MiLTOn: Sensing Product Integrity without Opening the Box using Non-Invasive Acoustic Vibrometry

MiLTOn: Sensing Product Integrity without Opening the Box using Non-Invasive Acoustic Vibrometry
复制标题

DOI:
10.1109/ipsn54338.2022.00038
复制
发表时间:
2022-05
期刊:
2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)
影响因子:
--
通讯作者:
Akshay Gadre;Deepak Vasisht;N. Raghuvanshi;B. Priyantha;Manikanta Kotaru;Swarun Kumar;Ranveer Chandra
Akshay Gadre;Deepak Vasisht;N. Raghuvanshi;B. Priyantha;Manikanta Kotaru;Swarun Kumar;Ranveer Chandra
中科院分区:
其他
文献类型:
--
作者:
Akshay Gadre;Deepak Vasisht;N. Raghuvanshi;B. Priyantha;Manikanta Kotaru;Swarun Kumar;Ranveer Chandra

文献摘要

相似文献

本文提出以下问题:“我们能在不打开包装的情况下检测出由瓷器或玻璃制成的易碎产品在沿着供应链运输时是否受损吗?”我们提出这个问题的背景下,数十亿美元的全球供应链行业的脆弱产品,经历了巨大的管理费用,由于产品退货。本文介绍了米尔顿,这是一种新型的基于声波和毫米波的解决方案,用于通过盒子的非侵入式产品完整性检测,对物体中即使是微小的亚毫米裂缝也很敏感。米尔顿的灵感来自声学振动测量法,例如用于监测铁路裂缝。与传统的振动测量不同,MiL-TOn的独特之处在于它能够使用外部传感器和麦克风非侵入性地检测产品,两者都不直接接触箱内的物体。米尔顿处理来自麦克风的测量结果,以设计一个稳健且与环境无关的产品签名,可用于检测产品缺陷的存在。我们对大量不同材料的易碎产品进行了广泛的评估,结果表明,在识别产品损坏方面的准确率达到97%。
This paper asks: “Can we detect whether a fragile product, made of porcelain or glass is damaged as it travels along the supply chain, without opening its packaging?” We ask this question in the context of the multi-billion dollar global supply chain industry of fragile products that experience large overheads due to product returns. This paper presents MiLTOn, a novel acoustic and mm-wave based solution for through-box non-invasive product integrity sensing that is sensitive to even minute sub-mm cracks in the object. MiLTOn is inspired by acoustic vibrometry used for instance to monitor cracks in railroads. Unlike traditional vibrometry, MiL-TOn is unique in its ability to sense products non-invasively using an external transducer and microphone, neither of which are in direct physical contact of the object within the box. MiLTOn pro-cesses measurements from the microphone to design a robust and environment-independent product signature that can be used to sense presence of product defects. Our extensive evaluation on a large number of fragile products of diverse materials demonstrates 97% accuracy in identifying product damage.