Weld seam tracking system is easy to install

Purpose This paper aims to propose a weld seam tracking method based on proximal policy optimization (PPO). Design/methodology/approach By constructing a neural network based on PPO and using the reference image block and the image block to be detected as the dual-channel input of the network, the method predicts the translation relation between the two images and corrects the location of feature points in the weld image. The localization accuracy estimation network (LAE-Net) is built to update the reference image block during the welding process, which is helpful to reduce the tracking error. Findings Off-line simulation results show that the proposed algorithm has strong robustness and performs well on the test set of curved seam images with strong noise. In the welding experiment, the movement of welding torch is stable, the molten material is uniform and smooth and the welding error is small, which can meet the requirements of industrial production. Originality/value The idea of image registration is applied to weld seam tracking, and the weld seam tracking network is built on the basis of PPO. In order to further improve the tracking accuracy, the LAE-Net is constructed and the reference images can be updated.

Download Full-text

Underwater Wet Weld Seam Tracking Based on Passive Visual Sensor

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.683.725 ◽

2013 ◽

Vol 683 ◽

pp. 725-728

Author(s):

Bo Chen ◽

Chuan Bao Jia ◽

Ji Cai Feng

Keyword(s):

Weld Seam ◽

Tracking System ◽

Water Environment ◽

Welding Process ◽

Seam Tracking ◽

Visual Sensor ◽

Weld Seam Tracking ◽

Influence Of Water ◽

Image Processing Algorithms ◽

Weld Automation

Weld seam tracking system is urgently needed in weld automation process, but it has not been well studied in underwater weld applications. This paper used visual sensor to automatically monitor the weld seam in underwater wet weld process, and image processing algorithms were developed to remove the influence of water environment on the captured image and automatically obtain the weld torch deviation, and the weld torch was adjusted automatically according to the deviation obtained by the image, experiment results showed that the system could meet the requirements of underwater wet welding process.

Download Full-text

A Study on Modified Hough Algorithm for Image Processing in Weld Seam Tracking System

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1088.824 ◽

2015 ◽

Vol 1088 ◽

pp. 824-828 ◽

Cited By ~ 3

Author(s):

Jong Pyo Lee ◽

Qian Qian Wu ◽

Min Ho Park ◽

Cheol Kyun Park ◽

Ill Soo Kim

Keyword(s):

Image Processing ◽

Weld Seam ◽

Gma Welding ◽

Vision System ◽

Tracking System ◽

Computing Time ◽

Weld Line ◽

Welding Process ◽

Seam Tracking ◽

Weld Seam Tracking

In modern market, achieving mechanical and automatic arc welding process is the key issue to be solved in welding industries. Because of the high complexity of the welding environment, manual detection of the weld line information is hard to be successful and time consuming. Therefore, this study aim at developing a new image processing algorithm for seam tracking system in Gas Metal Arc (GMA) welding by modified Hough algorithm based on the laser vision system. Firstly, noises in the captured weld seam images by CCD camera were effectively removed by noise filtering algorithm and then weld joint position were detected by the modified Hough algorithm to realize the automatic weld seam tracking. To verify the efficiency of the developed image processing model, a common image processing method was employed and the processed results were compared with the proposed algorithm. Statistical results proved that the modified Hough algorithm was able to acquire the weld information precisely with less computing time and memory cost, which also capable for industrial application.

Download Full-text