Improving efficiency with AI-based smart data management in the food industry

Resource efficiency and maximizing uptime are also top priorities for food manufacturers. This recognition gave birth to the S3FOOD project, in the framework of which we are currently carrying out efficiency development for GoodMills Magyarország Malomipari Kft., together with REACH Solutions Kft. As companies experienced in automotive automation, we are proud to be able to utilize our i4.0 knowledge in the field of the agrifood sector.
 
Áron Pétervári, the Hungarian technical director of the well-known milling group, Goodmills, is aware that his industry still works with many traditional elements. He relized his company is in particular need of innovation, which allows them to work more efficiently and with less and less losses. Robot-X and REACH set out to increase efficiency and explore losses at the plant, when they joined the European Union’s S3Food project. 
 

--- 
Hatékonyságfejlesztés a komáromi malombanHatékonyságfejlesztés a komáromi malomban
Touch screen allows for operator interaction at Goodmills Komárom mill
 

---
The collaboration between Reach and Robot-X has a long history. The two companies may have several successful projects behind them in other industries. In this project, Robot-X’s extensive automation-robotization expertise and Reach’s software technology solutions made it possible to bring the entire spectrum into one hand, from data collection to visualization.
 
The cornerstone of the production digitization development in Komárom was data collection, the quality of which - in terms of both quantity and quality - increased significantly during the project. In the initial phase, a data collection layer was developed to transmit machine information to a database capable of handling large amounts of data. We then installed a touch display that enables operator interaction. The mill has also been enriched with a large display at the packaging line. As a result, current efficiency information on the line is immediately visible and accessible to both plant management and employees.
 
With the help of machine learning, by modeling the production line conditions, we are able to identify several forecasts and problems. In the same way, we can examine, predict and optimize performance.
 
The still ongoing project will finish in May 2021. The goal is to increase the mill’s previous OEE by 5% through more organized maintenance and downtime forecasting. In addition, our goal is for our system to be able to increase actual production time by 7,7% per shift, while reducing energy consumption by 4% and packaging waste by 8%.
 
---
OEE-improvement in agrifood

---