To identify quality issues within the production and prevent defect products to be delivered to customers is critical for most manufacturing companies, and usually performed both within and at the end of each production section. In this paper we investigate the use of deep neural networks for performing automatic quality inspections based on image processing, with the aim of eliminating today’s manual inspection processes. A deep neural network is implemented on a real-world industrial case study and its performance is evaluated and analyzed when it comes to detecting quality problems in produced products. The results show that the network has an accuracy of 94.5% which is considered good in comparison to the 70-80% accuracy that a trained human inspector can achieve.
CC BY-NC-ND 4.0
Edited by Robert X. Gao, Kornel Ehmann
The authors would like to thank Jonsac AB for their support in the study and for allowing us to work in their facility. The authors also want to thank Vinnova for financing the VISION project through the strategic innovation program Produktion2030, within which this work has been undertaken.