arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.17642cs.LG
收藏

A.R.I.S.:基于深度学习的电子废弃物分类自动回收识别系统

A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning

Apple(苹果公司)

Dhruv Talwar, Harsh Desai, Wendong Yin, Goutam Mohanty, Rafael Reveles

AI总结:

A.R.I.S.通过深度学习实现电子废弃物的高效自动分拣,提升材料回收效率并降低先进回收技术的门槛。

摘要:

传统电子回收过程由于材料分离和识别能力不足,导致资源损失严重,限制了材料回收效率。我们提出了A.R.I.S.(自动回收识别系统),一种低成本、便携式的碎屑电子废弃物分拣器,以解决这一效率缺口。该系统采用YOLOx模型对金属、塑料和电路板进行实时分类,实现低推理延迟和高检测精度。实验评估显示整体精度达90%,平均平均精度(mAP)为82.2%,分拣纯度为84%。通过将深度学习与现有分拣方法结合,A.R.I.S.提高了材料回收效率,降低了先进回收技术的采用门槛。本工作补充了延长产品生命周期、支持以旧换新和回收计划以及减少供应链环境影响的更广泛努力。

英文摘要:

Traditional electronic recycling processes suffer from significant resource loss due to inadequate material separation and identification capabilities, limiting material recovery. We present A.R.I.S. (Automated Recycling Identification System), a low-cost, portable sorter for shredded e-waste that addresses this efficiency gap. The system employs a YOLOx model to classify metals, plastics, and circuit boards in real time, achieving low inference latency with high detection accuracy. Experimental evaluation yielded 90% overall precision, 82.2% mean average precision (mAP), and 84% sortation purity. By integrating deep learning with established sorting methods, A.R.I.S. enhances material recovery efficiency and lowers barriers to advanced recycling adoption. This work complements broader initiatives in extending product life cycles, supporting trade-in and recycling programs, and reducing environmental impact across the supply chain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑