• Otoole, Michael D.
• Williams, Kane C.
• Mallaburn, Michael
• Peyton, Antony J.

Abstract

Magnetic induction is widely used as a non-destructive technique to detect and classify metal objects over a range of applications. This paper applies magnetic induction spectroscopy (MIS) as a technique to classify non-ferrous metals within shredded metal waste streams on a moving conveyor. The magnetic response of the metal piece as it passes over the sensor is used to predict the metal, where the measured complex impedance components are used as features for the machine learning models. MIS performs well, even when surface contaminants are present, compared to other techniques that require the metal pieces to be cleaned; this saves time and reduces cost when large amounts of surface contamination are present in a waste stream, such as biomass incinerator metals. MIS allows for a lower cost system when compared to X-ray and sink-float methods with a high throughput, which makes it an economical approach.

Topics

• impedance spectroscopy
• surface
• machine learning