Research on the seam tracking of narrow gap P-GMAW based on arc sound sensing

Liu, Wenji; Zhenyu, Guan; Xiao, Jin-Long; Li, Liangyu; Jianfeng, Yue

doi:10.1016/j.sna.2019.04.015

Cited by 19 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of sensor technology, numerous methods have been proposed to accurately set and control the welding torch trajectory and reduce sidewall incomplete defects. In this regard, electromagnetic sensors [11], inductive sensors [12], ultrasonic sensors [13], sound sensors [14], and vision sensors [15][16][17][18] have been proposed so far to conduct welding seam tracking research. Among these sensors, the method of welding seam tracking using a vision sensor has been developed significantly.…”

Section: Introductionmentioning

confidence: 99%

Implementation of a two-stage algorithm for NG-GMAW seam tracking and oscillation width adaptation in pipeline welding

Liu,

Xue,

Zhou

et al. 2023

Science and Technology of Welding and Joining

View full text Add to dashboard Cite

Seam tracking and oscillation width adaptation could effectively reduce the sidewall fusion defects in automatic narrow-gap gas metal arc welding (NG-GMAW). This study proposes a twostage algorithm to realise seam tracking and oscillation width adaptation in NG-GMAW pipeline welding. The first stage involves using the principal component analysis (PCA) eigenvectors to adjust the oscillating centre, enabling seam tracking and oscillation width adaptation for the hot and fill layer. In the second stage, dataset was prepared based on the tracking data from the first stage, which can guide the welding torch trajectory for the cap layer. Experimental results show that the proposed scheme achieves seam tracking and oscillation width adaptation with an accuracy of 0.1 mm.

show abstract

Section: Introductionmentioning

confidence: 99%

Implementation of a two-stage algorithm for NG-GMAW seam tracking and oscillation width adaptation in pipeline welding

Liu,

Xue,

Zhou

et al. 2023

Science and Technology of Welding and Joining

View full text Add to dashboard Cite

show abstract

“…In the welding process, thermal deformation of the welded parts can easily lead to the failure of trajectory planning using linear or arc interpolation, resulting in deviation of the welding trajectory. Therefore, many scholars have applied advanced sensor technology to welding robots to achieve real-time correction of welding trajectories [ 4 , 5 , 6 ]. Among various sensors, active optical-vision sensors are more commonly used in welding tracking due to their ability to overcome complex environmental interference using light sources compared to passive vision sensors that use natural light or arc light generated during welding.…”

Section: Introductionmentioning

confidence: 99%

YOLO-Weld: A Modified YOLOv5-Based Weld Feature Detection Network for Extreme Weld Noise

Gao

Fan

et al. 2023

Sensors

View full text Add to dashboard Cite

Weld feature point detection is a key technology for welding trajectory planning and tracking. Existing two-stage detection methods and conventional convolutional neural network (CNN)-based approaches encounter performance bottlenecks under extreme welding noise conditions. To better obtain accurate weld feature point locations in high-noise environments, we propose a feature point detection network, YOLO-Weld, based on an improved You Only Look Once version 5 (YOLOv5). By introducing the reparameterized convolutional neural network (RepVGG) module, the network structure is optimized, enhancing detection speed. The utilization of a normalization-based attention module (NAM) in the network enhances the network’s perception of feature points. A lightweight decoupled head, RD-Head, is designed to improve classification and regression accuracy. Furthermore, a welding noise generation method is proposed, increasing the model’s robustness in extreme noise environments. Finally, the model is tested on a custom dataset of five weld types, demonstrating better performance than two-stage detection methods and conventional CNN approaches. The proposed model can accurately detect feature points in high-noise environments while meeting real-time welding requirements. In terms of the model’s performance, the average error of detecting feature points in images is 2.100 pixels, while the average error in the world coordinate system is 0.114 mm, sufficiently meeting the accuracy needs of various practical welding tasks.

show abstract

“…Control of arc length. Liu et al [8] studied the influence of the sidewall of the groove on the arc sound signal and the sensitivity of the arc sound characteristics to the torch deviation, using the arc sound signal to adjust the arc length, and the welding seam tracking accuracy is 0.6 mm; Shanghai Jiao Tong University Robot Welding Intelligence Chemical Technology Laboratory [9] has many years of research using arc sound signals to control arc length. Through the acquisition and processing of acoustic signals, experimental results based on adaptive PID controllers show that the maximum error of arc length control is 0.58 mm.…”

Section: Introductionmentioning

confidence: 99%

Research on Compensation Control Technology Based on Arc Length Tracking in the Process of Tube Sheet Welding

2022

Proceedings of WCSE 2022 Spring Event: 2022 9th International Conference on Industrial Engineering and Applications

View full text Add to dashboard Cite

During the Gas Tungsten Arc Welding(GTAW) process, the arc length will change along with welding thermal deformation, uneven surface of the work-piece and wear of the tungsten electrode. Considering the large fluctuation of arc length in all positions of circular seam welding under multi-variable coupling, the method of real-time arc length fuzzy control in circular seam welding is studied. In this paper, an isolated circuit of arc length collection is designed, and a real-time arc length tracking algorithm based on DC pulse TIG welding is proposed to implement the calculation of arc voltage in the pulse peak phase and the adjustment of arc length in the pulse base phase. Experiments show that the arc length adaptive method based on the fuzzy control algorithm can significantly improve the arc length stability, and obviously improve the welding quality and stability.

show abstract

Research on the seam tracking of narrow gap P-GMAW based on arc sound sensing

Cited by 19 publications

References 5 publications

Implementation of a two-stage algorithm for NG-GMAW seam tracking and oscillation width adaptation in pipeline welding

Implementation of a two-stage algorithm for NG-GMAW seam tracking and oscillation width adaptation in pipeline welding

YOLO-Weld: A Modified YOLOv5-Based Weld Feature Detection Network for Extreme Weld Noise

Research on Compensation Control Technology Based on Arc Length Tracking in the Process of Tube Sheet Welding

Contact Info

Product

Resources

About