20.500.12556/DKUM-95864 A machine vision approach to assessing steel properties through spark imaging Accurate and efficient evaluation of steel properties is crucial for modern manufacturing. This study presents a novel approach that combines spark imaging and deep learning to predict carbon content in steel. By capturing and analyzing sparks generated during grinding, the method offers a fast and cost-effective alternative to conventional testing. Using convolutional neural networks (CNNs), the proposed models demonstrate high reliability and adaptability across different steel types. Among the tested architectures, MobileNet-v2 achieved the best performance, balancing accuracy and computational efficiency. The findings highlight the potential of machine vision and artificial intelligence in non-destructive steel analysis, providing rapid and precise insights for industrial applications. carbon content prediction convolutional neural networks deep learning machine vision spark imaging steel analysis napoved vsebnosti ogljika konvolucijske nevronske mreže globoko učenje strojni vid analiza jekla true false true Hrčak srce Angleški jezik Slovenski jezik https://hrcak.srce.hr/330646 Članek v reviji 2025-11-03 12:09:31 2025-11-03 12:09:31 2025-11-04 03:34:50 0000-00-00 00:00:00 2025 0 0 str. 77-81 no. 1, [article no.] 330646 Vol. 19 2025 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 2025-06-01 004.8:669.1 248815619 10.31803/tg-20250327093142 1848-5588 tj_19_2025_si1_77-81.pdf tj_19_2025_si1_77-81.pdf 1 43D4B20D73A8033F872817FE0D093072 338bcfa8d11b2e2eb77123d757ad99e9869ac3fe7883fa23edb8c92180104caa 275f4c05-b8a6-11f0-b13b-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=200343 https://hrcak.srce.hr/330646 0 30ec66d9-b8a6-11f0-b13b-00155d000105 https://dk.um.si/Dokument.php?lang=slv&id=200344 Fakulteta za strojništvo 0 0 0