XIA YUXIONG

Dr. XIA YUXIONG

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
10 February 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JLJidong Lu
Jidong Lu
SYSatoshi Yamane
Satoshi Yamane
WWWeixi Wang Wang
Weixi Wang Wang
NLNing Li
Ning Li
SWSiqi Wang
Siqi Wang
XYXIA YUXIONG
XIA YUXIONG
Plasma arc welding can achieve high-quality welding joints in high-strength manufacturing fields, such as aviation and automotive, and improve production efficiency. It is important to observe the weld pool state in real-time in robot automatic welding. However, the electrodes of the plasma welding torch cannot be observed from the outside. Teaching the weld line to torch in real-time to be observable to humans will be difficult. Also, it is difficult to process the image to obtain the position of the weld line in K-PAW. In this study, a camera was utilized to observe the weld pool. The authors estimate the weld line position in real time by image processing based on U-Net prediction. The U-Net model demonstrates sufficient prediction where the accuracy reached 99.5% for the training data and 96.5% for the test data recognition. Moreover, a control method utilized weld line position estimated from the boundary area to verify the effectiveness of this prediction model from 3 mm within the deviation of 1 mm, which is within the range of permissible welding errors. It could reduce image processing errors in the weld pool image and provide higher recognition accuracy than image processing. Combining vision sensing technologies and deep learning methods will provide new technologies to enable higher welding precision and improve welding quality. It could also accelerate the development of welding technology in the intelligent manufacturing field.

13 August 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YLYuxi Luo
Yuxi Luo
SYSatoshi Yamane
Satoshi Yamane
WWWeixi Wang Wang
Weixi Wang Wang
RTRei Tsumori
Rei Tsumori
KOKohei Ochiai
Kohei Ochiai
XYXIA YUXIONG
XIA YUXIONG
While modern power sources have improved process stability, real-time monitoring and feedback control remain essential for ensuring consistent weld quality under dynamic conditions. To address this need, a vision-based closed-loop control system was developed for pulsed Metal-Active Gas (MAG) welding. The system dynamically adjusts the welding speed based on real-time visual feedback in the welding process. Otsu thresholding combined with morphological operations was applied to molten pool images for brightness-based feature extraction. These features, representing the dynamic behavior of the molten pool, were incorporated into a feedback loop for real-time control. Without relying on complex model-based prediction or sensor fusion, the proposed method reduces fluctuations in weld bead geometry and lowers the occurrence of defects. The experimental results showed that, under optimized control conditions and after a steady welding state was achieved, the weld bead’s height deviation exhibited an average standard deviation of 0.08 mm, and a process stability rate of 92%. The combination of conventional hardware and straightforward image processing makes the proposed approach practical for industrial implementation.

12 May 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XYXIA YUXIONG
XIA YUXIONG
SYSatoshi Yamane
Satoshi Yamane
WWWeixi Wang Wang
Weixi Wang Wang
HIHiroki Ihara
Hiroki Ihara
JLJidong Lu
Jidong Lu
YLYuxi Luo
Yuxi Luo
Real-time management of short-term ozone peaks during arc welding remains challenging because ventilation- and enclosure-defined transport boundaries can create strong position-dependent peak behavior, even under fixed process settings. This study establishes a coordinate-referenced, event-level monitoring and analysis framework to quantify ozone–fume peak coupling under a controlled local exhaust ventilation (LEV) suction boundary during CO2 arc welding. A controlled process–environment testbed with a defined suction condition was implemented, and synchronized ozone and fume signals were acquired at three sampling points referenced to the arc position and the LEV inlet direction. The particulate channel was anchored to a PM4 gravimetric reference, yielding a condition-specific traceable CPM-to-mass conversion factor K1 of 1.76 × 10−2 mg/(m3·CPM) and enabling standardized peak-fume endpoints on a mass-concentration scale. The primary inferential analysis used the curtain-on dataset, comprising 21 sessions and 42 event-level records balanced across three sampling points. Under the same suction boundary, peak coupling was strongly monitoring-coordinate dependent: LEV-aligned locations showed statistically supported ln–ln scaling between peak ozone and peak fume, whereas the opposite-side location did not exhibit statistically supported scaling; a pooled point-parameterized ln–ln model achieved an adjusted R2 of 0.777. As a descriptive control-relevant contrast, adding a curtain enclosure under continuous LEV produced strong event-level ozone peak suppression at LEV-aligned locations, with a maximum reduction of 87.8%, while attenuation at the opposite-side location remained limited. Overall, the results provide a ventilation-boundary-consistent, coordinate-specific basis for monitoring placement and control evaluation, identifying where peak translation is supported and where direct ozone monitoring remains necessary.