About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Aluminum Reduction Technology
|
| Presentation Title |
Inferring Localized Current Patterns and Anodic Incidents Using Hall Sensors for Individual Anode Monitoring |
| Author(s) |
Samuel Duplessis, Julien Lauzon-Gauthier, Patrice Doiron, Marcel Guerreiro Neiro, Dany Gauthier |
| On-Site Speaker (Planned) |
Samuel Duplessis |
| Abstract Scope |
The integration of advanced sensor technology into Alcoa’s R&D pots has enabled real-time monitoring of individual anodes, replacing labor intensive manual voltage drop measurements. The contactless system continuously captures detailed data, allowing for proactive anode fault detection. By applying machine learning techniques, including pattern recognition and anomaly detection, we identified indicators of these various anode disturbance through different type of signals. By collecting data on multiple pots, time clustering revealed strong correlations between current distribution patterns and localized variations. Since direct Anode-Cathode Distance (ACD) measurement is impractical in industrial settings, we inferred ACD dynamics from individual anode signals, enabling localized tracking. To improve model robustness, we embedded constraints, combining domain expertise with data-driven insights. This hybrid approach significantly enhanced the precision and reliability to find impactful anodic problems such as spikes, deformations, burnoffs, and other irregularities enabling faster, more targeted and better responses than before. |
| Proceedings Inclusion? |
Planned: Light Metals |
| Keywords |
Aluminum, Process Technology, |