Researchers from the College of Illinois Urbana-Champaign have developed a brand new technique for figuring out the supply of 3D printed components utilizing high-resolution images and deep studying. The method analyzes manufacturing fingerprints – distinctive bodily traits embedded in components throughout manufacturing – to find out which printer created a element. This know-how addresses vital challenges in manufacturing provide chains, the place monitoring components throughout a number of suppliers has historically been troublesome.
The examine examined this identification technique on 9,192 components produced from 21 completely different sources, utilizing three distinctive designs and 6 supplies. Researchers achieved over 98% accuracy in figuring out the supply printer. The system might additionally decide the manufacturing course of, materials sort, and particular location the place the half was printed inside the machine.
In contrast to earlier analysis that centered totally on consumer-grade desktop printers, this examine focused industrial additive manufacturing tools utilized in manufacturing environments. 4 forms of AM tools and 7 completely different printer fashions had been included within the testing. The method proved efficient throughout various supplies and half designs.
Conventional half identification strategies like labels, RFID tags, or laser engravings could be simply compromised or eliminated. By analyzing inherent bodily attributes created throughout manufacturing, this deep studying method presents a safer various. The system can establish patterns which might be undetectable to human inspectors.
Manufacturing supply identification has vital functions for high quality management, defect identification, provide chain administration, and authenticity verification. This turns into significantly invaluable in additive manufacturing, the place distributed provide chains pose distinctive challenges. The know-how gives a brand new device for validating supplies, processes, and accomplished components in advanced manufacturing networks.
Supply: nature.com