An aluminum alloy fusion welding back face fusion width detection method with a pseudo edge

Abstract

The invention provides an aluminum alloy fusion welding back face fusion width detection method with a pseudo edge. In the aluminum alloy fusion welding process, collecting a back welding seam image at the current moment; carrying out MEDIUM FILTERING and gray scale stretching, based on the corresponding relation between the minimum gray value point and the welding seam edge feature point; recognition of weld edge feature points is completed by searching a minimum gray value point; extracting edge characteristics of the back welding seam; Hough conversion is carried out; By means of the method, the problem that in the aluminum alloy fusion welding back fusion width real-time detection process, the pseudo edge interferes with a welding seam edge extraction algorithm is effectively solved, the extraction precision of the back welding seam edge characteristics is improved, and closed-loop control over the back fusion width can be achieved easily.

Description

technical field [0001] The invention belongs to the technical field of welding process detection and control, and in particular relates to a method for detecting the melting width of the back side of aluminum alloy fusion welding with false edges. Background technique [0002] As a lightweight material, aluminum alloy is widely used in aerospace, railway transportation, national defense and other fields due to its excellent physical properties such as corrosion resistance, low density, and high specific strength. In industrial production, fusion welding is mainly used to efficiently connect aluminum alloy components. However, when welding aluminum alloy components, it is often difficult to ensure the forming stability of the weld due to the influence of factors such as machining accuracy, tooling positioning deviation, and welding thermal deformation. In order to obtain high-quality welds with uniform penetration, online adjustment of welding process parameters can be used ...

AI Technical Summary

Problems solved by technology

However, the collected images of aluminum alloy backside welds often contain false edges. If the traditional first-order differential edge detection operator is used as the edge extraction method, it is often impossible to effectively distinguish the false edges from the real edges, resulting in a large gap in the backside weld width. Detection error affects the control accuracy of closed-loop control

Images