Yanling Xu

Yanling Xu

Auto-generated profile, based on publicly available information

Yanling Xu

School of Materials Science and Engineering, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 February 2023 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
RXRunquan Xiao
Runquan Xiao
YXYanling Xu
Yanling Xu
FXFengjing Xu
Fengjing Xu
ZHZhen Hou
Zhen Hou
HZHuajun Zhang
Huajun Zhang
Shanben ChenShanben Chen
Shanben Chen
Laser vision-based welding seam tracking has become the key technology to realize intelligent robotic welding, and extracting the feature point of welding seam is an essential step. Aiming at the low flexibility of classical methods, this article proposed a laser stripe feature point tracker (LSFP-tracker) based on siamese network for robotic welding seam tracking. First, a lightweight feature extraction network is constructed to produce high resolution feature maps that contain both low-level geometric details and high-level semantic information, which can ensure model's tracking accuracy and antinoise capability. Moreover, a feature refinement module is designed, which can enhance the tracking stability on specific seams through channel-wise emphasizing useful features. Subsequently, stripe's curvature and three preset templates were introduced to adaptively detect the initial feature point and corresponding bounding box, which is helpful to enlarge the applicability scope of LSFP-tracker. The experimental results show that the LSFP-tracker can maintain satisfying tracking performance on various welding seams, such as butt, V-groove, multi-pass seams, etc., even under the interference of welding noise. And the comparison tests prove the advantage of LSFP-tracker, which has great application potential in practical welding.

17 March 2026 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
HYHe Yinshui
He Yinshui
YKYang Kuang
Yang Kuang
GMGuohong Ma
Guohong Ma
YXYanling Xu
Yanling Xu
Weld seam profile (WSP) extraction is critical for intelligent robotic welding with laser vision sensing. Current methods exhibit limitations in anti-interference capability, robustness, generalization capability, and precision when processing diverse joint types and complex backgrounds. This study introduces a novel YOLOv8-based WSP extraction structure to handle various joint types with enhanced robustness and generalization performance. The key innovations include the following: first, a cross-stage partial fusion block employing directional switchable dilated convolutions that model orientation cues to enhance discrimination of elongated laser stripes for improved anti-interference ability, second, an improved C2 module incorporating multiscale dilated attention to boost high-level semantic contextual modeling, and 3) an enhanced channel–spatial attention module that integrates efficient channel weighting and dynamic spatial attention to enable more targeted feature recalibration, thereby improving the feature discriminability for WSP. Ablation studies confirm the effectiveness of each module, with the complete model achieving significant gains over the baseline: 3.39% (precision), 2.16% (recall), 4.26% (mAP at 50), and 2.76% (F1-score). Comparative tests against several state-of-the-art models further highlight its robustness and superior generalization for WSP extraction.