Recycling automotive, electronic, and other end-of-life waste liberates large quantities of metals, which can be returned to the supply chain. Sorting the nonferrous metals, however, is not straightforward. Common methods range from laborious hand-sorting to expensive and environmentally deleterious wet processes. The goal is to move toward dry processes, such as induction sensors and vision systems, which can identify and sort nonferrous scrap efficiently and economically. In this paper, we present a new classification method using magnetic induction spectroscopy (MIS) to sort three high-value metals that make up the majority of the nonferrous fraction—copper, aluminum, and brass. Two approaches are investigated: the first uses MIS with a set of geometric features returned by a vision system, where metal fragments are matched to known test pieces from a training set. The second approach uses MIS only . A surprisingly effective classifier can be constructed by combining the MIS frequency components in a manner determined by how eddy currents circulate in the metal fragment. An average precision and recall (purity and recovery rate) of around 92% was shown. This has significant industrial relevance, as the MIS-only classifier is simple, scalable, and straightforward to implement on existing commercial sorting lines.

中文翻译：

---

使用磁感​​应光谱法对有色金属进行分类


回收汽车、电子产品和其他报废废物会释放大量金属，这些金属可以返回供应链。然而，对有色金属进行分类并不简单。常见的方法包括费力的手工分拣到昂贵且对环境有害的湿法工艺。目标是转向干法工艺，例如感应传感器和视觉系统，可以高效、经济地识别和分类有色金属废料。在本文中，我们提出了一种新的分类方法，使用磁感应光谱 (MIS) 对构成有色金属成分大部分的三种高价值金属——铜、铝和黄铜进行分类。研究了两种方法：第一种方法使用 MIS 和视觉系统返回的一组几何特征，其中金属碎片与训练集中的已知测试件进行匹配。第二种方法仅使用 MIS。通过以涡流在金属碎片中的循环方式确定的方式组合 MIS 频率分量，可以构建出令人惊讶的有效分类器。显示平均精确度和召回率（纯度和回收率）约为 92%。这具有重要的工业相关性，因为仅 MIS 的分类器简单、可扩展，并且可以直接在现有的商业分拣线上实施。