About this Abstract |
Meeting |
2022 TMS Annual Meeting & Exhibition
|
Symposium
|
Electrode Technology for Aluminum Production
|
Presentation Title |
Machine Vision Sensor Based on Image Texture Analysis Applied to Industrial Anode Paste |
Author(s) |
Julien Lauzon-Gauthier, Carl Duchesne, Jayson Tessier |
On-Site Speaker (Planned) |
Julien Lauzon-Gauthier |
Abstract Scope |
The development of rapid and non-destructive measurement methods for green anode quality assessment during production is important for the industry. It would improve process agility and robustness to face increasing variability in the raw materials. A machine vision sensor using a combination of image texture methods was used for extracting relevant paste textural features which were used as inputs of a Partial Least Squares regression model trained on the process variables. Previous work on laboratory anodes demonstrated sensitivity to pitch demand and particle size distribution. This sensor was then tested in a paste plant to assess its responsiveness to the industrial variability. The sensor was found sensitive to the variations in pitch during optimization experiments. |
Proceedings Inclusion? |
Planned: Light Metals |