Discrimination of Disposable Vapes from Batteries Using the Magnetic Polarizability Tensor

Disposable vapes pose an environmental and fire hazard to waste streams when disposed of incorrectly. The lithium battery inside disposable vapes can produce an exothermic reaction when the lithium inside the battery is inadvertently exposed to air and moisture. New sensing technologies may be needed to screen waste streams for these vape hazards and this paper considers the potential of inductive techniques based on the magnetic polarisability tensor (MPT) representation. The MPT can be described by three complex components based on a target regardless of orientation. In this paper, the rank 2 MPT is measured and calculated for 10 vapes and 37 batteries for 28 logarithmically spaced frequencies from 119 Hz to 95.4 KHz. The 168 features of each object are reduced down to 2 features using principal component analysis (PCA) and linear discriminant analysis. The reduction of the features allows for the visualisation and grouping of the objects. Three clear groups of objects can be seen when the maximum feature scales the measurement and a two-component PCA transform is applied. The first group is the vapes, which are grouped away from the other batteries. The second is the batteries, which are grouped by size. Finally, zinc batteries are grouped away from the rest due to their case material.