Robotic seam tracking system based on vision sensing and human-machine interaction for multi-pass MAG welding

Kunxi, Xue; Wang, Zhijiang; Shen, Junqi; Hu, Shengsun; Zhen, Yahui; Liu, Jie; Dingyong, WU; Yang, Hui

doi:10.1016/j.jmapro.2020.02.026

Cited by 36 publications

(14 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It aims to help intelligent robots automatically correct the welding position during the welding process to ensure that the end of the welding gun moves along the correct welding seam trajectory. To this end, many scholars have proposed some welding seam tracking methods based on different sensing methods, such as tactile sensing, arc sensing, sound sensing, magneto-optical sensing, and visual sensing [10][11][12].…”

Section: Introductionmentioning

confidence: 99%

A vibration-resistant detection method of position and gap for seam tracking of Z-weave GMAW

Gao,

Hong,

Jia

et al. 2024

Preprint

View full text Add to dashboard Cite

Aiming at the failure problem of automatic weave weld tracking of V-butt welds with gaps due to arc light, molten metal splash, seam gap variations, and inertial vibration of the weave motion in the manufacture of weave gas metal arc welding for pipelines vessels and ships, a vibration-resistant detection method of position and gap based on laser vision sensing was proposed. In this method, an improved random sampling consistency algorithm and an adaptive grayscale centroid algorithm are proposed to overcome the interference of arc light and molten metal splash to achieve the simultaneous image detection of weld position and gap, as well as a moving polynomial fitting algorithm was proposed to overcome the interference of vibration at the direction of weave motion and to further correct the weld position. Finally, the experimental results of Z-weave welding seam tracking of S-curve welds show that the proposed method is effective and can significantly reduce the weld tracking error, which meets the requirements of practical welding. This study provides a novel solution for eliminating the vibration interference of system device in practical weave welding manufacture.

show abstract

Section: Introductionmentioning

confidence: 99%

A vibration-resistant detection method of position and gap for seam tracking of Z-weave GMAW

Gao,

Hong,

Jia

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The current test of eddy current can be automated, but the applicable materials are limited and the accuracy is low. Therefore, numerous researchers have proposed several solutions for real-time welding quality monitoring through sensing technology to provide real-time information to control the welding process, containing vision sensors [13], acoustic sensors [14], arc sensors and spectral sensors [15,16]. Among them, acoustic sensors are expensive and difficult to be used in large-scale actual welding production.…”

Section: Introductionmentioning

confidence: 99%

An active visual monitoring method for GMAW weld surface defects based on random forest model

Zhu

Yuan

2022

Mater. Res. Express

View full text Add to dashboard Cite

In the automatic manufacturing of robotic welding, real-time monitoring of weld quality is a difficult problem. Meanwhile, due to volatilization of zinc vapor in galvanized steel and complexity of welding process, the existence of welding defects greatly affects industrial production process. And real-time detection of welding defects is a key step in development of intelligent welding. To realize real-time monitoring of weld surface defects, an active visual monitoring method for weld surface defects is proposed. Firstly, after applying Gabor filter to remove interference signals such as arc and noise, obtain weld centerline image; then employ the slope analysis method to extract peak valley coefficient of weld defects, extract five feature points of weld surface quality by Douglas-Puke algorithm, and analyse geometric and spatial distribution features of different types of defects in weld laser stripe images. Finally, using eight feature vectors extracted from weld features, design a weld defect recognition random forest model based on decision tree. After optimizing the decision tree depth and number of model evaluators, compared with the traditional decision tree ID3 and CART algorithm model, this model has better performance than traditional machine learning algorithms on five weld surface defect data sets. The experimental results show that accuracy of weld defect identification in the training set is 99.26%, accuracy of weld defect recognition in the test set is 96%, and processing time of a single image is only 5.3 ms, which overcomes difficulty of real-time weld defect detection in intelligent welding and ensures real-time and accuracy.

show abstract

“…The control inputs are mostly obtained by a combination of feedforward inputs, calculated from reference trajectory, and feedback control law. (Lim et al, 2023;Xue et al, 2021) The stabilization to reference trajectory requires a nonzero motion condition. Predictive control techniques are a very important area of research (Belousov et al, 2022).…”

Section: Introductionmentioning

confidence: 99%

The Feasibility of Trajectory Controller by SS Equation of an Error Model in WMR

Qev

Meshach

2022

IJEC

View full text Add to dashboard Cite

There has been an increasing amount of research on WMRs. The WMRs have lots of advantages: their mechanical system is usually simple; the whole movement mostly contains two dependent motors; and their motions in two-dimensional space are quite adaptable. At the same time, the WMRs have better power efficiency. WMRs have been studied from many points of view, such as modelling control, obstacle avoidance, localization, tip-over stability, and so on. This paper discusses the control algorithm. WMRs have nonholonomic constraints. That is, the mobile robot may not be able to reach a specific position and angle in a specific time; however, the robot can reach the target in a different motion or within a limited time. In this paper, an error model based on the WMR is introduced. The model explains the error between the actual position and the ideal or target position in the continuous motion of WMRs. The error model will be transformed into a state-space equation in order to demonstrate that the algorithm that controls the WMR`s movement is controllable. By splitting the inputs into and , the whole equation is transformed into a zero-input state-space system. Then, the errors can be minimized with the optimization of the feedback. The results show that by optimizing the time-varying feedback matrix, the error is asymptotically stable and close to zero. Therefore, by adding this control law to the controller, an approach to making mobile robots follow the planned trajectory is obtained.

show abstract

Robotic seam tracking system based on vision sensing and human-machine interaction for multi-pass MAG welding

Cited by 36 publications

References 22 publications

A vibration-resistant detection method of position and gap for seam tracking of Z-weave GMAW

A vibration-resistant detection method of position and gap for seam tracking of Z-weave GMAW

An active visual monitoring method for GMAW weld surface defects based on random forest model

The Feasibility of Trajectory Controller by SS Equation of an Error Model in WMR

Contact Info

Product

Resources

About