A plate cutting and slagging morphology self-adaptive quantization method, device, equipment and medium

CN122243935APending Publication Date: 2026-06-19BEIHANG UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
BEIHANG UNIV
Filing Date
2026-03-18
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing technologies struggle to accurately quantify the morphology of slag deposits during sheet cutting, especially in the case of thermal deformation of the sheet and scanning noise interference, which lead to measurement inaccuracies and insufficient quantification of continuous characteristics.

Method used

A multi-stage benchmark reconstruction method based on 3D point cloud data is adopted, including panoramic height field matrix construction, nonlinear benchmark difference reconstruction, bidirectional manifold competition separation, and topological connectivity analysis, to achieve adaptive quantization of slag hanging height.

Benefits of technology

It achieves high-precision quantification of the slag morphology of cut plates, and can accurately obtain the maximum height, linear coverage and height fluctuation, filling the technical gap of traditional methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122243935A_ABST
    Figure CN122243935A_ABST
Patent Text Reader

Abstract

This application discloses an adaptive quantification method, apparatus, equipment, and medium for the morphology of dross deposits after cutting sheet metal, relating to the field of industrial cutting quality inspection. The method includes: acquiring multi-segment dross three-dimensional point cloud data of the target sheet metal along the cutting direction to determine the panoramic height field matrix; performing panoramic coarse positioning and pose correction based on the panoramic height field matrix to obtain the rotated height field; determining the leveled height field based on the rotated height field using a nonlinear reference difference reconstruction method based on three-point distributed sampling; separating the background in the leveled height field using an adaptive separation algorithm based on bidirectional manifold competition to obtain the true dross height field; and performing morphological statistics on the true dross height field based on topological connected component analysis to obtain the quantification results of the dross morphology of the target sheet metal cutting; the quantification results include: maximum height, linear coverage, and height fluctuation. This application can achieve accurate quantification of the dross morphology of sheet metal cutting.
Need to check novelty before this filing date? Find Prior Art