Skip to content
Quality, standards & compliancePumps & ValvesElectronics & SensorsMachinery & Plant EngineeringTool & Mold Making+3

Check nameplate and safety labels by photo

A photo of each plate and label is enough: demi checks them against order, declaration and risk assessment.

Today

At final inspection someone looks at the nameplate and the safety labels and ticks a checklist. Whether serial number, year of manufacture and electrical ratings really match the order, and whether every warning label is in the right language in its place, is rarely checked against the documents. The errors are then found by the customer, the installer at commissioning or the market surveillance authority.

An example

At Conveyra Fördertechnik two BK 10 t bridge cranes with an 18 m span are in final inspection; one is going to Lyon. The inspector photographs nameplate and safety labels. demi reports three deviations: the serial number belongs to the sister crane, the plate shows last year as the year of manufacture, and the supplementary sign to the suspended-load warning is in German instead of French. After the swap the inspector takes new photos, and quality assurance releases the crane.
Fictional company, typical workflow.

Your data, wherever it lives

Today the target values are scattered: the order and voltage variant in the ERP, the nameplate template in the PLM, the declaration of conformity and risk assessment as PDFs in the DMS, the inspection photos in a chat or on the inspector's phone. demi reads and understands all of it, links it via the serial number and keeps your access rights. The AI then compares each photo with every target value in seconds, and quality assurance decides whether the machine may ship.

Where the data lives today

  • Photos, video & audio
  • ERP
  • PLM
  • DMS & archive
  • PDFs
  • Chats
Data LayerOne view of everything, with your rights

How demi solves it

Three layers in this order: connect the data first, then the rights, then the AI.

  1. 1 · ConnectData Layer

    Data sources in this case: photos from final inspection, the ERP, PLM and DMS. demi replaces nothing and links each photo, via the serial number, to the order, the nameplate template, the declaration of conformity and the machine's risk assessment. So next to every label sits what it must say and where that target value comes from.

  2. 2 · PermitPermission Layer

    Any inspector can upload photos, only quality assurance can release; the agent can never release a machine itself. Photos, deviations and the decision are recorded in the machine's log with date and inspector.

  3. 3 · ActIntelligence Layer

    The agent reads text, numbers and marks from the photos, recognizes pictograms and compares everything exactly with the target values from order, declaration and risk assessment. It shows each deviation right on the photo, with target value and source. If a photo is blurred or a label is not visible, it asks for a new photo instead of guessing.

How it runs

  1. 1

    At final inspection you photograph the nameplate and safety labels with a phone or tablet.

  2. 2

    demi assigns the photos to the machine and its order via the serial number.

  3. 3

    The agent reads every field and pictogram and compares it with order, declaration and risk assessment.

  4. 4

    You see the deviations marked on the photo, each with target value and source.

  5. 5

    Quality assurance releases the machine, and the photos go into its file as evidence.

What changes

  • Wrong nameplates are caught in the plant, not at the customer

  • Every warning label in the right language and place

  • Photo evidence per machine for customers and authorities

What does it bring you?

Check it with your own numbers

Every starting value is an assumption you can change. The calculation sits right below, step by step.

Assumption, editable

Your numbers

Result

+96 hfreed per year

Assumptions and calculation

demi checks the nameplate and label photos against order and file; you release the machine.

20 min → 12 min per case

How does it run today?

What is already digital saves less: the factor lowers the share demi brings.

How we calculate

60 machines × 20 min × 40% × 1.0 (manual) × 12 months = 5,760 min = 96 h

Value per year, before demi costs

Freed per year+96 h

Assumption: labor cost of $48.62 per hour in US manufacturing in June 2026 (BLS), plus workplace, IT and overhead.

= Value per year, before demi costs

+$6,240

gained per year

96 h ÷ 1,760 h per role = 0.1 full-time roles

An estimate, not a promise. The starting values are assumptions for an industrial company with 150 to 500 people.

Combine with more cases and get the package

Questions about this use case

Which photos does demi need for the check?

One photo of the nameplate and one of each safety label, taken with a phone or tablet. From the risk assessment the agent knows which labels belong where on this machine and asks for them photo by photo. If a photo is blurred or reflects, it asks for a new one.

How does demi know what the nameplate must say?

From your own documents: serial number, variant and electrical ratings from the order in the ERP, the layout from the nameplate template in the PLM, marks and directives from the declaration of conformity. Every target value shows its source. If two sources contradict each other, the agent flags it instead of picking one.

Does demi also check the language of the warning labels?

Yes. From the order the agent knows the country of destination and so the language required there on labels. Text in the wrong language appears as a deviation on the list. Pictograms are compared with what the risk assessment specifies.

Who releases the machine in the end?

Quality assurance. The agent checks and marks, it can never release anything itself. Photos, deviations and the decision go into the machine's file with date and inspector. If a customer or an authority asks later, you can show how the machine left the plant.

See this case with your data

In the demo we show you the workflow on your own systems.

Your configurator

No use cases yet

Your configurator is still empty

Add a use case from any card or case page and see what it brings per year, with the calculation. Free, no sign-up, no commitment: try it out and change any number.

Browse use cases