A visual identification method with position recovering and contour comparison for highly similar non-planar aviation angle pieces

Abstract

The assembly quality of angle-piece connectors in aviation equipment significantly affects its structural stability and flight safety. In the production environment, there are many highly similar angle pieces mixed together, making it difficult for workers to distinguish them. Additionally, the complex non-planar structure of the angle pieces and the extremely small differences between them render conventional identification methods ineffective. This paper proposes a new visual identification method for highly similar non-planar aviation angle pieces based on position recovering and contour comparison. Our method integrates overhead and side-view information, effectively separating non-planar regions in angle piece images and accurately extracting the characteristic contours of planar regions. By using the fillet features of the angle pieces for position recognition and adjustment, the method addresses the issue of difficult position recovering of small-sized angle pieces, achieving precise identification of their types. The results indicate that for 30 types of highly similar angle pieces with minimum dimension differences of 0.1 mm and minimum angle variances of 0.1 degrees, the method proposed achieves a position recovering error of less than 1 % and a correct identification rate of 94.33 %. This demonstrates practical significance for the automation of angle pieces production in aviation equipment.