Toward Automated Detection of Permanent Magnet Motors in WEEE Recycling Using Discriminative Transfer Learning

Rare Earth Elements (REEs) represent strategic and critical raw materials for the energy transition and must therefore be integrated into efficient and functional recycling processes. Their adoption in electric motors is rapidly expanding, raising significant challenges for end-of-life (EoL) management, starting from the collection phase. In this context, this work proposes the integration of an image-based classification framework within the Waste Electrical and Electronic Equipment (WEEE) recycling pipeline to selectively identify electric motors containing permanent magnets (PMs) and direct them toward dedicated recycling processes for rare earth recovery. The proposed methodology relies on a Discriminative Transfer Learning (DTL) approach based on a ResNeXt convolutional neural network (CNN), adapted to a proprietary and heterogeneous dataset of electric motors acquired in an industrial recycling facility. The objective is twofold: first, to identify motors containing PMs; second, to classify motors into construction categories according to their likelihood of incorporating PMs. Experimental results show promising performance in terms of PM-containing motor detection capability, establishing a robust foundation for the automated recovery of REEs at an industrial scale. Furthermore, the model’s generalization capabilities can be further enhanced through the expansion of collaborative datasets and the integration of advanced scanning technologies.