Abstract:
Waste management and the economy are intertwined in various ways. Adopting sustainable waste management techniques can contribute to economic growth and resource conservation. Artificial intelligence (AI)-based classification is very crucial for rapid and contactless classification of metals in electronic waste (e-waste) management. In the present research work, five types of aluminium alloys, because of their extensive use in structural, electrical and thermotechnical functions in the electronics industry, were taken. Laser-induced breakdown spectroscopy (LIBS), a spectral identifier technique, was employed in conjunction with machine learning (ML) classification models of AI. Principal component analysis (PCA), an unsupervised ML classifier, was found incapable to differentiate LIBS data of alloys. Supervised ML classifier was then trained (for 10-fold cross-validation) on randomly selected 80% and tested on 20% spectral data of each alloy to assess classification capacity of each. In most of the tested variants of K nearest neighbour (kNN) the resulting accuracy was lower than 30% but kNN ensembled with random subspace method showed improved accuracy up to 98%. This study revealed that an AI-based LIBS system can classify e-waste alloys rather effectively in a non-contactless mode and could potentially be connected with robotic systems, hence, minimizing manual labour.
摘要:
废物管理和经济以各种方式交织在一起。采用可持续的废物管理技术可以促进经济增长和资源保护。基于人工智能(AI)的分类对于电子废物(电子废物)管理中金属的快速和非接触式分类至关重要。在目前的研究工作中,五种铝合金,由于它们在结构上的广泛使用,电子工业中的电气和热技术功能,被带走了。激光诱导击穿光谱(LIBS),光谱识别技术,与人工智能的机器学习(ML)分类模型结合使用。主成分分析(PCA),无监督ML分类器,被发现无法区分合金的LIBS数据。然后在随机选择的80%上训练受监督的ML分类器(用于10倍交叉验证),并在每种合金的20%光谱数据上测试以评估每种合金的分类能力。在大多数测试的K最近邻(kNN)变体中,所得精度低于30%,但与随机子空间方法结合的kNN显示出提高的精度高达98%。这项研究表明,基于AI的LIBS系统可以在非非接触式模式下对电子废物合金进行相当有效的分类,并且可能与机器人系统连接。因此,尽量减少体力劳动。