Anode spikes crisis have a major impact on current efficiency and can jeopardize smelter operation. All the time spent with a spike under an anode is a period where current is lost, and the longer the spike remains present, the bigger are the mid-term consequences on the reduction process. Consequently, detecting these spikes, and removing them from the pots as early as possible is a priority.
A new tool based on anode current live measurement, combined with machine learning, has been developed and tested. It is an efficient way of detecting many of these spikes, usually with a few days of anticipation. The tool development and the first results on industrial cells are presented.