Machine vision cutting method applied to laser cutting machine

Abstract

The invention discloses a machine vision cutting method applied to a laser cutting machine. The machine vision cutting method comprises an image distortion correction module, an image contour recognition module, a parameter optimization module based on supervised machine learning and a cutting path generation module; the image distortion correction module processes an acquired image to obtain an original image; the image contour recognition module performs contour recognition on the original image; the cutting path generation module generates a cutting path of the laser cutting machine according to a contour recognition result; and the parameter optimization module based on the supervised machine learning optimizes the image contour recognition module, so that the recognition contour extraction of the image contour recognition module is more accurate. The method of the invention has the advantages of being easy to operate, high in recognition precision, high in recognition speed and the like, can be adapted to a complex production environment, and improves the generality of the laser cutting machine.

Description

technical field [0001] The invention relates to the fields of machine vision and machine learning, in particular to a machine vision cutting method applied to a laser cutting machine. Background technique [0002] With the continuous update of production technology, the traditional laser cutting machine based on fixed pattern cutting is increasingly unable to meet the existing production needs. Existing laser cutting machines based on machine vision generally have the problems of matching with preset graphics, low recognition accuracy, strict requirements for recognizing ambient light sources, and complicated operations. The invention combines machine vision and machine learning technology to propose a new machine vision method applied to laser cutting machines. [0003] The present invention can realize accurate image contour recognition for materials with arbitrary patterns without preset graphics, generate cutting paths, and complete cutting of material patterns. Using ...

AI Technical Summary

Problems solved by technology

[0002] With the continuous update of production technology, the traditional laser cutting machine based on fixed pattern cutting is increasingly unable to meet the existing production needs

Existing laser cutting machines based on machine vision generally have the problems of matching with preset graphics, low recognition accuracy, strict requirements for recognizing ambient light sources, and complicated operations

Images