SolutionsIndustriesTechnologiesR&DProjectsAboutBlog  Robotics Integration  Industrial Automation  Mechanical Engineering  AI for Manufacturing  Digital Twin  Machine Vision  Physical AI  Factory AutomationCareersContactTalk to an engineer

Your industrial AI project will be decided by the data contract, not the model

We have assessed a substantial number of manufacturing AI proposals. The ones that failed rarely failed at modelling. They failed because the data required to answer the question was never recorded, was recorded inconsistently, or could not be joined to an outcome.

The three questions that decide feasibility

Before any discussion of architecture, three questions determine whether a project is viable. They can usually be answered in a week.

  • Is the outcome labelled? To predict scrap you need historical records of which units were scrapped, joined to the process conditions that produced them. Shift-summary scrap counts without unit-level linkage cannot train anything.
  • Are timestamps synchronised? If the PLC historian, the vision system and the quality database disagree by even a few seconds, correlation across them is noise. Clock discipline is unglamorous and decisive.
  • Does the data span the variation you care about? Twelve months of data from a process that only ran one product, one tool and one season will not generalise to the conditions you actually want it to handle.

The failure mode nobody plans for

The most common blocker is not missing data. It is a tag namespace that changed. Somebody renamed tags during a controller upgrade eighteen months ago, and the historian now contains two incompatible naming schemes with no mapping. Reconstructing that mapping is archaeology, and it is frequently the largest single line item in a first industrial AI project.

This is why we start every engagement with a data readiness assessment rather than a model proposal. It is a small, cheap piece of work, and it either de-risks the project or saves you the entire budget.

A readiness checklist

DimensionMinimum viableComfortable
History lengthCovers 3+ cycles of the phenomenon12+ months across conditions
Sample rateFaster than the dynamics of interest10× the dynamics of interest
Label qualityUnit-level outcome, consistently appliedLabelled with reviewer agreement measured
Time syncAll sources within 1 secondPTP or NTP disciplined, sub-100 ms
Join keyA unit or batch identifier that survives across systemsFull genealogy from raw material to shipment
CoverageIncludes failure cases, not only normal operationFailure cases across multiple root causes

Start narrow

The instinct to build a plant-wide data platform before proving anything is the single most reliable way to spend a large budget and show nothing after a year. One machine, one clearly defined outcome, one measurable baseline. Prove the value, then generalise the infrastructure to serve a use case that has already earned it.

Always measure against the incumbent

Every model must be compared to what it replaces: the experienced operator, the SPC rule, the fixed maintenance interval. Surprisingly often the incumbent wins, and finding that out in week six is a good outcome — it is the cheapest possible result. A team unwilling to run that comparison is not doing engineering.

L0 · SENSORS, DRIVES, ROBOTS, SAFETY I/O L1 · PLC / MOTION / SAFETY CONTROLLER — PROFINET, EtherCAT L2 · EDGE COMPUTE — VISION, ROS 2, JETSON, OPC UA L3 · DIGITAL TWIN + AI SERVICES — OMNIVERSE, MODEL SERVING L4 · MES / ERP / HISTORIAN / CLOUD ANALYTICS DETERMINISTIC ↑ CONTEXTUAL
FIG. — Data path from field to modelSHEET RL-500 · REV B

Talk to us about this

If this is relevant to a line you are working on, our engineers are happy to look at the specifics. Related capability: AI for Manufacturing. You can also browse delivered projects, the technology stack or contact the engineering team.

Next step

Ready to scope your next automation programme?

Send us a drawing, a cycle-time target or a line layout. Our engineers respond with a technical assessment — not a brochure.