Lattice structure defect detection method and system based on super-resolution reconstruction

Abstract

The invention relates to a lattice structure defect detection method and system based on super-resolution reconstruction. The method comprises the following steps: acquiring a CT image of a lattice structure; utilizing an image super-resolution reconstruction module in the Faster R-CNN detection network model to perform feature extraction on the CT image to obtain a high-resolution feature image;performing defect detection on the high-resolution feature image by using a detection module in the Faster R-CNN detection network model to obtain defect parameters in the high-resolution feature image, wherein the defect parameters comprise defect types, defect positions and defect confidence coefficients, and wherein the defect types comprise breakpoint defects and adhesion defects; and mappingthe defect parameters to the CT image to obtain a defect identification result of the CT image. According to the invention, the accuracy of automatic defect identification can be improved.

Description

technical field [0001] The invention relates to the field of defect detection, in particular to a method and system for detecting defects in a lattice structure based on super-resolution reconstruction. Background technique [0002] Metal lattice structure material is a new type of multifunctional material, which is widely used in biomedicine, aerospace, automobile manufacturing and other industries. Additive manufacturing (AM) enables the fabrication of strong, lightweight structures with geometries unattainable by conventional manufacturing methods, including complex lattice structures. [0003] In 2011, Hao, L et al. used Selective Laser Melting (SLM) technology to successfully prepare a graphene honeycomb lattice structure with a unit size of 2mm to 8mm, which proved the high manufacturability of the lattice structure. However, in the process of preparing SLM lattice structures, due to factors such as laser power, molten pool temperature, and residual stress, the lattic...

AI Technical Summary

Problems solved by technology

However, when there are multiple types of defects in CT slice images with complex lattice structures, and the size of the defects is small, and the difference from the background is small, the detection effect of the algorithm is not ideal.

Images