<img height="1" width="1" style="display:none" src="https://www.facebook.com/tr?id=323483448267600&amp;ev=PageView&amp;noscript=1">

Solutions by industry / Food & beverage

Pistachio roasting on target humidity, 4× ROI in one year

Ireco, a leading pistachio producer, uses AI closed-loop automation to reach the target humidity in every batch with less energy, now on three roasters.

4×return on investment in the first year
−3%energy consumption
3 roastersrunning the same model, maintained centrally
Industry
Food & beverageRoasting
Focus
QualityEnergyReliability
With Wizata
Digital twinProcess optimisationEnergy efficiencyClosed-loop automation

The challenge

The right humidity, with the least energy

In roasting, the priority is to reach the target humidity in the end product, use the least energy to get there, and keep quality consistent.

The difficulty is that the raw product never arrives the same, and the energy needed to reach the right roast varies with it:

Variable raw-material humidityUnpredictable humidity lossEnergy consumptionMachinery reliability

The plan, in two steps

  1. Real-time set-point recommendation. A model calculates the optimal value of three set points from the raw material's characteristics, accounting for humidity lost during roasting and packing.
  2. Data-driven automation. After a period of open-loop recommendations for testing and fine-tuning, the model moves to AI closed-loop control of the roasting conditions.

Our approach

From one roaster's data to three roasters in closed loop

Wizata and Ireco's local experts worked side by side, with measurable ROI as the target from day one.

1Connect

A digital twin of the roaster

The Wizata platform, hosted in Ireco's own Azure tenant, ingests data from the roaster sensors, the raw material and the end product, organised in a digital twin built around the roaster.

2Recommend

Real-time set points

Process data is transformed and put in context. Machine-learning models from the platform produce real-time recommendations, with dashboards for each stakeholder.

3Automate

Closed loop, then replicated

Once validated in open loop, the model runs in closed loop and has been replicated to two more roasters.

The outcome

More output, less energy, stable quality

Return on investment 4×

The rise in annual production value quadrupled the initial investment in one year.

01

3% less energy

Lower operating costs, in line with Ireco's commitment to sustainable production.

02

Higher output

A consistent process and the right humidity raised annual production value.

03

Real-time response

Contextualised data lets the team react to incidents before quality drifts.

04

One model, every roaster

Models are maintained centrally, so a change reaches all roasters at once.

Built on the Wizata platform

Explore the platform →
Data HubEach roaster as a digital twin: sensors, raw material and end product.
AI LabSet-point models for three set points, maintained centrally for all roasters.
Control PanelDashboards for each stakeholder, recommendations, then closed loop.

Next step

Hit your target on every batch

You don't have to do it alone. Talk to one of our engineers, or spend one or two days with our team on your own data.

Your contact Philippe Maes pma@wizata.com +32 476 209 149