Research on quality inspection for backside weld of tailored blank laser welding based on texture feature

2014 ◽  
Author(s):  
Yuanyuan Zou ◽  
Lingshen Fang ◽  
Hui Zhang ◽  
Miao Kou
Keyword(s):  
Laser Welding ◽  
Texture Feature ◽  
Quality Inspection ◽  
Tailored Blank

Post-Weld Quality Inspection for CO2 Laser Tailored Blank Welding with Vision Sensor

2010 ◽  
Vol 97-101 ◽  
pp. 4337-4341 ◽  
Author(s):  
Yuan Yuan Zou ◽  
Ming Yang Zhao ◽  
Lian Zhu Liu
Keyword(s):  
Laser Welding ◽  
Weld Seam ◽  
Quality Inspection ◽  
Weld Quality ◽  
Image Processing Algorithm ◽  
Visual Sensor ◽  
Tailored Blank ◽  
Time Required ◽  
Visual Testing ◽  
Geometrical Defects

The traditional method for post-weld quality inspection is visual testing by people. Major limitations of this method are the subjectivity of judgments and time required to perform the inspection. With the increasing use of laser welding in the automotive industry, the manufacturers are struggling with the challenge to automate the quality inspection process. This paper discussed the automatic post-weld quality inspection technology by computer vision sensing for mono-thickness tailored blanks of CO2 laser welding. A visual sensor was developed for acquiring the original image of the weld seam. The sensor consists of a PC based vision camera and a stripe-type laser diode. An image processing algorithm was presented to detect the geometrical defects of the weld seam. Some experiments are carried out and some applications are given.

scholarly journals Implementation and evaluation of an echo state network for a quality inspection system for laser welding

Procedia CIRP ◽  
2021 ◽  
Vol 99 ◽  
pp. 496-501
Author(s):  
Ivan Vishev ◽  
Claus-Philipp Feuring ◽  
Oliver Bringmann
Keyword(s):  
Laser Welding ◽  
Inspection System ◽  
Echo State Network ◽  
Quality Inspection

‘Mean Contrast’ Texture Feature Model of Nature Environmental Protection Fabric

2010 ◽  
Vol 113-116 ◽  
pp. 943-946
Author(s):  
Zhe Liu
Keyword(s):  
Three Dimensional ◽  
Texture Feature ◽  
Feature Model ◽  
Quality Inspection ◽  
Dimensional Model ◽  
Three Dimensional Model ◽  
Numerical Convergence ◽  
Texture Characteristics ◽  
The Mean ◽  
Contrast Feature

Aiming at lack of mature texture feature model of natural green fabric image, this paper presents a new “Mean Contrast” texture feature model, which can express better on the type of collecting and narrow-long and some irregular defects. First, three-dimensional model of texture characteristics is established, various natural green fabrics are tested in experiments using the contrast feature, and then “Mean Contrast” feature is proposed, so that characteristic value of fabric texture can be converged. Finally, experimental results show that the “mean contrast” feature is so simple and effective that better show a variety of fabric texture variation, and has the numerical convergence. So it provides a contrasting texture feature model for continue related to fabric quality inspection.

Sign in / Sign up

Export Citation Format

Share Document