and their connection over the validation period. | Sensor, meter or device data | Technical |
| Operator completion rate | Where a panel workflow is in scope: share of expected operator entries actually completed. | MSF platform data | Adoption |
| Installation effort | Hours per machine including preparation, wiring and commissioning — the number the fleet quote is built on. | Observation and user interview | Financial |
| Restart and recovery behaviour | What happens after a power cut or network loss, and whether any counts are lost. | Sensor, meter or device data | Technical |
Before implementation, MSF and your team agree how each metric is calculated, where the baseline comes from, what data is excluded, and what result supports a rollout decision. This page lists what gets measured; the actual targets belong in the written PoC scope, not in a marketing claim.
Commercial terms, hardware ownership, travel, integration scope and any rollout credit are defined in the written PoC proposal. They are not the same for every product, and this page does not promise them.
This PoC validates capture on the machines in the pilot. Older machines vary enormously, so a result on three machines is an installation standard and a cost model for the fleet — it is not a guarantee that every remaining machine exposes an equivalent signal.
No. Smart I/O reads existing signals — cycle contacts, lamps, counters, sensor outputs — without changing machine control or touching any safety circuit. The tapping points are agreed with your own electrical owner before anything is wired.
That is a real outcome and it is better found in week two than in a rollout. The alternatives are then costed: an added sensor, camera-based counting, or an operator panel for manual reporting on that machine family.
Because the question is narrow and physical. It is not proving an MES — it is proving that these machines can produce trustworthy data and what connecting them costs. The MES PoC is the natural next step, and it usually reuses this installation.
By reconciling three independent sources across several shifts: the captured count, the machine’s own counter, and what the operator recorded. Agreement between all three is evidence; agreement between the system and itself is not.
Tell us the scope you have in mind and we will come back with a written PoC plan: what gets connected, what you provide, how success is measured and what the decision at the end looks like.