Abstract
In all industries, an important characteristic of product quality is the integrity of the structure and the absence of mechanical damage, which determines the relevance of the development of flaw detection methods that meet the requirements for the safety and reliability of products. The article presents the results of experimental studies of surface flaw detection of metal cylindrical products by the optical method using a convolutional neural network algorithm, presents the advantages of the method and selects the optimal confidence threshold, which is a compromise between accuracy and completeness of defect prediction, and also validates the operation of the system with defects located at different angles relative to the axis of the product.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
