According to the Russian steelmaker, the two tools, a digital model dubbed Adelina and a deep learning algorithm dubbed Ruban, work in parallel at its Cherepovets facility.  

“Adelina controls the speed of the unit, and Ruban adjusts the speed to achieve optimal results. This partnership has made the production process more flexible and secure as the model and agent are able to adjust the speed of the unit every second and respond instantly to any unforeseen situation,” the company said. 

The Adelina model was introduced in 2019 and boosted productivity by 5%, the company said. 

“In March 2020, we produced a record volume of pickled metal at this unit — more than 130,000 tons. After introducing the Ruban agent, we recorded a further 1.5% increase in productivity, and we estimate that using the two technologies in parallel could provide more than 80,000 tons of additional metal each year. This is a remarkable increase for one of the most significant units in the production of flat-rolled products,” said Evgeny Vinogradov, chief executive of Severstal’s Russian steel division.  
You can read more about the effort here.