This paper presents a Convolutional Neural Network-based image classification approach for industry 4.0-based manufacturing systems that automatically distinguishes between defective and non-defective electrical cable ends, which have a high impact on the reliability of the electric power infrastructure. Our model achieves an excellent balanced accuracy of 99.47 percent on completely unseen image data, setting a benchmark in detecting defective cable ends before being connected. Our work can be used for an automated camera-based 100 percent in-line inspection during production, contributing to a near-zero level of defect generation.
Breitenbach, Johannes; Gross, Jan; Baumgartl, Hermann; Ulrich, Patrick Sven; and Buettner, Ricardo, "Artificial Intelligence for Industry 4.0: Automated In-Line Quality Control of Electrical Cable Ends Based on Convolutional Neural Networks" (2022). PACIS 2022 Proceedings. 282.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.