Abstract: Magnetic field components measured around and along a remelting furnace and other measured furnace parameters are used to estimate concentricity of the electrode within the crucible of the furnace, to estimate a distribution of drip shorts across a gap between the electrode and the melt pool, or to detect, locate, and categorize anomalous events during the remelting process. Those can be used to control the operation of the furnace during the remelting process, or incorporated into a longitudinal or three-dimensional map of the resulting ingot. Artificial intelligence, machine learning, or a neural network can be employed.