Case studies

Projects from production and energy

From mid-sized family businesses to corporate environments. Excerpts from our work on data foundations, analysis, automation and energy.

Companies in whose projects we have worked

Plastics processing

One data foundation for 40 injection moulding machines

Heterogeneous controllers connected over OPC UA and Modbus, historised as time series with shared semantics for ERP, maintenance and quality. Process and quality data now come from one source — a drift shows up while it can still be corrected. Reporting stopped being a separate task.

90%less scrap
40machines connected
1data model for all systems
0manual rework in reporting

Food industry

A palletising cell, calculated before the investment

Feasibility study in Visual Components, then a DOBOT palletising cell at the end of the line connected to the existing data foundation. Cycle time and layer pattern were proven before ordering.

3Dvalidated before ordering
24/7operation at end of line
OPC UAfeedback into the data foundation

Metalworking

Energy cost per order instead of per site

Energy data from meters and machines was joined with order data. Management sees unit cost including energy, production management sees load peaks in real time.

€/unitenergy in the unit cost
Real timeload peaks visible
NIS2evidence covered

Battery storage

A battery controlled from load profile, weather and market

An industrial storage system of 17 MWh alongside a PV array of 3 MWp peak. How it charges and discharges is not decided by rules of thumb but from three sources at once: the measured load profile, the weather forecast and exchange prices. We contributed on the data side — making sure those three line up in time and that the control logic runs on figures it can rely on.

17 MWhindustrial battery
3 MWpPV peak output
3data sources: load, weather, market
EWEgrid operator for the generating plant

Recycling

An AI camera in sorting: feasibility first, plant second

Whether an AI camera reliably tells apart what needs telling apart in a running material stream is not something a datasheet can answer. Using the Cognex starter kit for AI cameras, we tested it on real material before anyone decided on a plant. The result is a defensible statement of what this class of camera does in this application — and where its limit is.

Cognexstarter kit for AI cameras
Real materialtested on the running stream, not on samples
Up frontfeasibility before plant engineering

The project descriptions above deliberately carry no attribution to an individual customer. Reference contacts are shared on request during a call.

Partners and technologies we work with

Interested, but not ready to enquire?

An e-mail address is enough. We come back once with a short read on it — no newsletter.

Your details come straight to us and are used only to reply. More in our Privacy

Similar starting point?

Describe your production in a few lines. If we have had a comparable case, we will tell you what transfers — and what does not.

Book a conversation