Eramet

Success story

Eramet is one of the world’s leading metal alloy producers. The Eramet plant in Knivesdal, Norway, produces silicomanganese alloys.

Challenge

When manufacturing processes are optimized, premium raw materials can be replaced with less-expensive alternatives without affecting product quality. Eramet turned to Probayes for a real-time solution capable of detecting exactly when to switch out the more expensive raw material for the cheaper one and of generating recommendations for when to switch back in the event of drift.

The project

We applied an unsupervised classification algorithm to dozens of process variables to discern the different process operating behaviors. We then had Eramet process experts annotate the behaviors and trained a classifier to recognize them. Finally, we added an explainability module that generates, in real time, the parameters that characterize non-optimal behaviors.

Results

A family of several typical process behaviors was identified; these behaviors were annotated by Eramet process experts. The characteristics of the optimal process and of non-optimal behaviors were clearly described, allowing operators to operate the furnace at the Kvinesdal, Norway plant more efficiently.

“Lorem ipsum dolor sit amet, consectetur adipiscing elit. Fusce eu lacus diam. Cras congue, neque ac mattis efficitur, nibh ipsum fringilla nunc, sed iaculis neque odio non orci. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia Curae; Praesent lacinia, urna quis rhoncus lobortis, urna neque tempus tellus, quis auctor justo lectus vitae libero. Nulla non porta odio. Donec diam est, varius id ullamcorper a, efficitur nec libero”