Kane C. Williams

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.

Recycling aluminium is essential for a circular economy, reducing the energy required and greenhouse gas emissions compared to extraction from virgin ore. A ‘Twitch’ waste stream is a mix of shredded wrought and cast aluminium. Wrought must be separated before recycling to prevent contamination from the impurities present in the cast. In this paper, we demonstrate magnetic induction spectroscopy (MIS) to classify wrought from cast aluminium. MIS measures the scattering of an oscillating magnetic field to characterise a material. The conductivity difference between cast and wrought makes it a promising choice for MIS. We first show how wrought can be classified on a laboratory system with 89.66% recovery and 94.96% purity. We then implement the first industrial MIS material recovery solution for sorting Twitch, combining our sensors with a commercial-scale separator system. The industrial system did not reflect the laboratory results. The analysis found three areas of reduced performance: (1) metal pieces correctly classified by one sensor were misclassified by adjacent sensors that only captured part of the metal; (2) the metal surface facing the sensor can produce different classification results; and (3) the choice of machine learning algorithm is significant with artificial neural networks producing the best results on unseen data.

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.

The need to recover and recycle material towards building a circular economy is increasingly a global imperative. Non-ferrous metals in particular are highly recyclable and can be extracted using processes such as eddy current separation. However, their further separation into recyclable groups based on metal or alloy continues to pose a challenge. Recently, we proposed a new technique to discriminate between non-ferrous metals: Magnetic induction spectroscopy (MIS) measures how a metal fragment scatters an excitation magnetic field over different frequencies. MIS is related to conductivity, which can be used to classify the fragment according to this property. In this paper, we demonstrate for the first time the use of MIS with machine learning to classify non-ferrous scrap metals drawn from commercial waste streams. Two approaches are explored: (1) MIS over a bandwidth from 3 kHz to 90 kHz, and (2) the combination of MIS with physical colour of the metal samples. We show that MIS alone can obtain purity and recovery rates >80% for most metal groups and waste streams, rising to >93% for stainless steel. The exception was the Zorba waste stream where the mix of aluminium alloys within the sample set led to poor conductivity contrasts. The introduction of colour substantially improved results in this case, increasing purity and recovery rates by 20-35 percentage points. Of the machine learning models tested, we found that random forest, extra trees and support vector machine algorithms consistently achieved the highest performance.