In steel production severe quality issues can occur during the coiling phase resulting in scrap and substantial downtime. Predicting such a rare event.% called cobble formation.% can be done with machine learning techniques. An AI system collects a range of production and process parameters and makes a risk assessment for each steel strip that is produced. The operator can act upon it to prevent cobbles. We want to take this a step further. Not only should the operator benefit from the skills of his or here "AI colleague" who is able to interpret hundreds of variables in a split second. The AI colleague should be able to learn from the operator who is much better at providing the specific context of such anomalies. Next time a strip will pass the risk assessment.% the AI system will be able to relate it to newly learned context. This way human and machine operate together and interact as normal colleagues would do. Not only will the AI system learn to perform better.% but this way.% knowledge will be preserved and passed on to speed up learning curves of less experienced co-workers. This use case will demonstrates the power of interacting with AI systems.
Registration is now open for SAS Innovate 2025 , our biggest and most exciting global event of the year! Join us in Orlando, FL, May 6-9. Sign up by Dec. 31 to get the 2024 rate of just $495. Register now!
