Skip to content
Service & spare partsEnergy & Utilities

Rate rotor blades and PV modules from drone images

AI maps drone and thermal images to blade or module string, detects erosion, cracks and hotspots and compares them with last year.

Today

One inspection flight produces thousands of images. Engineers click through them by hand, painstakingly assign damage to blade and position and look for last year's finding in old reports. By the time everything is sorted, some damage has grown and some warranty periods have expired.

An example

Wattaris is technical operations manager for a wind farm with twelve turbines in Lusatia. After the autumn flight there are 5,400 images. The agent assigns them to turbine, blade and radius, finds a trailing-edge crack on turbine 07, blade B, at 38 m that has grown by 40 cm since last year, and shows that the warranty for this blade ends in February. The operations manager confirms the finding and files it with the manufacturer.
Fictional company, typical workflow.

Your data, wherever it lives

Thousands of drone photos and thermal images sit on hard drives and in the service provider's folders, inspection reports as PDFs, turbines, string plans and maintenance in a database, monitoring data on the park server and warranty contracts in the ERP. demi reads, understands and links them, with your rights, per turbine, blade and module string. The AI sorts an inspection flight in hours instead of weeks, and your operations manager decides on repairs and claims.

Where the data lives today

  • Photos, video & audio
  • NAS & hard disks
  • Folders & drives
  • PDFs
  • Databases
  • Machines & sensors
  • ERP
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: image folders and hard drives, inspection reports, turbine and string layouts, monitoring and the ERP. demi replaces nothing and links every image to turbine, blade and position or to module row, string and inverter, together with earlier findings, repairs and contracts.

  2. 2 · PermitPermission Layer

    Each operator and investor sees only their own parks, and external repair teams only the findings in their work order. The technical operations manager approves warranty and insurance claims, and this is recorded.

  3. 3 · ActIntelligence Layer

    The agent assigns images by position, flight log and image data and proposes damage type and category from your damage catalogue, with the image detail and last year's comparison. It prioritises repairs by category, growth and deadline. A rating counts only once an engineer confirms it.

How it runs

  1. 1

    After the inspection flight, photos and thermal images arrive with position data.

  2. 2

    demi assigns every image to turbine, blade and position or to module row and string.

  3. 3

    The agent detects erosion, cracks, lightning damage and hotspots, proposes the category and compares with last year.

  4. 4

    It prioritises repairs and shows where a warranty period is running out.

  5. 5

    The operations manager confirms the findings, orders repairs and approves claims.

What changes

  • Inspection images evaluated faster

  • Damage no longer grows unnoticed

  • Warranty claims filed in time

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

+240 hfreed per year

Assumptions and calculation

demi assigns drone images to turbine and position and proposes damage with a category; you confirm.

5 h → 3 h per case

How does it run today?

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

How we calculate

10 inspections × 5 h × 40% × 1.0 (manual) × 12 months = 240 h

Value per year, before demi costs

Freed per year+240 h

Assumption: labour cost of €49.50 per hour in German manufacturing in 2025 (Destatis), plus workplace, IT and overheads.

= Value per year, before demi costs

+€15,600

gained per year

240 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

How does demi know which blade or module an image belongs to?

From GPS position, flight log and image data, matched against your park layout and string plans. Images that cannot be assigned clearly are flagged and put in front of you for review instead of being guessed.

Who sets the damage category for a rotor blade?

Your engineer. The agent proposes damage type and category from your damage catalogue and shows the image detail and last year's image side by side. Only confirmed findings go into reports and claims.

Does it also work with thermal images of solar parks?

Yes. For PV plants, demi assigns hotspots, failed substrings and broken glass from thermography, for example to IEC TS 62446-3, to module, string and inverter. The agent places the string's monitoring data alongside, so you can see whether the finding is already costing yield.

Does it help with warranty and insurance claims?

Yes. The agent links every finding to the supply contract, warranty and insurance and reminds you before deadlines expire. For the claim it compiles images, positions and history. Nothing is sent until the operations manager approves it.

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