This website uses cookies primarily for visitor analytics. Certain pages will ask you to fill in contact details to receive additional information. On these pages you have the option of having the site log your details for future visits. Indicating you want the site to remember your details will place a cookie on your device. To view our full cookie policy, please click here. You can also view it at any time by going to our Contact Us page.

Close

The AI advantage for cheese production

23 October 2023

Find out how AI technology has helped a cheese producer optimise its yields using real-time data to rapidly detect process variations due to varying milk quality.

Headquartered in the Netherlands, Amalthea is a producer of goats cheese. It receives milk from around 50 farmers who make up the Amalthea Cooperative of Goat Farmers. 

One of the biggest challenges for dairy manufacturers is that milk composition varies across farms and seasons, meaning there is no standard recipe that can be applied across all milk batches to achieve consistent quality and yield. Close monitoring and steering of the cheese production process is therefore required to create standardised cheese consistency to maximise yield potential.

For each of its cheese batches, Amalthea traditionally would set a target yield based on the practical or past knowledge of production. When a cheese batch deviated from the target yield or the right target yield wasn’t set, factory operators had to take action and make changes to production to make the process more efficient. Production issues were identified by manually processing data and analysing it on a weekly basis. With approximately 240,000 litres of milk processed each day, it was not optimal to wait a week or sometimes a month to get insights and make necessary system changes to optimise yield.

“We had to do these milk yield calculations manually, and we were only able to do this once per week, or sometimes once a month, so it was too late,” explained Joris Aarts, Chief Financial Officer at Amalthea. “On top of that, we weren’t able to calculate the yields per batch. This meant we could improve milk yield somewhat, but not enough.”

In 2020, Amalthea modernised its ERP with Infor CloudSuite Food & Beverage, utilising Infor’s cloud technology platform to solve its critical milk yield problem. This was previously hard to tackle because of outdated and disconnected applications, data silos and lack of time and resources. The modernisation – including the implementation of AI technology supplied by Infor – formed the building blocks to create AI-driven applications quickly and efficiently. Amalthea’s AI-driven yield deviation detection and explanation, a solution implemented in less than 90 days, is now fully automated – from data collection and processing to presentation.

Milk utilisation
“Infor has a process catalogue specifically designed for dairy, and it can give us good insights into milk utilisation and yields,” continued Joris. “This utilisation of milk is the most important way in which we can manage costs, so Infor has already helped us save money with that. Now, AI implemented, we can stretch that even further because we have more real-time data and information about this milk yield. We can see the yields per cheese batch in real time as well as direct insight into what factors are causing a higher or lower milk yield, meaning operators can take direct action. This helps us to make our cheese production as stable and predictable as possible, in terms of quality and yield.”

For every 1% increase in yields, Amalthea expects to save approximately 500,000 euros, which it can reinvest to further develop the business. There are plans to significantly increase its manufacturing capacity in five years to meet the high demand for more cheese types and innovative solutions.  According to Joris, having the business now fully running in the cloud provides a strong foundation for this future growth, as data insights continue to play an increasingly important role in dairy production.


Contact Details and Archive...

Print this page | E-mail this page