Method for extracting shape of laser additive manufacturing molten pool

Abstract

The invention discloses a method for extracting the shape of a laser additive manufacturing molten pool. The method comprises the following steps: performing graying processing on the input molten pool image to generate a gray level image; performing filtering processing on the grayscale image; performing binarization processing on each frame of filtered grayscale image to obtain a binarized image; when the input molten pool image is not coaxially acquired with the laser, identifying and removing reflection spots in the binarized image, extracting a molten pool image contour in the binarized image, and obtaining an external minimum rectangle of the molten pool image contour, the length and width of the external minimum rectangle being the length and width of the molten pool.

Description

Technical field [0001] The invention belongs to the technical field of molten pool image processing, in particular to a method for extracting the shape of the molten pool by laser additive manufacturing. Background technique [0002] As an important manufacturing technology, laser additive manufacturing is widely used in industrial manufacturing, aerospace, biomedical and other fields. In the laser additive manufacturing process, the online monitoring of the molten pool includes real-time detection of the dynamic changes of the temperature, shape, area, length and width of the molten pool, and study the impact of these dynamic changes on the product, thereby affecting the manufacturing process Monitoring the abnormalities in the process is of great significance to ensure the quality of the final product and analyze the defects of the printing layer. However, due to the large laser power and fast scanning speed, a large number of molten pool pictures can be collected every second...

AI Technical Summary

Problems solved by technology

However, due to the high laser power and fast scanning speed, a large number of molten pool pictures can be collected every second during the manufacturing process, and because there are a lot of splashes and arc interference around the molten pool, the molten pool collected by the molten pool monitoring system will be affected. The images cause unavoidable effects, which affect the extraction of melt pool information

[0003] For the detection of molten pool parameters, the existing method is to perform ellipse fitting on the molten pool, and then calculate the relevant parameters of the molten pool. This method can calculate the area and length and width parameters of the molten pool, but the ellipse fitting process is complicated. , is greatly affected by background noise, and is limited to elliptical or nearly elliptical molten pool edges; and the pixel values ​​of the molten pool image are used to calculate the main inertial axis of the molten pool to obtain corresponding parameters. This method is suitable for different shapes of molten pools The universality is not high, and the result obtained is not accurate enough when the shape of the molten pool is irregular

Images