Feasibility study of a method for identification and classification of magnesium and aluminum with ME-XRT

The identification of magnesium and aluminum in scrap metal recycling has always been a difficult point. In this paper, a material identification method of multi-energy X-ray transmission (ME-XRT) based on photon counting detector (PCD) and machine learning algorithm was proposed and used to identify and classify magnesium and aluminum. This method includes three main steps: using PCD to obtain X-ray attenuation images of five energy bins, feature extraction, and the machine learning classification. The performance of several machine learning models was compared for the fine-grained classification task. The prediction results demonstrate that the best achieved recognition rates of aluminum and magnesium are 96.43% and 98.81%, respectively.

Automated summary

In this study, a method based on multi-energy X-ray transmission and machine learning was proposed for the accurate identification and classification of magnesium and aluminum in scrap metal recycling, achieving high recognition rates of 96.43% and 98.81% respectively.