Optimizing dynamic capacity master data based on internal & external factors


One of Europe’s largest privately held food processing companies.

Active in processing agricultural raw materials into sugar, alcohol and starch. Its final products are distributed towards food, animal food, pharmaceutical, paper & carton industry.

The sugar(-related) industries are facing one of the largest market transformations ever as a result of changing European regulations. As a result, optimizing and aligning the supply chain with the opportunities & threats ahead to remain competitive in a new and reformed market will be crucial more than ever.


To optimize the use of the current assets, the customer aimed for an accurate and forward looking view of the capacity of their production lines.

Two years of history from +500 sensors per line and external weather data were used as data input.

Combining this data with LOP’s machine learning models enabled them to build a predictive capacity model.

By getting insights in the influencing factors of the capacity, they are now able to identify improvement actions to further increase the available capacity.

  • Create a virtual twin

  • Get end-to-end visibility

  • Set smart parameters

  • Optimize end-to-end financials

  • Monitor the control tower


Increased asset throughput

Reduced energy use & cost

Accurate parameters for IBP & MPS planning

Increased yield accuracy: 49,9% _> 50,2%

Increased capacity: 262 TDS/dy -> 282 TDS/dy

Want to know more?

Get in touch!