Abstract
Endoscope is an important method for defect detection of metal hose used in rocket engine. Due to the traditional endoscopic detection technology is dependent on manual and low detection efficiency, this paper introduces Ai Image recognition technology to detect inner surface defects of metal hose. Aiming at the problem that most of the defects on the inner wall of the bellows of metal hose are small in scale and easy to be misjudged, a method of post-processing and rechecking of the bellows defect detection model is proposed, it is used to strengthen the defect detection model of the inner wall of the bellows of the metal hose for rocket engine. In this paper, based on the block classification network, the defect detection of the captured image of bellows is carried out, and the defect detection results of n*n blocks are output, then the metal hose defects are classified by using the bi fine-grained classification network with small structure, and the final n*n multi-class detection results are obtained. The results show that the engine and model of Ai Algorithm reduce the rate of missed detection and false detection, and improve the reliability of endoscope detection.
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.
