{"id":2904,"date":"2026-06-23T10:51:07","date_gmt":"2026-06-23T10:51:07","guid":{"rendered":"https:\/\/artelnics.com\/case_studies\/celsa-rolling-mill-predictive-maintenance\/"},"modified":"2026-08-21T20:20:21","modified_gmt":"2026-08-21T20:20:21","slug":"celsa-rolling-mill-predictive-maintenance","status":"publish","type":"case_studies","link":"https:\/\/artelnics.com\/case_studies\/celsa-rolling-mill-predictive-maintenance\/","title":{"rendered":"Predictive maintenance in a rolling mill"},"content":{"rendered":"
\n
\n

Health indicators and anomaly detection models help detect abnormal behavior in rolling equipment before it turns into downtime.<\/p>\n

\n Steel manufacturing<\/span>
\n Anomaly detection<\/span>
\n Predictive maintenance<\/span>\n <\/div>\n

Challenge<\/h2>\n

Rolling mills generate many process signals across campaigns, products and routes. Maintenance teams need to know when equipment behavior deviates from normal operation.<\/p>\n

Data<\/h2>\n

Historical campaigns were grouped by product and route, using process variables such as speed, torque, tension, RPM and load indicators.<\/p>\n

Solution<\/h2>\n

Artelnics combined statistical ranges with auto-associative neural networks to calculate health indicators and detect deviations in real time.<\/p>\n

\n
Method<\/strong><\/p>\n

Auto-associative neural networks and statistical baselines.<\/p>\n<\/div>\n

Output<\/strong><\/p>\n

Deviation indicators and alarms by equipment context.<\/p>\n<\/div>\n<\/div>\n

Results<\/h2>\n

The solution supports proactive maintenance by highlighting when process behavior moves outside expected operating patterns.<\/p>\n

Illustrations<\/h2>\n
\"Deviation
Rolling mill deviation chart<\/figcaption><\/figure>\n<\/article>\n