Hot Strip Mill, Indiana, USA

Location: Hot rolling mill at a large Fortune 500 steel company in Indiana

Challenge: Cobbles during hot rolling steel create unplanned downtime, which is expensive and a safety hazard at a large steel manufacturer in the U.S.

Solution: Argus created a predictive machine learning model that can predict cobbles before they happen reducing unplanned downtime. Argus team worked with the client team to scrub and prep historical data from the iBA database. Using ArgusStudio the team detected hidden patterns that identified variables that could be pre-cursors to cobbles. Appropriate Machine Learning algorithms were selected and trained on the data set using ArgusStudio libraries. The team is using ArgusFiretail to validate the prediction model on live data.